scholarly journals Automated Procurement of Training Data for Machine Learning Algorithm on Ship Detection Using AIS Information

2020 ◽  
Vol 12 (9) ◽  
pp. 1443
Author(s):  
Juyoung Song ◽  
Duk-jin Kim ◽  
Ki-mook Kang
Keyword(s):  
Learning Algorithm ◽  
Doppler Frequency ◽  
Training Model ◽  
Training Data ◽  
Automatic Identification ◽  
Identification System ◽  
Visual Interpretation ◽  
Sar Images ◽  
Ship Detection ◽  
Detection Model

Development of convolutional neural network (CNN) optimized for object detection, led to significant developments in ship detection. Although training data critically affect the performance of the CNN-based training model, previous studies focused mostly on enhancing the architecture of the training model. This study developed a sophisticated and automatic methodology to generate verified and robust training data by employing synthetic aperture radar (SAR) images and automatic identification system (AIS) data. The extraction of training data initiated from interpolating the discretely received AIS positions to the exact position of the ship at the time of image acquisition. The interpolation was conducted by applying a Kalman filter, followed by compensating the Doppler frequency shift. The bounding box for the ship was constructed tightly considering the installation of the AIS equipment and the exact size of the ship. From 18 Sentinel-1 SAR images using a completely automated procedure, 7489 training data were obtained, compared with a different set of training data from visual interpretation. The ship detection model trained using the automatic training data obtained 0.7713 of overall detection performance from 3 Sentinel-1 SAR images, which exceeded that of manual training data, evading the artificial structures of harbors and azimuth ambiguity ghost signals from detection.

scholarly journals LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images

2020 ◽  
Vol 12 (18) ◽  
pp. 2997 ◽  
Author(s):  
Tianwen Zhang ◽  
Xiaoling Zhang ◽  
Xiao Ke ◽  
Xu Zhan ◽  
Jun Shi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Google Earth ◽  
Detection Methods ◽  
False Alarms ◽  
Automatic Identification ◽  
Identification System ◽  
Sar Images ◽  
Ship Detection ◽  
Small Ship

Ship detection in synthetic aperture radar (SAR) images is becoming a research hotspot. In recent years, as the rise of artificial intelligence, deep learning has almost dominated SAR ship detection community for its higher accuracy, faster speed, less human intervention, etc. However, today, there is still a lack of a reliable deep learning SAR ship detection dataset that can meet the practical migration application of ship detection in large-scene space-borne SAR images. Thus, to solve this problem, this paper releases a Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-v1.0) from Sentinel-1, for small ship detection under large-scale backgrounds. LS-SSDD-v1.0 contains 15 large-scale SAR images whose ground truths are correctly labeled by SAR experts by drawing support from the Automatic Identification System (AIS) and Google Earth. To facilitate network training, the large-scale images are directly cut into 9000 sub-images without bells and whistles, providing convenience for subsequent detection result presentation in large-scale SAR images. Notably, LS-SSDD-v1.0 has five advantages: (1) large-scale backgrounds, (2) small ship detection, (3) abundant pure backgrounds, (4) fully automatic detection flow, and (5) numerous and standardized research baselines. Last but not least, combined with the advantage of abundant pure backgrounds, we also propose a Pure Background Hybrid Training mechanism (PBHT-mechanism) to suppress false alarms of land in large-scale SAR images. Experimental results of ablation study can verify the effectiveness of the PBHT-mechanism. LS-SSDD-v1.0 can inspire related scholars to make extensive research into SAR ship detection methods with engineering application value, which is conducive to the progress of SAR intelligent interpretation technology.

scholarly journals Lightweight Ship Detection Methods Based on YOLOv3 and DenseNet

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Zhelin Li ◽  
Lining Zhao ◽  
Xu Han ◽  
Mingyang Pan ◽  
Feng-Jang Hwang
Keyword(s):  
Spatial Separation ◽  
Experimental Results ◽  
Detection Methods ◽  
Automatic Identification ◽  
Identification System ◽  
Ship Detection ◽  
Detection Model ◽  
Backbone Network ◽  
Time Requirements ◽  
Detection Speed

Ship detection is one of the most important research contents of ship intelligent navigation and monitoring. As a supplement to classical navigational equipment such as radar and the Automatic Identification System (AIS), target detection based on computer vision and deep learning has become a new important method. A target detector called YOLOv3 has the advantages of detection speed and accuracy and meets the real-time requirements for ship detection. However, YOLOv3 has a large number of backbone network parameters and requires high hardware performance, which is not conducive to the popularization of applications. On the basis of YOLOv3, this paper proposes a lightweight ship detection model (LSDM) in which the backbone network is improved by using dense connection inspired from DenseNet, and the feature pyramid networks are improved by using spatial separation convolution to replace normal convolution. The two improvements reduce parameters and optimize the network structure greatly. The experimental results show that, with only one-third of parameters of YOLOv3, the LSDM has higher accuracy and speed for ship detection. In addition, the LSDM is simplified further by reducing the number of densely connected units to form a model called LSDM-tiny. The experimental results show that, LSDM-tiny has similar detection speed with YOLOv3-tiny, but has a lot higher accuracy.

Applying machine learning to satellite imagery and vessel-tracking data to detect chronic oil pollution from ships at sea and identify the polluters

2021 ◽  
Author(s):  
Jona Raphael ◽  
Ben Eggleston ◽  
Ryan Covington ◽  
Tatianna Evanisko ◽  
Sasha Bylsma ◽  
...  
Keyword(s):  
Machine Learning ◽  
Oil Spills ◽  
Oil Pollution ◽  
Satellite Image ◽  
Petroleum Products ◽  
Training Data ◽  
Automatic Identification ◽  
Identification System ◽  
Sar Imagery ◽  
Pollution Events

<p><strong>Operational oil discharges from ships</strong>, also known as “bilge dumping,” have been identified as a major source of petroleum products entering our oceans, cumulatively exceeding the largest oil spills, such as the Exxon Valdez and Deepwater Horizon spills, even when considered over short time spans. However, we still don’t have a good estimate of</p><ul><li>How much oil is being discharged;</li> <li>Where the discharge is happening;</li> <li>Who the responsible vessels are.</li> </ul><p>This makes it difficult to prevent and effectively respond to oil pollution that can damage our marine and coastal environments and economies that depend on them.</p><p> </p><p>In this presentation we will share SkyTruth’s recent work to address these gaps using machine learning tools to detect oil pollution events and identify the responsible vessels when possible. We use a convolutional neural network (CNN) in a ResNet-34 architecture to perform <strong>pixel segmentation</strong> on all incoming <strong>Sentinel-1 synthetic aperture radar</strong> (SAR) imagery to classify slicks. Despite the satellites’ incomplete oceanic coverage, we have been detecting an average of <strong>135 vessel slicks per month</strong>, and have identified several geographic hotspots where oily discharges are occurring regularly. For the images that capture a vessel in the act of discharging oil, we rely on an <strong>Automatic Identification System</strong> (AIS) database to extract details about the ships, including vessel type and flag state. We will share our experience</p><ul><li>Making sufficient training data from inherently sparse satellite image datasets;</li> <li>Building a computer vision model using PyTorch and fastai;</li> <li>Fully automating the process in the Amazon Web Services (AWS) cloud.</li> </ul><p>The application has been running continuously since August 2020, has processed over 380,000 Sentinel-1 images, and has populated a database with more than 1100 high-confidence slicks from vessels. We will be discussing <strong>preliminary results</strong> from this dataset and remaining challenges to be overcome.</p><p> </p><p>Our objective in making this information and the underlying code, models, and training data <strong>freely available to the public</strong> and governments around the world is to enable public pressure campaigns to improve the prevention of and response to pollution events. Learn more at https://skytruth.org/bilge-dumping/</p>

scholarly journals Ship Detection from X-Band SAR Images Using M2Det Deep Learning Model

2020 ◽  
Vol 10 (21) ◽  
pp. 7751
Author(s):  
Seong-Jae Hong ◽  
Won-Kyung Baek ◽  
Hyung-Sup Jung
Keyword(s):  
Deep Learning ◽  
Learning Process ◽  
Intensity Difference ◽  
Sar Images ◽  
Ship Detection ◽  
Detection Model ◽  
Learning Techniques ◽  
Vessel Detection ◽  
Intensity Images ◽  
Deep Learning Model

Synthetic aperture radar (SAR) images have been used in many studies for ship detection because they can be captured without being affected by time and weather. In recent years, the development of deep learning techniques has facilitated studies on ship detection in SAR images using deep learning techniques. However, because the noise from SAR images can negatively affect the learning of the deep learning model, it is necessary to reduce the noise through preprocessing. In this study, deep learning vessel detection was performed using preprocessed SAR images, and the effects of the preprocessing of the images on deep learning vessel detection were compared and analyzed. Through the preprocessing of SAR images, (1) intensity images, (2) decibel images, and (3) intensity difference and texture images were generated. The M2Det object detection model was used for the deep learning process and preprocessed SAR images. After the object detection model was trained, ship detection was performed using test images. The test results are presented in terms of precision, recall, and average precision (AP), which were 93.18%, 91.11%, and 89.78% for the intensity images, respectively, 94.16%, 94.16%, and 92.34% for the decibel images, respectively, and 97.40%, 94.94%, and 95.55% for the intensity difference and texture images, respectively. From the results, it can be found that the preprocessing of the SAR images can facilitate the deep learning process and improve the ship detection performance. The results of this study are expected to contribute to the development of deep learning-based ship detection techniques in SAR images in the future.

scholarly journals Improved Testing of AI-Based Anomaly Detection Systems Using Synthetic Surveillance Data

Proceedings ◽  
2020 ◽  
Vol 59 (1) ◽  
pp. 9
Author(s):  
Antoine Chevrot ◽  
Alexandre Vernotte ◽  
Pierre Bernabe ◽  
Aymeric Cretin ◽  
Fabien Peureux ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Cyber Security ◽  
Surveillance Data ◽  
Automatic Identification ◽  
Identification System ◽  
Surveillance Systems ◽  
Sea Transport ◽  
Detection Model ◽  
Detection Systems ◽  
Anomalous Data

Major transportation surveillance protocols have not been specified with cyber security in mind and therefore provide no encryption nor identification. These issues expose air and sea transport to false data injection attacks (FDIAs), in which an attacker modifies, blocks or emits fake surveillance messages to dupe controllers and surveillance systems. There has been growing interest in conducting research on machine learning-based anomaly detection systems that address these new threats. However, significant amounts of data are needed to achieve meaningful results with this type of model. Raw, genuine data can be obtained from existing databases but need to be preprocessed before being fed to a model. Acquiring anomalous data is another challenge: such data is much too scarce for both the Automatic Dependent Surveillance–Broadcast (ADS-B) and the Automatic Identification System (AIS). Crafting anomalous data by hand, which has been the sole method applied to date, is hardly suitable for broad detection model testing. This paper proposes an approach built upon existing libraries and ideas that offers ML researchers the necessary tools to facilitate the access and processing of genuine data as well as to automatically generate synthetic anomalous surveillance data to constitute broad, elaborated test datasets. We demonstrate the usability of the approach by discussing work in progress that includes the reproduction of related work, creation of relevant datasets and design of advanced anomaly detection models for both domains of application.

scholarly journals Large-Scale Automatic Vessel Monitoring Based on Dual-Polarization Sentinel-1 and AIS Data

2019 ◽  
Vol 11 (9) ◽  
pp. 1078 ◽  
Author(s):  
Ramona Pelich ◽  
Marco Chini ◽  
Renaud Hostache ◽  
Patrick Matgen ◽  
Carlos Lopez-Martinez ◽  
...  
Keyword(s):  
Detection Rate ◽  
Large Scale ◽  
Added Value ◽  
Automatic Identification ◽  
Identification System ◽  
Dual Polarization ◽  
Ship Detection ◽  
Traffic Conditions ◽  
Intensity Images ◽  
Polarization Channel

This research addresses the use of dual-polarimetric descriptors for automatic large-scale ship detection and characterization from synthetic aperture radar (SAR) data. Ship detection is usually performed independently on each polarization channel and the detection results are merged subsequently. In this study, we propose to make use of the complex coherence between the two polarization channels of Sentinel-1 and to perform vessel detection in this domain. Therefore, an automatic algorithm, based on the dual-polarization coherence, and applicable to entire large scale SAR scenes in a timely manner, is developed. Automatic identification system (AIS) data are used for an extensive and also large scale cross-comparison with the SAR-based detections. The comparative assessment allows us to evaluate the added-value of the dual-polarization complex coherence, with respect to SAR intensity images in ship detection, as well as the SAR detection performances depending on a vessel’s size. The proposed methodology is justified statistically and tested on Sentinel-1 data acquired over two different and contrasting, in terms of traffic conditions, areas: the English Channel the and Pacific coastline of Mexico. The results indicate a very high SAR detection rate, i.e., >80%, for vessels larger than 60 m and a decrease of detection rate up to 40 % for smaller size vessels. In addition, the analysis highlights many SAR detections without corresponding AIS positions, indicating the complementarity of SAR with respect to cooperative sources for detecting dark vessels.

scholarly journals X-Band/C-Band-Comparison of Ship Wake Detectability

2020 ◽  
Author(s):  
Björn Tings ◽  
Sven Jacobsen ◽  
Stefan Wiehle ◽  
Egbert Schwarz ◽  
Holger Daedelow
Keyword(s):  
Detection Performance ◽  
Automatic Identification ◽  
Identification System ◽  
Sar Images ◽  
Ship Wake ◽  
X Band ◽  
System Data ◽  
Wake Detection ◽  
Sar Imagery ◽  
The Individual

Recent studies investigated the detectability of ship wake signatures on SAR imagery using a large number of SAR images collocated with Automatic Identification System data for training machine learning models. These detectability models are in agreement with oceanographic expectations from preceding studies and can therefore be used for comparing the performance of different SAR sensors in terms of wake detectability. Previous model comparisons showed better wake detection performance of TerraSAR-X (TS-X) than of RADARSAT-2 (RS2) and Sentinel-1 (S1). A comparison between CosmoSkymed (CSK) and RS2 is performed here, to examine the hypothesis that X-Band is generally better for wake detection than C-Band. Finally, this hypothesis is not confirmed, as the detectability models for TS-X, CSK and RS2 reveal similar performances. A comparison of wake detection performance should take the individual wake components into account separately.

scholarly journals Ship Identification and Characterization in Sentinel-1 SAR Images with Multi-Task Deep Learning

2019 ◽  
Vol 11 (24) ◽  
pp. 2997 ◽  
Author(s):  
Clément Dechesne ◽  
Sébastien Lefèvre ◽  
Rodolphe Vadaine ◽  
Guillaume Hajduch ◽  
Ronan Fablet
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Architecture ◽  
Large Scale ◽  
Visual Analysis ◽  
Automatic Identification ◽  
Identification System ◽  
Human Observer ◽  
Convolutional Network ◽  
Ship Detection

The monitoring and surveillance of maritime activities are critical issues in both military and civilian fields, including among others fisheries’ monitoring, maritime traffic surveillance, coastal and at-sea safety operations, and tactical situations. In operational contexts, ship detection and identification is traditionally performed by a human observer who identifies all kinds of ships from a visual analysis of remotely sensed images. Such a task is very time consuming and cannot be conducted at a very large scale, while Sentinel-1 SAR data now provide a regular and worldwide coverage. Meanwhile, with the emergence of GPUs, deep learning methods are now established as state-of-the-art solutions for computer vision, replacing human intervention in many contexts. They have been shown to be adapted for ship detection, most often with very high resolution SAR or optical imagery. In this paper, we go one step further and investigate a deep neural network for the joint classification and characterization of ships from SAR Sentinel-1 data. We benefit from the synergies between AIS (Automatic Identification System) and Sentinel-1 data to build significant training datasets. We design a multi-task neural network architecture composed of one joint convolutional network connected to three task specific networks, namely for ship detection, classification, and length estimation. The experimental assessment shows that our network provides promising results, with accurate classification and length performance (classification overall accuracy: 97.25%, mean length error: 4.65 m ± 8.55 m).

A Beam Scanning Method based on the Helical Antenna for Space-based AIS

2014 ◽  
Vol 68 (1) ◽  
pp. 52-70 ◽  
Author(s):  
Yun Cheng ◽  
Lihu Chen ◽  
Xiaoqian Chen
Keyword(s):  
Detection Probability ◽  
Automatic Identification ◽  
Identification System ◽  
Helical Antenna ◽  
Beam Scanning ◽  
Scanning Method ◽  
Ship Detection ◽  
Low Earth Orbits ◽  
Earth Orbits ◽  
Scanning Antenna

We investigate a strategy to address the problem of low ship detection probability of space-based Automatic Identification System (AIS). A directional AIS antenna and an innovative beam scanning method are proposed, which scan the antenna across a wide swath to provide complete coverage and maintain the advantage of a narrow footprint to reduce signal collision. Aiming at the mission requirement of global ship detection by the year 2016, the appropriate swath, the scanning range and the scanning rate were studied and designed in detail. Theoretical analysis and simulations showed that this scanning antenna can greatly improve ship detection probability and hold the detection probability at an average reporting interval from six to 15 seconds for most oceans when compared with the traditional fixed wide beam antenna. Furthermore, the detection capacity of this scanning antenna was little affected by the heights of different Low Earth Orbits. The results of this work show that the design of the helical antenna along with the beam scanning method can be considered as a building block of future space-based AIS.

scholarly journals DEEP LEARNING FOR VESSEL DETECTION AND IDENTIFICATION FROM SPACEBORNE OPTICAL IMAGERY

2021 ◽  
Vol V-3-2021 ◽  
pp. 303-310
Author(s):  
G. Matasci ◽  
J. Plante ◽  
K. Kasa ◽  
P. Mousavi ◽  
A. Stewart ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Input Image ◽  
Automatic Identification ◽  
Identification System ◽  
Optical Remote Sensing ◽  
Detection Model ◽  
Model Based ◽  
Optical Images ◽  
Vessel Detection

Abstract. We present a deep learning-based vessel detection and (re-)identification approach from spaceborne optical images. We introduce these two components as part of a maritime surveillance from space pipeline and present experimental results on challenging real-world maritime datasets derived from WorldView imagery. First, we developed a vessel detection model based on RetinaNet achieving a performance of 0.795 F1-score on a challenging multi-scale dataset. We then collected a large-scale dataset for vessel identification by applying the detection model on 200+ optical images, detecting the vessels therein and assigning them an identity via an Automatic Identification System association framework. A vessel re-identification model based on Twin neural networks has then been trained on this dataset featuring 2500+ unique vessels with multiple repeated occurrences across different acquisitions. The model allows to naturally establish similarities between vessel images. It returns a relevant ranking of candidate vessels from a database when provided an input image for a specific vessel the user might be interested in, with top-1 and top-10 accuracies of 38.7% and 76.5%, respectively. This study demonstrates the potential offered by the latest advances in deep learning and computer vision when applied to optical remote sensing imagery in a maritime context, opening new opportunities for automated vessel monitoring and tracking capabilities from space.

Sign in / Sign up

Export Citation Format

Share Document