A Cross-Stage Focused Small Object Detection Network for Unmanned Aerial Vehicle Assisted Maritime Applications
The application potential of unmanned aerial vehicles (UAVs) in marine search and rescue is especially of concern for the ongoing advancement of visual recognition technology and image processing technology. Limited computing resources, insufficient pixel representation for small objects in high-alt...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/13/1/82 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588187284799488 |
|---|---|
| author | Gege Ding Jiayue Liu Dongsheng Li Xiaming Fu Yucheng Zhou Mingrui Zhang Wantong Li Yanjuan Wang Chunxu Li Xiongfei Geng |
| author_facet | Gege Ding Jiayue Liu Dongsheng Li Xiaming Fu Yucheng Zhou Mingrui Zhang Wantong Li Yanjuan Wang Chunxu Li Xiongfei Geng |
| author_sort | Gege Ding |
| collection | DOAJ |
| description | The application potential of unmanned aerial vehicles (UAVs) in marine search and rescue is especially of concern for the ongoing advancement of visual recognition technology and image processing technology. Limited computing resources, insufficient pixel representation for small objects in high-altitude images, and challenging visibility conditions hinder UAVs’ target recognition performance in maritime search and rescue operations, highlighting the need for further optimization and enhancement. This study introduces an innovative detection framework, CFSD-UAVNet, designed to boost the accuracy of detecting minor objects within imagery captured from elevated altitudes. To improve the performance of the feature pyramid network (FPN) and path aggregation network (PAN), a newly designed PHead structure was proposed, focusing on better leveraging shallow features. Then, structural pruning was applied to refine the model and enhance its capability in detecting small objects. Moreover, to conserve computational resources, a lightweight CED module was introduced to reduce parameters and conserve the computing resources of the UAV. At the same time, in each detection layer, a lightweight CRE module was integrated, leveraging attention mechanisms and detection heads to enhance precision for small object detection. Finally, to enhance the model’s robustness, WIoUv2 loss function was employed, ensuring a balanced treatment of positive and negative samples. The CFSD-UAVNet model was evaluated on the publicly available SeaDronesSee maritime dataset and compared with other cutting-edge algorithms. The experimental results showed that the CFSD-UAVNet model achieved an mAP@50 of 80.1% with only 1.7 M parameters and a computational cost of 10.2 G, marking a 12.1% improvement over YOLOv8 and a 4.6% increase compared to DETR. The novel CFSD-UAVNet model effectively balances the limitations of scenarios and detection accuracy, demonstrating application potential and value in the field of UAV-assisted maritime search and rescue. |
| format | Article |
| id | doaj-art-2c9cf3817b4b4a98ac7c7d2721688e61 |
| institution | Kabale University |
| issn | 2077-1312 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj-art-2c9cf3817b4b4a98ac7c7d2721688e612025-01-24T13:36:47ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-01-011318210.3390/jmse13010082A Cross-Stage Focused Small Object Detection Network for Unmanned Aerial Vehicle Assisted Maritime ApplicationsGege Ding0Jiayue Liu1Dongsheng Li2Xiaming Fu3Yucheng Zhou4Mingrui Zhang5Wantong Li6Yanjuan Wang7Chunxu Li8Xiongfei Geng9Department of Intelligence, China Waterborne Transport Research Institute, Beijing 100088, ChinaCollege of Rail Intelligent Engineering, Dalian Jiaotong University, Dalian 116028, ChinaDepartment of Intelligence, China Waterborne Transport Research Institute, Beijing 100088, ChinaShanghai Rules and Research Institute, China Classification Society, Shanghai 200135, ChinaDepartment of Intelligence, China Waterborne Transport Research Institute, Beijing 100088, ChinaDepartment of Intelligence, China Waterborne Transport Research Institute, Beijing 100088, ChinaDepartment of Intelligence, China Waterborne Transport Research Institute, Beijing 100088, ChinaCollege of Rail Intelligent Engineering, Dalian Jiaotong University, Dalian 116028, ChinaDepartment of Intelligence, China Waterborne Transport Research Institute, Beijing 100088, ChinaDepartment of Intelligence, China Waterborne Transport Research Institute, Beijing 100088, ChinaThe application potential of unmanned aerial vehicles (UAVs) in marine search and rescue is especially of concern for the ongoing advancement of visual recognition technology and image processing technology. Limited computing resources, insufficient pixel representation for small objects in high-altitude images, and challenging visibility conditions hinder UAVs’ target recognition performance in maritime search and rescue operations, highlighting the need for further optimization and enhancement. This study introduces an innovative detection framework, CFSD-UAVNet, designed to boost the accuracy of detecting minor objects within imagery captured from elevated altitudes. To improve the performance of the feature pyramid network (FPN) and path aggregation network (PAN), a newly designed PHead structure was proposed, focusing on better leveraging shallow features. Then, structural pruning was applied to refine the model and enhance its capability in detecting small objects. Moreover, to conserve computational resources, a lightweight CED module was introduced to reduce parameters and conserve the computing resources of the UAV. At the same time, in each detection layer, a lightweight CRE module was integrated, leveraging attention mechanisms and detection heads to enhance precision for small object detection. Finally, to enhance the model’s robustness, WIoUv2 loss function was employed, ensuring a balanced treatment of positive and negative samples. The CFSD-UAVNet model was evaluated on the publicly available SeaDronesSee maritime dataset and compared with other cutting-edge algorithms. The experimental results showed that the CFSD-UAVNet model achieved an mAP@50 of 80.1% with only 1.7 M parameters and a computational cost of 10.2 G, marking a 12.1% improvement over YOLOv8 and a 4.6% increase compared to DETR. The novel CFSD-UAVNet model effectively balances the limitations of scenarios and detection accuracy, demonstrating application potential and value in the field of UAV-assisted maritime search and rescue.https://www.mdpi.com/2077-1312/13/1/82UAVfeature pyramidattention mechanismsmall object detectionmarine search and rescue |
| spellingShingle | Gege Ding Jiayue Liu Dongsheng Li Xiaming Fu Yucheng Zhou Mingrui Zhang Wantong Li Yanjuan Wang Chunxu Li Xiongfei Geng A Cross-Stage Focused Small Object Detection Network for Unmanned Aerial Vehicle Assisted Maritime Applications Journal of Marine Science and Engineering UAV feature pyramid attention mechanism small object detection marine search and rescue |
| title | A Cross-Stage Focused Small Object Detection Network for Unmanned Aerial Vehicle Assisted Maritime Applications |
| title_full | A Cross-Stage Focused Small Object Detection Network for Unmanned Aerial Vehicle Assisted Maritime Applications |
| title_fullStr | A Cross-Stage Focused Small Object Detection Network for Unmanned Aerial Vehicle Assisted Maritime Applications |
| title_full_unstemmed | A Cross-Stage Focused Small Object Detection Network for Unmanned Aerial Vehicle Assisted Maritime Applications |
| title_short | A Cross-Stage Focused Small Object Detection Network for Unmanned Aerial Vehicle Assisted Maritime Applications |
| title_sort | cross stage focused small object detection network for unmanned aerial vehicle assisted maritime applications |
| topic | UAV feature pyramid attention mechanism small object detection marine search and rescue |
| url | https://www.mdpi.com/2077-1312/13/1/82 |
| work_keys_str_mv | AT gegeding acrossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT jiayueliu acrossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT dongshengli acrossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT xiamingfu acrossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT yuchengzhou acrossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT mingruizhang acrossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT wantongli acrossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT yanjuanwang acrossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT chunxuli acrossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT xiongfeigeng acrossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT gegeding crossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT jiayueliu crossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT dongshengli crossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT xiamingfu crossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT yuchengzhou crossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT mingruizhang crossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT wantongli crossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT yanjuanwang crossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT chunxuli crossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications AT xiongfeigeng crossstagefocusedsmallobjectdetectionnetworkforunmannedaerialvehicleassistedmaritimeapplications |