Multiple Object Tracking with Mixture Density Networks for Trajectory Estimation
This work addresses challenges like occlusions and identity switching in multiple object tracking, offering an incremental improvement for computer vision applications.
The paper tackles the problem of multiple object tracking by introducing TrajE, a trajectory estimator based on recurrent mixture density networks, which improves tracking performance when integrated into existing algorithms. Results show boosts of 6.3 and 0.3 points in MOTA score and 1.8 and 3.1 in IDF1 on the MOTChallenge 2017 test set for CenterTrack and Tracktor, respectively.
Multiple object tracking faces several challenges that may be alleviated with trajectory information. Knowing the posterior locations of an object helps disambiguating and solving situations such as occlusions, re-identification, and identity switching. In this work, we show that trajectory estimation can become a key factor for tracking, and present TrajE, a trajectory estimator based on recurrent mixture density networks, as a generic module that can be added to existing object trackers. To provide several trajectory hypotheses, our method uses beam search. Also, relying on the same estimated trajectory, we propose to reconstruct a track after an occlusion occurs. We integrate TrajE into two state of the art tracking algorithms, CenterTrack [63] and Tracktor [3]. Their respective performances in the MOTChallenge 2017 test set are boosted 6.3 and 0.3 points in MOTA score, and 1.8 and 3.1 in IDF1, setting a new state of the art for the CenterTrack+TrajE configuration