Unified Graph based Multi-Cue Feature Fusion for Robust Visual Tracking

TL;DR

This paper introduces a unified graph fusion framework that combines multiple visual cues through cross-diffusion, enhancing robustness in visual tracking against appearance changes, occlusion, and background clutter.

Contribution

The work presents a novel unified graph fusion method with cross-diffusion of features and a kernel-based adaptation strategy for improved visual tracking.

Findings

Enhanced robustness to object deformations and occlusion

Improved accuracy in distinguishing foreground from background

Effective adaptation to dynamic environments

Abstract

Visual Tracking is a complex problem due to unconstrained appearance variations and dynamic environment. Extraction of complementary information from the object environment via multiple features and adaption to the target's appearance variations are the key problems of this work. To this end, we propose a robust object tracking framework based on Unified Graph Fusion (UGF) of multi-cue to adapt to the object's appearance. The proposed cross-diffusion of sparse and dense features not only suppresses the individual feature deficiencies but also extracts the complementary information from multi-cue. This iterative process builds robust unified features which are invariant to object deformations, fast motion, and occlusion. Robustness of the unified feature also enables the random forest classifier to precisely distinguish the foreground from the background, adding resilience to background clutter. In addition, we present a novel kernel-based adaptation strategy using outlier detection and a transductive reliability metric.