Better Feature Tracking Through Subspace Constraints

TL;DR

This paper introduces a joint feature tracking framework using subspace constraints that improves tracking robustness in noisy, poorly-lit videos, handling occlusions and nonrigid motions in real time without explicit scene modeling.

Contribution

It proposes a novel joint tracking method leveraging subspace constraints, enhancing performance over traditional single-feature trackers in challenging conditions.

Findings

Effective in tracking features in dark, noisy videos

Handles occlusions and nonrigid motions robustly

Operates in real time on a single CPU core

Abstract

Feature tracking in video is a crucial task in computer vision. Usually, the tracking problem is handled one feature at a time, using a single-feature tracker like the Kanade-Lucas-Tomasi algorithm, or one of its derivatives. While this approach works quite well when dealing with high-quality video and "strong" features, it often falters when faced with dark and noisy video containing low-quality features. We present a framework for jointly tracking a set of features, which enables sharing information between the different features in the scene. We show that our method can be employed to track features for both rigid and nonrigid motions (possibly of few moving bodies) even when some features are occluded. Furthermore, it can be used to significantly improve tracking results in poorly-lit scenes (where there is a mix of good and bad features). Our approach does not require direct modeling of the structure or the motion of the scene, and runs in real time on a single CPU core.