Two-Level Supervised Network for Small Ship Target Detection in Shallow Thin Cloud-Covered Optical Satellite Images
Ship detection under cloudy and foggy conditions is a significant challenge in remote sensing satellite applications, as cloud cover often reduces contrast between targets and backgrounds. Additionally, ships are small and affected by noise, making them difficult to detect. This paper proposes a Clo...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/24/11558 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850240005349310464 |
|---|---|
| author | Fangjian Liu Fengyi Zhang Mi Wang Qizhi Xu |
| author_facet | Fangjian Liu Fengyi Zhang Mi Wang Qizhi Xu |
| author_sort | Fangjian Liu |
| collection | DOAJ |
| description | Ship detection under cloudy and foggy conditions is a significant challenge in remote sensing satellite applications, as cloud cover often reduces contrast between targets and backgrounds. Additionally, ships are small and affected by noise, making them difficult to detect. This paper proposes a Cloud Removal and Target Detection (CRTD) network to detect small ships in images with thin cloud cover. The process begins with a Thin Cloud Removal (TCR) module for image preprocessing. The preprocessed data are then fed into a Small Target Detection (STD) module. To improve target–background contrast, we introduce a Target Enhancement module. The TCR and STD modules are integrated through a dual-stage supervision network, which hierarchically processes the detection task to enhance data quality, minimizing the impact of thin clouds. Experiments on the GaoFen-4 satellite dataset show that the proposed method outperforms existing detectors, achieving an average precision (AP) of 88.9%. |
| format | Article |
| id | doaj-art-53a8d4b50c81419282b05aeabef5f1d8 |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-53a8d4b50c81419282b05aeabef5f1d82025-08-20T02:00:59ZengMDPI AGApplied Sciences2076-34172024-12-0114241155810.3390/app142411558Two-Level Supervised Network for Small Ship Target Detection in Shallow Thin Cloud-Covered Optical Satellite ImagesFangjian Liu0Fengyi Zhang1Mi Wang2Qizhi Xu3State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan 430079, China Beijing Institute of Technology, School of Mechatronical Engineering, Beijing 100081, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan 430079, China Beijing Institute of Technology, School of Mechatronical Engineering, Beijing 100081, ChinaShip detection under cloudy and foggy conditions is a significant challenge in remote sensing satellite applications, as cloud cover often reduces contrast between targets and backgrounds. Additionally, ships are small and affected by noise, making them difficult to detect. This paper proposes a Cloud Removal and Target Detection (CRTD) network to detect small ships in images with thin cloud cover. The process begins with a Thin Cloud Removal (TCR) module for image preprocessing. The preprocessed data are then fed into a Small Target Detection (STD) module. To improve target–background contrast, we introduce a Target Enhancement module. The TCR and STD modules are integrated through a dual-stage supervision network, which hierarchically processes the detection task to enhance data quality, minimizing the impact of thin clouds. Experiments on the GaoFen-4 satellite dataset show that the proposed method outperforms existing detectors, achieving an average precision (AP) of 88.9%.https://www.mdpi.com/2076-3417/14/24/11558ship detectioncloud removaldouble-layer supervised networkobject detectionoptical satellite images |
| spellingShingle | Fangjian Liu Fengyi Zhang Mi Wang Qizhi Xu Two-Level Supervised Network for Small Ship Target Detection in Shallow Thin Cloud-Covered Optical Satellite Images Applied Sciences ship detection cloud removal double-layer supervised network object detection optical satellite images |
| title | Two-Level Supervised Network for Small Ship Target Detection in Shallow Thin Cloud-Covered Optical Satellite Images |
| title_full | Two-Level Supervised Network for Small Ship Target Detection in Shallow Thin Cloud-Covered Optical Satellite Images |
| title_fullStr | Two-Level Supervised Network for Small Ship Target Detection in Shallow Thin Cloud-Covered Optical Satellite Images |
| title_full_unstemmed | Two-Level Supervised Network for Small Ship Target Detection in Shallow Thin Cloud-Covered Optical Satellite Images |
| title_short | Two-Level Supervised Network for Small Ship Target Detection in Shallow Thin Cloud-Covered Optical Satellite Images |
| title_sort | two level supervised network for small ship target detection in shallow thin cloud covered optical satellite images |
| topic | ship detection cloud removal double-layer supervised network object detection optical satellite images |
| url | https://www.mdpi.com/2076-3417/14/24/11558 |
| work_keys_str_mv | AT fangjianliu twolevelsupervisednetworkforsmallshiptargetdetectioninshallowthincloudcoveredopticalsatelliteimages AT fengyizhang twolevelsupervisednetworkforsmallshiptargetdetectioninshallowthincloudcoveredopticalsatelliteimages AT miwang twolevelsupervisednetworkforsmallshiptargetdetectioninshallowthincloudcoveredopticalsatelliteimages AT qizhixu twolevelsupervisednetworkforsmallshiptargetdetectioninshallowthincloudcoveredopticalsatelliteimages |