TransTrack: Multiple Object Tracking with Transformer
This work simplifies the multi-step process of tracking-by-detection methods for researchers and practitioners in computer vision by integrating detection and association into a single shot.
This paper proposes TransTrack, a multiple object tracking method that uses a transformer architecture to perform joint detection and tracking. It achieves competitive performance on MOT17 and MOT20 benchmarks, with MOTA scores of 74.5% and 64.5% respectively.
In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems. TransTrack leverages the transformer architecture, which is an attention-based query-key mechanism. It applies object features from the previous frame as a query of the current frame and introduces a set of learned object queries to enable detecting new-coming objects. It builds up a novel joint-detection-and-tracking paradigm by accomplishing object detection and object association in a single shot, simplifying complicated multi-step settings in tracking-by-detection methods. On MOT17 and MOT20 benchmark, TransTrack achieves 74.5\% and 64.5\% MOTA, respectively, competitive to the state-of-the-art methods. We expect TransTrack to provide a novel perspective for multiple object tracking. The code is available at: \url{https://github.com/PeizeSun/TransTrack}.