联合人体姿态估计和多目标跟踪的跨数据集学习  

Cross-dataset Learning Combining Multi-object Tracking and Human Pose Estimation

作　　者：曾泽华 罗会兰[1] ZENG Zehua;LUO Huilan(School of Information Engineering,Jiangxi University of Science and Technology,Ganzhou,Jiangxi 341000,China)

机构地区：[1]江西理工大学信息工程学院,江西赣州341000

出　　处：《计算机科学》2023年第S01期502-508,共7页Computer Science

基　　金：国家自然科学基金(61862031);江西省主要学科学术和技术带头人培养计划--领军人才项目(20213BCJ22004)。

摘　　要：近年来,多目标跟踪任务获得了较大的进展,尤其是针对行人的多目标跟踪。通过对行人进行联合姿态估计,能够提升多目标跟踪算法对行人的运动预测,同时为更高阶的任务例如自动驾驶算法提供更多的信息。然而,在当前包含人体姿态估计标签的多目标跟踪数据集中,视频长度较短且目标稀疏,限制了多目标跟踪算法的研究。文中使用具有更多行人的多目标跟踪数据集MOT17和多人姿态估计数据集COCO进行跨数据集学习,基于循环训练策略有效提升了联合人体姿态估计下的多目标跟踪算法的性能。同时极化自注意力下采样和注意力上采样的使用,在提升算法训练速度的同时,增强了算法的人体姿态估计性能。In recent years,multi-object tracking has gained significant progress,especially for pedestrians.By performing joint pose estimation on pedestrians,it is possible to improve the motion prediction of pedestrians by multi-object tracking algorithms,while providing more information for higher-order tasks such as autonomous driving.However,in the current multi-object tra-cking dataset containing human pose estimation labels,the video length is short and the targets are sparse,limits the research of multi-object tracking.In the paper,cross-dataset learning is performed using the multi-object tracking dataset MOT17 and the multi-human pose estimation dataset COCO with more pedestrians.The performance of the multi-object tracking algorithm under joint human pose estimation is effectively improved based on a round-robin training strategy.The use of simultaneous polarized self-attention down-sampling and attention up-sampling enhances the human pose estimation performance of the algorithm while improving the algorithm training speed.

关 键 词：多目标跟踪 跨数据集学习 人体姿态估计 注意力机制 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]