Robust video object tracking via Bayesian model averaging based feature fusion

TL;DR

This paper introduces a robust video object tracking algorithm that uses Bayesian model averaging to fuse multiple features, effectively handling occlusion, color confusion, and size changes in dynamic scenes.

Contribution

It presents a novel Bayesian framework with feature fusion via BMA and particle filtering, enhancing robustness and flexibility in object tracking.

Findings

Demonstrates robustness against occlusion and appearance changes

Achieves improved tracking accuracy over existing methods

Flexible framework allowing multiple feature integration

Abstract

In this article, we are concerned with tracking an object of interest in video stream. We propose an algorithm that is robust against occlusion, the presence of confusing colors, abrupt changes in the object feature space and changes in object size. We develop the algorithm within a Bayesian modeling framework. The state space model is used for capturing the temporal correlation in the sequence of frame images by modeling the underlying dynamics of the tracking system. The Bayesian model averaging (BMA) strategy is proposed for fusing multi-clue information in the observations. Any number of object features are allowed to be involved in the proposed framework. Every feature represents one source of information to be fused and is associated with an observation model. The state inference is performed by employing the particle filter methods. In comparison with related approaches, the BMA based tracker is shown to have robustness, expressivity, and comprehensibility.