Robust Multi-body Feature Tracker: A Segmentation-free Approach
This work addresses a fundamental problem in computer vision for applications like visual SLAM and action recognition, offering an incremental improvement over conventional methods.
The paper tackles the problem of multi-body feature tracking in computer vision by introducing a segmentation-free approach that avoids motion assignment and uses closed-form solutions, resulting in improved tracking accuracy and robustness to noise.
Feature tracking is a fundamental problem in computer vision, with applications in many computer vision tasks, such as visual SLAM and action recognition. This paper introduces a novel multi-body feature tracker that exploits a multi-body rigidity assumption to improve tracking robustness under a general perspective camera model. A conventional approach to addressing this problem would consist of alternating between solving two subtasks: motion segmentation and feature tracking under rigidity constraints for each segment. This approach, however, requires knowing the number of motions, as well as assigning points to motion groups, which is typically sensitive to the motion estimates. By contrast, here, we introduce a segmentation-free solution to multi-body feature tracking that bypasses the motion assignment step and reduces to solving a series of subproblems with closed-form solutions. Our experiments demonstrate the benefits of our approach in terms of tracking accuracy and robustness to noise.