Detecting and Matching Related Objects with One Proposal Multiple Predictions

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021)(2021)

引用 7|浏览17
暂无评分
摘要
Tracking players in sports videos is commonly done in a tracking-by-detection framework, first detecting players in each frame, and then performing association over time. While for some sports tracking players is sufficient for game analysis, sports like hockey, tennis and polo may require additional detections, that include the object the player is holding (e.g. racket, stick). The baseline solution for this problem involves detecting these objects as separate classes, and matching them to player detections based on the intersection over union (IoU). This approach, however, leads to poor matching performance in crowded situations, as it does not model the relationship between players and objects. In this paper, we propose a simple yet efficient way to detect and match players and related objects at once without extra cost, by considering an implicit association for prediction of multiple objects through the same proposal box. We evaluate the method on a dataset of broadcast ice hockey videos, and also a new public dataset we introduce called COCO +Torso. On the ice hockey dataset, the proposed method boosts matching performance from 57.1% to 81.4%, while also improving the meanAP of player+stick detections from 68.4% to 88.3%. On the COCO +Torso dataset, we see matching improving from 47.9% to 65.2%. The COCO +Torso dataset, code and pre-trained models will be released at https://github.com/foreverYoungGitHub/detect-and-match-related-objects.
更多
查看译文
关键词
object matching,one proposal multiple predictions,sports videos,tracking-by-detection framework,sports tracking players,player detections,ice hockey dataset,player+stick detections,COCO +Torso dataset,object detection,intersection over union,ice hockey video broadcasting
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要