The SportsMOT competition aims to solve multiple object tracking of athletes in different sports scenes such as basketball or soccer. The competition is challenging because of the unstable camera view, athletes' complex trajectory, and complicated background. Previous MOT methods can not match enough high-quality tracks of athletes. To pursue higher performance of MOT in sports scenes, we introduce an innovative tracker named SportsTrack, we utilize tracking by detection as our detection paradigm. Then we will introduce a three-stage matching process to solve the motion blur and body overlapping in sports scenes. Meanwhile, we present another innovation point: one-to-many correspondence between detection bboxes and crowded tracks to handle the overlap of athletes' bodies during sports competitions. Compared to other trackers such as BOT-SORT and ByteTrack, We carefully restored edge-lost tracks that were ignored by other trackers. Finally, we reached the top 1 tracking score (76.264 HOTA) in the ECCV 2022 DeepAction SportsMOT competition.
翻译：体育MOT竞赛旨在解决不同体育场景,如篮球或足球场景中运动员的多重目标跟踪问题。 比赛具有挑战性, 原因是相机视图不稳定, 运动员的复杂轨迹, 以及背景复杂。 以往的MOT方法无法与运动员的高质量轨迹匹配。 为了在体育场景中提高MOT的绩效, 我们引入了一个创新的追踪器, 名为“ 运动跟踪”, 我们用探测跟踪作为我们的检测模式。 然后我们将引入一个三阶段匹配程序, 以解决运动在体育场景中的模糊和身体重叠问题。 同时, 我们提出另一个创新点: 检测盒和拥挤轨迹之间的一对一对一通信, 以便在体育场比赛中处理运动员身体重叠问题。 比起其他跟踪器, 如 BOT- SORT 和 ByteTrack, 我们小心地修复了被其他跟踪器忽略的边线。 最后, 我们达到了ECV 2022 深动作运动运动比赛中前一追踪分数( 76264 HOMTA) 。
相关内容
微信扫码咨询专知VIP会员