CCRANet: A Two-Stage Local Attention Network for Single-Frame Low-Resolution Infrared Small Target Detection
Infrared small target detection technology is widely used in infrared search and tracking, infrared precision guidance, low and slow small aircraft detection, and other projects. Its detection ability is very important in terms of finding unknown targets as early as possible, warning in time, and al...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/23/5539 |
| _version_ | 1797399625293889536 |
|---|---|
| author | Wenjing Wang Chengwang Xiao Haofeng Dou Ruixiang Liang Huaibin Yuan Guanghui Zhao Zhiwei Chen Yuhang Huang |
| author_facet | Wenjing Wang Chengwang Xiao Haofeng Dou Ruixiang Liang Huaibin Yuan Guanghui Zhao Zhiwei Chen Yuhang Huang |
| author_sort | Wenjing Wang |
| collection | DOAJ |
| description | Infrared small target detection technology is widely used in infrared search and tracking, infrared precision guidance, low and slow small aircraft detection, and other projects. Its detection ability is very important in terms of finding unknown targets as early as possible, warning in time, and allowing for enough response time for the security system. This paper combines the target characteristics of low-resolution infrared small target images and studies the infrared small target detection method under a complex background based on the attention mechanism. The main contents of this paper are as follows: (1) by sorting through and expanding the existing datasets, we construct a single-frame low-resolution infrared small target (SLR-IRST) dataset and evaluate the existing datasets on three aspects—target number, target category, and target size; (2) to improve the pixel-level metrics of low-resolution infrared small target detection, we propose a small target detection network with two stages and a corresponding method. Regarding the SLR-IRST dataset, the proposed method is superior to the existing methods in terms of pixel-level metrics and target-level metrics and has certain advantages in model processing speed. |
| first_indexed | 2024-03-09T01:43:46Z |
| format | Article |
| id | doaj.art-2d8a4cd84e3f49d3b0157229432cc33d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T01:43:46Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2d8a4cd84e3f49d3b0157229432cc33d2023-12-08T15:24:56ZengMDPI AGRemote Sensing2072-42922023-11-011523553910.3390/rs15235539CCRANet: A Two-Stage Local Attention Network for Single-Frame Low-Resolution Infrared Small Target DetectionWenjing Wang0Chengwang Xiao1Haofeng Dou2Ruixiang Liang3Huaibin Yuan4Guanghui Zhao5Zhiwei Chen6Yuhang Huang7Science and Technology on Multi-Spectral Information Processing Laboratory, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, ChinaScience and Technology on Multi-Spectral Information Processing Laboratory, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, ChinaChina Academy of Space Technology (Xi’an), Xi’an 710100, ChinaChina Academy of Space Technology (Xi’an), Xi’an 710100, ChinaChina Academy of Space Technology (Xi’an), Xi’an 710100, ChinaScience and Technology on Multi-Spectral Information Processing Laboratory, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, ChinaScience and Technology on Multi-Spectral Information Processing Laboratory, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, ChinaScience and Technology on Multi-Spectral Information Processing Laboratory, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, ChinaInfrared small target detection technology is widely used in infrared search and tracking, infrared precision guidance, low and slow small aircraft detection, and other projects. Its detection ability is very important in terms of finding unknown targets as early as possible, warning in time, and allowing for enough response time for the security system. This paper combines the target characteristics of low-resolution infrared small target images and studies the infrared small target detection method under a complex background based on the attention mechanism. The main contents of this paper are as follows: (1) by sorting through and expanding the existing datasets, we construct a single-frame low-resolution infrared small target (SLR-IRST) dataset and evaluate the existing datasets on three aspects—target number, target category, and target size; (2) to improve the pixel-level metrics of low-resolution infrared small target detection, we propose a small target detection network with two stages and a corresponding method. Regarding the SLR-IRST dataset, the proposed method is superior to the existing methods in terms of pixel-level metrics and target-level metrics and has certain advantages in model processing speed.https://www.mdpi.com/2072-4292/15/23/5539infrared imagesmall target detectiondeep learningself-attention |
| spellingShingle | Wenjing Wang Chengwang Xiao Haofeng Dou Ruixiang Liang Huaibin Yuan Guanghui Zhao Zhiwei Chen Yuhang Huang CCRANet: A Two-Stage Local Attention Network for Single-Frame Low-Resolution Infrared Small Target Detection Remote Sensing infrared image small target detection deep learning self-attention |
| title | CCRANet: A Two-Stage Local Attention Network for Single-Frame Low-Resolution Infrared Small Target Detection |
| title_full | CCRANet: A Two-Stage Local Attention Network for Single-Frame Low-Resolution Infrared Small Target Detection |
| title_fullStr | CCRANet: A Two-Stage Local Attention Network for Single-Frame Low-Resolution Infrared Small Target Detection |
| title_full_unstemmed | CCRANet: A Two-Stage Local Attention Network for Single-Frame Low-Resolution Infrared Small Target Detection |
| title_short | CCRANet: A Two-Stage Local Attention Network for Single-Frame Low-Resolution Infrared Small Target Detection |
| title_sort | ccranet a two stage local attention network for single frame low resolution infrared small target detection |
| topic | infrared image small target detection deep learning self-attention |
| url | https://www.mdpi.com/2072-4292/15/23/5539 |
| work_keys_str_mv | AT wenjingwang ccranetatwostagelocalattentionnetworkforsingleframelowresolutioninfraredsmalltargetdetection AT chengwangxiao ccranetatwostagelocalattentionnetworkforsingleframelowresolutioninfraredsmalltargetdetection AT haofengdou ccranetatwostagelocalattentionnetworkforsingleframelowresolutioninfraredsmalltargetdetection AT ruixiangliang ccranetatwostagelocalattentionnetworkforsingleframelowresolutioninfraredsmalltargetdetection AT huaibinyuan ccranetatwostagelocalattentionnetworkforsingleframelowresolutioninfraredsmalltargetdetection AT guanghuizhao ccranetatwostagelocalattentionnetworkforsingleframelowresolutioninfraredsmalltargetdetection AT zhiweichen ccranetatwostagelocalattentionnetworkforsingleframelowresolutioninfraredsmalltargetdetection AT yuhanghuang ccranetatwostagelocalattentionnetworkforsingleframelowresolutioninfraredsmalltargetdetection |