Single-Frame Infrared Small Target Detection Network Based on Multibranch Feature Aggregation
Single-frame infrared small target detection is critical in fields, such as remote sensing, aerospace, and ecological monitoring. Enhancing both the accuracy and speed of this detection process can substantially improve the overall performance of infrared target detection and tracking. While deep le...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2025-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10811940/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832592940345589760 |
---|---|
author | Ziqiang Hao Zheng Jiang Xiaoyu Xu Zhuohao Wang Zhicheng Sun |
author_facet | Ziqiang Hao Zheng Jiang Xiaoyu Xu Zhuohao Wang Zhicheng Sun |
author_sort | Ziqiang Hao |
collection | DOAJ |
description | Single-frame infrared small target detection is critical in fields, such as remote sensing, aerospace, and ecological monitoring. Enhancing both the accuracy and speed of this detection process can substantially improve the overall performance of infrared target detection and tracking. While deep learning-based methods have shown promising results in general detection tasks, increasing network depth vertically to improve feature extraction often results in the loss of small targets. To address this challenge, we propose a network framework based on multibranch feature aggregation, which expands the network depth horizontally. The parallel auxiliary branches are carefully designed to provide the main branch with semantic information at varying depths and scales. Furthermore, we introduce a differential correction module that corrects erroneous target features through differential methods, significantly boosting detection accuracy. Lastly, we develop a joint attention module that combines channel and spatial attention mechanisms, enabling the network to accurately localize and reconstruct small targets. Extensive experiments on the NUDT-SIRST, SIRST, and NUST-SIRST datasets demonstrate the clear superiority of our approach over other state-of-the-art infrared small target detection methods. |
format | Article |
id | doaj-art-91ed54679638497a8d406b9d34f71f83 |
institution | Kabale University |
issn | 1939-1404 2151-1535 |
language | English |
publishDate | 2025-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj-art-91ed54679638497a8d406b9d34f71f832025-01-21T00:00:17ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183356337010.1109/JSTARS.2024.352105710811940Single-Frame Infrared Small Target Detection Network Based on Multibranch Feature AggregationZiqiang Hao0Zheng Jiang1https://orcid.org/0009-0001-9268-3579Xiaoyu Xu2https://orcid.org/0009-0003-2308-4198Zhuohao Wang3Zhicheng Sun4College of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, ChinaCollege of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, ChinaCollege of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, ChinaCollege of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, ChinaCollege of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, ChinaSingle-frame infrared small target detection is critical in fields, such as remote sensing, aerospace, and ecological monitoring. Enhancing both the accuracy and speed of this detection process can substantially improve the overall performance of infrared target detection and tracking. While deep learning-based methods have shown promising results in general detection tasks, increasing network depth vertically to improve feature extraction often results in the loss of small targets. To address this challenge, we propose a network framework based on multibranch feature aggregation, which expands the network depth horizontally. The parallel auxiliary branches are carefully designed to provide the main branch with semantic information at varying depths and scales. Furthermore, we introduce a differential correction module that corrects erroneous target features through differential methods, significantly boosting detection accuracy. Lastly, we develop a joint attention module that combines channel and spatial attention mechanisms, enabling the network to accurately localize and reconstruct small targets. Extensive experiments on the NUDT-SIRST, SIRST, and NUST-SIRST datasets demonstrate the clear superiority of our approach over other state-of-the-art infrared small target detection methods.https://ieeexplore.ieee.org/document/10811940/Channel spatial attentiondeep learningfeature interactioninfrared small target detection (ISTD)information aggregation |
spellingShingle | Ziqiang Hao Zheng Jiang Xiaoyu Xu Zhuohao Wang Zhicheng Sun Single-Frame Infrared Small Target Detection Network Based on Multibranch Feature Aggregation IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Channel spatial attention deep learning feature interaction infrared small target detection (ISTD) information aggregation |
title | Single-Frame Infrared Small Target Detection Network Based on Multibranch Feature Aggregation |
title_full | Single-Frame Infrared Small Target Detection Network Based on Multibranch Feature Aggregation |
title_fullStr | Single-Frame Infrared Small Target Detection Network Based on Multibranch Feature Aggregation |
title_full_unstemmed | Single-Frame Infrared Small Target Detection Network Based on Multibranch Feature Aggregation |
title_short | Single-Frame Infrared Small Target Detection Network Based on Multibranch Feature Aggregation |
title_sort | single frame infrared small target detection network based on multibranch feature aggregation |
topic | Channel spatial attention deep learning feature interaction infrared small target detection (ISTD) information aggregation |
url | https://ieeexplore.ieee.org/document/10811940/ |
work_keys_str_mv | AT ziqianghao singleframeinfraredsmalltargetdetectionnetworkbasedonmultibranchfeatureaggregation AT zhengjiang singleframeinfraredsmalltargetdetectionnetworkbasedonmultibranchfeatureaggregation AT xiaoyuxu singleframeinfraredsmalltargetdetectionnetworkbasedonmultibranchfeatureaggregation AT zhuohaowang singleframeinfraredsmalltargetdetectionnetworkbasedonmultibranchfeatureaggregation AT zhichengsun singleframeinfraredsmalltargetdetectionnetworkbasedonmultibranchfeatureaggregation |