Covariance Tracking via Geometric Particle Filtering

Yunpeng Liu,Zelin Shi,Guangwei Li

doi:10.1155/2010/583918

Abstract

Region covariance descriptor recently proposed has been approved robust and elegant to describe a region of interest, which has been applied to visual tracking. We develop a geometric method for visual tracking, in which region covariance is used to model objects appearance; then tracking is led by implementing the particle filter with the constraint that the system state lies in a low dimensional manifold: affine Lie group. The sequential Bayesian updating consists of drawing state samples while moving on the manifold geodesics; the region covariance is updated using a novel approach in a Riemannian space. Our main contribution is developing a general particle filtering-based racking algorithm that explicitly take the geometry of affine Lie groups into consideration in deriving the state equation on Lie groups. Theoretic analysis and experimental evaluations demonstrate the promise and effectiveness of the proposed tracking method.

Highlights

Visual tracking in an image sequence, which is an active area of research in computer vision, is widely applied to vision guidance, surveillance, robotic navigation, humancomputer interaction, and so forth
Region covariance descriptor recently proposed has been approved robust and elegant to describe a region of interest, which has been applied to visual tracking
We develop a geometric method for visual tracking, in which region covariance is used to model objects appearance; tracking is led by implementing the particle filter with the constraint that the system state lies in a low dimensional manifold: affine Lie group

Summary

Introduction

Visual tracking in an image sequence, which is an active area of research in computer vision, is widely applied to vision guidance, surveillance, robotic navigation, humancomputer interaction, and so forth. The classic Lucas-Kanade tracker [3, 4] and Meanshift tracker [5] get the model parameters through gradient descent which minimizes the difference between the template and the current region of the image. The methods may converge to a local maximum, they are sensitive to background clutter, occlusion, and quick moving objects These problems can be mitigated by stochastic methods which maintain multiple hypotheses in the state space and in this way, achieve more robustness to the local maximum. Particle filters simultaneously track multiple hypotheses and recursively approximate the posterior probability density function in the state space with a set of random sampled particles

Objectives

Methods

Results

Conclusion