An Investigation of Infrared Small Target Detection by Using the SPT–YOLO Technique
To detect and recognize small-size and submerged complex background targets in infrared images, we combine a dynamic receptive field fusion strategy and a multi-scale feature fusion mechanism to improve the detection performance of small targets significantly. The space-to-depth convolution module i...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Technologies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7080/13/1/40 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587454481170432 |
|---|---|
| author | Yongjun Qi Shaohua Yang Zhengzheng Jia Yuanmeng Song Jie Zhu Xin Liu Hongxing Zheng |
| author_facet | Yongjun Qi Shaohua Yang Zhengzheng Jia Yuanmeng Song Jie Zhu Xin Liu Hongxing Zheng |
| author_sort | Yongjun Qi |
| collection | DOAJ |
| description | To detect and recognize small-size and submerged complex background targets in infrared images, we combine a dynamic receptive field fusion strategy and a multi-scale feature fusion mechanism to improve the detection performance of small targets significantly. The space-to-depth convolution module is introduced as a downsampling layer in the backbone first and achieves the same sampling effect. More detailed information is retained at the same time. Thus, the model’s detection capability for small targets has been enhanced. Then, the pyramid level 2 feature map with minimum receptive field and maximum resolution is added to the neck, which reduces the loss of positional information during feature sampling. Furthermore, x-small detection heads are added, the understanding of the overall characteristics and structure of the target is enhanced much more, and the representation and localization of small targets have been improved. Finally, the cross-entropy loss function in the original network model is replaced by an adaptive threshold focal loss function, forcing the model to allocate more attention to target features. The above methods are based on a public tool, the eighth version of You Only Look Once (YOLO) improved, it is named SPT–YOLO (SPDConv + P2 + Adaptive Threshold + YOLOV8s) in this paper. Some experiments on datasets such as infrared small object detection (IR-SOD) and infrared small target detection 1K(IRSTD-1K), etc. have been executed to verify the proposed algorithm; and the mean average precision of 94.0% and 69% under the condition of threshold at 0.5 and over a range from 0.5 to 0.95 is obtained, respectively. The results show that the proposed method achieves the best performance of infrared small target detection compared to existing methods. |
| format | Article |
| id | doaj-art-c4ebbab0fda045d28aaff73e5bec6ec8 |
| institution | Kabale University |
| issn | 2227-7080 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Technologies |
| spelling | doaj-art-c4ebbab0fda045d28aaff73e5bec6ec82025-01-24T13:50:50ZengMDPI AGTechnologies2227-70802025-01-011314010.3390/technologies13010040An Investigation of Infrared Small Target Detection by Using the SPT–YOLO TechniqueYongjun Qi0Shaohua Yang1Zhengzheng Jia2Yuanmeng Song3Jie Zhu4Xin Liu5Hongxing Zheng6School of Computer Science and Engineering of North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Aeronautics and Astronautics of North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Computer Science and Engineering of North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Computer Science and Engineering of North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Computer Science and Engineering of North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Optoelectronic Engineering, Xidian University, Xi’an 710071, ChinaSchool of Computer Science and Engineering of North China Institute of Aerospace Engineering, Langfang 065000, ChinaTo detect and recognize small-size and submerged complex background targets in infrared images, we combine a dynamic receptive field fusion strategy and a multi-scale feature fusion mechanism to improve the detection performance of small targets significantly. The space-to-depth convolution module is introduced as a downsampling layer in the backbone first and achieves the same sampling effect. More detailed information is retained at the same time. Thus, the model’s detection capability for small targets has been enhanced. Then, the pyramid level 2 feature map with minimum receptive field and maximum resolution is added to the neck, which reduces the loss of positional information during feature sampling. Furthermore, x-small detection heads are added, the understanding of the overall characteristics and structure of the target is enhanced much more, and the representation and localization of small targets have been improved. Finally, the cross-entropy loss function in the original network model is replaced by an adaptive threshold focal loss function, forcing the model to allocate more attention to target features. The above methods are based on a public tool, the eighth version of You Only Look Once (YOLO) improved, it is named SPT–YOLO (SPDConv + P2 + Adaptive Threshold + YOLOV8s) in this paper. Some experiments on datasets such as infrared small object detection (IR-SOD) and infrared small target detection 1K(IRSTD-1K), etc. have been executed to verify the proposed algorithm; and the mean average precision of 94.0% and 69% under the condition of threshold at 0.5 and over a range from 0.5 to 0.95 is obtained, respectively. The results show that the proposed method achieves the best performance of infrared small target detection compared to existing methods.https://www.mdpi.com/2227-7080/13/1/40infrared small target detectiondynamic receptive field fusionmulti-scale feature fusionspace-to-depth convolutionYOLO |
| spellingShingle | Yongjun Qi Shaohua Yang Zhengzheng Jia Yuanmeng Song Jie Zhu Xin Liu Hongxing Zheng An Investigation of Infrared Small Target Detection by Using the SPT–YOLO Technique Technologies infrared small target detection dynamic receptive field fusion multi-scale feature fusion space-to-depth convolution YOLO |
| title | An Investigation of Infrared Small Target Detection by Using the SPT–YOLO Technique |
| title_full | An Investigation of Infrared Small Target Detection by Using the SPT–YOLO Technique |
| title_fullStr | An Investigation of Infrared Small Target Detection by Using the SPT–YOLO Technique |
| title_full_unstemmed | An Investigation of Infrared Small Target Detection by Using the SPT–YOLO Technique |
| title_short | An Investigation of Infrared Small Target Detection by Using the SPT–YOLO Technique |
| title_sort | investigation of infrared small target detection by using the spt yolo technique |
| topic | infrared small target detection dynamic receptive field fusion multi-scale feature fusion space-to-depth convolution YOLO |
| url | https://www.mdpi.com/2227-7080/13/1/40 |
| work_keys_str_mv | AT yongjunqi aninvestigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT shaohuayang aninvestigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT zhengzhengjia aninvestigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT yuanmengsong aninvestigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT jiezhu aninvestigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT xinliu aninvestigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT hongxingzheng aninvestigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT yongjunqi investigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT shaohuayang investigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT zhengzhengjia investigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT yuanmengsong investigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT jiezhu investigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT xinliu investigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique AT hongxingzheng investigationofinfraredsmalltargetdetectionbyusingthesptyolotechnique |