Ship Surveillance by Integration of Space-borne SAR and AIS – Review of Current Research

Zhao, Zhi; Ji, Kefeng; Xing, Xiangwei; Zou, Huanxin; Zhou, Shilin

doi:10.1017/s0373463313000659

Cited by 56 publications

(34 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays, space-borne SAR data represent an adequate solution for vessel surveillance applications due to the capacity of SAR systems to operate day and night, on all weather conditions (Tello et al, 2006), (Zhao et al, 2014a). The Vessel Monitoring System (VMS) provides the position and identification of fishing vessels longer than 15 m. Likewise, the Automatic Identification System (AIS) gives the position and enables the identification of large merchant vessels.…”

Section: Sar For Vessel Surveillancementioning

confidence: 99%

“…SAR data acquired by the current operational satellites have high resolution and cover large areas. However, the ideal approach is the integration of SAR data with AIS data in order to achieve near-real and global surveillance, as the collected information is complementary (Zhao et al, 2014a). The automatic detection of ships based on SAR data benefits from a large number of scientific studies.…”

Section: Sar For Vessel Surveillancementioning

confidence: 99%

See 1 more Smart Citation

Sentinel-1/2 Data for Ship Traffic Monitoring on the Danube River

Negula¹,

Poenaru²,

Olteanu³

et al. 2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:After a long period of drought, the water level of the Danube River has significantly dropped especially on the Romanian sector, in July-August 2015. Danube reached the lowest water level recorded in the last 12 years, causing the blockage of the ships in the sector located close to Zimnicea Harbour. The rising sand banks in the navigable channel congested the commercial traffic for a few days with more than 100 ships involved. The monitoring of the decreasing water level and the traffic jam was performed based on Sentinel-1 and Sentinel-2 free data provided by the European Space Agency and the European Commission within the Copernicus Programme. Specific processing methods (calibration, speckle filtering, geocoding, change detection, image classification, principal component analysis, etc.) were applied in order to generate useful products that the responsible authorities could benefit from. The Sentinel data yielded good results for water mask extraction and ships detection. The analysis continued after the closure of the crisis situation when the water reached the nominal level again. The results indicate that Sentinel data can be successfully used for ship traffic monitoring, building the foundation of future endeavours for a durable monitoring of the Danube River.

show abstract

Section: Sar For Vessel Surveillancementioning

confidence: 99%

Section: Sar For Vessel Surveillancementioning

confidence: 99%

Sentinel-1/2 Data for Ship Traffic Monitoring on the Danube River

Negula¹,

Poenaru²,

Olteanu³

et al. 2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…As Zhao (2014) [90] shows, many countries in Europe, Asia and North America are working to develop ship surveillance systems to detect ships that may be used for extra-legal migration, illegal fishing, piracy and smuggling along maritime borders (cf. [91]).…”

Section: Remote Sensing Of Smuggling and Extra-legal Migrationmentioning

confidence: 99%

“…Although we did not find any studies that chronicled the active detection of crime (e.g., piracy, extra-legal immigration, smuggling), there exists a plethora of studies that present theoretical or retrospective case studies of how this might take place. These studies tested the use of TerraSAR-X, TanDEM-X, RapidEye, RADARSAT, Envisat-ASAR, Cosmo-Skymed, MODIS and ALOS images to detect the presence of ships in the Mediterranean, the North Sea, the Gulf of Aden, the Campos Basin, the English Channel, the Port of Halifax, the Bosporus, the Ionian Sea, the Southern Ocean and the Strait of Italy [90][91][92][93][94][95][96][97][98][99][100][101]. There also exists a fairly extensive literature that deals with the active detection of oil spills (e.g., Brekke and Solberg [102]), as well as illicit drift-net fishing (e.g., Horn and Zegers [103]).…”

Section: Remote Sensing Of Smuggling and Extra-legal Migrationmentioning

confidence: 99%

Validating the Remotely Sensed Geography of Crime: A Review of Emerging Issues

Kelly

2014

Remote Sensing

View full text Add to dashboard Cite

This paper explores the existing literature on the active detection of crimes using remote sensing technologies. The paper reviews sixty-one studies that use remote sensing to actively detect crime. Considering the serious consequences of misidentifying crimes or sites of crimes (e.g., opening that place and its residents up to potentially needless intrusion, intimidation, surveillance or violence), the authors were surprised to find a lack of rigorous validation of the remote sensing methods utilized in these studies. In some cases, validation was not mentioned, while in others, validation was severely hampered by security issues, rough terrain and weather conditions. The paper also considers the potential hazards of the use of Google Earth to identify crimes and criminals. The paper concludes by considering alternate, "second order" validation techniques that could add vital context and understanding to remotely sensed images in a law enforcement context. With this discussion, the authors seek to initiate a discussion on other potential "second order" validation techniques, as well as on the exponential growth of surveillance in our everyday lives.

show abstract

“…Many investigations relating to ship detection in SAR imagery have been carried out. Traditional methods [7][8][9] detect targets after sea-land segmentation and utilize the hand-crafted features for discrimination, which has poor performance on nearshore areas and has difficulty ruling out false alarms, such as icebergs and small islands. Additionally, the existence of speckle noises and motion blurring in SAR images causes undesirable differences between ships, which creates difficulty for traditional SAR ship detection combined with a downscaled shallow layer and an up-sampled deep layer to predict the bounding box.…”

Section: Introductionmentioning

confidence: 99%

Contextual Region-Based Convolutional Neural Network with Multilayer Fusion for SAR Ship Detection

et al. 2017

Self Cite

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) ship detection has been playing an increasingly essential role in marine monitoring in recent years. The lack of detailed information about ships in wide swath SAR imagery poses difficulty for traditional methods in exploring effective features for ship discrimination. Being capable of feature representation, deep neural networks have achieved dramatic progress in object detection recently. However, most of them suffer from the missing detection of small-sized targets, which means that few of them are able to be employed directly in SAR ship detection tasks. This paper discloses an elaborately designed deep hierarchical network, namely a contextual region-based convolutional neural network with multilayer fusion, for SAR ship detection, which is composed of a region proposal network (RPN) with high network resolution and an object detection network with contextual features. Instead of using low-resolution feature maps from a single layer for proposal generation in a RPN, the proposed method employs an intermediate layer combined with a downscaled shallow layer and an up-sampled deep layer to produce region proposals. In the object detection network, the region proposals are projected onto multiple layers with region of interest (ROI) pooling to extract the corresponding ROI features and contextual features around the ROI. After normalization and rescaling, they are subsequently concatenated into an integrated feature vector for final outputs. The proposed framework fuses the deep semantic and shallow high-resolution features, improving the detection performance for small-sized ships. The additional contextual features provide complementary information for classification and help to rule out false alarms. Experiments based on the Sentinel-1 dataset, which contains twenty-seven SAR images with 7986 labeled ships, verify that the proposed method achieves an excellent performance in SAR ship detection.

show abstract

Ship Surveillance by Integration of Space-borne SAR and AIS – Review of Current Research

Cited by 56 publications

References 27 publications

Sentinel-1/2 Data for Ship Traffic Monitoring on the Danube River

Sentinel-1/2 Data for Ship Traffic Monitoring on the Danube River

Validating the Remotely Sensed Geography of Crime: A Review of Emerging Issues

Contextual Region-Based Convolutional Neural Network with Multilayer Fusion for SAR Ship Detection

Contact Info

Product

Resources

About