具有双目深度信息重建功能的车辆目标跟踪方法OA
Vehicle Target Tracking Method with Binocular Depth Information Reconstruction Function
针对交通场景中纯视觉车辆目标跟踪因缺乏深度信息而导致的目标车辆轨迹标签频繁切换的问题,基于 Deep SORT框架引入双目深度信息重建模块,利用 AD-Census 双目立体匹配技术精确重建目标车辆的三维信息,结合高效的 DETR 目标检测网络构建一个集目标检测、双目深度估计与目标跟踪技术于一体的端到端车辆目标跟踪系统.实验结果表明,该系统在车辆轨迹跟踪时的标签切换次数(IDSW)减少到最多切换 15 次,但平均跟踪精度(MOTP)可达 79.768%,跟踪准确度(MOTA)可达 84.687%.本文提出的方法有效地降低了行车轨迹标签的切换频率,提升了跟踪的准确度和稳定性.
To address the problem of frequent trajectory label switching of target vehicles in pure vis-ion-based vehicle target tracking in traffic scenes caused by the lack of depth information,a binocular depth information reconstruction module based on the Deep SORT framework was introduced.The AD-Census binocular stereo matching technique was utilized to accurately reconstruct the three-dimensional informa-tion of target vehicles.Meanwhile,by combining with the efficient DETR target detection network,an end-to-end vehicle target tracking system integrating target detection,binocular depth estimation,and target tracking technologies was constructed.Experimental results demonstrate that the number of label switches(IDSW)during vehicle trajectory tracking is reduced to a maximum of 15,while the average tracking preci-sion(MOTP)reaches 79.768%,and the tracking accuracy(MOTA)reaches 84.687%.The method pro-posed in this paper effectively reduces the switching frequency of driving trajectory labels and improves the tracking accuracy and stability.
余杨;彭忆强;何刘
西华大学汽车与交通学院,四川 成都 610039西华大学汽车与交通学院,四川 成都 610039||汽车测控与安全四川省重点实验室(西华大学),四川 成都 610039西华大学汽车与交通学院,四川 成都 610039||汽车测控与安全四川省重点实验室(西华大学),四川 成都 610039||四川省新能源汽车智能控制与仿真测试技术工程研究中心(西华大学),四川 成都 610039
信息技术与安全科学
车辆目标跟踪双目视觉AD-CensusDETR
vehicle target trackingbinocular visionAD-CensusDETR
《西华大学学报（自然科学版）》 2026 (4)
77-89,13
四川省科技创新基地建设项目(2022ZYD0125)国家自然科学青年科学基金项目(52205129).
评论