MotionTrack: Learning Motion Predictor for Multiple Object Tracking
This addresses the problem of inaccurate tracking in scenarios with homogeneous appearance and heterogeneous motion for applications like sports and dance analysis, representing a novel method for a known bottleneck.
The paper tackled the challenge of tracking objects with similar appearance but varied motion in multi-object tracking by introducing MotionTrack, a learnable motion predictor that uses trajectory information, achieving state-of-the-art performance on datasets like Dancetrack and SportsMOT.
Significant progress has been achieved in multi-object tracking (MOT) through the evolution of detection and re-identification (ReID) techniques. Despite these advancements, accurately tracking objects in scenarios with homogeneous appearance and heterogeneous motion remains a challenge. This challenge arises from two main factors: the insufficient discriminability of ReID features and the predominant utilization of linear motion models in MOT. In this context, we introduce a novel motion-based tracker, MotionTrack, centered around a learnable motion predictor that relies solely on object trajectory information. This predictor comprehensively integrates two levels of granularity in motion features to enhance the modeling of temporal dynamics and facilitate precise future motion prediction for individual objects. Specifically, the proposed approach adopts a self-attention mechanism to capture token-level information and a Dynamic MLP layer to model channel-level features. MotionTrack is a simple, online tracking approach. Our experimental results demonstrate that MotionTrack yields state-of-the-art performance on datasets such as Dancetrack and SportsMOT, characterized by highly complex object motion.