SMOT: Single-Shot Multi Object Tracking
This addresses the challenge of efficient and accurate object tracking in videos, offering a novel framework that improves over existing methods.
The paper tackles the problem of multi-object tracking by converting single-shot detectors into online trackers, achieving state-of-the-art performance on benchmarks like Hannah, Music Videos, and MOT17.
We present single-shot multi-object tracker (SMOT), a new tracking framework that converts any single-shot detector (SSD) model into an online multiple object tracker, which emphasizes simultaneously detecting and tracking of the object paths. Contrary to the existing tracking by detection approaches which suffer from errors made by the object detectors, SMOT adopts the recently proposed scheme of tracking by re-detection. We combine this scheme with SSD detectors by proposing a novel tracking anchor assignment module. With this design SMOT is able to generate tracklets with a constant per-frame runtime. A light-weighted linkage algorithm is then used for online tracklet linking. On three benchmarks of object tracking: Hannah, Music Videos, and MOT17, the proposed SMOT achieves state-of-the-art performance.