Object Tracking via Non-Euclidean Geometry: A Grassmann Approach

TL;DR

This paper introduces a novel object tracking method using affine subspaces and Grassmannian geometry to improve robustness against occlusion, pose, and illumination changes, outperforming recent state-of-the-art techniques.

Contribution

It presents a new tracking approach based on affine subspaces and Grassmann manifold geometry, enhancing robustness and accuracy in challenging video conditions.

Findings

Outperforms recent methods like Tracking-Learning-Detection and MILtrack

Handles occlusion, pose, and illumination variations effectively

Uses affine subspaces and Grassmannian geometry for improved tracking

Abstract

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.