Invisible Gas Detection: An RGB-Thermal Cross Attention Network and A New Benchmark

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Jue, Lin, Yuxiang, Zhao, Qi, Luo, Dong, Chen, Shuaibao, Chen, Wei, Peng, Xiaojiang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913492550811648
author Wang, Jue
Lin, Yuxiang
Zhao, Qi
Luo, Dong
Chen, Shuaibao
Chen, Wei
Peng, Xiaojiang
author_facet Wang, Jue
Lin, Yuxiang
Zhao, Qi
Luo, Dong
Chen, Shuaibao
Chen, Wei
Peng, Xiaojiang
contents The widespread use of various chemical gases in industrial processes necessitates effective measures to prevent their leakage during transportation and storage, given their high toxicity. Thermal infrared-based computer vision detection techniques provide a straightforward approach to identify gas leakage areas. However, the development of high-quality algorithms has been challenging due to the low texture in thermal images and the lack of open-source datasets. In this paper, we present the RGB-Thermal Cross Attention Network (RT-CAN), which employs an RGB-assisted two-stream network architecture to integrate texture information from RGB images and gas area information from thermal images. Additionally, to facilitate the research of invisible gas detection, we introduce Gas-DB, an extensive open-source gas detection database including about 1.3K well-annotated RGB-thermal images with eight variant collection scenes. Experimental results demonstrate that our method successfully leverages the advantages of both modalities, achieving state-of-the-art (SOTA) performance among RGB-thermal methods, surpassing single-stream SOTA models in terms of accuracy, Intersection of Union (IoU), and F2 metrics by 4.86%, 5.65%, and 4.88%, respectively. The code and data can be found at https://github.com/logic112358/RT-CAN.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17712
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Invisible Gas Detection: An RGB-Thermal Cross Attention Network and A New Benchmark
Wang, Jue
Lin, Yuxiang
Zhao, Qi
Luo, Dong
Chen, Shuaibao
Chen, Wei
Peng, Xiaojiang
Computer Vision and Pattern Recognition
The widespread use of various chemical gases in industrial processes necessitates effective measures to prevent their leakage during transportation and storage, given their high toxicity. Thermal infrared-based computer vision detection techniques provide a straightforward approach to identify gas leakage areas. However, the development of high-quality algorithms has been challenging due to the low texture in thermal images and the lack of open-source datasets. In this paper, we present the RGB-Thermal Cross Attention Network (RT-CAN), which employs an RGB-assisted two-stream network architecture to integrate texture information from RGB images and gas area information from thermal images. Additionally, to facilitate the research of invisible gas detection, we introduce Gas-DB, an extensive open-source gas detection database including about 1.3K well-annotated RGB-thermal images with eight variant collection scenes. Experimental results demonstrate that our method successfully leverages the advantages of both modalities, achieving state-of-the-art (SOTA) performance among RGB-thermal methods, surpassing single-stream SOTA models in terms of accuracy, Intersection of Union (IoU), and F2 metrics by 4.86%, 5.65%, and 4.88%, respectively. The code and data can be found at https://github.com/logic112358/RT-CAN.
title Invisible Gas Detection: An RGB-Thermal Cross Attention Network and A New Benchmark
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.17712