Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking

TL;DR

This paper introduces CD-CNN, a new neural network model for visual object tracking that leverages temporal continuity and object-centroid concepts to improve accuracy and reduce drifting in video sequences.

Contribution

The paper presents a novel CD-CNN model that incorporates temporal appearance continuity and object-centroid features, enhancing tracking performance over existing methods.

Findings

Achieves competitive accuracy on benchmark datasets.

Effectively models temporal relationships in video sequences.

Reduces target drifting through novel object-centroid feature.

Abstract

This paper proposes a novel model, named Continuity-Discrimination Convolutional Neural Network (CD-CNN), for visual object tracking. Existing state-of-the-art tracking methods do not deal with temporal relationship in video sequences, which leads to imperfect feature representations. To address this problem, CD-CNN models temporal appearance continuity based on the idea of temporal slowness. Mathematically, we prove that, by introducing temporal appearance continuity into tracking, the upper bound of target appearance representation error can be sufficiently small with high probability. Further, in order to alleviate inaccurate target localization and drifting, we propose a novel notion, object-centroid, to characterize not only objectness but also the relative position of the target within a given patch. Both temporal appearance continuity and object-centroid are jointly learned during offline training and then transferred for online tracking. We evaluate our tracker through extensive experiments on two challenging benchmarks and show its competitive tracking performance compared with state-of-the-art trackers.