###
计算机系统应用英文版:2024,33(11):15-26
本文二维码信息
码上扫一扫!
联合判别性外观和运动线索的行人多目标跟踪
(南京信息工程大学 软件学院, 南京 210044)
Pedestrian Multi-object Tracking Combining Discriminative Appearance and Motion Cues
(School of Software, Nanjing University of Information Science & Technology, Nanjing 210044, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 16次   下载 471
Received:April 25, 2024    Revised:May 29, 2024
中文摘要: 在多目标跟踪任务中, 外界噪声的干扰会导致传统方法的系统建模不可靠, 从而降低目标位置预测的准确性; 而密集人群引起的拥挤和遮挡问题则会严重影响目标外观的可靠性, 导致错误的身份关联. 为了解决这些问题, 本文提出一种多目标跟踪算法Ecsort. 该算法在传统运动预测的基础上, 引入噪声补偿模块, 降低噪声干扰引起的误差, 提高位置预测的准确性. 其次, 引入特征相似度匹配模块, 通过学习目标的判别性外观特征, 并结合运动线索和判别性外观特征的优势, 从而实现精确的身份关联. 通过在多目标跟踪基准数据集上进行的大量实验结果表明, 与基线模型相比, 该方法在MOT17测试集上的IDF1 (ID F1 score)、HOTA (higher order tracking accuracy)、AssA (association accuracy)、DetA (detection accuracy)分别提高了1.1%、0.5%、0.6%、0.3%, 在MOT20测试集上的IDF1、HOTA、AssA、DetA分别提高了2.3%、1.9%、3.4%、0.2%.
Abstract:In multi-object tracking tasks, the interference of external noise can lead to unreliable system modeling of traditional methods, thus reducing the accuracy of object position prediction; and the congestion and obstruction caused by dense crowds seriously affect the reliability of the object appearance, resulting in incorrect identity association. To address these issues, this study proposes a multi-object tracking algorithm Ecsort. This algorithm improves position prediction accuracy by introducing a noise compensation module based on traditional motion prediction to reduce errors caused by noise interference. Secondly, this algorithm introduces a feature similarity matching module. It can achieve accurate identity association by learning discriminative appearance features of objects and combining the advantages of motion cues and discriminative appearance features. Extensive experimental results on multi-object tracking benchmark datasets demonstrate that, compared to the baseline model, this method improves ID F1 score (IDF1), higher order tracking accuracy (HOTA), association accuracy (AssA), and detection accuracy (DetA) by 1.1%, 0.5%, 0.6%, and 0.3% respectively on the MOT17 test set, and by 2.3%, 1.9%, 3.4%, and 0.2% respectively on the MOT20 test set.
文章编号:     中图分类号:    文献标志码:
基金项目:国家自然科学基金(41975183)
引用文本:
王军,李迎春,程勇.联合判别性外观和运动线索的行人多目标跟踪.计算机系统应用,2024,33(11):15-26
WANG Jun,LI Ying-Chun,CHENG Yong.Pedestrian Multi-object Tracking Combining Discriminative Appearance and Motion Cues.COMPUTER SYSTEMS APPLICATIONS,2024,33(11):15-26