Fishing boat detection using Sentinel-1 validated with VIIRS Data

Abstract Detecting fishing boat activity is still a challenge for the biggest archipelago countries, such as Indonesia, to monitor the huge marine area. Space technology using sensors SAR to detect ships has been developed since 1985. However, the cost of using SAR images is one of the barriers to operational aspects, mainly for detecting fishing boats to deter IUU fishing activities. This research aims to evaluate the use of Sentinel 1-SAR imagery for identifying fishing boats from space. We used VIIRS data for validating the purposes. Both data sources could be accessed freely. The object detection process can be derived into three steps: pre-processing, object detection and object validation. We used the constant false alarm rate (CFAR) method to discriminate against objects at sea. To identify fishing vessels, we used the size of the vessels and the intensity of light captured by VIIRS. According to the findings, 21 boats were discovered using sentinel 1-SAR imagery and four boats using VIIRS data based on the the area of interest.

Download Full-text

Detection of Small Ship Objects Using Anchor Boxes Cluster and Feature Pyramid Network Model for SAR Imagery

Journal of Marine Science and Engineering ◽

10.3390/jmse8020112 ◽

2020 ◽

Vol 8 (2) ◽

pp. 112 ◽

Cited By ~ 3

Author(s):

Peng Chen ◽

Ying Li ◽

Hui Zhou ◽

Bingxin Liu ◽

Peng Liu

Keyword(s):

Object Detection ◽

Clustering Algorithm ◽

Weather Conditions ◽

Object Identification ◽

Maritime Transportation ◽

Small Object ◽

Sar Images ◽

Feature Pyramid ◽

Sar Imagery ◽

Small Ship

The synthetic aperture radar (SAR) has a special ability to detect objects in any climate and weather conditions. Consequently, SAR images are widely used in maritime transportation safety and fishery law enforcement for maritime object detection. Currently, deep-learning models are being extensively used for the detection of objects from images. Among them, the feature pyramid network (FPN) uses pyramids for representing semantic information regardless of the scale and has an improved accuracy of object detection. It is also suitable for the detection of multiple small ship objects in SAR images. This study aims to resolve the problems associated with small-object and multi-object ship detection in complex scenarios e.g., when a ship nears the port, by proposing a detection method based on an optimized FPN model. The feature pyramid model is first embedded in a traditional region proposal network (RPN) and mapped into a new feature space for object identification. Subsequently, the k-means clustering algorithm based on the shape similar distance (SSD) measure is used to optimize the FPN. Initial anchor boxes and tests are created using the SAR ship dataset. Experimental results show that the proposed algorithm for object detection shows an accuracy of 98.62%. Compared with Yolo, the RPN based on VGG/ResNet, FPN based on VGG/ResNet, and other models in complex scenarios, the proposed model shows a higher accuracy rate and better overall performance.

Download Full-text

Coupling Denoising to Detection for SAR Imagery

Applied Sciences ◽

10.3390/app11125569 ◽

2021 ◽

Vol 11 (12) ◽

pp. 5569

Author(s):

Sujin Shin ◽

Youngjung Kim ◽

Insu Hwang ◽

Junhee Kim ◽

Sungho Kim

Keyword(s):

Remote Sensing ◽

Object Detection ◽

Performance Improvement ◽

Information Loss ◽

Synthetic Aperture ◽

Sar Image ◽

Remote Sensing Images ◽

Sar Images ◽

Backbone Networks ◽

Sar Imagery

Detecting objects in synthetic aperture radar (SAR) imagery has received much attention in recent years since SAR can operate in all-weather and day-and-night conditions. Due to the prosperity and development of convolutional neural networks (CNNs), many previous methodologies have been proposed for SAR object detection. In spite of the advance, existing detection networks still have limitations in boosting detection performance because of inherently noisy characteristics in SAR imagery; hence, separate preprocessing step such as denoising (despeckling) is required before utilizing the SAR images for deep learning. However, inappropriate denoising techniques might cause detailed information loss and even proper denoising methods does not always guarantee performance improvement. In this paper, we therefore propose a novel object detection framework that combines unsupervised denoising network into traditional two-stage detection network and leverages a strategy for fusing region proposals extracted from both raw SAR image and synthetically denoised SAR image. Extensive experiments validate the effectiveness of our framework on our own object detection datasets constructed with remote sensing images from TerraSAR-X and COSMO-SkyMed satellites. Extensive experiments validate the effectiveness of our framework on our own object detection datasets constructed with remote sensing images from TerraSAR-X and COSMO-SkyMed satellites. The proposed framework shows better performances when we compared the model with using only noisy SAR images and only denoised SAR images after despeckling under multiple backbone networks.

Download Full-text

Realizing Target Detection in SAR Images Based on Multiscale Superpixel Fusion

Sensors ◽

10.3390/s21051643 ◽

2021 ◽

Vol 21 (5) ◽

pp. 1643

Author(s):

Ming Liu ◽

Shichao Chen ◽

Fugang Lu ◽

Mengdao Xing ◽

Jingbiao Wei

Keyword(s):

Synthetic Aperture Radar ◽

False Alarm ◽

False Alarm Rate ◽

Target Detection ◽

Synthetic Aperture ◽

False Alarms ◽

Sar Image ◽

Constant False Alarm Rate ◽

Sar Images ◽

Complex Scenes

For target detection in complex scenes of synthetic aperture radar (SAR) images, the false alarms in the land areas are hard to eliminate, especially for the ones near the coastline. Focusing on the problem, an algorithm based on the fusion of multiscale superpixel segmentations is proposed in this paper. Firstly, the SAR images are partitioned by using different scales of superpixel segmentation. For the superpixels in each scale, the land-sea segmentation is achieved by judging their statistical properties. Then, the land-sea segmentation results obtained in each scale are combined with the result of the constant false alarm rate (CFAR) detector to eliminate the false alarms located on the land areas of the SAR image. In the end, to enhance the robustness of the proposed algorithm, the detection results obtained in different scales are fused together to realize the final target detection. Experimental results on real SAR images have verified the effectiveness of the proposed algorithm.

Download Full-text

Extended GLRT Detection of Moving Targets for Multichannel SAR Based on Generalized Steering Vector

Sensors ◽

10.3390/s21041478 ◽

2021 ◽

Vol 21 (4) ◽

pp. 1478

Author(s):

Chong Song ◽

Bingnan Wang ◽

Maosheng Xiang ◽

Wei Li

Keyword(s):

Likelihood Ratio ◽

Likelihood Ratio Test ◽

Moving Target ◽

Ratio Test ◽

Constant False Alarm Rate ◽

Moving Targets ◽

Sar Images ◽

Steering Vector ◽

Current Cell ◽

Data Vector

A generalized likelihood ratio test (GLRT) with the constant false alarm rate (CFAR) property was recently developed for adaptive detection of moving targets in focusing synthetic aperture radar (SAR) images. However, in the multichannel SAR-ground moving-target indication (SAR-GMTI) system, image defocus is inevitable, which will remarkably degrade the performance of the GLRT detector, especially for the lower radar cross-section (RCS) and slower radial velocity moving targets. To address this issue, based on the generalized steering vector (GSV), an extended GLRT detector is proposed and its performance is evaluated by the optimum likelihood ratio test (LRT) in the Neyman-Pearson (NP) criterion. The joint data vector formulated by the current cell and its adjacent cells is used to obtain the GSV, and then the extended GLRT is derived, which coherently integrates signal and accomplishes moving-target detection and parameter estimation. Theoretical analysis and simulated SAR data demonstrate the effectiveness and robustness of the proposed detector in the defocusing SAR images.

Download Full-text

Synthetic Aperture Radar Processing Approach for Simultaneous Target Detection and Image Formation

Sensors ◽

10.3390/s18103377 ◽

2018 ◽

Vol 18 (10) ◽

pp. 3377 ◽

Cited By ~ 5

Author(s):

Jifang Pei ◽

Yulin Huang ◽

Weibo Huo ◽

Yuxuan Miao ◽

Yin Zhang ◽

...

Keyword(s):

Synthetic Aperture Radar ◽

Target Detection ◽

Time Domain ◽

Image Formation ◽

Visual Saliency ◽

Synthetic Aperture ◽

Sar Images ◽

Saliency Maps ◽

Sar Imaging ◽

Sar Imagery

Finding out interested targets from synthetic aperture radar (SAR) imagery is an attractive but challenging problem in SAR application. Traditional target detection is independent on SAR imaging process, which is purposeless and unnecessary. Hence, a new SAR processing approach for simultaneous target detection and image formation is proposed in this paper. This approach is based on SAR imagery formation in time domain and human visual saliency detection. First, a series of sub-aperture SAR images with resolutions from low to high are generated by the time domain SAR imaging method. Then, those multiresolution SAR images are detected by the visual saliency processing, and the corresponding intermediate saliency maps are obtained. The saliency maps are accumulated until the result with a sufficient confidence level. After some screening operations, the target regions on the imaging scene are located, and only these regions are focused with full aperture integration. Finally, we can get the SAR imagery with high-resolution detected target regions but low-resolution clutter background. Experimental results have shown the superiority of the proposed approach for simultaneous target detection and image formation.

Download Full-text

Localization Approach of Damage in Welded Joint Based on Acoustic Emission Beamforming

Volume 13: Vibration, Acoustics and Wave Propagation ◽

10.1115/imece2014-37658 ◽

2014 ◽

Author(s):

Denghong Xiao ◽

Tian He ◽

Xiandong Liu ◽

Yingchun Shan

Keyword(s):

Acoustic Emission ◽

Welded Joints ◽

Welded Joint ◽

Steel Tube ◽

Area Of Interest ◽

Novel Approach ◽

Line Array ◽

The Cost ◽

Localization Approach ◽

Ae Signals

A novel approach of locating damage in welded joints is proposed based on acoustic emission (AE) beamforming, which is particularly applicable to complex plate-like structures. First, five AE sensors used to obtain AE signals generated from damage are distributed on the surface of the structure in a uniform line array. Then the beamforming method is adopted to detect the weld joints in the area of interest rather than all the points of the whole structure, and to determine the location and obtain information of AE sources. In order to study the ability of the proposed method more comprehensively, a rectangular steel tube with welded joints is taken for the pencil-lead-broken test. The localization results indicate that the proposed localization approach can effectively localize the failure welded joints. This improvement greatly reduces the cost of computation and also improves the efficiency of localization work compared with the traditional beamforming.

Download Full-text

Promoting Cooperation of Monitoring, Control, and Surveillance of IUU Fishing in the Asia-Pacific

Sustainability ◽

10.3390/su131810231 ◽

2021 ◽

Vol 13 (18) ◽

pp. 10231

Author(s):

Iwao Fujii ◽

Yumi Okochi ◽

Hajime Kawamura

Keyword(s):

Literature Review ◽

Coastal Areas ◽

Asia Pacific ◽

Sustainable Fisheries ◽

Communication Platform ◽

Iuu Fishing ◽

Fishing Vessels ◽

Vessel Tracking ◽

The Status ◽

Current Systems

Illegal, unreported, and unregulated (IUU) fishing is becoming a growing threat to sustainable fisheries and the economy worldwide. To solve this issue, various efforts on monitoring, control, and surveillance (MCS) have been made at the national, regional, and international levels. However, there is still the lack of measures against IUU fishing vessels at the multilateral level. Here, we assessed the situations of fisheries, and the current systems and challenges of MCS in eight Asia-Pacific countries with a focus on MCS of IUU fishing vessels at sea. Through a literature review and interviews, we confirmed that IUU fishing was linked with the status of fisheries in each country, and that each country implements various MCS measures with different emphases. However, there was a trend of enhancing or newly establishing four areas of MCS: vessel tracking, patrol, onboard observers, and port State measures, with amended or newly adopted laws. We also identified challenges of MCS such as insufficient MCS in coastal areas and fragmented cooperation among the countries. Based on our findings, we advance several recommendations including the enhancement of cooperation among stakeholders, especially fishers, for co-monitoring in coastal areas and the establishment of a communication platform for Asia-Pacific countries.

Download Full-text

FISHING-VESSEL DETECTION USING SYNTHETIC APERTURE RADAR (SAR) SENTINEL-1 (CASE STUDY: JAVA SEA)

International Journal of Remote Sensing and Earth Sciences (IJReSES) ◽

10.30536/j.ijreses.2019.v16.a3235 ◽

2020 ◽

Vol 16 (2) ◽

pp. 131

Author(s):

Sarah Putri Fitriani ◽

Jonson Lumban Gaol ◽

Dony Kushardono

Keyword(s):

Synthetic Aperture Radar ◽

Object Identification ◽

Synthetic Aperture ◽

Overlay Analysis ◽

Constant False Alarm Rate ◽

Fishing Vessel ◽

Fishing Vessels ◽

Sensing Technology ◽

Vessel Detection ◽

Aperture Radar

The synthetic aperture radar (SAR) instrument of Sentinel-1 is a remote sensing technology being developed to enable the detection of vessel distribution. The purpose of this research is to study fishing-vessel detection using SAR Sentinel-1 data. In this study, the constant false alarm rate method (CFAR) for Sentinel-1 data is used for the detection of fishing vessels in Indramayu sea waters. The data used to detect ships includes SAR Sentinel-1A images and vessel monitoring system (VMS) data acquired on 8 March and 20 March 2018. SAR Sentinel-1 imagery data is obtained through pre-processing and object identification using Sentinel Application Platform (SNAP) software. Overlay analysis is then used to enable discrimination of immovable and movable objects and validation of ships detected from SAR Sentinel-1 imagery is performed using VMS data. From overlay analysis, 46 ships were detected on 8 March 2018 and 39 ships on 20 March 2018. Of all the ship points detected using SAR Sentinel-1, 7.06% could be detected by VMS data while 92.94% could not. The number of ships detected by SAR Sentinel-1 is greater than those detected by VMS because not all ships use VMS devices.

Download Full-text

Scale Expansion Pyramid Network for Cross-Scale Object Detection in Sar Images

10.1109/igarss47720.2021.9554986 ◽

2021 ◽

Author(s):

Zheng Zhou ◽

Rui Guan ◽

Zongyong Cui ◽

Zongjie Cao ◽

Yiming Pi ◽

...

Keyword(s):

Object Detection ◽

Sar Images ◽

Scale Expansion

Download Full-text

Ship-Iceberg Classification in SAR and Multispectral Satellite Images with Neural Networks

Remote Sensing ◽

10.3390/rs12152353 ◽

2020 ◽

Vol 12 (15) ◽

pp. 2353

Author(s):

Henning Heiselberg

Keyword(s):

Neural Networks ◽

Satellite Images ◽

Deep Neural Networks ◽

Data Augmentation ◽

Neural Nets ◽

The Arctic ◽

Support Vector ◽

Sar Images ◽

Multispectral Satellite Images ◽

The Cost

Classification of ships and icebergs in the Arctic in satellite images is an important problem. We study how to train deep neural networks for improving the discrimination of ships and icebergs in multispectral satellite images. We also analyze synthetic-aperture radar (SAR) images for comparison. The annotated datasets of ships and icebergs are collected from multispectral Sentinel-2 data and taken from the C-CORE dataset of Sentinel-1 SAR images. Convolutional Neural Networks with a range of hyperparameters are tested and optimized. Classification accuracies are considerably better for deep neural networks than for support vector machines. Deeper neural nets improve the accuracy per epoch but at the cost of longer processing time. Extending the datasets with semi-supervised data from Greenland improves the accuracy considerably whereas data augmentation by rotating and flipping the images has little effect. The resulting classification accuracies for ships and icebergs are 86% for the SAR data and 96% for the MSI data due to the better resolution and more multispectral bands. The size and quality of the datasets are essential for training the deep neural networks, and methods to improve them are discussed. The reduced false alarm rates and exploitation of multisensory data are important for Arctic search and rescue services.

Download Full-text