DEPDet: A Cross-Spatial Multiscale Lightweight Network for Ship Detection of SAR Images in Complex Scenes
Nowadays, the intricate nature of synthetic aperture radar (SAR) ship scenes, coupled with the presence of multiscale targets, poses a significant challenge in detection accuracy. Furthermore, to reduce the financial outlay on hardware, there is also a considerable challenge in lightweighting the mo...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10695810/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536214100869120 |
|---|---|
| author | Jing Zhang Fan Deng Yonghua Wang Jie Gong Ziyang Liu Wenjun Liu Yinmei Zeng Zeqiang Chen |
| author_facet | Jing Zhang Fan Deng Yonghua Wang Jie Gong Ziyang Liu Wenjun Liu Yinmei Zeng Zeqiang Chen |
| author_sort | Jing Zhang |
| collection | DOAJ |
| description | Nowadays, the intricate nature of synthetic aperture radar (SAR) ship scenes, coupled with the presence of multiscale targets, poses a significant challenge in detection accuracy. Furthermore, to reduce the financial outlay on hardware, there is also a considerable challenge in lightweighting the model. In order to resolve the aforementioned concerns, we propose a cross-spatial multiscale lightweight network, designated as DEPDet. First, a new efficient multiscale detection backbone network DEMNet is redesigned. To improve the feature extraction capability of the network, a cross-spatial multiscale convolution (CSMSConv) is designed and a new CSMSConv module CSMSC2F is constructed. Meanwhile, we introduce an efficient multiscale attention module. DEMNet is capable of more effectively extracting information pertaining to multiscale ships. Moreover, to enhance the fusion of features at diverse scales, we design a new path aggregation feature pyramid network DEPAFPN, which combines deformable convolution and CSMSC2F. Finally, we introduce partial convolution to construct a lightweight detection head module PCHead, which can be employed to extract spatial features with greater efficiency. The publicly available SAR ship datasets, SAR Ship Detection Dataset and High-Resolution SAR Image Dataset, are employed for the purpose of conducting experiments. The mean average precision (mAP) obtained was 98.2% (+1.4%) and 91.6% (+1.6%), respectively. The F1 obtained 0.950 (+1.7%) and 0.871 (+1.4%), respectively. Concurrently, the Params decreased from 3.2M to 2.1M, a decrease of approximately 34%. The floating-point operations (FLOPs) decreased from 8.7G to 4.5G, a decrease of approximately 48%. The experimental results indicate that the network achieves an effective balance between detection accuracy and lightweight effect with good generalization and extensibility. |
| format | Article |
| id | doaj-art-e9ab120ad48d49e3b3a76c88bef789ff |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-e9ab120ad48d49e3b3a76c88bef789ff2025-01-15T00:00:55ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-0117181821819810.1109/JSTARS.2024.346920910695810DEPDet: A Cross-Spatial Multiscale Lightweight Network for Ship Detection of SAR Images in Complex ScenesJing Zhang0https://orcid.org/0009-0003-3882-3539Fan Deng1https://orcid.org/0000-0003-2323-2077Yonghua Wang2Jie Gong3Ziyang Liu4Wenjun Liu5Yinmei Zeng6Zeqiang Chen7https://orcid.org/0000-0001-6624-6693School of Geosciences, Yangtze University, Wuhan, ChinaSchool of Geosciences, Yangtze University, Wuhan, ChinaWuhan Huaxin Lianchuang Technology Engineering, Company Ltd., Wuhan, ChinaWuhan Huaxin Lianchuang Technology Engineering, Company Ltd., Wuhan, ChinaSchool of Geosciences, Yangtze University, Wuhan, ChinaSchool of Geosciences, Yangtze University, Wuhan, ChinaSchool of Geosciences, Yangtze University, Wuhan, ChinaNational Engineering Research Center of Geographic Information System, China University of Geosciences, Wuhan, ChinaNowadays, the intricate nature of synthetic aperture radar (SAR) ship scenes, coupled with the presence of multiscale targets, poses a significant challenge in detection accuracy. Furthermore, to reduce the financial outlay on hardware, there is also a considerable challenge in lightweighting the model. In order to resolve the aforementioned concerns, we propose a cross-spatial multiscale lightweight network, designated as DEPDet. First, a new efficient multiscale detection backbone network DEMNet is redesigned. To improve the feature extraction capability of the network, a cross-spatial multiscale convolution (CSMSConv) is designed and a new CSMSConv module CSMSC2F is constructed. Meanwhile, we introduce an efficient multiscale attention module. DEMNet is capable of more effectively extracting information pertaining to multiscale ships. Moreover, to enhance the fusion of features at diverse scales, we design a new path aggregation feature pyramid network DEPAFPN, which combines deformable convolution and CSMSC2F. Finally, we introduce partial convolution to construct a lightweight detection head module PCHead, which can be employed to extract spatial features with greater efficiency. The publicly available SAR ship datasets, SAR Ship Detection Dataset and High-Resolution SAR Image Dataset, are employed for the purpose of conducting experiments. The mean average precision (mAP) obtained was 98.2% (+1.4%) and 91.6% (+1.6%), respectively. The F1 obtained 0.950 (+1.7%) and 0.871 (+1.4%), respectively. Concurrently, the Params decreased from 3.2M to 2.1M, a decrease of approximately 34%. The floating-point operations (FLOPs) decreased from 8.7G to 4.5G, a decrease of approximately 48%. The experimental results indicate that the network achieves an effective balance between detection accuracy and lightweight effect with good generalization and extensibility.https://ieeexplore.ieee.org/document/10695810/Complex scenescross-spatial multiscale convolution (CSMSConv)lightweight networkmultiscale shipssynthetic aperture radar (SAR) |
| spellingShingle | Jing Zhang Fan Deng Yonghua Wang Jie Gong Ziyang Liu Wenjun Liu Yinmei Zeng Zeqiang Chen DEPDet: A Cross-Spatial Multiscale Lightweight Network for Ship Detection of SAR Images in Complex Scenes IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Complex scenes cross-spatial multiscale convolution (CSMSConv) lightweight network multiscale ships synthetic aperture radar (SAR) |
| title | DEPDet: A Cross-Spatial Multiscale Lightweight Network for Ship Detection of SAR Images in Complex Scenes |
| title_full | DEPDet: A Cross-Spatial Multiscale Lightweight Network for Ship Detection of SAR Images in Complex Scenes |
| title_fullStr | DEPDet: A Cross-Spatial Multiscale Lightweight Network for Ship Detection of SAR Images in Complex Scenes |
| title_full_unstemmed | DEPDet: A Cross-Spatial Multiscale Lightweight Network for Ship Detection of SAR Images in Complex Scenes |
| title_short | DEPDet: A Cross-Spatial Multiscale Lightweight Network for Ship Detection of SAR Images in Complex Scenes |
| title_sort | depdet a cross spatial multiscale lightweight network for ship detection of sar images in complex scenes |
| topic | Complex scenes cross-spatial multiscale convolution (CSMSConv) lightweight network multiscale ships synthetic aperture radar (SAR) |
| url | https://ieeexplore.ieee.org/document/10695810/ |
| work_keys_str_mv | AT jingzhang depdetacrossspatialmultiscalelightweightnetworkforshipdetectionofsarimagesincomplexscenes AT fandeng depdetacrossspatialmultiscalelightweightnetworkforshipdetectionofsarimagesincomplexscenes AT yonghuawang depdetacrossspatialmultiscalelightweightnetworkforshipdetectionofsarimagesincomplexscenes AT jiegong depdetacrossspatialmultiscalelightweightnetworkforshipdetectionofsarimagesincomplexscenes AT ziyangliu depdetacrossspatialmultiscalelightweightnetworkforshipdetectionofsarimagesincomplexscenes AT wenjunliu depdetacrossspatialmultiscalelightweightnetworkforshipdetectionofsarimagesincomplexscenes AT yinmeizeng depdetacrossspatialmultiscalelightweightnetworkforshipdetectionofsarimagesincomplexscenes AT zeqiangchen depdetacrossspatialmultiscalelightweightnetworkforshipdetectionofsarimagesincomplexscenes |