TopTrack: Tracking Objects By Their Top
Jacob Meilleur, Guillaume-Alexandre Bilodeau

TL;DR
TopTrack introduces a novel multi-object tracking method that uses the top of objects as keypoints for detection, improving visibility in crowded scenes and reducing missed detections compared to center-based methods.
Contribution
It proposes using the object top as a keypoint for detection and employs separate streams for consecutive frames to enhance training and tracking accuracy.
Findings
Reduces missed detections in crowded scenarios.
Achieves competitive results on MOT benchmarks.
Leads to more complete and less lost trajectories.
Abstract
In recent years, the joint detection-and-tracking paradigm has been a very popular way of tackling the multi-object tracking (MOT) task. Many of the methods following this paradigm use the object center keypoint for detection. However, we argue that the center point is not optimal since it is often not visible in crowded scenarios, which results in many missed detections when the objects are partially occluded. We propose TopTrack, a joint detection-and-tracking method that uses the top of the object as a keypoint for detection instead of the center because it is more often visible. Furthermore, TopTrack processes consecutive frames in separate streams in order to facilitate training. We performed experiments to show that using the object top as a keypoint for detection can reduce the amount of missed detections, which in turn leads to more complete trajectories and less lost…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Surveillance and Tracking Methods · Air Quality Monitoring and Forecasting · IoT-based Smart Home Systems
