A Lightweight Model for Real-Time Monitoring of Ships
Real-time monitoring of ships is crucial for inland navigation management. Under complex conditions, it is difficult to balance accuracy, real-time performance, and practicality in ship detection and tracking. We propose a lightweight model, YOLOv8-FAS, to address this issue for real-time ship detec...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/18/3804 |
| _version_ | 1797580437791440896 |
|---|---|
| author | Bowen Xing Wei Wang Jingyi Qian Chengwu Pan Qibo Le |
| author_facet | Bowen Xing Wei Wang Jingyi Qian Chengwu Pan Qibo Le |
| author_sort | Bowen Xing |
| collection | DOAJ |
| description | Real-time monitoring of ships is crucial for inland navigation management. Under complex conditions, it is difficult to balance accuracy, real-time performance, and practicality in ship detection and tracking. We propose a lightweight model, YOLOv8-FAS, to address this issue for real-time ship detection and tracking. First, FasterNet and the attention mechanism are integrated and introduced to achieve feature extraction simply and efficiently. Second, the lightweight GSConv convolution method and a one-shot aggregation module are introduced to construct an efficient network neck to enhance feature extraction and fusion. Furthermore, the loss function is improved based on ship characteristics to make the model more suitable for ship datasets. Finally, the advanced Bytetrack tracke is added to achieve the real-time detection and tracking of ship targets. Compared to the YOLOv8 model, YOLOv8-FAS reduces computational complexity by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.8</mn><mo>×</mo><msup><mn>10</mn><mn>9</mn></msup></mrow></semantics></math></inline-formula> terms of FLOPs and reduces model parameters by 20%, resulting in only <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.4</mn><mo>×</mo><msup><mn>10</mn><mn>6</mn></msup></mrow></semantics></math></inline-formula> parameters. The mAP-0.5 is improved by 0.9%, reaching 98.50%, and the real-time object tracking precision of the model surpasses 88%. The YOLOv8-FAS model combines light weight with high precision, and can accurately perform ship detection and tracking tasks in real time. Moreover, it is suitable for deployment on hardware resource-limited devices such as unmanned surface ships. |
| first_indexed | 2024-03-10T22:50:56Z |
| format | Article |
| id | doaj.art-260df35441374fa3b22b82c805599ffd |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T22:50:56Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-260df35441374fa3b22b82c805599ffd2023-11-19T10:21:34ZengMDPI AGElectronics2079-92922023-09-011218380410.3390/electronics12183804A Lightweight Model for Real-Time Monitoring of ShipsBowen Xing0Wei Wang1Jingyi Qian2Chengwu Pan3Qibo Le4College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, ChinaCollege of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, ChinaCollege of Electronic and Information Engineering, Tongji University, Shanghai 201804, ChinaNingbo Communication Center, Ningbo 315800, ChinaNingbo Communication Center, Ningbo 315800, ChinaReal-time monitoring of ships is crucial for inland navigation management. Under complex conditions, it is difficult to balance accuracy, real-time performance, and practicality in ship detection and tracking. We propose a lightweight model, YOLOv8-FAS, to address this issue for real-time ship detection and tracking. First, FasterNet and the attention mechanism are integrated and introduced to achieve feature extraction simply and efficiently. Second, the lightweight GSConv convolution method and a one-shot aggregation module are introduced to construct an efficient network neck to enhance feature extraction and fusion. Furthermore, the loss function is improved based on ship characteristics to make the model more suitable for ship datasets. Finally, the advanced Bytetrack tracke is added to achieve the real-time detection and tracking of ship targets. Compared to the YOLOv8 model, YOLOv8-FAS reduces computational complexity by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.8</mn><mo>×</mo><msup><mn>10</mn><mn>9</mn></msup></mrow></semantics></math></inline-formula> terms of FLOPs and reduces model parameters by 20%, resulting in only <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.4</mn><mo>×</mo><msup><mn>10</mn><mn>6</mn></msup></mrow></semantics></math></inline-formula> parameters. The mAP-0.5 is improved by 0.9%, reaching 98.50%, and the real-time object tracking precision of the model surpasses 88%. The YOLOv8-FAS model combines light weight with high precision, and can accurately perform ship detection and tracking tasks in real time. Moreover, it is suitable for deployment on hardware resource-limited devices such as unmanned surface ships.https://www.mdpi.com/2079-9292/12/18/3804ship monitoringdeep learninglightweight modelreal-time trackingYOLOv8 |
| spellingShingle | Bowen Xing Wei Wang Jingyi Qian Chengwu Pan Qibo Le A Lightweight Model for Real-Time Monitoring of Ships Electronics ship monitoring deep learning lightweight model real-time tracking YOLOv8 |
| title | A Lightweight Model for Real-Time Monitoring of Ships |
| title_full | A Lightweight Model for Real-Time Monitoring of Ships |
| title_fullStr | A Lightweight Model for Real-Time Monitoring of Ships |
| title_full_unstemmed | A Lightweight Model for Real-Time Monitoring of Ships |
| title_short | A Lightweight Model for Real-Time Monitoring of Ships |
| title_sort | lightweight model for real time monitoring of ships |
| topic | ship monitoring deep learning lightweight model real-time tracking YOLOv8 |
| url | https://www.mdpi.com/2079-9292/12/18/3804 |
| work_keys_str_mv | AT bowenxing alightweightmodelforrealtimemonitoringofships AT weiwang alightweightmodelforrealtimemonitoringofships AT jingyiqian alightweightmodelforrealtimemonitoringofships AT chengwupan alightweightmodelforrealtimemonitoringofships AT qibole alightweightmodelforrealtimemonitoringofships AT bowenxing lightweightmodelforrealtimemonitoringofships AT weiwang lightweightmodelforrealtimemonitoringofships AT jingyiqian lightweightmodelforrealtimemonitoringofships AT chengwupan lightweightmodelforrealtimemonitoringofships AT qibole lightweightmodelforrealtimemonitoringofships |