Underwater Object Detection Algorithm Based on Adding Channel and Spatial Fusion Attention Mechanism
Underwater target detection is the foundation and guarantee for the autonomous operation of underwater vehicles and is one of the key technologies in marine exploration. Due to the complex and special underwater environment, the detection effect is poor, and the detection precision is not high. In t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/11/6/1116 |
| _version_ | 1797593980564668416 |
|---|---|
| author | Xingyao Wang Gang Xue Shuting Huang Yanjun Liu |
| author_facet | Xingyao Wang Gang Xue Shuting Huang Yanjun Liu |
| author_sort | Xingyao Wang |
| collection | DOAJ |
| description | Underwater target detection is the foundation and guarantee for the autonomous operation of underwater vehicles and is one of the key technologies in marine exploration. Due to the complex and special underwater environment, the detection effect is poor, and the detection precision is not high. In this paper, YOLOv5 (You Only Look Once v5) is used as the overall structural framework of the target detection algorithm, and improvement is made on the basis of its detection precision in the underwater environment. Specifically, an attention mechanism (Channel and Spatial Fusion Attention, CSFA) that fuses the channel attention and spatial attention is proposed and added to the YOLOv5 network framework, enabling the network to focus on both the prominent features of the detected object and the spatial information of the detected object. The proposed method was tested on the underwater target detection dataset provided by the China Underwater Robot Professional Competition. The experimental detection precision (<i>P</i>) reached 85%, the recall (<i>R</i>) reached 82.2%, and the mean average precision (<i>mAP</i>) reached 87.5%. The effectiveness of the proposed method was verified, and its underwater target detection performance was better than that of ordinary models. |
| first_indexed | 2024-03-11T02:17:10Z |
| format | Article |
| id | doaj.art-3854827806c547afbba69195206050fd |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-11T02:17:10Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-3854827806c547afbba69195206050fd2023-11-18T11:06:07ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-05-01116111610.3390/jmse11061116Underwater Object Detection Algorithm Based on Adding Channel and Spatial Fusion Attention MechanismXingyao Wang0Gang Xue1Shuting Huang2Yanjun Liu3Institute of Marine Science and Technology, Shandong University, Qingdao 266237, ChinaInstitute of Marine Science and Technology, Shandong University, Qingdao 266237, ChinaInstitute of Marine Science and Technology, Shandong University, Qingdao 266237, ChinaInstitute of Marine Science and Technology, Shandong University, Qingdao 266237, ChinaUnderwater target detection is the foundation and guarantee for the autonomous operation of underwater vehicles and is one of the key technologies in marine exploration. Due to the complex and special underwater environment, the detection effect is poor, and the detection precision is not high. In this paper, YOLOv5 (You Only Look Once v5) is used as the overall structural framework of the target detection algorithm, and improvement is made on the basis of its detection precision in the underwater environment. Specifically, an attention mechanism (Channel and Spatial Fusion Attention, CSFA) that fuses the channel attention and spatial attention is proposed and added to the YOLOv5 network framework, enabling the network to focus on both the prominent features of the detected object and the spatial information of the detected object. The proposed method was tested on the underwater target detection dataset provided by the China Underwater Robot Professional Competition. The experimental detection precision (<i>P</i>) reached 85%, the recall (<i>R</i>) reached 82.2%, and the mean average precision (<i>mAP</i>) reached 87.5%. The effectiveness of the proposed method was verified, and its underwater target detection performance was better than that of ordinary models.https://www.mdpi.com/2077-1312/11/6/1116underwater target detectionYOLOv5channel attentionspatial attentionattention mechanism |
| spellingShingle | Xingyao Wang Gang Xue Shuting Huang Yanjun Liu Underwater Object Detection Algorithm Based on Adding Channel and Spatial Fusion Attention Mechanism Journal of Marine Science and Engineering underwater target detection YOLOv5 channel attention spatial attention attention mechanism |
| title | Underwater Object Detection Algorithm Based on Adding Channel and Spatial Fusion Attention Mechanism |
| title_full | Underwater Object Detection Algorithm Based on Adding Channel and Spatial Fusion Attention Mechanism |
| title_fullStr | Underwater Object Detection Algorithm Based on Adding Channel and Spatial Fusion Attention Mechanism |
| title_full_unstemmed | Underwater Object Detection Algorithm Based on Adding Channel and Spatial Fusion Attention Mechanism |
| title_short | Underwater Object Detection Algorithm Based on Adding Channel and Spatial Fusion Attention Mechanism |
| title_sort | underwater object detection algorithm based on adding channel and spatial fusion attention mechanism |
| topic | underwater target detection YOLOv5 channel attention spatial attention attention mechanism |
| url | https://www.mdpi.com/2077-1312/11/6/1116 |
| work_keys_str_mv | AT xingyaowang underwaterobjectdetectionalgorithmbasedonaddingchannelandspatialfusionattentionmechanism AT gangxue underwaterobjectdetectionalgorithmbasedonaddingchannelandspatialfusionattentionmechanism AT shutinghuang underwaterobjectdetectionalgorithmbasedonaddingchannelandspatialfusionattentionmechanism AT yanjunliu underwaterobjectdetectionalgorithmbasedonaddingchannelandspatialfusionattentionmechanism |