Online Object Tracking with Proposal Selection

TL;DR

This paper introduces a new proposal selection method for online object tracking that handles challenging transformations by using geometric cues and multiple scoring strategies, achieving state-of-the-art results.

Contribution

It proposes a novel proposal estimation from geometric transformations and a multi-cue selection strategy for improved tracking under challenging conditions.

Findings

Achieves top performance on VOT 2014 and OTB datasets.

Outperforms existing trackers in handling object transformations.

Demonstrates robustness to severe rotations and appearance changes.

Abstract

Tracking-by-detection approaches are some of the most successful object trackers in recent years. Their success is largely determined by the detector model they learn initially and then update over time. However, under challenging conditions where an object can undergo transformations, e.g., severe rotation, these methods are found to be lacking. In this paper, we address this problem by formulating it as a proposal selection task and making two contributions. The first one is introducing novel proposals estimated from the geometric transformations undergone by the object, and building a rich candidate set for predicting the object location. The second one is devising a novel selection strategy using multiple cues, i.e., detection score and edgeness score computed from state-of-the-art object edges and motion boundaries. We extensively evaluate our approach on the visual object tracking 2014 challenge and online tracking benchmark datasets, and show the best performance.