Infrared Small Target Detection Based on Weak Feature Enhancement and Target Adaptive Proliferation

The imbalance between positive and negative samples and the loss of small targets in complex backgrounds are catastrophic for infrared small target detection. To address these issues, we proposed an infrared small target detection method based on weak feature enhancement and target adaptive prolifer...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoyu Xu, Weida Zhan, Yichun Jiang, Depeng Zhu, Yu Chen, Jinxin Guo, Ziqiang Hao, Deng Han
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/10772282/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850285049631473664
author Xiaoyu Xu
Weida Zhan
Yichun Jiang
Depeng Zhu
Yu Chen
Jinxin Guo
Ziqiang Hao
Deng Han
author_facet Xiaoyu Xu
Weida Zhan
Yichun Jiang
Depeng Zhu
Yu Chen
Jinxin Guo
Ziqiang Hao
Deng Han
author_sort Xiaoyu Xu
collection DOAJ
description The imbalance between positive and negative samples and the loss of small targets in complex backgrounds are catastrophic for infrared small target detection. To address these issues, we proposed an infrared small target detection method based on weak feature enhancement and target adaptive proliferation (IRSTD-WFETAP). First, we utilized a sparse sampling mechanism and hybrid filtering method to flexibly capture the complex shapes and edge information of small targets while reducing the loss and shift of scarce features. Then, we introduced a multiscale feature enhancement module that used vertical-horizontal bidirectional attention and multiscale feature encoding to establish stable feature interaction channels between the encoder and decoder, further enhancing key features of small targets. In addition, we introduced a target data self-adaptive proliferation strategy (DSAS) to address the imbalance of positive and negative samples, enhancing the generalization and expression capability of the detection datasets. Finally, we proposed a target-background joint loss to alleviate the imbalance issue and help the network converge smoothly. Extensive experiments on NUAA-SIRST, IRSTD-1k, and our custom-made dataset demonstrated the effectiveness of the proposed IRSTD-WFETAP method, achieving superior performance in nIoU, Pd, Fa, and F1-measure compared to the latest methods.
format Article
id doaj-art-2e55ebe4447643faa07d1f262e288aeb
institution OA Journals
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-2e55ebe4447643faa07d1f262e288aeb2025-08-20T01:47:25ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01182829285010.1109/JSTARS.2024.350999310772282Infrared Small Target Detection Based on Weak Feature Enhancement and Target Adaptive ProliferationXiaoyu Xu0https://orcid.org/0009-0003-2308-4198Weida Zhan1https://orcid.org/0000-0003-1011-7416Yichun Jiang2https://orcid.org/0000-0002-0178-9416Depeng Zhu3https://orcid.org/0000-0002-1227-539XYu Chen4Jinxin Guo5Ziqiang Hao6Deng Han7College 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, ChinaCollege of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, ChinaCollege of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, ChinaJilin Province Zhixing IoT Research Institute Company Ltd., Changchun, ChinaThe imbalance between positive and negative samples and the loss of small targets in complex backgrounds are catastrophic for infrared small target detection. To address these issues, we proposed an infrared small target detection method based on weak feature enhancement and target adaptive proliferation (IRSTD-WFETAP). First, we utilized a sparse sampling mechanism and hybrid filtering method to flexibly capture the complex shapes and edge information of small targets while reducing the loss and shift of scarce features. Then, we introduced a multiscale feature enhancement module that used vertical-horizontal bidirectional attention and multiscale feature encoding to establish stable feature interaction channels between the encoder and decoder, further enhancing key features of small targets. In addition, we introduced a target data self-adaptive proliferation strategy (DSAS) to address the imbalance of positive and negative samples, enhancing the generalization and expression capability of the detection datasets. Finally, we proposed a target-background joint loss to alleviate the imbalance issue and help the network converge smoothly. Extensive experiments on NUAA-SIRST, IRSTD-1k, and our custom-made dataset demonstrated the effectiveness of the proposed IRSTD-WFETAP method, achieving superior performance in nIoU, Pd, Fa, and F1-measure compared to the latest methods.https://ieeexplore.ieee.org/document/10772282/Deep learningthermal infrared imagethermal infrared small target detection (IRSTD)weak feature enhancement
spellingShingle Xiaoyu Xu
Weida Zhan
Yichun Jiang
Depeng Zhu
Yu Chen
Jinxin Guo
Ziqiang Hao
Deng Han
Infrared Small Target Detection Based on Weak Feature Enhancement and Target Adaptive Proliferation
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning
thermal infrared image
thermal infrared small target detection (IRSTD)
weak feature enhancement
title Infrared Small Target Detection Based on Weak Feature Enhancement and Target Adaptive Proliferation
title_full Infrared Small Target Detection Based on Weak Feature Enhancement and Target Adaptive Proliferation
title_fullStr Infrared Small Target Detection Based on Weak Feature Enhancement and Target Adaptive Proliferation
title_full_unstemmed Infrared Small Target Detection Based on Weak Feature Enhancement and Target Adaptive Proliferation
title_short Infrared Small Target Detection Based on Weak Feature Enhancement and Target Adaptive Proliferation
title_sort infrared small target detection based on weak feature enhancement and target adaptive proliferation
topic Deep learning
thermal infrared image
thermal infrared small target detection (IRSTD)
weak feature enhancement
url https://ieeexplore.ieee.org/document/10772282/
work_keys_str_mv AT xiaoyuxu infraredsmalltargetdetectionbasedonweakfeatureenhancementandtargetadaptiveproliferation
AT weidazhan infraredsmalltargetdetectionbasedonweakfeatureenhancementandtargetadaptiveproliferation
AT yichunjiang infraredsmalltargetdetectionbasedonweakfeatureenhancementandtargetadaptiveproliferation
AT depengzhu infraredsmalltargetdetectionbasedonweakfeatureenhancementandtargetadaptiveproliferation
AT yuchen infraredsmalltargetdetectionbasedonweakfeatureenhancementandtargetadaptiveproliferation
AT jinxinguo infraredsmalltargetdetectionbasedonweakfeatureenhancementandtargetadaptiveproliferation
AT ziqianghao infraredsmalltargetdetectionbasedonweakfeatureenhancementandtargetadaptiveproliferation
AT denghan infraredsmalltargetdetectionbasedonweakfeatureenhancementandtargetadaptiveproliferation