Lightweight enhanced YOLOv8n underwater object detection network for low light environments
Abstract In response to the challenges of target misidentification, missed detection, and other issues arising from severe light attenuation, low visibility, and complex environments in current underwater target detection, we propose a lightweight low-light underwater target detection network, named...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-79211-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846165221345853440 |
|---|---|
| author | Jifeng Ding Junquan Hu Jiayuan Lin Xiaotong Zhang |
| author_facet | Jifeng Ding Junquan Hu Jiayuan Lin Xiaotong Zhang |
| author_sort | Jifeng Ding |
| collection | DOAJ |
| description | Abstract In response to the challenges of target misidentification, missed detection, and other issues arising from severe light attenuation, low visibility, and complex environments in current underwater target detection, we propose a lightweight low-light underwater target detection network, named PDSC-YOLOv8n. Firstly, we enhance the input images using the improved Pro MSRCR algorithm for data augmentation. Secondly, we replace the traditional convolutions in the backbone and neck networks of YOLOv8n with Ghost and GSConv modules respectively to achieve lightweight network modeling. Additionally, we integrate the improved DCNv3 module into the C2f module of the backbone network to enhance the capability of target feature extraction. Furthermore, we introduce the GAM into the SPPF and incorporate the CBAM attention mechanism into the last layer of the backbone network to enhance the model’s perceptual and generalization capabilities. Finally, we optimize the training process of the model using WIoUv3 as the loss function. The model is successfully deployed on an embedded platform, achieving real-time detection of underwater targets on the embedded platform. We first conduct experiments on the RUOD underwater dataset. Meanwhile, we also utilized the Pascal VOC2012 dataset to evaluate our approach. The mAP@0.5 and mAP@0.5:0.95 of the original YOLOv8n algorithm on RUOD dataset were 79.6% and 58.2%, respectively, and the PDSC -YOLOv8n algorithm mAP@0.5 and mAP@0.5:0.95 can reach 86.1% and 60.8%. The number of parameters of the model is reduced by about 15.5%, the detection accuracy is improved by 6.5%. The original YOLOv8n algorithm was 73% and 53.2% mAP@0.5 and mAP@0.5:0.95 on the Pascal VOC dataset, respectively. The PDSC-YOLOv8n algorithm mAP@0.5 and mAP@0.5:0.95 were 78.5% and 57%, respectively. The superior performance of PDSC-YOLOv8n indicates its effectiveness in the field of underwater target detection. |
| format | Article |
| id | doaj-art-e138211b33a74249827aa81880eb2c90 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-e138211b33a74249827aa81880eb2c902024-11-17T12:29:50ZengNature PortfolioScientific Reports2045-23222024-11-0114112210.1038/s41598-024-79211-7Lightweight enhanced YOLOv8n underwater object detection network for low light environmentsJifeng Ding0Junquan Hu1Jiayuan Lin2Xiaotong Zhang3College of Information and Communication Engineering, Dalian Minzu UniversityCollege of Information and Communication Engineering, Dalian Minzu UniversityCollege of Information and Communication Engineering, Dalian Minzu UniversityCollege of Information and Communication Engineering, Dalian Minzu UniversityAbstract In response to the challenges of target misidentification, missed detection, and other issues arising from severe light attenuation, low visibility, and complex environments in current underwater target detection, we propose a lightweight low-light underwater target detection network, named PDSC-YOLOv8n. Firstly, we enhance the input images using the improved Pro MSRCR algorithm for data augmentation. Secondly, we replace the traditional convolutions in the backbone and neck networks of YOLOv8n with Ghost and GSConv modules respectively to achieve lightweight network modeling. Additionally, we integrate the improved DCNv3 module into the C2f module of the backbone network to enhance the capability of target feature extraction. Furthermore, we introduce the GAM into the SPPF and incorporate the CBAM attention mechanism into the last layer of the backbone network to enhance the model’s perceptual and generalization capabilities. Finally, we optimize the training process of the model using WIoUv3 as the loss function. The model is successfully deployed on an embedded platform, achieving real-time detection of underwater targets on the embedded platform. We first conduct experiments on the RUOD underwater dataset. Meanwhile, we also utilized the Pascal VOC2012 dataset to evaluate our approach. The mAP@0.5 and mAP@0.5:0.95 of the original YOLOv8n algorithm on RUOD dataset were 79.6% and 58.2%, respectively, and the PDSC -YOLOv8n algorithm mAP@0.5 and mAP@0.5:0.95 can reach 86.1% and 60.8%. The number of parameters of the model is reduced by about 15.5%, the detection accuracy is improved by 6.5%. The original YOLOv8n algorithm was 73% and 53.2% mAP@0.5 and mAP@0.5:0.95 on the Pascal VOC dataset, respectively. The PDSC-YOLOv8n algorithm mAP@0.5 and mAP@0.5:0.95 were 78.5% and 57%, respectively. The superior performance of PDSC-YOLOv8n indicates its effectiveness in the field of underwater target detection.https://doi.org/10.1038/s41598-024-79211-7Underwater target detectionLow-lightDeformable convolutionAttention mechanisms |
| spellingShingle | Jifeng Ding Junquan Hu Jiayuan Lin Xiaotong Zhang Lightweight enhanced YOLOv8n underwater object detection network for low light environments Scientific Reports Underwater target detection Low-light Deformable convolution Attention mechanisms |
| title | Lightweight enhanced YOLOv8n underwater object detection network for low light environments |
| title_full | Lightweight enhanced YOLOv8n underwater object detection network for low light environments |
| title_fullStr | Lightweight enhanced YOLOv8n underwater object detection network for low light environments |
| title_full_unstemmed | Lightweight enhanced YOLOv8n underwater object detection network for low light environments |
| title_short | Lightweight enhanced YOLOv8n underwater object detection network for low light environments |
| title_sort | lightweight enhanced yolov8n underwater object detection network for low light environments |
| topic | Underwater target detection Low-light Deformable convolution Attention mechanisms |
| url | https://doi.org/10.1038/s41598-024-79211-7 |
| work_keys_str_mv | AT jifengding lightweightenhancedyolov8nunderwaterobjectdetectionnetworkforlowlightenvironments AT junquanhu lightweightenhancedyolov8nunderwaterobjectdetectionnetworkforlowlightenvironments AT jiayuanlin lightweightenhancedyolov8nunderwaterobjectdetectionnetworkforlowlightenvironments AT xiaotongzhang lightweightenhancedyolov8nunderwaterobjectdetectionnetworkforlowlightenvironments |