Visual Tracking via Dynamic Graph Learning

TL;DR

This paper introduces a dynamic graph learning approach for visual tracking, modeling objects with patch-based graphs that adaptively refine foreground-background separation to improve tracking accuracy.

Contribution

It proposes a novel patch-based graph learning framework with dynamic optimization for robust visual tracking, enhancing object localization by refining patch weights during tracking.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively refines foreground-background separation during tracking.

Demonstrates robustness to background clutter and appearance changes.

Abstract

Existing visual tracking methods usually localize a target object with a bounding box, in which the performance of the foreground object trackers or detectors is often affected by the inclusion of background clutter. To handle this problem, we learn a patch-based graph representation for visual tracking. The tracked object is modeled by with a graph by taking a set of non-overlapping image patches as nodes, in which the weight of each node indicates how likely it belongs to the foreground and edges are weighted for indicating the appearance compatibility of two neighboring nodes. This graph is dynamically learned and applied in object tracking and model updating. During the tracking process, the proposed algorithm performs three main steps in each frame. First, the graph is initialized by assigning binary weights of some image patches to indicate the object and background patches according to the predicted bounding box. Second, the graph is optimized to refine the patch weights by using a novel alternating direction method of multipliers. Third, the object feature representation is updated by imposing the weights of patches on the extracted image features. The object location is predicted by maximizing the classification score in the structured support vector machine. Extensive experiments show that the proposed tracking algorithm performs well against the state-of-the-art methods on large-scale benchmark datasets.