Journal
COMPUTER VISION, ECCV 2022, PT XXII
Volume 13682, Issue -, Pages 627-643Publisher
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-031-20047-2_36
Keywords
3D Tracking; Pose estimation
Funding
- NSFC [62172260]
- Industrial Internet Innovation and Development Project in 2019 of China
Ask authors/readers for more resources
In this paper, a fast and effective non-local 3D tracking method is proposed, which can adapt to different frame displacements and outperform previous methods in terms of accuracy and real-time performance.
Optimization-based 3D object tracking is known to be precise and fast, but sensitive to large inter-frame displacements. In this paper we propose a fast and effective non-local 3D tracking method. Based on the observation that erroneous local minimum are mostly due to the out-of-plane rotation, we propose a hybrid approach combining non-local and local optimizations for different parameters, resulting in efficient non-local search in the 6D pose space. In addition, a precomputed robust contour-based tracking method is proposed for the pose optimization. By using long search lines with multiple candidate correspondences, it can adapt to different frame displacements without the need of coarse-to-fine search. After the pre-computation, pose updates can be conducted very fast, enabling the non-local optimization to run in real time. Our method outperforms all previous methods for both small and large displacements. For large displacements, the accuracy is greatly improved (81.7% v.s. 19.4%). At the same time, real-time speed (>50 fps) can be achieved with only CPU. The source code is available at https://github.com/cvbubbles/nonlocal-3dtracking.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available