首页|长短时算法:一种视频多目标关联算法

长短时算法:一种视频多目标关联算法

扫码查看
视频多目标跟踪面临的主要挑战是严重遮挡带来的身份切换问题.解决身份切换的技术为视频目标关联,即识别不同帧中的同一目标并分配身份编号.针对身份切换提出长短时视频目标关联算法,该算法在短时即相邻帧之间使用运动特征进行目标匹配,在长时即不相邻帧之间增加外观特征进行目标匹配,实现对于遮挡后被检出目标的再匹配.此外对卡尔曼滤波进行改进,增加框宽参数,使得预测框更准确;还使用平均外观特征并增加检测置信度作为更新参数,使得外观特征鲁棒性更强,在复杂环境下仍能表现良好.长短时算法在数据集MOT17 上多目标跟踪精度得分 81.3,身份F1 值得分 81.3,实现了严重遮挡场景下的稳定跟踪.
Long-short time association algorithm:a robust data association algorithm
The main challenge of multi-object tracking(MOT)is identity switch caused by severe occlusion.The solution to identity switching is video object association,which assigns an identity number to the same target in different frames.In this paper,a long-short time association algorithm is proposed for identity switching.In the short-time,that is,the motion fea-tures between adjacent frames are used to match,and in the long-time,that is,the non-adjacent frames are directly added to the appearance features for association to rematch the object detected after occlusion.Besides,the Kalman filter is improved and the frame width parameter is added to make the predicted frame more accurate;appearance features use average appear-ance features and increase detection confidence as update parameters to make appearance more robust and can still work in complex scenes.The new tracker,LSATrack,achieves 81.3MOTA and 81.3IDF1 in the MOT17 and achieves stable tracking in severe occlusion scenarios.

video object associationmulti-object trackingtracking-by-detectionaverage appearance feature

王锐、丁春山

展开 >

江苏自动化研究所,江苏 连云港 222061

视频目标关联 视频多目标跟踪 先检测后跟踪 平均外观特征

2024

指挥控制与仿真
中国船舶重工集团公司 第七一六研究所

指挥控制与仿真

CSTPCD
影响因子:0.309
ISSN:1673-3819
年,卷(期):2024.46(3)
  • 18