Fast Online 3D Multi-Camera Multi-Object Tracking and Pose Estimation
Linh Van Ma, Tran Thien Dat Nguyen, Moongu Jeon

TL;DR
This paper introduces a fast, online multi-camera 3D multi-object tracking and pose estimation method that relies on 2D detections, offering high efficiency and robustness without extensive training.
Contribution
It presents an efficient Bayes-optimal tracking algorithm that operates online using only 2D detections, avoiding costly 3D training data and deep models.
Findings
Significantly faster than state-of-the-art methods
Maintains high accuracy with only 2D detections
Robust to camera disconnections and reconnections
Abstract
This paper proposes a fast and online method for jointly performing 3D multi-object tracking and pose estimation using multiple monocular cameras. Our algorithm requires only 2D bounding box and pose detections, eliminating the need for costly 3D training data or computationally expensive deep learning models. Our solution is an efficient implementation of a Bayes-optimal multi-object tracking filter, enhancing computational efficiency while maintaining accuracy. We demonstrate that our algorithm is significantly faster than state-of-the-art methods without compromising accuracy, using only publicly available pre-trained 2D detection models. We also illustrate the robust performance of our algorithm in scenarios where multiple cameras are intermittently disconnected or reconnected during operation.
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
