An extensive review of SAR remote sensing in mode transportation studies: Major findings and future recommendations

Fatwa Ramdani

doi:10.12688/f1000research.160735.1

Home Browse An extensive review of SAR remote sensing in mode transportation studies:...

ALL Metrics

-

Views

-

Downloads

Get PDF

Get XML

Export

▬

✚

Research Article

An extensive review of SAR remote sensing in mode transportation studies: Major findings and future recommendations

[version 1; peer review: 1 approved]

Fatwa Ramdani

PUBLISHED 24 Mar 2025

Author details Author details

International Public Policy, University of Tsukuba, Tsukuba, Ibaraki Prefecture, Japan

Fatwa Ramdani
Roles: Conceptualization, Data Curation, Formal Analysis, Investigation, Methodology, Visualization, Writing – Original Draft Preparation, Writing – Review & Editing

OPEN PEER REVIEW

REVIEWER STATUS

This article is included in the Japan Institutional Gateway gateway.

Abstract

Background

The availability of synthetic aperture radar (SAR) remote sensing technology and platform has been widely used in the study of transportation. It includes all three modes of air, water, and land. This review aims to determine the importance of SAR remote sensing technology in a specific mode of transportation focus area.

Methods

For this reason, an extensive literature review was conducted. This review used the Web of Science, the IEEEXplore, and the ScienceDirect database. The systematic search strategy was developed for query-related research papers. The rules were then proposed to filter more related research papers. Then the selected papers were classified into five classes (mode, container, infrastructure, geographic distribution, and pattern of publication). Finally, a descriptive statistical analysis was conducted.

Results

Many studies have been done in the last three decades for mode transportation. Based on the mode of transportation and its container, the water mode of transportation and ship were the most studied. It is due to the contrast differences between the ship as the detected object and the sea as the background. While based on the infrastructure the airport was the most studied object, followed by the railway and harbour. Most of the studies on using SAR as the mode of transportation were conducted in the northern part of the equator. Currently, neural networks and deep learning algorithms are introduced to detect the mode of transportation using SAR remote sensing datasets.

Conclusion

Future research is expected to detect ships in a more heterogeneous background. More studies in moving object detection using SAR are also expected in the future.

Keywords

SAR, remote sensing, mode of transportation, earth observation

Corresponding author: Fatwa Ramdani

Competing interests: No competing interests were disclosed.

Grant information: This research was supported by the University of Tsukuba Basic Research Support Program (Type S)
The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Copyright: © 2025 Ramdani F. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

How to cite: Ramdani F. An extensive review of SAR remote sensing in mode transportation studies: Major findings and future recommendations [version 1; peer review: 1 approved]. F1000Research 2025, 14:322 (https://doi.org/10.12688/f1000research.160735.1) First published: 24 Mar 2025, 14:322 (https://doi.org/10.12688/f1000research.160735.1) Latest published: 24 Mar 2025, 14:322 (https://doi.org/10.12688/f1000research.160735.1)

Introduction

The importance of transportation to national development is growing. It is a significant factor in determining patterns of production and commerce, and as a result, economic integration. It can also assist some nations in generating cash by offering transportation services.¹ There is a need to detect and monitor the most current condition of transportation, especially the mode of transportation, the container types, as well as the related infrastructures. The information acquired can be used for taking immediate actions that will allow maintenance, mitigations, and sustainable development.

However, evaluating, monitoring, and detecting the mode of transportation is time-consuming expensive, and labour-intensive. The traditional way can only cover small scale and use in situ measurement techniques. One of the most famous methods that allow us to collect information on a large scale, time-efficient, and without direct interaction with the object is using remote sensing technologies. Especially Synthetic Aperture Radar (SAR) remote sensing, which can be operated day or night, penetrate clouds, and without weather issues because it uses microwave electromagnetic energy.

The length of microwave electromagnetic wave used in SAR remote sensing is between 1 centimetre to 1 meter. Similar to optical remote sensing, radar sensors also operate with one or more bands. It is identified by letters, such as P, L, S, C, X, K, Q, V, and W. The longest band is P with 100 cm of wavelength, while the shortest band is W with 0.3 cm of wavelength. On the contrary, the highest frequency is the W-band, with 100 GHz, and the lowest frequency is the P-band with 0.3 GHz.²

L band has higher penetration than C- or X-bands, therefore for mapping the volume of vegetation L- and C-band is better since they can be penetrated deeper into the vegetation canopy. While the X-band will scatter close to the surface of the vegetation canopy.³ When the frequency becomes lower, it can propagate with low attenuation and penetrate deeper, like the P-band that can penetrate several centimetres of the forest, dry ground, snow, ice, and the soil surface.⁴

Surface roughness affects the dark level of the produced SAR remote sensing image. Smooth surfaces like water bodies, roads, and other paved surfaces will produce a dark image since there is no return of backscatter signal due to it having a specular reflection. Rough surfaces like buildings, towers, tree trunks, and other vertical structures will produce a bright image since there is a strong return of backscatter signal due to it having diffuse scattering.³

SAR remote sensing is categorized as an active sensor and can be classified as an imaging sensor. The image produced using SAR remote sensing depends on the polarization of an electromagnetic wave. Different images will produce different visualizations if using different types of polarization. Polarization is the orientation of the plane of oscillation of a propagating signal.⁵ Concerning the Earth's surface, the perpendicular polarization planes are commonly referred to arbitrarily as horizontal and vertical. Polarization interacts differently with objects on the Earth’s surface, which leads to the different brightness levels recorded in a specific polarization channel.³

In SAR remote sensing the polarization uses abbreviations, such as horizontal transmission and horizontal reception (HH), vertical transmission and vertical reception (VV), horizontal transmission and vertical reception (HV), and vertical transmission and horizontal reception (VH).

One of the earliest generations of SAR remote sensing sensors is Canada’s RADARSAT program includes RADARSAT-1, RADARSAT-2, and the RADARSAT Constellation Mission (RCM). RADARSAT-1 (launched in 1995) and RADARSAT-2 (2007) operated in the C-band, offering high-resolution imaging for disaster monitoring, agriculture, and forestry. The RCM, launched in 2019, comprises three satellites that ensure daily global coverage, improving monitoring capabilities for Arctic regions, sea ice, and maritime safety. RADARSAT-2, with its ability to capture fine-resolution imagery, is also used for oil spill detection and urban mapping (https://www.asc-csa.gc.ca/eng/satellites/radarsat/).

Currently, there are many types of SAR remote sensing sensors available. One of the well-known is the Sentinel-1 SAR belonging European Space Agency (ESA). Sentinel-1 carries a C-band with dual polarization (HH+HV, VV+VH) and a temporal resolution of 12 days (sentinels.copernicus.eu). PALSAR-3 belongs to Japan Aerospace Exploration Agency (JAXA), revisit time is 46 days, and carries an L-band with multiple polarization (eorc.jaxa.jp). PALSAR with HH signal polarization can penetrate the forest canopy deeper and is returned from the bottom of the forest stronger than the VV signal polarization.⁶ TerraSAR-X is a commercial SAR remote sensing sensor belonging to the German Aerospace Center (DLR) with a 1-meter spatial resolution and temporal resolution of 11 days. TerraSAR-X carries an X-band, with a range of different modes of operation, allowing it to record images with different swath widths, resolutions, and polarizations (dlr.de).

Italy's COSMO-SkyMed constellation, developed by the Italian Space Agency (ASI), consists of four satellites operating in the X-band. These satellites provide rapid revisit times and high-resolution imaging for military and civilian applications, including disaster management, land cover mapping, and infrastructure monitoring. A second-generation COSMO-SkyMed constellation has been launched to enhance data quality and revisit frequency (https://portal.cosmo-skymed.it/CDMFE/home).

Other Asian countries also have launched SAR remote sensing sensors. It is India’s Radar Imaging Satellite (RISAT) series, including RISAT-1 (C-band) and RISAT-2 (X-band). These satellites are used for agricultural monitoring, disaster management, and surveillance. Additionally, the upcoming NASA-ISRO Synthetic Aperture Radar (NISAR) mission is a collaboration between NASA and the Indian Space Research Organisation (ISRO). Scheduled for launch in 2025, NISAR will operate in both L-band and S-band, making it the first dual-band SAR system. It is expected to provide unprecedented data for applications ranging from ice sheet dynamics to natural hazards (https://www.isro.gov.in/NISARSatellite.html).

South American countries also have SAR remote sensing sensors. The Argentine Space Agency (CONAE) developed the Satélite Argentino de Observación COn Microondas (SAOCOM) constellation, consisting of SAOCOM-1A and SAOCOM-1B. These satellites operate in the L-band and are primarily designed for agriculture and soil moisture studies. Their ability to penetrate soil makes them excellent for monitoring water content in agricultural fields, and improving crop management (https://saocom.invap.com.ar/).

With better spatial and temporal resolution, SAR remote sensing is suitable for transportation detection and monitoring activities. Many kinds of research used SAR remote sensing for the mode of transportation studies. Studies for monitoring the airport were done in 2001⁷ and 2004.⁸ Studies for ship detection were introduced in 2003⁹ and car detection in 2007¹⁰ and 2016.¹¹

As discussed, the remarkable capabilities of SAR remote sensing provide unprecedented opportunities to employ these technologies in a broad variety of modes of transportation studies. There are currently some SAR remote sensing literature review studies conducted. Gend and Genderen¹² was the first comprehensive SAR remote sensing review paper conducted related to the Interferometric Synthetic Aperture Radar (InSAR). The author comprehensively discussed the issues, techniques, and application of InSAR. Ouchi¹³ has summarized the recent trends and advances in SAR remote sensing on various topics. A topic such as fields of applications, specifications of airborne and spaceborne SAR, and information content of interpretation, InSAR, and Polarimetric SAR (PolSAR). However, the review is too general and does not focus on transportation issues. Other references [14] also briefly discussed the remote sensing techniques for road evaluation. They concluded that remote sensing techniques offer new potential for pavement stakeholders to evaluate large areas in an efficient time. The authors provided comprehensive information about remote sensing technologies, not only SAR but also Ground Penetrating Radar (GPR), infrared thermography, LiDAR and terrestrial laser scanning, hyperspectral, and emerging technology such as mobile smartphones. Further, other references [15] also introduced the trend in commercial SAR remote sensing. They introduced high-resolution wide-swath capabilities, multi-polarimetry, and the development of increased bandwidth of SAR sensors. They also emphasized that the timely availability and delivery of SAR remote sensing data is important. Therefore, expanding the number of satellite constellations and ground station networks is needed to fulfil the requirement.

There is still a need for a more comprehensive and focused review to discuss various aspects of the application of SAR remote sensing for transportation studies. Thus, the main objective of this study is to 1) identify the trend and gaps in the use of SAR remote sensing technologies for them to be easily adopted by transportation stakeholders; and 2) to classify the use of various SAR remote sensing technologies regarding the information they can provide in various mode of transportation detection, evaluation, and monitoring.

Method

Systematic search strategy

I used three scientific databases for a systematic search strategy. The databases are Web of Science (https://www.webofscience.com/), IEEE Xplore (https://ieeexplore.ieee.org/), and ScienceDirect (www.sciencedirect.com). Within the Web of Science and ScienceDirect database, only article document types were selected, while proceedings, books, or book chapters were excluded. While within IEEE Xplore, only journals type were selected, while conferences and magazines were excluded. Table 1 shows the keyword used to search the scientific papers.

Table 1. Keyword used to search the scientific papers.

Databases	Address	Keywords
Web of Science	https://www.webofscience.com/	(TS=(SAR) OR TS=(Synthetic aperture radar) OR TS=(remote sensing) OR TS=(airplane) OR TS=(aircraft) OR TS=(airport) or TS=(runway)) AND (TS=(ship) OR TS=(port) OR TS= (harbor) OR TS=(car) OR TS=(truck) OR TS=(train)) AND (TS=(terminal) OR TS=(parking) OR TS= (station) OR TS=(railway) OR TS=(vehicle) OR TS=(vessel))
IEEE Xplore	https://ieeexplore.ieee.org/	“All Metadata”: SAR AND Synthetic aperture radar AND remote sensing AND airplane AND aircraft AND airport AND runway AND ship AND port AND harbor AND car AND truck AND train AND terminal AND parking AND station AND railway AND vehicle AND vessel
Scopus	www.sciencedirect.com	TITLE-ABS-KEY(“SAR” OR “Synthetic aperture radar” OR “remote sensing” OR “airplane” OR “aircraft” OR “airport” OR “runway”) TITLE-ABS-KEY(“ship” OR “port” OR “harbor” OR “vessel”) TITLE-ABS-KEY(“car” OR “truck” OR “train” OR “railway” OR “vehicle”)

Querying result

This study focuses on the trend of SAR remote sensing in modes of transportation. Therefore, only the articles or journals from 1990 to 2022 were selected. The preferred reporting items for systematic reviews and meta-analyses (PRISMA) framework was adopted (https://www.prisma-statement.org//).

In the identification phase, there are 167 articles in total were collected. There are three articles published in languages other than English, and there are five articles published in Proceedings. Furthermore, there are three articles where full text was not accessible and one article is redundant. Thus, all of these articles were eliminated. Finally, there are 155 articles and journals were selected for the review process. Figure 1 shows the PRISMA flow diagram of this study.

Figure 1. The PRISMA framework flow diagram.

Classifying result

The selected articles and journals were then classified into five classes related to the review objectives. The first topic was the classification of the different modes of transportation. The different modes of transportation are air, land, and water. The second classification is the container of the mode of transportation, which includes aeroplane, car, truck, train, and ship or vessel. Then, the third classification is the infrastructure of the mode of transportation such as airport, runway, road, railway, port, and harbour, The fourth and fifth classifications are geographic distribution and publication pattern. Table 2 summarises the classification of topics used in this review study.

Table 2. Classification of topics for the review study.

Classification	Subclass
Mode of transportation	Air, land, water
Container of the mode of transportation	Aeroplane, car, truck, train, and ship or vessel
The infrastructure of the mode of transportation	Airport, runway, road, railway, and harbour
Geographic distribution	Asia, Europe, North America
Pattern of publication	Subscribed and open access

Descriptive statistics

The descriptive statistics include the number of articles and journals published annually and by the journal’s name. Furthermore, analyses were conducted by mode of transportation, container type, infrastructure type, geographic distribution, and pattern of publication.

Result and discussion

Total number of articles and journals

Based on the result, the first article that discussed ship detection was published in 1990.¹⁶ Then the utilization of SAR remote sensing for modes of transportation was relatively stagnant for two decades. After 2009, the result of the analysis showed that the utilization of SAR for modes of transportation gradually increased. After 2014, the utilization of SAR remote sensing increased dramatically. It is the open public policy by the European Space Agency (ESA) that makes the availability of the Sentinel-1 mission open to the public. Consequently, the adoption of SAR remote sensing for modes of transportation research is increasing by up to 36 articles by the year 2022 ( Figure 2).

Figure 2. The number of articles or journals on SAR remote sensing for the mode of transportation analysis from 1990-2022.

Geographic distribution

Our result found that most of the studies were conducted in the Asia region, especially in China (30), Korea (10), Hong Kong (6), Singapore (4), Japan (4), and Taiwan (3). The second most studies were conducted in the European region, especially Spain (7), Italy (4), and the United Kingdom (3). The last region is North America, where there were 6 studies conducted using SAR for the mode of transportation analysis. However, there are many articles or journals did not specifically mention the study area.

The most studied ship detection was in the busiest strait such as the Strait of Gibraltar,^17–21 Singapore and Malacca Strait,^18,22–24 and South Korea,^25–27 Gulf of Guinea,²⁸ and Canada.²⁹ While the studies of airports, aircraft, and related things are mostly conducted in China.^{7,8,30–49,37,38} There are few studies on airports conducted in Turkey⁵⁰ and South Korea.⁵¹ The studies on railways were mostly conducted in China^52–56 and a study in the Netherlands.⁵⁷ While the studies of roads, vehicles, and related things were conducted in European countries,⁵⁸ China,⁵⁹ and Thailand.⁶⁰

Interestingly, this finding is informed us that the study of using SAR for the mode of transportation mostly conducted in the northern part of the equator ( Figure 3). We assumed that it is due to the developed countries mostly being located in the northern part of the equator. They have the most developed mode of transportation and need to detect, evaluate, and monitor the condition of the infrastructures such as airports,^{31–35,40,49} railways,^52–57 and harbours.^61–63

Figure 3. Geographic distribution of articles or journals.

This figure was created using QGIS-LTR Desktop version 3.28.10-Firenze.

Pattern on publications

Most articles were published in the IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (23), followed by IEEE Geoscience Remote Sensing Letter (22), and Remote Sensing (19) and open access journal by Multidisciplinary Digital Publishing Institute (MDPI)

According to our findings, the first journal that published an article related to SAR remote sensing for the mode of transportation is IEEE Transaction on Geoscience and Remote Sensing in 1990.¹⁶ However, it took 14 years to publish the second article⁶⁴ related to SAR remote sensing for the mode of transportation in the same journal. This journal is the fourth most published article in the SAR remote sensing for the mode of transportation. Figure 4 summarises the top ten journals that published articles related to SAR remote sensing for the mode of transportation in alphabetical order.

Figure 4. Top ten journals that published articles related to SAR remote sensing for the mode of transportation studies.

Open-access journals like Remote Sensing, Sensors, and Sustainability have become more popular as a place to publish studies related to SAR remote sensing for the mode of transportation.

Mode of transportation

As it is visualized in Figure 5, the water mode of transportation is the most frequent that is assessed and evaluated with SAR remote sensing (63.9%). Followed by air and land, with 20% and 16.1%, respectively. The main reason why the water mode transportation is the most frequent is due to the data characteristics of SAR remote sensing. The ship as the target of classification is located on a homogeneous water background, making it easier to analyse. compared to aircraft or cars which have a more heterogeneous background.

Figure 5. The classification of the mode of transportation.

Container of the mode of transportation

The result of the container of the mode of transportation is shown in Figure 6. According to the analysis of the result, most of the studies using SAR remote sensing in the mode of transportation are mostly for ship detection (75), car (14), aeroplane (5), and truck (1). As we explained earlier, ship detection is relatively easier compared to other modes of transportation. Since it is located in the water, with a homogenous background. Figure 7 visualized the condition of the Singapore Strait with the large number of ships in the water. The seasonality of the ship from April to September 2022 is represented in rainbow colour.

Figure 6. The classification of the container of the mode of transportation is arranged in alphabetical order.

Figure 7. Sentinel-1 SAR data captured the seasonality of the Singapore Strait from April to May 2023.

Ships are represented in rainbow colours. Processed using Google Earth Engine (GEE) by authors. A’ is a zoom-in area of A, allowing readers to more clearly see the presence of the ship.

Currently, studies on ship detection using SAR remote sensing are focused on speed and accuracy,^65,66 and only a few studies to detect ships in multiscale^67,68 and in complex backgrounds.^67,69,70 Thereafter, future studies are expected to cover ship detection in multiscale and in a more heterogeneous background. Furthermore, most studies were conducted to detect stationary containers, few studies were conducted to detect moving containers.^{64,71–73,73–77} Future studies are expected to cover moving containers. Regarding the sensor used to detect the ships or vessels, most studies used satellite-based sensors. Only a few studies used airborne sensors.^78,79

Infrastructures of the mode of transportation

Figure 8 shows the result of the infrastructure of the mode of transportation. Surprisingly, the airport as the air mode of transportation become the most studied object (24). Where the railway as the land mode of transportation is the second most studied (6), the harbour as the water mode of transportation was the third most studied object (4), and road and tunnel as the land mode of transportation are the least studied, with only one paper each.

Figure 8. The classification of the infrastructure of the mode of transportation is arranged in alphabetical order.

Methods

The Differential Interferometric Synthetic Aperture Radar (DInSAR) method has been widely used in studies aimed at monitoring transportation infrastructures, as highlighted by numerous works in the literature.^{7,8,27,30,43,45,46,48,50,52,80–82} This method is particularly valuable because it enables researchers to detect and measure the three-dimensional displacement of transportation infrastructure over time, providing a detailed time series of movement or deformation. The capability to track such displacements is crucial for understanding the structural stability and functionality of infrastructure systems, such as roads, railways, bridges, and airports which are integral to modern transportation networks ( Figure 9).

Figure 9. The principle of the DinSAR technique in monitoring the land subsidence of an airport using the difference range distance (Δd).

The DInSAR process involves using two radar images of the same area, captured from slightly different vantage points by a satellite or airborne radar system. These images are acquired at different times, and their slight positional difference creates a phase shift in the returned radar signals. This phase difference arises because the radar signals travel slightly different distances to and from the sensor, a phenomenon referred to as the "range difference." By analyzing the phase differences between the two images, researchers can derive critical height and displacement information about the study area.

To create an interferogram, which is the core product of the DInSAR technique, the phase differences between the two radar images are processed. The interferogram visually represents these differences, and with further processing, it can reveal subtle ground movements or deformations in the monitored area. These deformations are often caused by natural processes, such as earthquakes, landslides, or subsidence, or by human activities, such as construction or mining.

The utility of DInSAR lies not only in its ability to detect minute displacements but also in its capacity to do so over large areas with high spatial resolution. This makes it an indispensable tool for transportation infrastructure monitoring, as it helps engineers and policymakers assess potential risks and develop mitigation strategies. For instance, runways of airports experiencing subsidence in a specific section could be identified early using DInSAR, allowing maintenance efforts to be targeted effectively, thereby minimizing risks to public safety and reducing economic losses.

Algorithms and taxonomy

After 2010, the use of neural network classifier algorithms gained significant popularity in applications of Synthetic Aperture Radar (SAR) remote sensing for analyzing container modes of transportation. This marked a shift from earlier methods that required more human intervention in feature extraction and classification. Neural networks became a preferred choice because of their ability to model complex patterns and relationships within data, improving the accuracy of classification tasks.^{23,37,42,77,83–93}

However, a new trend emerged between 2018 and 2022, as advancements in computational power and algorithmic research propelled the adoption of deep learning classifier algorithms for SAR applications.^{41,58,94–98} Deep learning, which is a subset of machine learning, relies on artificial neural networks with many layers (also called deep neural networks). Figure 10 demonstrates the principle of this approach, where the deep learning algorithm autonomously performs feature extraction, labeling, and classification without requiring manual intervention. This self-learning capability is achieved through interconnected layers of nodes, which process and transform data hierarchically to identify patterns and generate outputs.^18,66,95,96

Figure 10. The principle of the deep learning algorithm.

Where there are many layers and connected nodes used to extract the feature information and process the classification.

Neural networks and deep learning algorithms fall under the category of two-stage object detection algorithms. These algorithms follow a sequential approach: in the first stage, they generate candidate regions where objects might exist, and in the second stage, they refine these regions by classifying objects and determining their precise positions.

In contrast, one-stage object detection algorithms simplify this process by directly generating the target object's category and positional information in a single step. This streamlined approach is faster and more efficient, making it particularly useful for real-time applications. Examples of popular one-stage object detection algorithms include the Single Shot Multibox Detector (SSD)^99–101 and the You Only Look Once (YOLO) series.^102–105 These algorithms have gained widespread use due to their ability to balance speed and accuracy, which is essential for tasks like detecting and tracking objects in SAR data.

The progression from neural networks to deep learning, and the subsequent emergence of one-stage object detection algorithms like SSD and YOLO, reflects the rapid evolution of machine learning techniques in SAR remote sensing. These advancements have transformed how data is analysed, enabling more automated, accurate, and efficient processing methods.

Figure 11 shows the taxonomy of SAR remote sensing for transportation studies. In the studies related to infrastructures of transportation, most research uses the DinSAR methodology. While in the studies related to the container can be divided into two sub-classes; traditional and modern methodology. In the traditional methodology, most research utilized the backscatter, polarization, geometric, and feature-based. In the modern methodology, there are two sub-classes; one-stage and two-stage methodology.

Figure 11. The taxonomy of algorithm used in the study of transportation using SAR remote sensing.

The one-stage methodology is designed to be simple and fast. It combines all the steps required for a task, such as locating objects and classifying them, into a single process. This approach is direct and efficient, making it suitable for applications that need quick results, like object detection of modes in transportation studies. However, because everything happens in a single step, the predictions might not be as refined or precise as those made using a two-stage approach. Examples of one-stage deep learning models include YOLO and SSD.

The two-stage methodology takes a more careful and detailed approach by splitting the process into two distinct steps, region proposal and classification. This two-step process makes the two-stage methodology slower than the one-stage approach but often more accurate. It allows the system to refine its predictions by carefully analysing the regions of interest. Models like Faster Region-Convolutional Neural Network (R-CNN) are examples of the two-stage methodology, often used in applications where precision is more critical than speed, such as detailed object analysis of transportation modes.

Conclusion

Synthetic Aperture Radar (SAR) remote sensing has been extensively utilized in transportation studies for over three decades, contributing significantly to monitoring and understanding various modes of transportation. The evolution of SAR sensor technology, coupled with advancements in algorithm development, has enabled the application of SAR in this domain. Moving forward, the role of SAR remote sensing is anticipated to expand, particularly in the detection and monitoring of moving transportation objects such as vehicles, ships, and aircraft.

Most transportation systems studied using SAR remote sensing are concentrated in the Northern Hemisphere, where the most developed transportation networks are located. This geographic focus reflects the higher demand for advanced transportation research in industrialized and densely populated regions. Among the different modes of transportation, maritime transportation has been the most extensively studied. The primary reason for this lies in the strong contrast between the ship, as the detected object, and the surrounding sea, which serves as a relatively homogeneous background. This distinct contrast makes ship detection more feasible and reliable using SAR. However, future research aims to address the challenges of detecting ships in more heterogeneous backgrounds, such as coastal areas or inland waterways, where the environment is more complex.

When it comes to transportation infrastructure, SAR studies have primarily focused on airports, followed by railways and harbours. Airports are often studied due to their critical role in global transportation networks and their vulnerability to environmental changes, such as land subsidence. The Differential Interferometric Synthetic Aperture Radar (DInSAR) method has been the most commonly employed technique for monitoring transportation infrastructure. By using time-series SAR data, DInSAR allows researchers to detect and measure land subsidence in three dimensions. This capability is invaluable for assessing the stability and safety of transportation infrastructure, particularly in areas prone to geological or environmental changes.

In terms of algorithms, significant advancements have been made in the last decade. Neural network algorithms began to gain traction after 2010, revolutionizing how SAR data is processed and analysed for transportation studies. More recently, deep learning techniques have emerged as the state-of-the-art approach for detecting and monitoring modes of transportation. These methods are highly effective in identifying complex patterns in SAR datasets, enabling the accurate detection of transportation objects and activities. However, deep learning is computationally intensive, requiring significant processing power and time. Therefore, future research must balance the trade-offs between accuracy and computational efficiency when applying deep learning algorithms to SAR data from diverse sources.

SAR's potential in transportation studies continues to grow, driven by technological advancements and the increasing availability of diverse SAR datasets. Future research is likely to focus on improving detection capabilities in complex environments, enhancing algorithm efficiency, and expanding the scope of applications to include emerging transportation technologies and systems.

Ethical consideration

Ethical approval and consent were not required

Data availability

Zenodo: Data on SAR remote sensing in mode transportation studies. https://doi.org/10.5281/zenodo.14768621.

The project contains the following underlaying data:

- Raw data from the articles,
- Shapefile containing point vector data to map the spatial distribution of articles or journals, and

Reference

1. Secretariat U: Efficient transport and trade facilitation to improve participation by developing countries in international trade.2003. Publisher Full Text
2. Tempfli K, Kerle N, Huurneman GC, et al.: Principles of Remote Sensing: An introductory textbook. Enschede, The Netherlands: The International Institute for Geo-Information Science and Earth Observation (ITC); 2009.
3. Flores-Anderson AI, Herndon KE, Thapa RB, et al.: The SAR Handbook: Comprehensive Methodologies for Forest Monitoring and Biomass Estimation. Huntsville, Alabama: SERVIR Global Science Coordination Office National Space Science and Technology Center; 2019.
4. Yamaguchi Y: Polarimetric SAR Imaging: Theory and Applications. Boca Raton, Florida: CRC Taylor & Francis; First edit2020.
5. Woodhouse IH: Introduction to Microwave Remote Sensing. Boca Raton, Florida: CRC Taylor & Francis; 2006.
6. Shimada M: Imaging from Spaceborne and Airborne SARs, Calibration, and Applications. Boca Raton: Florida; 2019.
7. Guoxiang LIU, Xiaoli D, Yongqi C, et al.: Ground settlement of Chek Lap Kok Airport, Hong Kong, detected by satellite synthetic aperture radar interferometry. Chin. Sci. Bull. 2001; 46(21): 1778–1782.
8. Ding XL, Liu GX, Li ZW, et al.: Ground Subsidence Monitoring in Hong Kong with Satellite SAR Interferometry. Photogramm. Eng. Remote Sensing. 2004; October: 1151–1156.
9. Pastina D, Lombardo P, Farina A, et al.: Super-resolution of polarimetric SAR images of ship targets. Signal Process. 2003; 83(8): 1737–1748. Publisher Full Text
10. Palubinskas G, Runge H: Radar signatures of a passenger car. IEEE Geosci. Remote Sens. Lett. 2007; 4(4): 644–648. Publisher Full Text
11. Huang Y, Liu F: Detecting Cars in VHR SAR Images via Semantic CFAR Algorithm. IEEE Geosci. Remote Sens. Lett. 2016; 13(6): 801–805. Publisher Full Text
12. Gens R, Van Genderen JL: Review Article SAR interferometry — issues, techniques, applications. Int. J. Remote Sens. 2007; March 2014: pp. 37–41. doi: To cite this article: R. GENS & J. L. VAN GENDEREN (1996): Review Article SAR interferometry—issues, techniques, applications, International Journal of R. Publisher Full Text
13. Ouchi K: Recent trend and advance of synthetic aperture radar with selected topics. Remote Sens. 2013; 5(2): 716–807. Publisher Full Text
14. Schnebele E, Tanyu BF, Cervone G, et al.: Review of remote sensing methodologies for pavement management and assessment. Eur. Transp. Res. Rev. 2015; 7(2). Publisher Full Text
15. Kaptein A, Janoth J, Lang O, et al.: Trends in commercial radar remote sensing industry. IEEE Geosci. Remote Sens. Mag. 2014; 2(1): 42–46. Publisher Full Text
16. Rey MT, Tunaley JK, Folinsbee JT, et al.: Application of Radon Transform Techniques to Wake Detection in Seasat-A SAR Images. IEEE Trans. Geosci. Remote Sens. 1990; 28(4): 553–560. Publisher Full Text
17. Hou B, Chen X, Jiao L: Multilayer CFAR detection of ship targets in very high resolution SAR images. IEEE Geosci. Remote Sens. Lett. 2015; 12(4): 811–815. Publisher Full Text
18. Zhang T, et al.: LS-SSDD-v1.0: A deep learning dataset dedicated to small ship detection from large-scale Sentinel-1 SAR images. Remote Sens. 2020; 12(18): 1–37. Publisher Full Text
19. Wang C, Shen P, Member S: Full Polarimetric SAR Data in Pursuit Monostatic Mode. IEEE Trans. Geosci. Remote Sens. 2015; vol. PP(March): pp. 1–15. 2019.
20. Atteia GE, Collins MJ: On the use of compact polarimetry SAR for ship detection. ISPRS J. Photogramm. Remote Sens. 2013; 80: 1–9. Publisher Full Text
21. Zhang M, Qiao B, Xin M, et al.: Phase spectrum based automatic ship detection in synthetic aperture radar images. J. Ocean Eng. Sci. 2021; 6(2): 185–195. Publisher Full Text
22. Zhang T, et al.: Balance learning for ship detection from synthetic aperture radar remote sensing imagery. ISPRS J. Photogramm. Remote Sens. 2021; 182(November): 190–207. Publisher Full Text
23. Zhang T, Zhang X, Ke X: Quad-fpn: A novel quad feature pyramid network for sar ship detection. Remote Sens. 2021; 13(14). Publisher Full Text
24. Song S, Xu B, Yang J: Ship detection in polarimetric SAR images via variational Bayesian inference. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017; 10(6): 2819–2829. Publisher Full Text
25. Hwang J, Kim D, Jung H-S: An efficient ship detection method for KOMPSAT-5 synthetic aperture radar imagery based on adaptive filtering approach. Korean J. Remote Sens. 2017; 33(1): 89–95. Publisher Full Text
26. Safety M: Land Masking Methods of Sentinel-1 SAR Imagery for Ship Detection Considering Coastline Changes and Noise. Korean J. Remote Sens. 2017; 33(4): 437–444.
27. Ramirez RA, Kwon T-H: Sentinel-1 Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) for Long-Term Remote Monitoring of Ground Subsidence: A Case Study of a Port in Busan, South Korea. KSCE J. Civ. Eng. 2022; 26: 4317–4329. Publisher Full Text
28. Stasolla M, Mallorqui JJ, Margarit G, et al.: A comparative study of operational vessel detectors for maritime surveillance using satellite-borne synthetic aperture radar. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2016; 9(6): 2687–2701. Publisher Full Text
29. Mahgoun H, Chaffa NE, Ouarzeddine M, et al.: The combination of singular values decomposition with constant false alarm algorithms to enhance ship detection in a polarimetric SAR application. Remote Sens. Appl. Soc. Environ. 2022; 27(August): 100815. Publisher Full Text
30. Wu S, Yang Z, Ding X, et al.: Two decades of settlement of Hong Kong International Airport measured with multi-temporal InSAR. Remote Sens. Environ. 2020; 248(June): 111976. Publisher Full Text
31. Liu N, Cui Z, Cao Z, et al.: Airport Detection in Large-Scale SAR Images via Line Segment Grouping and Saliency Analysis. IEEE Geosci. Remote Sens. Lett. 2018; 15(3): 434–438. Publisher Full Text
32. Liu N, Cao Z, Cui Z, et al.: Multi-layer abstraction saliency for airport detection in SAR images. IEEE Trans. Geosci. Remote Sens. 2019; 57(12): 9820–9831. Publisher Full Text
33. Tu J, Gao F, Sun J, et al.: Airport Detection in SAR Images Via Salient Line Segment Detector and Edge-Oriented Region Growing. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021; 14: 314–326. Publisher Full Text
34. Wang D, Zhang F, Ma F, et al.: A Benchmark Sentinel-1 SAR Dataset for Airport Detection. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2022; 15: 6671–6686. Publisher Full Text
35. Chen L, et al.: A new framework for automatic airports extraction from SAR images using multi-level dual attention mechanism. Remote Sens. 2020; 12(3). Publisher Full Text
36. Zhuo G, et al.: Evaluating potential ground subsidence geo-hazard of Xiamen Xiang’an new airport on reclaimed land by SAR interferometry. Sustain. 2020; 12(17). Publisher Full Text
37. Zhang L, Li C, Zhao L, et al.: A cascaded three-look network for aircraft detection in SAR images. Remote Sens. Lett. 2020; 11(1): 57–65. Publisher Full Text
38. Tan Y, Li Q, Li Y, et al.: Aircraft detection in high-resolution SAR images based on a gradient textural saliency map. Sensors (Switzerland). 2015; 15(9): 23071–23094. PubMed Abstract | Publisher Full Text | Free Full Text
39. Lv W, Dai K, Wu L, et al.: Runway Detection in SAR Images Based on Fusion Sparse Representation and Semantic Spatial Matching. IEEE Access. 2018; 6: 27984–27992. Publisher Full Text
40. Wang Y, Song Q, Wang J, et al.: Airport Runway Foreign Object Debris Detection System Based on Arc-Scanning SAR Technology. IEEE Trans. Geosci. Remote Sens. 2022; 60: 1–16. Publisher Full Text
41. Wang J, et al.: Integrating weighted feature fusion and the spatial attention module with convolutional neural networks for automatic aircraft detection from sar images. Remote Sens. 2021; 13(5): 1–21. Publisher Full Text
42. He C, Tu M, Xiong D, et al.: A component-based multi-layer parallel network for airplane detection in SAR imagery. Remote Sens. 2018; 10(7): 1–14. Publisher Full Text
43. Dai K, et al.: Diagnosing subsidence geohazard at beijing capital international airport, from high-resolution SAR interferometry. Sustain. 2020; 12(6): 1–16. Publisher Full Text
44. Liu X, Zhao C, Zhang Q, et al.: Characterizing and monitoring ground settlement of marine reclamation land of Xiamen New Airport, China with Sentinel-1 SAR Datasets. Remote Sens. 2019; 11(5). Publisher Full Text
45. Jiang L, Lin H: Integrated analysis of SAR interferometric and geological data for investigating long-term reclamation settlement of Chek Lap Kok Airport, Hong Kong. Eng. Geol. 2010; 110(3–4): 77–92. Publisher Full Text
46. Zhang S, et al.: Surface Deformation of Expansive Soil at Ankang Airport, China, Revealed by InSAR Observations. Remote Sens. 2022; 14(9). Publisher Full Text
47. Jiang Y, Liao M, Wang H, et al.: Deformation monitoring and analysis of the geological environment of Pudong International Airport with persistent scatterer SAR interferometry. Remote Sens. 2016; 8(12). Publisher Full Text
48. Ciampoli LB, Gagliardi V, Ferrante C, et al.: Displacement monitoring in airport runways by persistent scatterers sar interferometry. Remote Sens. 2020; 12(21): 1–14. Publisher Full Text
49. Tan S, Chen L, Pan Z, et al.: Geospatial contextual attention mechanism for automatic and fast airport detection in SAR imagery. IEEE Access. 2020; 8: 173627–173640. Publisher Full Text
50. Bayik C, Abdikan S: Monitoring of small-scale deformation at sea-filled Ordu-Giresun Airport, Turkey from multi-temporal SAR data. Eng. Fail. Anal. 2021; 130(September): 105738. Publisher Full Text
51. Wang T, et al.: Subsidence Monitoring and Mechanism Analysis of Anju Airport in Suining Based on InSAR and Numerical Simulation. Remote Sens. 2022; 14(15): 3759. Publisher Full Text
52. Wang Y, et al.: Using TerraSAR X-Band and Sentinel-1 C-Band SAR Interferometry for Deformation along Beijing-Tianjin Intercity Railway Analysis. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021; 14: 4832–4841. Publisher Full Text
53. Zhang Z, et al.: Deformation Feature Analysis of Qinghai-Tibet Railway Using TerraSAR-X and Sentinel-1A Time-Series Interferometry. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2019; 12(12): 5199–5212. Publisher Full Text
54. Shi X, Jiang L, Jiang H, et al.: Geohazards Analysis of the Litang-Batang Section of Sichuan-Tibet Railway Using SAR Interferometry. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021; 14: 11998–12006. Publisher Full Text
55. Qin X, Liao M, Zhang L, et al.: Structural health and stability assessment of high-speed railways via thermal dilation mapping with time-series InSAR analysis. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017; 10(6): 2999–3010. Publisher Full Text
56. Chai H, Lv X, Yao J, et al.: Off-Grid Differential Tomographic SAR and Its Application to Railway Monitoring. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2019; 12(10): 3999–4013. Publisher Full Text
57. Chang L, Dollevoet RPBJ, Hanssen RF: Nationwide Railway Monitoring Using Satellite SAR Interferometry. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017; 10(2): 596–604. Publisher Full Text
58. Henry C, Azimi SM, Merkle N: Road segmentation in SAR satellite images with deep fully convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 2018; 15(12): 1867–1871. Publisher Full Text
59. Zhang B, Wang C, Zhang H, et al.: Detectability analysis of road vehicles in radarsat-2 fully polarimetric SAR images for traffic monitoring. Sensors (Switzerland). 2017; 17(2). PubMed Abstract | Publisher Full Text | Free Full Text
60. Suanpaga W, Yoshikazu K: Riding quality model for asphalt pavement monitoring using phase array type L-band synthetic aperture radar (PALSAR). Remote Sens. 2010; 2(11): 2531–2546. Publisher Full Text
61. Liu C, Xie C, Yang J, et al.: A method for coastal oil tank detection in polarimetrie SAR images based on recognition of T-shaped harbor. J. Syst. Eng. Electron. 2018; 29(3): 499–509. Publisher Full Text
62. Wang R, et al.: A Multidirectional One-Dimensional Scanning Method for Harbor Detection from SAR Images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021; 14: 10003–10016. Publisher Full Text
63. Liu C, Xiao Y, Yang J, et al.: Harbor Detection in Polarimetric SAR Images Based on the Characteristics of Parallel Curves. IEEE Geosci. Remote Sens. Lett. 2016; 13(10): 1400–1404. Publisher Full Text
64. Zhang Y, Sun J, Lei P, et al.: SAR-based paired echo focusing and suppression of vibrating targets. IEEE Trans. Geosci. Remote Sens. 2014; 52(12): 7593–7605. Publisher Full Text
65. Zhu M, Hu G, Zhou H, et al.: H2Det: A High-Speed and High-Accurate Ship Detector in SAR Images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021; 14: 12455–12466. Publisher Full Text
66. Zhang T, Zhang X, Shi J, et al.: HyperLi-Net: A hyper-light deep learning network for high-accurate and high-speed ship detection from synthetic aperture radar imagery. ISPRS J. Photogramm. Remote Sens. 2020; 167(January): 123–153. Publisher Full Text
67. Yang X, Zhang X, Wang N, et al.: A Robust One-Stage Detector for Multiscale Ship Detection with Complex Background in Massive SAR Images. IEEE Trans. Geosci. Remote Sens. 2022; 60: 1–12. Publisher Full Text
68. Ma X, Hou S, Wang Y, et al.: Multiscale and Dense Ship Detection in SAR Images Based on Key-Point Estimation and Attention Mechanism. IEEE Trans. Geosci. Remote Sens. 2022; 60: 1–11. Publisher Full Text
69. Ao W, Xu F, Li Y, et al.: Detection and Discrimination of Ship Targets in Complex Background from Spaceborne ALOS-2 SAR Images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2018; 11(2): 536–550. Publisher Full Text
70. Wang X, Chen C: Ship Detection for Complex Background SAR Images Based on a Multiscale Variance Weighted Image Entropy Method. IEEE Geosci. Remote Sens. Lett. 2017; 14(2): 184–187. Publisher Full Text
71. Vasuki P, Roomi SMM: Automatic target classification of man-made objects in synthetic aperture radar images using Gabor wavelet and neural network. J. Appl. Remote. Sens. 2013; 7(1): 073592. Publisher Full Text
72. Xu J, Huang Z, Yan L, et al.: SAR ground moving target indication based on relative residue of DPCA processing. Sensors (Switzerland). 2016; 16(10). PubMed Abstract | Publisher Full Text | Free Full Text
73. Gao G, Wang X, Lai T: Detection of Moving Ships Based on a Combination of Magnitude and Phase in Along-Track Interferometric SAR - Part I: SIMP Metric and Its Performance. IEEE Trans. Geosci. Remote Sens. 2015; 53(7): 3565–3581. Publisher Full Text
74. Palm S, Sommer R, Janssen D, et al.: Airborne circular W-Band SAR for multiple aspect urban site monitoring. IEEE Trans. Geosci. Remote Sens. 2019; 57(9): 6996–7016. Publisher Full Text
75. Kirscht M, Mietzner J, Bickert B, et al.: An Airborne Radar Sensor for Maritime & Ground Surveillance and Reconnaissance. IEEE J. Sel. Top. Appl. EARTH Obs. Remote Sens. 2016; 9(3): 971–979. Publisher Full Text
76. Ouchi K, Tamaki S, Yaguchi H, et al.: Ship detection based on coherence images derived from cross correlation of multilook SAR images. IEEE Geosci. Remote Sens. Lett. 2004; 1(3): 184–187. Publisher Full Text
77. Kang KM, Kim DJ: Ship Velocity Estimation from Ship Wakes Detected Using Convolutional Neural Networks. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2019; 12(11): 4379–4388. Publisher Full Text
78. Zhu D, Wang X, Li G, et al.: Vessel detection via multi-order saliency-based fuzzy fusion of spaceborne and airborne SAR images. Inf. Fusion. 2022; 89: 473–485. Publisher Full Text
79. Liu C, Vachon PW, Geling GW: Improved ship detection with airborne polarimetric SAR data. Can. J. Remote. Sens. 2005; 31(1): 122–131. Publisher Full Text
80. Hoppe EJ, et al.: Historical analysis of tunnel approach displacements with satellite remote sensing. Transp. Res. Rec. 2015; 2510(2510): 15–23. Publisher Full Text
81. Bruckno B, Vaccari A, Hoppe E, et al.: Validation of Interferometric Synthetic Aperture Radar as a tool for identification of geohazards and at-risk transportation infrastructure. Pap. Earth Atmos. Sci. 2013; 1–19.
82. Zhao Q, Lin H, Gao W, et al.: InSAR detection of residual settlement of an ocean reclamation engineering project: A case study of Hong Kong International Airport. J. Oceanogr. 2011; 67(4): 415–426. Publisher Full Text
83. Hwang JI, Chae SH, Kim D, et al.: Application of artificial neural networks to ship detection from X-band Kompsat-5 imagery. Appl. Sci. 2017; 7(9). Publisher Full Text
84. Liu S, et al.: Multi-Scale Ship Detection Algorithm Based on a Lightweight Neural Network for Spaceborne SAR Images. Remote Sens. 2022; 14(5). Publisher Full Text
85. Zhang T, Zhang X: A polarization fusion network with geometric feature embedding for SAR ship classification. Pattern Recogn. 2022; 123: 108365. Publisher Full Text
86. Li X, Li D, Liu H, et al.: A-BFPN: An Attention-Guided Balanced Feature Pyramid Network for SAR Ship Detection. Remote Sens. 2022; 14(15): 3829. Publisher Full Text
87. Li L, Du Y, Du L: Vehicle Target Detection Network in SAR Images Based on Rectangle-Invariant Rotatable Convolution. Remote Sens. 2022; 14(13). Publisher Full Text
88. Niu Y, Li Y, Huang J, et al.: Efficient Encoder-Decoder Network with Estimated Direction for SAR Ship Detection. IEEE Geosci. Remote Sens. Lett. 2022; 19: 1–5. Publisher Full Text
89. Hu Q, Hu S, Liu S: BANet: A Balance Attention Network for Anchor-Free Ship Detection in SAR Images. IEEE Trans. Geosci. Remote Sens. 2022; 60: 1–12. Publisher Full Text
90. Javali A, Gupta J, Sahoo A: A review on Synthetic Aperture Radar for Earth Remote Sensing: Challenges and Opportunities. Proc. 2nd Int. Conf. Electron. Sustain. Commun. Syst. ICESC 2021. 2021; pp. 596–601. Publisher Full Text
91. Raj JA, Idicula SM, Paul B: One-Shot Learning-Based SAR Ship Classification Using New Hybrid Siamese Network. IEEE Geosci. Remote Sens. Lett. 2022; 19: 1–5. Publisher Full Text
92. Zhao M, Shi J, Wang Y: Orientation-Aware Feature Fusion Network for Ship Detection in SAR Images. IEEE Geosci. Remote Sens. Lett. 2022; 19: 1–5. Publisher Full Text
93. Yu Y, Wang B, Zhang L: Hebbian-based neural networks for bottom-up visual attention and its applications to ship detection in SAR images. Neurocomputing. 2011; 74(11): 2008–2017. Publisher Full Text
94. Chen C, He C, Hu C, et al.: MSARN: A Deep Neural Network Based on an Adaptive Recalibration Mechanism for Multiscale and Arbitrary-Oriented SAR Ship Detection. IEEE Access. 2019; 7: 159262–159283. Publisher Full Text
95. Chen C, He C, Hu C, et al.: A Deep Neural Network Based on an Attention Mechanism for SAR Ship Detection in Multiscale and Complex Scenarios. IEEE Access. 2019; 7: 104848–104863. Publisher Full Text
96. Wu Z, Hou B, Ren B, et al.: A deep detection network based on interaction of instance segmentation and object detection for sar images. Remote Sens. 2021; 13(13). Publisher Full Text
97. Bentes C, Velotto D, Tings B: Ship Classification in TerraSAR-X Images with Convolutional Neural Networks. IEEE J. Ocean. Eng. 2018; 43(1): 258–266. Publisher Full Text
98. Zhang L, et al.: Domain Knowledge Powered Two-Stream Deep Network for Few-Shot SAR Vehicle Recognition. IEEE Trans. Geosci. Remote Sens. 2022; 60: 1–15. Publisher Full Text
99. Zhu M, Hu G, Zhou H, et al.: A Ship Detection Method Via Redesigned FCOS in Large-Scale SAR Images. Remote Sens. 2022; 14(5). Publisher Full Text
100. Zou B, Qin J, Zhang L: Vehicle Detection Based on Semantic-Context Enhancement for High-Resolution SAR Images in Complex Background. IEEE Geosci. Remote Sens. Lett. 2022; 19: 1–5. Publisher Full Text
101. Zhao K, Zhou Y, Chen X, et al.: Ship detection from scratch in Synthetic Aperture Radar (SAR) images. Int. J. Remote Sens. 2021; 42(13): 5010–5024. Publisher Full Text
102. Gao S, Liu JM, Miao YH, et al.: A High-Effective Implementation of Ship Detector for SAR Images. IEEE Geosci. Remote Sens. Lett. 2022; 19: 1–5. Publisher Full Text
103. Zou L, Zhang H, Wang C, et al.: Mw-acgan: Generating multiscale high-resolution SAR images for ship detection. Sensors (Switzerland). 2020; 20(22): 1–16. PubMed Abstract | Publisher Full Text | Free Full Text
104. Li S, Fu X, Dong J: Improved Ship Detection Algorithm Based on YOLOX for SAR Outline Enhancement Image. Remote Sens. 2022; 14(16): 4070. Publisher Full Text
105. Wang J, Lin Y, Guo J, et al.: SSS-YOLO: towards more accurate detection for small ships in SAR image. Remote Sens. Lett. 2021; 12(2): 93–102. Publisher Full Text

Comments on this article Comments (0)

Version 1

VERSION 1 PUBLISHED 24 Mar 2025

Author details Author details

International Public Policy, University of Tsukuba, Tsukuba, Ibaraki Prefecture, Japan

Fatwa Ramdani
Roles: Conceptualization, Data Curation, Formal Analysis, Investigation, Methodology, Visualization, Writing – Original Draft Preparation, Writing – Review & Editing

Competing interests

No competing interests were disclosed.

Grant information

This research was supported by the University of Tsukuba Basic Research Support Program (Type S)
The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Article Versions (1)

version 1

Published: 24 Mar 2025, 14:322

https://doi.org/10.12688/f1000research.160735.1

Copyright

© 2025 Ramdani F. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Download

Export To

metrics

	Views	Downloads
F1000Research	-	-
PubMed Central Data from PMC are received and updated monthly.	-	-

Citations

0

SEE MORE DETAILS

CITE

how to cite this article

Ramdani F. An extensive review of SAR remote sensing in mode transportation studies: Major findings and future recommendations [version 1; peer review: 1 approved]. F1000Research 2025, 14:322 (https://doi.org/10.12688/f1000research.160735.1)

NOTE: If applicable, it is important to ensure the information in square brackets after the title is included in all citations of this article.

track

receive updates on this article

Track an article to receive email alerts on any updates to this article.

Open Peer Review

Version 1

VERSION 1

PUBLISHED 24 Mar 2025

Views

3

Reviewer Report 09 May 2025

Liyuan Li, Fudan University, Shanghai, Shanghai, China

Approved

https://doi.org/10.5256/f1000research.176671.r376400

This review summarizes 30 years of research progress in SAR image-based vehicle detection (aircraft, ships, railways, etc.), with clear literature organization and intuitive spatiotemporal analysis. The claim that "research concentration in the Northern Hemisphere stems from advanced transportation" may oversimplify. ... Continue reading

This review summarizes 30 years of research progress in SAR image-based vehicle detection (aircraft, ships, railways, etc.), with clear literature organization and intuitive spatiotemporal analysis. The claim that "research concentration in the Northern Hemisphere stems from advanced transportation" may oversimplify. Recommend additions: Differentiation between technology-exporting countries (e.g., Europe/US) and application hotspots (e.g., high-traffic maritime zones).Regional impacts of military vs. civilian needs (e.g., uniqueness of Arctic ship detection).The article provides valuable insights for field development. Prioritize refining multi-factor analysis of geographical distribution and methodology-region correlations. Recommend acceptance after revision.

Is the work clearly and accurately presented and does it cite the current literature?

Yes
Is the study design appropriate and is the work technically sound?

Partly
Are sufficient details of methods and analysis provided to allow replication by others?

Yes
If applicable, is the statistical analysis and its interpretation appropriate?

Partly
Are all the source data underlying the results available to ensure full reproducibility?

Yes
Are the conclusions drawn adequately supported by the results?

Partly

Competing Interests: No competing interests were disclosed.

Reviewer Expertise: remote sensing, ship detection

I confirm that I have read this submission and believe that I have an appropriate level of expertise to confirm that it is of an acceptable scientific standard.

CITE

Report a concern

Respond or Comment

Comments on this article Comments (0)

Version 1

VERSION 1 PUBLISHED 24 Mar 2025

Open Peer Review

Reviewer Status

Reviewer Reports

	Invited Reviewers
	1
Version 1 24 Mar 25	read

Liyuan Li, Fudan University, Shanghai, China

Comments on this article

All Comments(0)

Add a comment

Sign up for content alerts

Browse by related subjects

Back to all reports

Reviewer Report

3 Views

09 May 2025 | for Version 1

Liyuan Li, Fudan University, Shanghai, Shanghai, China

3 Views Cite this report Responses(0)

Approved

This review summarizes 30 years of research progress in SAR image-based vehicle detection (aircraft, ships, railways, etc.), with clear literature organization and intuitive spatiotemporal analysis. The claim that "research concentration in the Northern Hemisphere stems from advanced transportation" may oversimplify. Recommend additions: Differentiation between technology-exporting countries (e.g., Europe/US) and application hotspots (e.g., high-traffic maritime zones).Regional impacts of military vs. civilian needs (e.g., uniqueness of Arctic ship detection).The article provides valuable insights for field development. Prioritize refining multi-factor analysis of geographical distribution and methodology-region correlations. Recommend acceptance after revision.

Is the work clearly and accurately presented and does it cite the current literature?

Yes
Is the study design appropriate and is the work technically sound?

Partly
Are sufficient details of methods and analysis provided to allow replication by others?

Yes
If applicable, is the statistical analysis and its interpretation appropriate?

Partly
Are all the source data underlying the results available to ensure full reproducibility?

Yes
Are the conclusions drawn adequately supported by the results?

Partly

Competing Interests

No competing interests were disclosed.

Reviewer Expertise

remote sensing, ship detection

I confirm that I have read this submission and believe that I have an appropriate level of expertise to confirm that it is of an acceptable scientific standard.

Respond to this report

Responses (0)

[1] 1. Secretariat U: Efficient transport and trade facilitation to improve participation by developing countries in international trade.2003. Publisher Full Text

[2] 2. Tempfli K, Kerle N, Huurneman GC, et al.: Principles of Remote Sensing: An introductory textbook. Enschede, The Netherlands: The International Institute for Geo-Information Science and Earth Observation (ITC); 2009.

[3] 3. Flores-Anderson AI, Herndon KE, Thapa RB, et al.: The SAR Handbook: Comprehensive Methodologies for Forest Monitoring and Biomass Estimation. Huntsville, Alabama: SERVIR Global Science Coordination Office National Space Science and Technology Center; 2019.

[4] 4. Yamaguchi Y: Polarimetric SAR Imaging: Theory and Applications. Boca Raton, Florida: CRC Taylor & Francis; First edit2020.

[5] 5. Woodhouse IH: Introduction to Microwave Remote Sensing. Boca Raton, Florida: CRC Taylor & Francis; 2006.

[6] 6. Shimada M: Imaging from Spaceborne and Airborne SARs, Calibration, and Applications. Boca Raton: Florida; 2019.

[7] 7. Guoxiang LIU, Xiaoli D, Yongqi C, et al.: Ground settlement of Chek Lap Kok Airport, Hong Kong, detected by satellite synthetic aperture radar interferometry. Chin. Sci. Bull. 2001; 46(21): 1778–1782.

[8] 8. Ding XL, Liu GX, Li ZW, et al.: Ground Subsidence Monitoring in Hong Kong with Satellite SAR Interferometry. Photogramm. Eng. Remote Sensing. 2004; October: 1151–1156.

[9] 9. Pastina D, Lombardo P, Farina A, et al.: Super-resolution of polarimetric SAR images of ship targets. Signal Process. 2003; 83(8): 1737–1748. Publisher Full Text

[10] 10. Palubinskas G, Runge H: Radar signatures of a passenger car. IEEE Geosci. Remote Sens. Lett. 2007; 4(4): 644–648. Publisher Full Text

[11] 11. Huang Y, Liu F: Detecting Cars in VHR SAR Images via Semantic CFAR Algorithm. IEEE Geosci. Remote Sens. Lett. 2016; 13(6): 801–805. Publisher Full Text

[12] 12. Gens R, Van Genderen JL: Review Article SAR interferometry — issues, techniques, applications. Int. J. Remote Sens. 2007; March 2014: pp. 37–41. doi: To cite this article: R. GENS & J. L. VAN GENDEREN (1996): Review Article SAR interferometry—issues, techniques, applications, International Journal of R. Publisher Full Text

[13] 13. Ouchi K: Recent trend and advance of synthetic aperture radar with selected topics. Remote Sens. 2013; 5(2): 716–807. Publisher Full Text

[14] 14. Schnebele E, Tanyu BF, Cervone G, et al.: Review of remote sensing methodologies for pavement management and assessment. Eur. Transp. Res. Rev. 2015; 7(2). Publisher Full Text

[15] 15. Kaptein A, Janoth J, Lang O, et al.: Trends in commercial radar remote sensing industry. IEEE Geosci. Remote Sens. Mag. 2014; 2(1): 42–46. Publisher Full Text

[16] 16. Rey MT, Tunaley JK, Folinsbee JT, et al.: Application of Radon Transform Techniques to Wake Detection in Seasat-A SAR Images. IEEE Trans. Geosci. Remote Sens. 1990; 28(4): 553–560. Publisher Full Text

[17] 17. Hou B, Chen X, Jiao L: Multilayer CFAR detection of ship targets in very high resolution SAR images. IEEE Geosci. Remote Sens. Lett. 2015; 12(4): 811–815. Publisher Full Text

[18] 18. Zhang T, et al.: LS-SSDD-v1.0: A deep learning dataset dedicated to small ship detection from large-scale Sentinel-1 SAR images. Remote Sens. 2020; 12(18): 1–37. Publisher Full Text

[19] 19. Wang C, Shen P, Member S: Full Polarimetric SAR Data in Pursuit Monostatic Mode. IEEE Trans. Geosci. Remote Sens. 2015; vol. PP(March): pp. 1–15. 2019.

[20] 20. Atteia GE, Collins MJ: On the use of compact polarimetry SAR for ship detection. ISPRS J. Photogramm. Remote Sens. 2013; 80: 1–9. Publisher Full Text

[21] 21. Zhang M, Qiao B, Xin M, et al.: Phase spectrum based automatic ship detection in synthetic aperture radar images. J. Ocean Eng. Sci. 2021; 6(2): 185–195. Publisher Full Text

[22] 22. Zhang T, et al.: Balance learning for ship detection from synthetic aperture radar remote sensing imagery. ISPRS J. Photogramm. Remote Sens. 2021; 182(November): 190–207. Publisher Full Text

[23] 23. Zhang T, Zhang X, Ke X: Quad-fpn: A novel quad feature pyramid network for sar ship detection. Remote Sens. 2021; 13(14). Publisher Full Text

[24] 24. Song S, Xu B, Yang J: Ship detection in polarimetric SAR images via variational Bayesian inference. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017; 10(6): 2819–2829. Publisher Full Text

[25] 25. Hwang J, Kim D, Jung H-S: An efficient ship detection method for KOMPSAT-5 synthetic aperture radar imagery based on adaptive filtering approach. Korean J. Remote Sens. 2017; 33(1): 89–95. Publisher Full Text

[26] 26. Safety M: Land Masking Methods of Sentinel-1 SAR Imagery for Ship Detection Considering Coastline Changes and Noise. Korean J. Remote Sens. 2017; 33(4): 437–444.

[27] 27. Ramirez RA, Kwon T-H: Sentinel-1 Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) for Long-Term Remote Monitoring of Ground Subsidence: A Case Study of a Port in Busan, South Korea. KSCE J. Civ. Eng. 2022; 26: 4317–4329. Publisher Full Text

[28] 28. Stasolla M, Mallorqui JJ, Margarit G, et al.: A comparative study of operational vessel detectors for maritime surveillance using satellite-borne synthetic aperture radar. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2016; 9(6): 2687–2701. Publisher Full Text

[29] 29. Mahgoun H, Chaffa NE, Ouarzeddine M, et al.: The combination of singular values decomposition with constant false alarm algorithms to enhance ship detection in a polarimetric SAR application. Remote Sens. Appl. Soc. Environ. 2022; 27(August): 100815. Publisher Full Text

[30] 30. Wu S, Yang Z, Ding X, et al.: Two decades of settlement of Hong Kong International Airport measured with multi-temporal InSAR. Remote Sens. Environ. 2020; 248(June): 111976. Publisher Full Text

[31] 31. Liu N, Cui Z, Cao Z, et al.: Airport Detection in Large-Scale SAR Images via Line Segment Grouping and Saliency Analysis. IEEE Geosci. Remote Sens. Lett. 2018; 15(3): 434–438. Publisher Full Text

[32] 32. Liu N, Cao Z, Cui Z, et al.: Multi-layer abstraction saliency for airport detection in SAR images. IEEE Trans. Geosci. Remote Sens. 2019; 57(12): 9820–9831. Publisher Full Text

[33] 33. Tu J, Gao F, Sun J, et al.: Airport Detection in SAR Images Via Salient Line Segment Detector and Edge-Oriented Region Growing. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021; 14: 314–326. Publisher Full Text

[34] 34. Wang D, Zhang F, Ma F, et al.: A Benchmark Sentinel-1 SAR Dataset for Airport Detection. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2022; 15: 6671–6686. Publisher Full Text

[35] 35. Chen L, et al.: A new framework for automatic airports extraction from SAR images using multi-level dual attention mechanism. Remote Sens. 2020; 12(3). Publisher Full Text

[36] 36. Zhuo G, et al.: Evaluating potential ground subsidence geo-hazard of Xiamen Xiang’an new airport on reclaimed land by SAR interferometry. Sustain. 2020; 12(17). Publisher Full Text

[37] 37. Zhang L, Li C, Zhao L, et al.: A cascaded three-look network for aircraft detection in SAR images. Remote Sens. Lett. 2020; 11(1): 57–65. Publisher Full Text

[38] 38. Tan Y, Li Q, Li Y, et al.: Aircraft detection in high-resolution SAR images based on a gradient textural saliency map. Sensors (Switzerland). 2015; 15(9): 23071–23094. PubMed Abstract | Publisher Full Text | Free Full Text

[39] 39. Lv W, Dai K, Wu L, et al.: Runway Detection in SAR Images Based on Fusion Sparse Representation and Semantic Spatial Matching. IEEE Access. 2018; 6: 27984–27992. Publisher Full Text

[40] 40. Wang Y, Song Q, Wang J, et al.: Airport Runway Foreign Object Debris Detection System Based on Arc-Scanning SAR Technology. IEEE Trans. Geosci. Remote Sens. 2022; 60: 1–16. Publisher Full Text

[41] 41. Wang J, et al.: Integrating weighted feature fusion and the spatial attention module with convolutional neural networks for automatic aircraft detection from sar images. Remote Sens. 2021; 13(5): 1–21. Publisher Full Text

[42] 42. He C, Tu M, Xiong D, et al.: A component-based multi-layer parallel network for airplane detection in SAR imagery. Remote Sens. 2018; 10(7): 1–14. Publisher Full Text

[43] 43. Dai K, et al.: Diagnosing subsidence geohazard at beijing capital international airport, from high-resolution SAR interferometry. Sustain. 2020; 12(6): 1–16. Publisher Full Text

[44] 44. Liu X, Zhao C, Zhang Q, et al.: Characterizing and monitoring ground settlement of marine reclamation land of Xiamen New Airport, China with Sentinel-1 SAR Datasets. Remote Sens. 2019; 11(5). Publisher Full Text

[45] 45. Jiang L, Lin H: Integrated analysis of SAR interferometric and geological data for investigating long-term reclamation settlement of Chek Lap Kok Airport, Hong Kong. Eng. Geol. 2010; 110(3–4): 77–92. Publisher Full Text

[46] 46. Zhang S, et al.: Surface Deformation of Expansive Soil at Ankang Airport, China, Revealed by InSAR Observations. Remote Sens. 2022; 14(9). Publisher Full Text

[47] 47. Jiang Y, Liao M, Wang H, et al.: Deformation monitoring and analysis of the geological environment of Pudong International Airport with persistent scatterer SAR interferometry. Remote Sens. 2016; 8(12). Publisher Full Text

[48] 48. Ciampoli LB, Gagliardi V, Ferrante C, et al.: Displacement monitoring in airport runways by persistent scatterers sar interferometry. Remote Sens. 2020; 12(21): 1–14. Publisher Full Text

[49] 49. Tan S, Chen L, Pan Z, et al.: Geospatial contextual attention mechanism for automatic and fast airport detection in SAR imagery. IEEE Access. 2020; 8: 173627–173640. Publisher Full Text

[50] 50. Bayik C, Abdikan S: Monitoring of small-scale deformation at sea-filled Ordu-Giresun Airport, Turkey from multi-temporal SAR data. Eng. Fail. Anal. 2021; 130(September): 105738. Publisher Full Text

[51] 51. Wang T, et al.: Subsidence Monitoring and Mechanism Analysis of Anju Airport in Suining Based on InSAR and Numerical Simulation. Remote Sens. 2022; 14(15): 3759. Publisher Full Text

[52] 52. Wang Y, et al.: Using TerraSAR X-Band and Sentinel-1 C-Band SAR Interferometry for Deformation along Beijing-Tianjin Intercity Railway Analysis. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021; 14: 4832–4841. Publisher Full Text

[53] 53. Zhang Z, et al.: Deformation Feature Analysis of Qinghai-Tibet Railway Using TerraSAR-X and Sentinel-1A Time-Series Interferometry. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2019; 12(12): 5199–5212. Publisher Full Text

[54] 54. Shi X, Jiang L, Jiang H, et al.: Geohazards Analysis of the Litang-Batang Section of Sichuan-Tibet Railway Using SAR Interferometry. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021; 14: 11998–12006. Publisher Full Text

[55] 55. Qin X, Liao M, Zhang L, et al.: Structural health and stability assessment of high-speed railways via thermal dilation mapping with time-series InSAR analysis. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017; 10(6): 2999–3010. Publisher Full Text

[56] 56. Chai H, Lv X, Yao J, et al.: Off-Grid Differential Tomographic SAR and Its Application to Railway Monitoring. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2019; 12(10): 3999–4013. Publisher Full Text

[57] 57. Chang L, Dollevoet RPBJ, Hanssen RF: Nationwide Railway Monitoring Using Satellite SAR Interferometry. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017; 10(2): 596–604. Publisher Full Text

[58] 58. Henry C, Azimi SM, Merkle N: Road segmentation in SAR satellite images with deep fully convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 2018; 15(12): 1867–1871. Publisher Full Text

[59] 59. Zhang B, Wang C, Zhang H, et al.: Detectability analysis of road vehicles in radarsat-2 fully polarimetric SAR images for traffic monitoring. Sensors (Switzerland). 2017; 17(2). PubMed Abstract | Publisher Full Text | Free Full Text

[60] 60. Suanpaga W, Yoshikazu K: Riding quality model for asphalt pavement monitoring using phase array type L-band synthetic aperture radar (PALSAR). Remote Sens. 2010; 2(11): 2531–2546. Publisher Full Text

[61] 61. Liu C, Xie C, Yang J, et al.: A method for coastal oil tank detection in polarimetrie SAR images based on recognition of T-shaped harbor. J. Syst. Eng. Electron. 2018; 29(3): 499–509. Publisher Full Text

[62] 62. Wang R, et al.: A Multidirectional One-Dimensional Scanning Method for Harbor Detection from SAR Images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021; 14: 10003–10016. Publisher Full Text

[63] 63. Liu C, Xiao Y, Yang J, et al.: Harbor Detection in Polarimetric SAR Images Based on the Characteristics of Parallel Curves. IEEE Geosci. Remote Sens. Lett. 2016; 13(10): 1400–1404. Publisher Full Text

[64] 64. Zhang Y, Sun J, Lei P, et al.: SAR-based paired echo focusing and suppression of vibrating targets. IEEE Trans. Geosci. Remote Sens. 2014; 52(12): 7593–7605. Publisher Full Text

[65] 65. Zhu M, Hu G, Zhou H, et al.: H2Det: A High-Speed and High-Accurate Ship Detector in SAR Images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021; 14: 12455–12466. Publisher Full Text

[66] 66. Zhang T, Zhang X, Shi J, et al.: HyperLi-Net: A hyper-light deep learning network for high-accurate and high-speed ship detection from synthetic aperture radar imagery. ISPRS J. Photogramm. Remote Sens. 2020; 167(January): 123–153. Publisher Full Text

[67] 67. Yang X, Zhang X, Wang N, et al.: A Robust One-Stage Detector for Multiscale Ship Detection with Complex Background in Massive SAR Images. IEEE Trans. Geosci. Remote Sens. 2022; 60: 1–12. Publisher Full Text

[68] 68. Ma X, Hou S, Wang Y, et al.: Multiscale and Dense Ship Detection in SAR Images Based on Key-Point Estimation and Attention Mechanism. IEEE Trans. Geosci. Remote Sens. 2022; 60: 1–11. Publisher Full Text

[69] 69. Ao W, Xu F, Li Y, et al.: Detection and Discrimination of Ship Targets in Complex Background from Spaceborne ALOS-2 SAR Images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2018; 11(2): 536–550. Publisher Full Text

[70] 70. Wang X, Chen C: Ship Detection for Complex Background SAR Images Based on a Multiscale Variance Weighted Image Entropy Method. IEEE Geosci. Remote Sens. Lett. 2017; 14(2): 184–187. Publisher Full Text

[71] 71. Vasuki P, Roomi SMM: Automatic target classification of man-made objects in synthetic aperture radar images using Gabor wavelet and neural network. J. Appl. Remote. Sens. 2013; 7(1): 073592. Publisher Full Text

[72] 72. Xu J, Huang Z, Yan L, et al.: SAR ground moving target indication based on relative residue of DPCA processing. Sensors (Switzerland). 2016; 16(10). PubMed Abstract | Publisher Full Text | Free Full Text

[73] 73. Gao G, Wang X, Lai T: Detection of Moving Ships Based on a Combination of Magnitude and Phase in Along-Track Interferometric SAR - Part I: SIMP Metric and Its Performance. IEEE Trans. Geosci. Remote Sens. 2015; 53(7): 3565–3581. Publisher Full Text

[74] 74. Palm S, Sommer R, Janssen D, et al.: Airborne circular W-Band SAR for multiple aspect urban site monitoring. IEEE Trans. Geosci. Remote Sens. 2019; 57(9): 6996–7016. Publisher Full Text

[75] 75. Kirscht M, Mietzner J, Bickert B, et al.: An Airborne Radar Sensor for Maritime & Ground Surveillance and Reconnaissance. IEEE J. Sel. Top. Appl. EARTH Obs. Remote Sens. 2016; 9(3): 971–979. Publisher Full Text

[76] 76. Ouchi K, Tamaki S, Yaguchi H, et al.: Ship detection based on coherence images derived from cross correlation of multilook SAR images. IEEE Geosci. Remote Sens. Lett. 2004; 1(3): 184–187. Publisher Full Text

[77] 77. Kang KM, Kim DJ: Ship Velocity Estimation from Ship Wakes Detected Using Convolutional Neural Networks. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2019; 12(11): 4379–4388. Publisher Full Text

[78] 78. Zhu D, Wang X, Li G, et al.: Vessel detection via multi-order saliency-based fuzzy fusion of spaceborne and airborne SAR images. Inf. Fusion. 2022; 89: 473–485. Publisher Full Text

[79] 79. Liu C, Vachon PW, Geling GW: Improved ship detection with airborne polarimetric SAR data. Can. J. Remote. Sens. 2005; 31(1): 122–131. Publisher Full Text

[80] 80. Hoppe EJ, et al.: Historical analysis of tunnel approach displacements with satellite remote sensing. Transp. Res. Rec. 2015; 2510(2510): 15–23. Publisher Full Text

[81] 81. Bruckno B, Vaccari A, Hoppe E, et al.: Validation of Interferometric Synthetic Aperture Radar as a tool for identification of geohazards and at-risk transportation infrastructure. Pap. Earth Atmos. Sci. 2013; 1–19.

[82] 82. Zhao Q, Lin H, Gao W, et al.: InSAR detection of residual settlement of an ocean reclamation engineering project: A case study of Hong Kong International Airport. J. Oceanogr. 2011; 67(4): 415–426. Publisher Full Text

[83] 83. Hwang JI, Chae SH, Kim D, et al.: Application of artificial neural networks to ship detection from X-band Kompsat-5 imagery. Appl. Sci. 2017; 7(9). Publisher Full Text

[84] 84. Liu S, et al.: Multi-Scale Ship Detection Algorithm Based on a Lightweight Neural Network for Spaceborne SAR Images. Remote Sens. 2022; 14(5). Publisher Full Text

[85] 85. Zhang T, Zhang X: A polarization fusion network with geometric feature embedding for SAR ship classification. Pattern Recogn. 2022; 123: 108365. Publisher Full Text

[86] 86. Li X, Li D, Liu H, et al.: A-BFPN: An Attention-Guided Balanced Feature Pyramid Network for SAR Ship Detection. Remote Sens. 2022; 14(15): 3829. Publisher Full Text

[87] 87. Li L, Du Y, Du L: Vehicle Target Detection Network in SAR Images Based on Rectangle-Invariant Rotatable Convolution. Remote Sens. 2022; 14(13). Publisher Full Text

[88] 88. Niu Y, Li Y, Huang J, et al.: Efficient Encoder-Decoder Network with Estimated Direction for SAR Ship Detection. IEEE Geosci. Remote Sens. Lett. 2022; 19: 1–5. Publisher Full Text

[89] 89. Hu Q, Hu S, Liu S: BANet: A Balance Attention Network for Anchor-Free Ship Detection in SAR Images. IEEE Trans. Geosci. Remote Sens. 2022; 60: 1–12. Publisher Full Text

[90] 90. Javali A, Gupta J, Sahoo A: A review on Synthetic Aperture Radar for Earth Remote Sensing: Challenges and Opportunities. Proc. 2nd Int. Conf. Electron. Sustain. Commun. Syst. ICESC 2021. 2021; pp. 596–601. Publisher Full Text

[91] 91. Raj JA, Idicula SM, Paul B: One-Shot Learning-Based SAR Ship Classification Using New Hybrid Siamese Network. IEEE Geosci. Remote Sens. Lett. 2022; 19: 1–5. Publisher Full Text

[92] 92. Zhao M, Shi J, Wang Y: Orientation-Aware Feature Fusion Network for Ship Detection in SAR Images. IEEE Geosci. Remote Sens. Lett. 2022; 19: 1–5. Publisher Full Text

[93] 93. Yu Y, Wang B, Zhang L: Hebbian-based neural networks for bottom-up visual attention and its applications to ship detection in SAR images. Neurocomputing. 2011; 74(11): 2008–2017. Publisher Full Text

[94] 94. Chen C, He C, Hu C, et al.: MSARN: A Deep Neural Network Based on an Adaptive Recalibration Mechanism for Multiscale and Arbitrary-Oriented SAR Ship Detection. IEEE Access. 2019; 7: 159262–159283. Publisher Full Text

[95] 95. Chen C, He C, Hu C, et al.: A Deep Neural Network Based on an Attention Mechanism for SAR Ship Detection in Multiscale and Complex Scenarios. IEEE Access. 2019; 7: 104848–104863. Publisher Full Text

[96] 96. Wu Z, Hou B, Ren B, et al.: A deep detection network based on interaction of instance segmentation and object detection for sar images. Remote Sens. 2021; 13(13). Publisher Full Text

[97] 97. Bentes C, Velotto D, Tings B: Ship Classification in TerraSAR-X Images with Convolutional Neural Networks. IEEE J. Ocean. Eng. 2018; 43(1): 258–266. Publisher Full Text

[98] 98. Zhang L, et al.: Domain Knowledge Powered Two-Stream Deep Network for Few-Shot SAR Vehicle Recognition. IEEE Trans. Geosci. Remote Sens. 2022; 60: 1–15. Publisher Full Text

[99] 99. Zhu M, Hu G, Zhou H, et al.: A Ship Detection Method Via Redesigned FCOS in Large-Scale SAR Images. Remote Sens. 2022; 14(5). Publisher Full Text

[100] 100. Zou B, Qin J, Zhang L: Vehicle Detection Based on Semantic-Context Enhancement for High-Resolution SAR Images in Complex Background. IEEE Geosci. Remote Sens. Lett. 2022; 19: 1–5. Publisher Full Text

[101] 101. Zhao K, Zhou Y, Chen X, et al.: Ship detection from scratch in Synthetic Aperture Radar (SAR) images. Int. J. Remote Sens. 2021; 42(13): 5010–5024. Publisher Full Text

[102] 102. Gao S, Liu JM, Miao YH, et al.: A High-Effective Implementation of Ship Detector for SAR Images. IEEE Geosci. Remote Sens. Lett. 2022; 19: 1–5. Publisher Full Text

[103] 103. Zou L, Zhang H, Wang C, et al.: Mw-acgan: Generating multiscale high-resolution SAR images for ship detection. Sensors (Switzerland). 2020; 20(22): 1–16. PubMed Abstract | Publisher Full Text | Free Full Text

[104] 104. Li S, Fu X, Dong J: Improved Ship Detection Algorithm Based on YOLOX for SAR Outline Enhancement Image. Remote Sens. 2022; 14(16): 4070. Publisher Full Text

[105] 105. Wang J, Lin Y, Guo J, et al.: SSS-YOLO: towards more accurate detection for small ships in SAR image. Remote Sens. Lett. 2021; 12(2): 93–102. Publisher Full Text

An extensive review of SAR remote sensing in mode transportation studies: Major findings and future recommendations

Abstract

Background

Methods

Results

Conclusion

Keywords

Introduction

Method

Systematic search strategy

Table 1. Keyword used to search the scientific papers.

Querying result

Figure 1. The PRISMA framework flow diagram.

Classifying result

Table 2. Classification of topics for the review study.

Descriptive statistics

Result and discussion

Total number of articles and journals

Figure 2. The number of articles or journals on SAR remote sensing for the mode of transportation analysis from 1990-2022.

Geographic distribution

Figure 3. Geographic distribution of articles or journals.

Pattern on publications

Figure 4. Top ten journals that published articles related to SAR remote sensing for the mode of transportation studies.

Mode of transportation

Figure 5. The classification of the mode of transportation.

Container of the mode of transportation

Figure 6. The classification of the container of the mode of transportation is arranged in alphabetical order.

Figure 7. Sentinel-1 SAR data captured the seasonality of the Singapore Strait from April to May 2023.

Infrastructures of the mode of transportation

Figure 8. The classification of the infrastructure of the mode of transportation is arranged in alphabetical order.

Methods

Figure 9. The principle of the DinSAR technique in monitoring the land subsidence of an airport using the difference range distance (Δd).

Algorithms and taxonomy

Figure 10. The principle of the deep learning algorithm.

Figure 11. The taxonomy of algorithm used in the study of transportation using SAR remote sensing.

Conclusion

Ethical consideration

Data availability

Reference

Comments on this article Comments (0)

Open Peer Review

Comments on this article Comments (0)

Open Peer Review

Reviewer Status

Reviewer Reports

Comments on this article

Browse by related subjects

Competing Interests Policy

Stay Updated