Research on detection and tracking methods of unmanned ship water targets based on light vision

This study explores technical methods based on light vision to address the problem of target detection and tracking by surface unmanned ships in complex environments. We utilize an improved dark channel dehazing method and guided filtering for image preprocessing to improve the accuracy and efficien...

Full description

Saved in:
Bibliographic Details
Main Author: LIU Yibo, QIU Xinyu, WANG Tianhao, GAOYAN Xiusong, WANG Yintao
Format: Article
Language:zho
Published: Editorial Office of Command Control and Simulation 2024-12-01
Series:Zhihui kongzhi yu fangzhen
Subjects:
Online Access:https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1732684222418-1590951157.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850224849087102976
author LIU Yibo, QIU Xinyu, WANG Tianhao, GAOYAN Xiusong, WANG Yintao
author_facet LIU Yibo, QIU Xinyu, WANG Tianhao, GAOYAN Xiusong, WANG Yintao
author_sort LIU Yibo, QIU Xinyu, WANG Tianhao, GAOYAN Xiusong, WANG Yintao
collection DOAJ
description This study explores technical methods based on light vision to address the problem of target detection and tracking by surface unmanned ships in complex environments. We utilize an improved dark channel dehazing method and guided filtering for image preprocessing to improve the accuracy and efficiency of subsequent image processing. In terms of target detection, the YOLOv7 algorithm is used, which effectively improves the accuracy and recall rate of target detection by optimizing the loss function. In order to achieve accurate multi-target tracking, combined with self-trained model weights and Sort algorithm, continuous tracking of targets and accurate annotation of center point trajectories are successfully implemented. In addition, a binocular camera system is built on an unmanned ship platform for target ranging. Experimental results show that our method can achieve the ranging function with an average relative error of 6.46%. This result not only improves the navigation and positioning capabilities of unmanned ships, but also provides technical support for water surface safety monitoring. This research demonstrates that in the field of surface unmanned ships, target detection and tracking problems can be effectively solved by integrating advanced image processing technology and machine learning algorithms.
format Article
id doaj-art-5828722f2183445dbf0dcbcf540e6f4a
institution OA Journals
issn 1673-3819
language zho
publishDate 2024-12-01
publisher Editorial Office of Command Control and Simulation
record_format Article
series Zhihui kongzhi yu fangzhen
spelling doaj-art-5828722f2183445dbf0dcbcf540e6f4a2025-08-20T02:05:31ZzhoEditorial Office of Command Control and SimulationZhihui kongzhi yu fangzhen1673-38192024-12-01466788610.3969/j.issn.1673-3819.2024.06.013Research on detection and tracking methods of unmanned ship water targets based on light visionLIU Yibo, QIU Xinyu, WANG Tianhao, GAOYAN Xiusong, WANG Yintao01 System Engineering Research Institute, China Shipbuilding Corporation Limited, Beijing 100036, China;2 School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, ChinaThis study explores technical methods based on light vision to address the problem of target detection and tracking by surface unmanned ships in complex environments. We utilize an improved dark channel dehazing method and guided filtering for image preprocessing to improve the accuracy and efficiency of subsequent image processing. In terms of target detection, the YOLOv7 algorithm is used, which effectively improves the accuracy and recall rate of target detection by optimizing the loss function. In order to achieve accurate multi-target tracking, combined with self-trained model weights and Sort algorithm, continuous tracking of targets and accurate annotation of center point trajectories are successfully implemented. In addition, a binocular camera system is built on an unmanned ship platform for target ranging. Experimental results show that our method can achieve the ranging function with an average relative error of 6.46%. This result not only improves the navigation and positioning capabilities of unmanned ships, but also provides technical support for water surface safety monitoring. This research demonstrates that in the field of surface unmanned ships, target detection and tracking problems can be effectively solved by integrating advanced image processing technology and machine learning algorithms.https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1732684222418-1590951157.pdftarget detection|multi-target tracking|defogging
spellingShingle LIU Yibo, QIU Xinyu, WANG Tianhao, GAOYAN Xiusong, WANG Yintao
Research on detection and tracking methods of unmanned ship water targets based on light vision
Zhihui kongzhi yu fangzhen
target detection|multi-target tracking|defogging
title Research on detection and tracking methods of unmanned ship water targets based on light vision
title_full Research on detection and tracking methods of unmanned ship water targets based on light vision
title_fullStr Research on detection and tracking methods of unmanned ship water targets based on light vision
title_full_unstemmed Research on detection and tracking methods of unmanned ship water targets based on light vision
title_short Research on detection and tracking methods of unmanned ship water targets based on light vision
title_sort research on detection and tracking methods of unmanned ship water targets based on light vision
topic target detection|multi-target tracking|defogging
url https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1732684222418-1590951157.pdf
work_keys_str_mv AT liuyiboqiuxinyuwangtianhaogaoyanxiusongwangyintao researchondetectionandtrackingmethodsofunmannedshipwatertargetsbasedonlightvision