首页|基于YOLOv5-DeepSORT融合的低帧率水面航行多目标跟踪算法

基于YOLOv5-DeepSORT融合的低帧率水面航行多目标跟踪算法

扫码查看
原文链接
  • 万方数据
针对游弋舰船或近水面航行的潜艇等目标在低帧率或视频图像中缺失部分帧情况下,跟踪目标帧与帧之间存在较大差距,导致跟踪精度下降、效率低的问题,提出一种基于YOLOv5与DeepSORT融合的水面航行多目标跟踪算法.首先,引入超分辨率重建网络对跟踪目标图像进行增强,以消除云雾及海浪对识别网络的干扰,使图像中目标特征清晰化;其次,在YOLOv5中引入ShuffleAttention注意力模块以增强识别网络对目标特征的提取能力;最后,在DeepSORT算法级联匹配中引入欧氏距离匹配替代IOU匹配,以此提升目标跟踪精度.仿真结果表明,本文算法的跟踪效果良好,改进的YOLOv5模型相对mAP50-95值提升了 9.4％;在DeepSORT跟踪网络中,跟踪准确率对比优化前提升了 8.11％.
A multi-target tracking algorithm for low frame rate surface navigation based on YOLOv5-DeepSORT fusion
A multi-target tracking algorithm for water naviga-tion based on the fusion of YOLOv5 and DeepSORT was pro-posed to address the problem of significant differences between tracking target frames in low frame rates or missing frames in video images for targets such as cruising ships or submarines sailing near the water surface,resulting in decreased tracking accuracy and efficiency.Firstly,a super-resolution recon-struction network was introduced to enhance the tracking tar-get image to eliminate the interference of clouds,fog,and waves on the recognition network and make the target features in the image clear.Secondly,the ShuffleAttention module was introduced in YOLOv5 to enhance the recognition network's ability to extract target features.Finally,in the DeepSORT al-gorithm cascade matching,Euclidean distance matching was introduced instead of IOU matching to improve target tracking accuracy.Simulation results show that the tracking perform-ance of the algorithm proposed is good,and the improved YOLOv5 model has increased the mAP50-95 value by 9.4％,and in the DeepSORT tracking network,the tracking accuracy has increased by 8.11％compared to before optimization.

shipsurface navigationmulti-target trackingsuper resolution reconstructionYOLOv5DeepSORTEu-clidean distance matching

付诗文、韩星程、王黎明、武国强、王鸿儒、马文、王志勇

展开 >

中北大学信息与通信工程学院,太原 030051

太原重工股份有限公司,太原 030024

山西太重数智科技股份有限公司,太原 030024

山西国化能源有限责任公司,太原 030000

展开 >

船舶 水面航行 多目标跟踪 超分辨率重建 YOLOv5 DeepSORT 欧氏距离匹配

国家自然科学青年基金资助项目2021年山西省应用基础研究计划项目省部共建动态测试技术国家重点实验室开放研究基金资助项目

62203405202103021245452022-SYSJJ-08

2024

10.16411/j.cnki.issn1006-7736.2024.01.011

大连海事大学学报
大连海事大学

大连海事大学学报

CSTPCD北大核心
影响因子：0.469
ISSN：1006-7736
年,卷(期)：2024.50(1)
  • 14