Challenge-Aware RGBT Tracking

TL;DR

This paper introduces a challenge-aware neural network for RGBT tracking that models shared and specific challenges across modalities, leveraging a guidance module for improved discriminative features, achieving real-time performance and state-of-the-art results.

Contribution

The proposed network uniquely models shared and specific challenges with dedicated branches and uses a guidance module to transfer features between modalities for enhanced tracking.

Findings

Operates at real-time speed.

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

Effectively handles modality-specific and shared challenges.

Abstract

RGB and thermal source data suffer from both shared and specific challenges, and how to explore and exploit them plays a critical role to represent the target appearance in RGBT tracking. In this paper, we propose a novel challenge-aware neural network to handle the modality-shared challenges (e.g., fast motion, scale variation and occlusion) and the modality-specific ones (e.g., illumination variation and thermal crossover) for RGBT tracking. In particular, we design several parameter-shared branches in each layer to model the target appearance under the modality-shared challenges, and several parameterindependent branches under the modality-specific ones. Based on the observation that the modality-specific cues of different modalities usually contains the complementary advantages, we propose a guidance module to transfer discriminative features from one modality to another one, which could enhance the discriminative ability of some weak modality. Moreover, all branches are aggregated together in an adaptive manner and parallel embedded in the backbone network to efficiently form more discriminative target representations. These challenge-aware branches are able to model the target appearance under certain challenges so that the target representations can be learnt by a few parameters even in the situation of insufficient training data. From the experimental results we will show that our method operates at a real-time speed while performing well against the state-of-the-art methods on three benchmark datasets.