Observation Centric and Central Distance Recovery on Sports Player Tracking

TL;DR

This paper introduces a motion-based multi-object tracking algorithm with post-processing pipelines tailored for sports, effectively handling non-linear player movements and re-identification challenges in team sports like basketball, football, and volleyball.

Contribution

The work presents a novel motion-based tracking method with three post-processing pipelines specifically designed for sports, improving tracking accuracy over non-linear player movements.

Findings

Achieved a HOTA score of 73.968 on SportsMOT dataset

Ranked 3rd on the 2022 Sportsmot workshop leaderboard

Successfully tracked players with non-linear movement patterns

Abstract

Multi-Object Tracking over humans has improved rapidly with the development of object detection and re-identification. However, multi-actor tracking over humans with similar appearance and nonlinear movement can still be very challenging even for the state-of-the-art tracking algorithm. Current motion-based tracking algorithms often use Kalman Filter to predict the motion of an object, however, its linear movement assumption can cause failure in tracking when the target is not moving linearly. And for multi-players tracking over the sports field, because the players in the same team are usually wearing the same color of jersey, making re-identification even harder both in the short term and long term in the tracking process. In this work, we proposed a motionbased tracking algorithm and three post-processing pipelines for three sports including basketball, football, and volleyball, we successfully handle the tracking of the non-linear movement of players on the sports fields. Experiments result on the testing set of ECCV DeeperAction Challenge SportsMOT Dataset demonstrate the effectiveness of our method, which achieves a HOTA of 73.968, ranking 3rd place on the 2022 Sportsmot workshop final leaderboard.