SAR Ship Detection in Complex Scenes Based on Adaptive Anchor Assignment and IOU Supervise
This study aims to address the unreasonable assignment of positive and negative samples and poor localization quality in ship detection in complex scenes. Therefore, in this study, a Synthetic Aperture Radar (SAR) ship detection network (A3-IOUS-Net) based on adaptive anchor assignment and Intersect...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
China Science Publishing & Media Ltd. (CSPM)
2023-10-01
|
| Series: | Leida xuebao |
| Subjects: | |
| Online Access: | https://radars.ac.cn/cn/article/doi/10.12000/JR23059 |
| _version_ | 1827763017176055808 |
|---|---|
| author | Xiaowo XU Xiaoling ZHANG Tianwen ZHANG Zikang SHAO Yanqin XU Tianjiao ZENG |
| author_facet | Xiaowo XU Xiaoling ZHANG Tianwen ZHANG Zikang SHAO Yanqin XU Tianjiao ZENG |
| author_sort | Xiaowo XU |
| collection | DOAJ |
| description | This study aims to address the unreasonable assignment of positive and negative samples and poor localization quality in ship detection in complex scenes. Therefore, in this study, a Synthetic Aperture Radar (SAR) ship detection network (A3-IOUS-Net) based on adaptive anchor assignment and Intersection over Union (IOU) supervise in complex scenes is proposed. First, an adaptive anchor assignment mechanism is proposed, where a probability distribution model is established to adaptively assign anchors as positive and negative samples to enhance the ship samples’ learning ability in complex scenes. Then, an IOU supervise mechanism is proposed, which adds an IOU prediction branch in the prediction head to supervise the localization quality of detection boxes, allowing the network to accurately locate the SAR ship targets in complex scenes. Furthermore, a coordinate attention module is introduced into the prediction branch to suppress the background clutter interference and improve the SAR ship detection accuracy. The experimental results on the open SAR Ship Detection Dataset (SSDD) show that the Average Precision (AP) of A3-IOUS-Net in complex scenes is 82.04%, superior to the other 15 comparison models. |
| first_indexed | 2024-03-11T10:45:13Z |
| format | Article |
| id | doaj.art-a68283afcf49493fa9ab15e919f66c48 |
| institution | Directory Open Access Journal |
| issn | 2095-283X |
| language | English |
| last_indexed | 2024-03-11T10:45:13Z |
| publishDate | 2023-10-01 |
| publisher | China Science Publishing & Media Ltd. (CSPM) |
| record_format | Article |
| series | Leida xuebao |
| spelling | doaj.art-a68283afcf49493fa9ab15e919f66c482023-11-14T06:01:21ZengChina Science Publishing & Media Ltd. (CSPM)Leida xuebao2095-283X2023-10-011251097111110.12000/JR23059R23059SAR Ship Detection in Complex Scenes Based on Adaptive Anchor Assignment and IOU SuperviseXiaowo XU0Xiaoling ZHANG1Tianwen ZHANG2Zikang SHAO3Yanqin XU4Tianjiao ZENG5School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu 611731, ChinaThis study aims to address the unreasonable assignment of positive and negative samples and poor localization quality in ship detection in complex scenes. Therefore, in this study, a Synthetic Aperture Radar (SAR) ship detection network (A3-IOUS-Net) based on adaptive anchor assignment and Intersection over Union (IOU) supervise in complex scenes is proposed. First, an adaptive anchor assignment mechanism is proposed, where a probability distribution model is established to adaptively assign anchors as positive and negative samples to enhance the ship samples’ learning ability in complex scenes. Then, an IOU supervise mechanism is proposed, which adds an IOU prediction branch in the prediction head to supervise the localization quality of detection boxes, allowing the network to accurately locate the SAR ship targets in complex scenes. Furthermore, a coordinate attention module is introduced into the prediction branch to suppress the background clutter interference and improve the SAR ship detection accuracy. The experimental results on the open SAR Ship Detection Dataset (SSDD) show that the Average Precision (AP) of A3-IOUS-Net in complex scenes is 82.04%, superior to the other 15 comparison models.https://radars.ac.cn/cn/article/doi/10.12000/JR23059synthetic aperture radar (sar)ship detectioncomplex scenesadaptive anchor assignment (a3)iou supervise (ious) |
| spellingShingle | Xiaowo XU Xiaoling ZHANG Tianwen ZHANG Zikang SHAO Yanqin XU Tianjiao ZENG SAR Ship Detection in Complex Scenes Based on Adaptive Anchor Assignment and IOU Supervise Leida xuebao synthetic aperture radar (sar) ship detection complex scenes adaptive anchor assignment (a3) iou supervise (ious) |
| title | SAR Ship Detection in Complex Scenes Based on Adaptive Anchor Assignment and IOU Supervise |
| title_full | SAR Ship Detection in Complex Scenes Based on Adaptive Anchor Assignment and IOU Supervise |
| title_fullStr | SAR Ship Detection in Complex Scenes Based on Adaptive Anchor Assignment and IOU Supervise |
| title_full_unstemmed | SAR Ship Detection in Complex Scenes Based on Adaptive Anchor Assignment and IOU Supervise |
| title_short | SAR Ship Detection in Complex Scenes Based on Adaptive Anchor Assignment and IOU Supervise |
| title_sort | sar ship detection in complex scenes based on adaptive anchor assignment and iou supervise |
| topic | synthetic aperture radar (sar) ship detection complex scenes adaptive anchor assignment (a3) iou supervise (ious) |
| url | https://radars.ac.cn/cn/article/doi/10.12000/JR23059 |
| work_keys_str_mv | AT xiaowoxu sarshipdetectionincomplexscenesbasedonadaptiveanchorassignmentandiousupervise AT xiaolingzhang sarshipdetectionincomplexscenesbasedonadaptiveanchorassignmentandiousupervise AT tianwenzhang sarshipdetectionincomplexscenesbasedonadaptiveanchorassignmentandiousupervise AT zikangshao sarshipdetectionincomplexscenesbasedonadaptiveanchorassignmentandiousupervise AT yanqinxu sarshipdetectionincomplexscenesbasedonadaptiveanchorassignmentandiousupervise AT tianjiaozeng sarshipdetectionincomplexscenesbasedonadaptiveanchorassignmentandiousupervise |