TrackNetV4: Enhancing Fast Sports Object Tracking with Motion Attention Maps

TL;DR

TrackNetV4 improves high-speed sports object tracking by integrating motion attention maps with visual features, significantly enhancing accuracy in challenging scenarios like occlusion and low visibility.

Contribution

This paper introduces a novel motion-aware fusion mechanism for TrackNet, effectively combining visual features with motion attention maps to boost tracking performance.

Findings

Enhanced tracking accuracy on tennis ball and shuttlecock datasets.

Effective handling of occlusion and low visibility scenarios.

Lightweight, plug-and-play integration with existing TrackNet models.

Abstract

Accurately detecting and tracking high-speed, small objects, such as balls in sports videos, is challenging due to factors like motion blur and occlusion. Although recent deep learning frameworks like TrackNetV1, V2, and V3 have advanced tennis ball and shuttlecock tracking, they often struggle in scenarios with partial occlusion or low visibility. This is primarily because these models rely heavily on visual features without explicitly incorporating motion information, which is crucial for precise tracking and trajectory prediction. In this paper, we introduce an enhancement to the TrackNet family by fusing high-level visual features with learnable motion attention maps through a motion-aware fusion mechanism, effectively emphasizing the moving ball's location and improving tracking performance. Our approach leverages frame differencing maps, modulated by a motion prompt layer, to highlight key motion regions over time. Experimental results on the tennis ball and shuttlecock datasets show that our method enhances the tracking performance of both TrackNetV2 and V3. We refer to our lightweight, plug-and-play solution, built on top of the existing TrackNet, as TrackNetV4.