Global information aware network with global interaction graph attention for infrared small target detection

Abstract Detecting small targets in infrared images is crucial for ground surveillance and air traffic control. However, distinguishing small infrared targets from similar backgrounds is challenging due to their lack of structural and textural characteristics. To address these challenges, this study...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruimin Yang, Yidan Zhang, Guangshuai Gao, Liang Liao, Chunlei Li
Format: Article
Language:English
Published: Wiley 2024-10-01
Series:IET Image Processing
Subjects:
Online Access:https://doi.org/10.1049/ipr2.13203
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850200374702505984
author Ruimin Yang
Yidan Zhang
Guangshuai Gao
Liang Liao
Chunlei Li
author_facet Ruimin Yang
Yidan Zhang
Guangshuai Gao
Liang Liao
Chunlei Li
author_sort Ruimin Yang
collection DOAJ
description Abstract Detecting small targets in infrared images is crucial for ground surveillance and air traffic control. However, distinguishing small infrared targets from similar backgrounds is challenging due to their lack of structural and textural characteristics. To address these challenges, this study proposes a novel global information‐aware network with global interaction graph attention (GIGA) for infrared small target detection. The GIGA consists of a global interaction layer (GILayer), graph attention weights (GAW), and a global relational learning (GRL) module. Specifically, the GILayer dynamically learns global inter‐pixel relationships of small target images by enhancing the dependencies between feature dimensions. The GAW component calculates pixel‐by‐pixel similarity across the entire feature map using graph attention mechanisms, while the GRL module retains critical similarity features in the feature extraction network, thereby facilitating small target detection. Additionally, the multi‐scale context fusion module utilises self‐attention and dilation convolution to complement richer feature details at different scales. Experimental results on both natural and synthetic datasets demonstrate the proposed method's superiority over other state‐of‐the‐art conventional and deep learning approaches in infrared small target detection.
format Article
id doaj-art-142e159946e7496d970bc7ff9a7756da
institution OA Journals
issn 1751-9659
1751-9667
language English
publishDate 2024-10-01
publisher Wiley
record_format Article
series IET Image Processing
spelling doaj-art-142e159946e7496d970bc7ff9a7756da2025-08-20T02:12:20ZengWileyIET Image Processing1751-96591751-96672024-10-0118123650366610.1049/ipr2.13203Global information aware network with global interaction graph attention for infrared small target detectionRuimin Yang0Yidan Zhang1Guangshuai Gao2Liang Liao3Chunlei Li4School of Electronic and Information Engineering Zhongyuan University of Technology Zhengzhou ChinaSchool of Electronic and Information Engineering Zhongyuan University of Technology Zhengzhou ChinaSchool of Electronic and Information Engineering Zhongyuan University of Technology Zhengzhou ChinaSchool of Electronic and Information Engineering Zhongyuan University of Technology Zhengzhou ChinaSchool of Electronic and Information Engineering Zhongyuan University of Technology Zhengzhou ChinaAbstract Detecting small targets in infrared images is crucial for ground surveillance and air traffic control. However, distinguishing small infrared targets from similar backgrounds is challenging due to their lack of structural and textural characteristics. To address these challenges, this study proposes a novel global information‐aware network with global interaction graph attention (GIGA) for infrared small target detection. The GIGA consists of a global interaction layer (GILayer), graph attention weights (GAW), and a global relational learning (GRL) module. Specifically, the GILayer dynamically learns global inter‐pixel relationships of small target images by enhancing the dependencies between feature dimensions. The GAW component calculates pixel‐by‐pixel similarity across the entire feature map using graph attention mechanisms, while the GRL module retains critical similarity features in the feature extraction network, thereby facilitating small target detection. Additionally, the multi‐scale context fusion module utilises self‐attention and dilation convolution to complement richer feature details at different scales. Experimental results on both natural and synthetic datasets demonstrate the proposed method's superiority over other state‐of‐the‐art conventional and deep learning approaches in infrared small target detection.https://doi.org/10.1049/ipr2.13203computer visionconvolutional neural netsfeature extractionimage segmentationobject detectionremote sensing
spellingShingle Ruimin Yang
Yidan Zhang
Guangshuai Gao
Liang Liao
Chunlei Li
Global information aware network with global interaction graph attention for infrared small target detection
IET Image Processing
computer vision
convolutional neural nets
feature extraction
image segmentation
object detection
remote sensing
title Global information aware network with global interaction graph attention for infrared small target detection
title_full Global information aware network with global interaction graph attention for infrared small target detection
title_fullStr Global information aware network with global interaction graph attention for infrared small target detection
title_full_unstemmed Global information aware network with global interaction graph attention for infrared small target detection
title_short Global information aware network with global interaction graph attention for infrared small target detection
title_sort global information aware network with global interaction graph attention for infrared small target detection
topic computer vision
convolutional neural nets
feature extraction
image segmentation
object detection
remote sensing
url https://doi.org/10.1049/ipr2.13203
work_keys_str_mv AT ruiminyang globalinformationawarenetworkwithglobalinteractiongraphattentionforinfraredsmalltargetdetection
AT yidanzhang globalinformationawarenetworkwithglobalinteractiongraphattentionforinfraredsmalltargetdetection
AT guangshuaigao globalinformationawarenetworkwithglobalinteractiongraphattentionforinfraredsmalltargetdetection
AT liangliao globalinformationawarenetworkwithglobalinteractiongraphattentionforinfraredsmalltargetdetection
AT chunleili globalinformationawarenetworkwithglobalinteractiongraphattentionforinfraredsmalltargetdetection