arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1610.06136cs.CV
收藏

POI:具有高性能检测和外观特征的多目标跟踪

POI: Multiple Object Tracking with High Performance Detection and Appearance Feature

Beihang University(北京航空航天大学);University at Albany, SUNY(奥尔巴尼大学);Sensetime Group Limited(商汤科技集团有限公司)

Fengwei Yu, Wenbo Li, Quanquan Li, Yu Liu, Xiaohua Shi, Junjie Yan

摘要:

基于检测和学习的外观特征在基于数据关联的多目标跟踪(MOT)中起着核心作用,但大多数MOT工作通常忽略了它们,只关注手工特征和关联算法。在本文中,我们探索了基于外观特征的高性能检测和深度学习,并表明它们在在线和离线设置中都能显著改善MOT结果。我们公开提供我们的检测和外观功能。在接下来的部分中,我们首先总结了检测和外观功能,然后介绍了我们的名为Person of Interest(POI)的跟踪器,它有在线和离线版本。

英文摘要:

Detection and learning based appearance feature play the central role in data association based multiple object tracking (MOT), but most recent MOT works usually ignore them and only focus on the hand-crafted feature and association algorithms. In this paper, we explore the high-performance detection and deep learning based appearance feature, and show that they lead to significantly better MOT results in both online and offline setting. We make our detection and appearance feature publicly available. In the following part, we first summarize the detection and appearance feature, and then introduce our tracker named Person of Interest (POI), which has both online and offline version.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑