TL;DR
This paper evaluates seven multiple object trackers from OpenCV using the MOT20 dataset, providing insights into their performance with respect to accuracy and precision for various objects in real-time applications.
Contribution
It offers a comprehensive benchmark of OpenCV's multiple object trackers, addressing when and how to select the appropriate tracker for specific tasks.
Findings
OpenCV trackers vary significantly in performance
MOTA and MOTP metrics highlight strengths and weaknesses
Guidelines for tracker selection in real-time applications
Abstract
Object tracking is one of the most important and fundamental disciplines of Computer Vision. Many Computer Vision applications require specific object tracking capabilities, including autonomous and smart vehicles, video surveillance, medical treatments, and many others. The OpenCV as one of the most popular libraries for Computer Vision includes several hundred Computer Vision algorithms. Object tracking tasks in the library can be roughly clustered in single and multiple object trackers. The library is widely used for real-time applications, but there are a lot of unanswered questions such as when to use a specific tracker, how to evaluate its performance, and for what kind of objects will the tracker yield the best results? In this paper, we evaluate 7 trackers implemented in OpenCV against the MOT20 dataset. The results are shown based on Multiple Object Tracking Accuracy (MOTA) and…
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.
