Underwater Target Detection Algorithm Based on Improved YOLOv5
Underwater target detection plays an important role in ocean exploration, to which the improvement of relevant technology is of much practical significance. Although existing target detection algorithms have achieved excellent performance on land, they often fail to achieve satisfactory outcome of d...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/10/3/310 |
| _version_ | 1797470354860408832 |
|---|---|
| author | Fei Lei Feifei Tang Shuhan Li |
| author_facet | Fei Lei Feifei Tang Shuhan Li |
| author_sort | Fei Lei |
| collection | DOAJ |
| description | Underwater target detection plays an important role in ocean exploration, to which the improvement of relevant technology is of much practical significance. Although existing target detection algorithms have achieved excellent performance on land, they often fail to achieve satisfactory outcome of detection when in the underwater environment. In this paper, one of the most advanced target detection algorithms, YOLOv5 (You Only Look Once), was first applied in the underwater environment before being improved by combining it with some methods characteristic of the underwater environment. To be specific, the Swin Transformer was treated as the basic backbone network of YOLOv5, which makes the network suitable for those underwater images with blurred targets. It is possible for the network to focus on fusing the relatively important resolution features by improving the method of path aggregation network (PANet) for multi-scale feature fusion. The confidence loss function was improved on the basis of different detection layers, with the network biased to learn high-quality positive anchor boxes and make the network more capable of detecting the target. As suggested by the experimental results, the improved network model is effective in detecting underwater targets, with the mean average precision (mAP) reaching 87.2%, which makes it advantageous over general target detection models and fit for use in the complex underwater environment. |
| first_indexed | 2024-03-09T19:35:23Z |
| format | Article |
| id | doaj.art-3911df70cc354b61ae6aa0eb758891bc |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-09T19:35:23Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-3911df70cc354b61ae6aa0eb758891bc2023-11-24T01:56:20ZengMDPI AGJournal of Marine Science and Engineering2077-13122022-02-0110331010.3390/jmse10030310Underwater Target Detection Algorithm Based on Improved YOLOv5Fei Lei0Feifei Tang1Shuhan Li2Faculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaUnderwater target detection plays an important role in ocean exploration, to which the improvement of relevant technology is of much practical significance. Although existing target detection algorithms have achieved excellent performance on land, they often fail to achieve satisfactory outcome of detection when in the underwater environment. In this paper, one of the most advanced target detection algorithms, YOLOv5 (You Only Look Once), was first applied in the underwater environment before being improved by combining it with some methods characteristic of the underwater environment. To be specific, the Swin Transformer was treated as the basic backbone network of YOLOv5, which makes the network suitable for those underwater images with blurred targets. It is possible for the network to focus on fusing the relatively important resolution features by improving the method of path aggregation network (PANet) for multi-scale feature fusion. The confidence loss function was improved on the basis of different detection layers, with the network biased to learn high-quality positive anchor boxes and make the network more capable of detecting the target. As suggested by the experimental results, the improved network model is effective in detecting underwater targets, with the mean average precision (mAP) reaching 87.2%, which makes it advantageous over general target detection models and fit for use in the complex underwater environment.https://www.mdpi.com/2077-1312/10/3/310deep learningunderwater target detectionYOLOv5swin transformerconfidence loss functionfeature fusion |
| spellingShingle | Fei Lei Feifei Tang Shuhan Li Underwater Target Detection Algorithm Based on Improved YOLOv5 Journal of Marine Science and Engineering deep learning underwater target detection YOLOv5 swin transformer confidence loss function feature fusion |
| title | Underwater Target Detection Algorithm Based on Improved YOLOv5 |
| title_full | Underwater Target Detection Algorithm Based on Improved YOLOv5 |
| title_fullStr | Underwater Target Detection Algorithm Based on Improved YOLOv5 |
| title_full_unstemmed | Underwater Target Detection Algorithm Based on Improved YOLOv5 |
| title_short | Underwater Target Detection Algorithm Based on Improved YOLOv5 |
| title_sort | underwater target detection algorithm based on improved yolov5 |
| topic | deep learning underwater target detection YOLOv5 swin transformer confidence loss function feature fusion |
| url | https://www.mdpi.com/2077-1312/10/3/310 |
| work_keys_str_mv | AT feilei underwatertargetdetectionalgorithmbasedonimprovedyolov5 AT feifeitang underwatertargetdetectionalgorithmbasedonimprovedyolov5 AT shuhanli underwatertargetdetectionalgorithmbasedonimprovedyolov5 |