A machine vision method for the evaluation of ship-to-ship collision risk
The development of ship technology and information technology has been driving the continuous improvement of ship intelligence, with safety being an inevitable requirement in the shipping industry. A machine vision-based ship collision warning method is proposed for high monitoring system cost and l...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-02-01
|
Series: | Heliyon |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024011368 |
_version_ | 1797304464565075968 |
---|---|
author | Zhiqiang Jiang Lingyu Zhang Weijia Li |
author_facet | Zhiqiang Jiang Lingyu Zhang Weijia Li |
author_sort | Zhiqiang Jiang |
collection | DOAJ |
description | The development of ship technology and information technology has been driving the continuous improvement of ship intelligence, with safety being an inevitable requirement in the shipping industry. A machine vision-based ship collision warning method is proposed for high monitoring system cost and limited information acquisition in safety design of autonomous ship navigation. The method combines machine learning with image algorithms. Firstly, the backbone of YOLOv7 detector is replaced by EfficientFormerV2 network to achieve model lightweight while ensuring detection accuracy. Public datasets SeaShips, Flow and self-made ship pictures are combined, and the network is trained on this dataset. StrongSORT is used for target tracking. Secondly, a data fusion algorithm is introduced to determine the target point at the bow-bottom of the ship based on the time-varying attitude of the camera and the time-series features of the bounding boxes. Ship navigation trajectory estimation is performed using image algorithms. Finally, a collision evaluation model is established to calculate the collision risk index. Experimental results demonstrate that the improved YOLOv7 network maintains similar mAP.5 and Recall compared to the original model, while reducing the parameters by 31.2 % and GFLOPs by 58.4 %. The accuracy of target ship trajectory estimation is high, with MAE values below 1.5 % and RMSE values below 2 % in experiments. In ship collision warning experiments, the proposed method accurately identifies navigating vessels, estimates the trajectories, and provides timely warnings for imminent collision accidents. Compared to traditional ship collision warning methods, this paper offers a more intelligent and lightweight solution. |
first_indexed | 2024-03-08T00:10:54Z |
format | Article |
id | doaj.art-2cbd983a554d46bf852a3134b3685b6d |
institution | Directory Open Access Journal |
issn | 2405-8440 |
language | English |
last_indexed | 2024-03-08T00:10:54Z |
publishDate | 2024-02-01 |
publisher | Elsevier |
record_format | Article |
series | Heliyon |
spelling | doaj.art-2cbd983a554d46bf852a3134b3685b6d2024-02-17T06:39:38ZengElsevierHeliyon2405-84402024-02-01103e25105A machine vision method for the evaluation of ship-to-ship collision riskZhiqiang Jiang0Lingyu Zhang1Weijia Li2Huazhong University of Science and Technology, School of Naval Architecture and Ocean Engineering, 1037 Luoyu Road, Hongshan District, Wuhan, Hubei, 430074, ChinaHuazhong University of Science and Technology, School of Naval Architecture and Ocean Engineering, 1037 Luoyu Road, Hongshan District, Wuhan, Hubei, 430074, ChinaCorresponding author.; Huazhong University of Science and Technology, School of Naval Architecture and Ocean Engineering, 1037 Luoyu Road, Hongshan District, Wuhan, Hubei, 430074, ChinaThe development of ship technology and information technology has been driving the continuous improvement of ship intelligence, with safety being an inevitable requirement in the shipping industry. A machine vision-based ship collision warning method is proposed for high monitoring system cost and limited information acquisition in safety design of autonomous ship navigation. The method combines machine learning with image algorithms. Firstly, the backbone of YOLOv7 detector is replaced by EfficientFormerV2 network to achieve model lightweight while ensuring detection accuracy. Public datasets SeaShips, Flow and self-made ship pictures are combined, and the network is trained on this dataset. StrongSORT is used for target tracking. Secondly, a data fusion algorithm is introduced to determine the target point at the bow-bottom of the ship based on the time-varying attitude of the camera and the time-series features of the bounding boxes. Ship navigation trajectory estimation is performed using image algorithms. Finally, a collision evaluation model is established to calculate the collision risk index. Experimental results demonstrate that the improved YOLOv7 network maintains similar mAP.5 and Recall compared to the original model, while reducing the parameters by 31.2 % and GFLOPs by 58.4 %. The accuracy of target ship trajectory estimation is high, with MAE values below 1.5 % and RMSE values below 2 % in experiments. In ship collision warning experiments, the proposed method accurately identifies navigating vessels, estimates the trajectories, and provides timely warnings for imminent collision accidents. Compared to traditional ship collision warning methods, this paper offers a more intelligent and lightweight solution.http://www.sciencedirect.com/science/article/pii/S2405844024011368Machine visionObject trackingTrajectory estimationCollision warning |
spellingShingle | Zhiqiang Jiang Lingyu Zhang Weijia Li A machine vision method for the evaluation of ship-to-ship collision risk Heliyon Machine vision Object tracking Trajectory estimation Collision warning |
title | A machine vision method for the evaluation of ship-to-ship collision risk |
title_full | A machine vision method for the evaluation of ship-to-ship collision risk |
title_fullStr | A machine vision method for the evaluation of ship-to-ship collision risk |
title_full_unstemmed | A machine vision method for the evaluation of ship-to-ship collision risk |
title_short | A machine vision method for the evaluation of ship-to-ship collision risk |
title_sort | machine vision method for the evaluation of ship to ship collision risk |
topic | Machine vision Object tracking Trajectory estimation Collision warning |
url | http://www.sciencedirect.com/science/article/pii/S2405844024011368 |
work_keys_str_mv | AT zhiqiangjiang amachinevisionmethodfortheevaluationofshiptoshipcollisionrisk AT lingyuzhang amachinevisionmethodfortheevaluationofshiptoshipcollisionrisk AT weijiali amachinevisionmethodfortheevaluationofshiptoshipcollisionrisk AT zhiqiangjiang machinevisionmethodfortheevaluationofshiptoshipcollisionrisk AT lingyuzhang machinevisionmethodfortheevaluationofshiptoshipcollisionrisk AT weijiali machinevisionmethodfortheevaluationofshiptoshipcollisionrisk |