面向多类别舰船多目标跟踪的改进CSTrack算法  

Improved CSTrack algorithm for multi-class ship multi-object tracking

作　　者：袁志安 谷雨[1] 马淦 Yuan Zhian;Gu Yu;Ma Gan(School of Automation,Hangzhou Dianzi University,Hangzhou,Zhejiang 310018,China)

机构地区：[1]杭州电子科技大学自动化学院,浙江杭州310018

出　　处：《光电工程》2023年第12期13-27,共15页Opto-Electronic Engineering

基　　金：浙江省自然科学基金资助项目(LY21F030010,LZ23F030002)。

摘　　要：针对海面舰船多目标跟踪过程中图像背景复杂、目标尺度差异大等难点,提出了一种改进CSTrack的舰船多目标跟踪算法。首先,针对CSTrack算法使用暴力解耦分解颈部特征造成目标特征损失的问题,提出了一种结合Res2net模块的改进互相关解耦网络RES_CCN,使网络解耦后获得更加细粒度的特征。其次,为提升对多类别舰船的跟踪性能,采用检测头网络解耦设计分别预测目标类别、置信度和位置。最后,采用MOT2016数据集进行消融实验,验证了所提模块的有效性,在新加坡海事数据集上进行测试,所提算法的多目标跟踪精度提升了8.4%,目标识别准确度提升了3.1%,优于ByteTrack等算法。本文所提算法具有跟踪精度高、误检率低等优点,适用于海面舰船多目标跟踪任务。Due to the difficulties of complex backgrounds and large-scale differences between objects during the process of ship multi-object tracking in sea-surface scenarios,an improved CSTrack algorithm for ship multi-object tracking is proposed in this paper.Firstly,as violent decoupling is used in the CSTrack algorithm to decompose neck features and cause object feature loss,an improved cross-correlation decoupling network that combines the Res2net module(RES_CCN)is proposed,and thus more fine-grained features can be obtained.Secondly,to improve the tracking performance of multi-class ships,the decoupled design of the detection head network is used to predict the class,confidence,and position of objects,respectively.Finally,the MOT2016 dataset is used for the ablation experiment to verify the effectiveness of the proposed module.When tested on the Singapore maritime dataset,the multiple object tracking accuracy of the proposed algorithm is improved by 8.4%and the identification F1 score is increased by 3.1%,which are better than those of the ByteTrack and other algorithms.The proposed algorithm has the advantages of high tracking accuracy and low error detection rate and is suitable for ship multiobject tracking in sea-surface scenarios.

关 键 词：多目标跟踪 目标重识别 目标检测 细粒度特征 注意力机制 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]