Robust Multi-body Feature Tracker: A Segmentation-free Approach

TL;DR

This paper presents a segmentation-free multi-body feature tracker that enhances robustness and accuracy in motion tracking tasks by avoiding explicit motion segmentation, simplifying the process under a general perspective camera model.

Contribution

It introduces a novel segmentation-free approach to multi-body feature tracking that bypasses motion segmentation and assignment, improving robustness and simplifying computations.

Findings

Improved tracking accuracy over traditional methods.

Enhanced robustness to noise in feature tracking.

Simplified process without explicit motion segmentation.

Abstract

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.