短时记忆与CenterTrack的车辆多目标跟踪  

Short-term memory and CenterTrack based vehicle-related multi-target tracking method

作　　者：张瑶 卢焕章[1] 王珏 张路平 胡谋法 Zhang Yao;Lu Huanzhang;Wang Jue;Zhang Luping;Hu Moufa(National Key Laboratory of Science and Technology on Automatic Target Recognition,College of Electronic Science and Technology,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]国防科技大学电子科学学院自动目标识别重点实验室,长沙410073

出　　处：《中国图象图形学报》2023年第10期3107-3122,共16页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61921001);国防科技大学电子科学学院自动目标识别重点实验室春雨基金项目(WDZC282055000210)。

摘　　要：目的车辆多目标跟踪是智能交通领域关键技术,其性能对车辆轨迹分析和异常行为鉴别有显著影响。然而,车辆多目标跟踪常受外部光照、道路环境因素影响,车辆远近尺度变化以及相互遮挡等干扰,导致远处车辆漏检或车辆身份切换(ID switch,IDs)问题。本文提出短时记忆与CenterTrack的车辆多目标跟踪,提升车辆多目标跟踪准确度(multiple object tracking accuracy,MOTA),改善算法的适应性。方法利用小样本扩增增加远处小目标车辆训练样本数;通过增加的样本重新训练CenterTrack确定车辆位置及车辆在相邻帧之间的中心位移量;当待关联轨迹与检测目标匹配失败时通过轨迹运动信息预测将来的位置;利用短时记忆将待关联轨迹按丢失时间长短分级与待匹配检测关联以减少跟踪车辆IDs。结果在交通监控车辆多目标跟踪数据集UA-DETRAC(University at Albany detection and tracking)构建的5个测试序列数据中,本文方法在维持CenterTrack优势的同时,对其表现不佳的场景获得近30%的提升,与YOLOv4-DeepSort(you only look once—simple online and realtime tracking with deep association metric)相比,4种场景均获得近10%的提升,效果显著。Sherbrooke数据集的测试结果,本文方法同样获得了性能提升。结论本文扩增了远处小目标车辆训练样本,缓解了远处小目标与近处大目标存在的样本不均衡,提高了算法对远处小目标车辆的检测能力,同时短时记忆维持关联失败的轨迹运动信息并分级匹配检测目标,降低了算法对跟踪车辆的IDs,综合提高了MOTA。Objective The task of multi-object tracking is often focused on estimating the number,location or other related properties of objects in the scene.Specifically,it is required to be estimated accurately and consistently over a period of time.Vehicle-related multi-target tracking can be as a key technique for such domain like intelligent transportation,and its performance has a significant impact on vehicle trajectory analysis and abnormal behavior identification to some extent.Vehicle-related multi-target tracking is also recognized as a key branch of multi-target tracking and a potential technique for autonomous driving and intelligent traffic surveillance systems.For vehicle-related multi-target tracking,temporal-based motion status of vehicles in traffic scenes can be automatically obtained,which is beneficial to analyze traffic conditions and implement decisions-making quickly for transportation administrations,as well as the automatic driving system.How⁃ever,to resolve missed detection of distant vehicles or vehicle ID switch(IDs)problems,such factors are often to be dealt with in relevance to external illumination,road environment factors,changes in the scale of the vehicle near and far,and mutual occlusion.We develop an integrated short-term memory and CenterTrack ability to improve the vehicle multi-target tracking accuracy(multiple object tracking accuracy(MOTA)),and its adaptability of the algorithm can be optimized fur⁃ther.Method From the analysis of a large number of traffic monitoring video data,it can be seen the reasons for the unbal⁃anced samples in the training samples.On the one hand,due to the fast speed of the captured vehicle target,the identified distant small target vehicle can be preserved temperorily,and it lacks of more consistent frames.On the other hand,the amount of apparent feature information is lower derived from small target vehicle itself,and the amount of neural networkextracted feature information is disappeared quickly many times.The relative number of distant small targ

关 键 词：多目标跟踪 目标检测 轨迹记忆 样本扩增 轨迹关联 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]