Multiple Target Tracking by Learning Feature Representation and Distance Metric Jointly
This work addresses the challenge of robust affinity modeling in multiple target tracking, which is incremental as it combines existing CNN and LSTM components in a novel way.
The paper tackled the problem of multiple target tracking by proposing a unified deep architecture that jointly learns feature representation and distance metric, achieving competitive results on the MOT benchmark compared to recent state-of-the-art approaches.
Designing a robust affinity model is the key issue in multiple target tracking (MTT). This paper proposes a novel affinity model by learning feature representation and distance metric jointly in a unified deep architecture. Specifically, we design a CNN network to obtain appearance cue tailored towards person Re-ID, and an LSTM network for motion cue to predict target position, respectively. Both cues are combined with a triplet loss function, which performs end-to-end learning of the fused features in a desired embedding space. Experiments in the challenging MOT benchmark demonstrate, that even by a simple Linear Assignment strategy fed with affinity scores of our method, very competitive results are achieved when compared with the most recent state-of-theart approaches.