Detecting and Matching Related Objects with One Proposal Multiple Predictions

TL;DR

This paper introduces a method for detecting and matching players with related objects in sports videos using a single proposal multiple predictions approach, significantly improving matching accuracy and detection performance.

Contribution

The paper presents a novel approach that predicts multiple related objects simultaneously from the same proposal, enhancing matching accuracy without additional computational cost.

Findings

Matching performance improved from 57.1% to 81.4% on ice hockey dataset.

Mean Average Precision (mAP) increased from 68.4% to 88.3% for player+stick detections.

Matching accuracy improved from 47.9% to 65.2% on COCO +Torso dataset.

Abstract

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.