TENet: Targetness Entanglement Incorporating with Multi-Scale Pooling and Mutually-Guided Fusion for RGB-E Object Tracking

TL;DR

This paper introduces TENet, a novel RGB-E object tracking method that employs a specialized event backbone with multi-scale pooling and mutually-guided fusion, significantly enhancing tracking accuracy by effectively leveraging event data.

Contribution

The paper proposes a new event backbone with multi-scale pooling and a mutually-guided fusion module, tailored for event data's sparsity, improving RGB-E tracking performance.

Findings

Outperforms state-of-the-art trackers on VisEvent and COESOT datasets.

Achieves 4.9% higher precision and 5.2% higher success rate on COESOT.

Demonstrates the effectiveness of the proposed event-specific feature extraction and fusion methods.

Abstract

There is currently strong interest in improving visual object tracking by augmenting the RGB modality with the output of a visual event camera that is particularly informative about the scene motion. However, existing approaches perform event feature extraction for RGB-E tracking using traditional appearance models, which have been optimised for RGB only tracking, without adapting it for the intrinsic characteristics of the event data. To address this problem, we propose an Event backbone (Pooler), designed to obtain a high-quality feature representation that is cognisant of the innate characteristics of the event data, namely its sparsity. In particular, Multi-Scale Pooling is introduced to capture all the motion feature trends within event data through the utilisation of diverse pooling kernel sizes. The association between the derived RGB and event representations is established by an innovative module performing adaptive Mutually Guided Fusion (MGF). Extensive experimental results show that our method significantly outperforms state-of-the-art trackers on two widely used RGB-E tracking datasets, including VisEvent and COESOT, where the precision and success rates on COESOT are improved by 4.9% and 5.2%, respectively. Our code will be available at https://github.com/SSSpc333/TENet.