Learning multi-level graph attentional representation for thermal infrared object tracking

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18470%2F25%3A50022608" target="_blank" >RIV/62690094:18470/25:50022608 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S0952197625009571?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0952197625009571?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.engappai.2025.110957" target="_blank" >10.1016/j.engappai.2025.110957</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Learning multi-level graph attentional representation for thermal infrared object tracking

Popis výsledku v původním jazyce

Thermal infrared (TIR) object tracking is a fundamental task in computer vision that is not affected by changes in lighting conditions. It performs better than visible light trackers in extreme environments such as nighttime, heavy rain, haze, and sandstorms. However, TIR object tracking also faces challenges such as occlusion, thermal crossover, motion blur, and similarity interference. Unlike visual tracking, TIR images lack color information and texture features. These factors make it challenging to learn detailed and shape features of the targets, making it hard to distinguish between targets and interference effectively. In this study, we propose a graph-based deep learning model, SiamMLGR, within the Siamese framework for stable TIR object tracking to address these issues. Specifically, to extract more fine-grained features of TIR targets, we propose a multiple graph attention module (MGAM) to replace the global matching information transmission method in the Siamese framework. This module constructs a graph structure to establish local and global connections between the target and the search area. Furthermore, to retain more of the features learned by the MGAM, we propose a spatial graph convolutional module (SGCM), which uses an explicit graph adjacency matrix to propagate information between the attention graphs. Additionally, we incorporate large-scale datasets from the visual tracking field into the model training process. By mixing these with TIR datasets, we address the sample imbalance issue present in pure TIR datasets. Extensive experimental results indicate that the proposed method achieves state-of-the-art performance.

Název v anglickém jazyce

Learning multi-level graph attentional representation for thermal infrared object tracking

Popis výsledku anglicky

Thermal infrared (TIR) object tracking is a fundamental task in computer vision that is not affected by changes in lighting conditions. It performs better than visible light trackers in extreme environments such as nighttime, heavy rain, haze, and sandstorms. However, TIR object tracking also faces challenges such as occlusion, thermal crossover, motion blur, and similarity interference. Unlike visual tracking, TIR images lack color information and texture features. These factors make it challenging to learn detailed and shape features of the targets, making it hard to distinguish between targets and interference effectively. In this study, we propose a graph-based deep learning model, SiamMLGR, within the Siamese framework for stable TIR object tracking to address these issues. Specifically, to extract more fine-grained features of TIR targets, we propose a multiple graph attention module (MGAM) to replace the global matching information transmission method in the Siamese framework. This module constructs a graph structure to establish local and global connections between the target and the search area. Furthermore, to retain more of the features learned by the MGAM, we propose a spatial graph convolutional module (SGCM), which uses an explicit graph adjacency matrix to propagate information between the attention graphs. Additionally, we incorporate large-scale datasets from the visual tracking field into the model training process. By mixing these with TIR datasets, we address the sample imbalance issue present in pure TIR datasets. Extensive experimental results indicate that the proposed method achieves state-of-the-art performance.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Engineering applications of artificial intelligence

ISSN

0952-1976

e-ISSN

1873-6769

Svazek periodika

155

Číslo periodika v rámci svazku

September

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

12

Strana od-do

"Article Number: 110957"

Kód UT WoS článku

001491146700001

EID výsledku v databázi Scopus

2-s2.0-105004653868