Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

B. Munjal, A. Aftab, S. Amin, M. D. Brandlmaier, F. Tombari, F. Galasso
Joint detection and tracking in videos with identification features
Image and Vision Computing Journal, May 2020 (bib)

Recent works have shown that combining object detection and tracking tasks, in the case of video data, results inhigher performance for both tasks, but they require a high frame-rate as a strict requirement for performance. This assumption is often violated in real-world applications, when models run on embedded devices, often atonly a few frames per second. Videos at low frame-rate suffer from large object displacements. Here re-identification features may support to match large-displaced object detections, but current joint detection and re-identification formulations degradethe detector performance, as these two are contrasting tasks. In the real-world application having separate detector and re-id models is often not feasible, as both the memory and runtime effectively double. Towards robust long-term tracking applicable to reduced-computational-power devices, we propose the first joint optimization of detection, tracking and re-identification features for videos. Notably, our joint optimization maintains the detector performance, a typical multi-task challenge. At inference time, we leverage detections fortracking (tracking-by-detection) when the objects are visible, detectable and slowly moving in the image. We leverage instead re-identification features to match objects which disappeared (e.g. due to occlusion) for several frames or were not tracked due to fast motion (or low-frame-rate videos). Our proposed method reaches the state-of-the-art on MOT, it ranks 1st in the UA-DETRAC’18 tracking challenge among online trackers, and 3rd overall.
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each authors copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Edit | Attach | Refresh | Diffs | More | Revision r1.13 - 30 Jan 2019 - 15:16 - LeslieCasas

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif