A Diffusion Process on Riemannian Manifold for Visual Tracking

TL;DR

This paper introduces a novel visual tracking method using a diffusion process on Riemannian manifolds to model target variations and uncertainties, improving robustness to pose, illumination, and spatial changes.

Contribution

It proposes a new dynamical model for template update via a random walk on the Riemannian manifold of covariance descriptors, enabling joint uncertainty quantification.

Findings

Outperforms state-of-the-art incremental PCA in fast pose changes

Robust to illumination and spatial affine transformations

Maintains competitive performance in stable tracking scenarios

Abstract

Robust visual tracking for long video sequences is a research area that has many important applications. The main challenges include how the target image can be modeled and how this model can be updated. In this paper, we model the target using a covariance descriptor, as this descriptor is robust to problems such as pixel-pixel misalignment, pose and illumination changes, that commonly occur in visual tracking. We model the changes in the template using a generative process. We introduce a new dynamical model for the template update using a random walk on the Riemannian manifold where the covariance descriptors lie in. This is done using log-transformed space of the manifold to free the constraints imposed inherently by positive semidefinite matrices. Modeling template variations and poses kinetics together in the state space enables us to jointly quantify the uncertainties relating to the kinematic states and the template in a principled way. Finally, the sequential inference of the posterior distribution of the kinematic states and the template is done using a particle filter. Our results shows that this principled approach can be robust to changes in illumination, poses and spatial affine transformation. In the experiments, our method outperformed the current state-of-the-art algorithm - the incremental Principal Component Analysis method, particularly when a target underwent fast poses changes and also maintained a comparable performance in stable target tracking cases.