Adaptive Objectness for Object Tracking

TL;DR

This paper introduces ADOBING, an adaptive objectness measure tailored for visual object tracking, which improves existing trackers by integrating target-specific objectness learned via an adaptive SVM.

Contribution

The paper proposes a novel adaptive objectness measure, ADOBING, that enhances tracker performance by customizing generic objectness to specific tracking sequences.

Findings

ADOBING consistently improves performance of seven top trackers.

Enhanced trackers achieve state-of-the-art results on benchmark datasets.

Adaptive objectness is effective across different tracking environments.

Abstract

Object tracking is a long standing problem in vision. While great efforts have been spent to improve tracking performance, a simple yet reliable prior knowledge is left unexploited: the target object in tracking must be an object other than non-object. The recently proposed and popularized objectness measure provides a natural way to model such prior in visual tracking. Thus motivated, in this paper we propose to adapt objectness for visual object tracking. Instead of directly applying an existing objectness measure that is generic and handles various objects and environments, we adapt it to be compatible to the specific tracking sequence and object. More specifically, we use the newly proposed BING objectness as the base, and then train an object-adaptive objectness for each tracking task. The training is implemented by using an adaptive support vector machine that integrates information from the specific tracking target into the BING measure. We emphasize that the benefit of the proposed adaptive objectness, named ADOBING, is generic. To show this, we combine ADOBING with seven top performed trackers in recent evaluations. We run the ADOBING-enhanced trackers with their base trackers on two popular benchmarks, the CVPR2013 benchmark (50 sequences) and the Princeton Tracking Benchmark (100 sequences). On both benchmarks, our methods not only consistently improve the base trackers, but also achieve the best known performances. Noting that the way we integrate objectness in visual tracking is generic and straightforward, we expect even more improvement by using tracker-specific objectness.