Coordinate-Aware Thermal Infrared Tracking Via Natural Language Modeling

TL;DR

This paper introduces NLMTrack, a coordinate-aware thermal infrared tracking model that leverages natural language modeling and transformer-based techniques to improve tracking accuracy in low-contrast TIR images.

Contribution

The paper proposes a novel TIR tracking approach using natural language modeling and a unified encoder, enhancing coordinate and temporal information utilization.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Effectively enhances semantic representation with multi-scale features.

Improves tracking accuracy with an adaptive loss and template update strategy.

Abstract

Thermal infrared (TIR) tracking is pivotal in computer vision tasks due to its all-weather imaging capability. Traditional tracking methods predominantly rely on hand-crafted features, and while deep learning has introduced correlation filtering techniques, these are often constrained by rudimentary correlation operations. Furthermore, transformer-based approaches tend to overlook temporal and coordinate information, which is critical for TIR tracking that lacks texture and color information. In this paper, to address these issues, we apply natural language modeling to TIR tracking and propose a coordinate-aware thermal infrared tracking model called NLMTrack, which enhances the utilization of coordinate and temporal information. NLMTrack applies an encoder that unifies feature extraction and feature fusion, which simplifies the TIR tracking pipeline. To address the challenge of low detail and low contrast in TIR images, on the one hand, we design a multi-level progressive fusion module that enhances the semantic representation and incorporates multi-scale features. On the other hand, the decoder combines the TIR features and the coordinate sequence features using a causal transformer to generate the target sequence step by step. Moreover, we explore an adaptive loss aimed at elevating tracking accuracy and a simple template update strategy to accommodate the target's appearance variations. Experiments show that NLMTrack achieves state-of-the-art performance on multiple benchmarks. The Code is publicly available at \url{https://github.com/ELOESZHANG/NLMTrack}.