Object Tracking via Non-Euclidean Geometry: A Grassmann Approach
This addresses the problem of robust object tracking in computer vision for applications like surveillance and robotics, presenting a novel method for a known bottleneck.
The paper tackles robust visual tracking by proposing an approach based on affine subspaces and non-Euclidean geometry on Grassmann manifolds to handle occlusion, pose, and illumination variations, achieving considerably better performance than state-of-the-art methods like Tracking-Learning-Detection and MILtrack on challenging video sequences.
A robust visual tracking system requires an object appearance model that is able to handle occlusion, pose, and illumination variations in the video stream. This can be difficult to accomplish when the model is trained using only a single image. In this paper, we first propose a tracking approach based on affine subspaces (constructed from several images) which are able to accommodate the abovementioned variations. We use affine subspaces not only to represent the object, but also the candidate areas that the object may occupy. We furthermore propose a novel approach to measure affine subspace-to-subspace distance via the use of non-Euclidean geometry of Grassmann manifolds. The tracking problem is then considered as an inference task in a Markov Chain Monte Carlo framework via particle filtering. Quantitative evaluation on challenging video sequences indicates that the proposed approach obtains considerably better performance than several recent state-of-the-art methods such as Tracking-Learning-Detection and MILtrack.