A Ship’s Maritime Critical Target Identification Method Based on Lightweight and Triple Attention Mechanisms
The ability to classify and recognize maritime targets based on visual images plays an important role in advancing ship intelligence and digitalization. The current target recognition algorithms for common maritime targets, such as buoys, reefs, other ships, and bridges of different colors, face cha...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/12/10/1839 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850206150920765440 |
|---|---|
| author | Pu Wang Shenhua Yang Guoquan Chen Weijun Wang Zeyang Huang Yuanliang Jiang |
| author_facet | Pu Wang Shenhua Yang Guoquan Chen Weijun Wang Zeyang Huang Yuanliang Jiang |
| author_sort | Pu Wang |
| collection | DOAJ |
| description | The ability to classify and recognize maritime targets based on visual images plays an important role in advancing ship intelligence and digitalization. The current target recognition algorithms for common maritime targets, such as buoys, reefs, other ships, and bridges of different colors, face challenges such as incomplete classification, low recognition accuracy, and a large number of model parameters. To address these issues, this paper proposes a novel maritime target recognition method called DTI-YOLO (DualConv Triple Attention InnerEIOU-You Only Look Once). This method is based on a triple attention mechanism designed to enhance the model’s ability to classify and recognize buoys of different colors in the channel while also making the feature extraction network more lightweight. First, the lightweight double convolution kernel feature extraction layer is constructed using group convolution technology to replace the Conv structure of YOLOv9 (You Only Look Once Version 9), effectively reducing the number of parameters in the original model. Second, an improved three-branch structure is designed to capture cross-dimensional interactions of input image features. This structure forms a triple attention mechanism that accounts for the mutual dependencies between input channels and spatial positions, allowing for the calculation of attention weights for targets such as bridges, buoys, and other ships. Finally, InnerEIoU is used to replace CIoU to improve the loss function, thereby optimizing loss regression for targets with large scale differences. To verify the effectiveness of these algorithmic improvements, the DTI-YOLO algorithm was tested on a self-made dataset of 2300 ship navigation images. The experimental results show that the average accuracy of this method in identifying seven types of targets—including buoys, bridges, islands and reefs, container ships, bulk carriers, passenger ships, and other ships—reached 92.1%, with a 12% reduction in the number of parameters. This enhancement improves the model’s ability to recognize and distinguish different targets and buoy colors. |
| format | Article |
| id | doaj-art-7ab13da4f4da44bda3045a81808c07a6 |
| institution | OA Journals |
| issn | 2077-1312 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj-art-7ab13da4f4da44bda3045a81808c07a62025-08-20T02:10:54ZengMDPI AGJournal of Marine Science and Engineering2077-13122024-10-011210183910.3390/jmse12101839A Ship’s Maritime Critical Target Identification Method Based on Lightweight and Triple Attention MechanismsPu Wang0Shenhua Yang1Guoquan Chen2Weijun Wang3Zeyang Huang4Yuanliang Jiang5Navigation College, Jimei University, Xiamen 361021, ChinaNavigation College, Jimei University, Xiamen 361021, ChinaNavigation College, Jimei University, Xiamen 361021, ChinaNavigation College, Jimei University, Xiamen 361021, ChinaNavigation College, Jimei University, Xiamen 361021, ChinaNavigation College, Jimei University, Xiamen 361021, ChinaThe ability to classify and recognize maritime targets based on visual images plays an important role in advancing ship intelligence and digitalization. The current target recognition algorithms for common maritime targets, such as buoys, reefs, other ships, and bridges of different colors, face challenges such as incomplete classification, low recognition accuracy, and a large number of model parameters. To address these issues, this paper proposes a novel maritime target recognition method called DTI-YOLO (DualConv Triple Attention InnerEIOU-You Only Look Once). This method is based on a triple attention mechanism designed to enhance the model’s ability to classify and recognize buoys of different colors in the channel while also making the feature extraction network more lightweight. First, the lightweight double convolution kernel feature extraction layer is constructed using group convolution technology to replace the Conv structure of YOLOv9 (You Only Look Once Version 9), effectively reducing the number of parameters in the original model. Second, an improved three-branch structure is designed to capture cross-dimensional interactions of input image features. This structure forms a triple attention mechanism that accounts for the mutual dependencies between input channels and spatial positions, allowing for the calculation of attention weights for targets such as bridges, buoys, and other ships. Finally, InnerEIoU is used to replace CIoU to improve the loss function, thereby optimizing loss regression for targets with large scale differences. To verify the effectiveness of these algorithmic improvements, the DTI-YOLO algorithm was tested on a self-made dataset of 2300 ship navigation images. The experimental results show that the average accuracy of this method in identifying seven types of targets—including buoys, bridges, islands and reefs, container ships, bulk carriers, passenger ships, and other ships—reached 92.1%, with a 12% reduction in the number of parameters. This enhancement improves the model’s ability to recognize and distinguish different targets and buoy colors.https://www.mdpi.com/2077-1312/12/10/1839ship targetimproved YOLOv9triple attention mechanismlightweighting |
| spellingShingle | Pu Wang Shenhua Yang Guoquan Chen Weijun Wang Zeyang Huang Yuanliang Jiang A Ship’s Maritime Critical Target Identification Method Based on Lightweight and Triple Attention Mechanisms Journal of Marine Science and Engineering ship target improved YOLOv9 triple attention mechanism lightweighting |
| title | A Ship’s Maritime Critical Target Identification Method Based on Lightweight and Triple Attention Mechanisms |
| title_full | A Ship’s Maritime Critical Target Identification Method Based on Lightweight and Triple Attention Mechanisms |
| title_fullStr | A Ship’s Maritime Critical Target Identification Method Based on Lightweight and Triple Attention Mechanisms |
| title_full_unstemmed | A Ship’s Maritime Critical Target Identification Method Based on Lightweight and Triple Attention Mechanisms |
| title_short | A Ship’s Maritime Critical Target Identification Method Based on Lightweight and Triple Attention Mechanisms |
| title_sort | ship s maritime critical target identification method based on lightweight and triple attention mechanisms |
| topic | ship target improved YOLOv9 triple attention mechanism lightweighting |
| url | https://www.mdpi.com/2077-1312/12/10/1839 |
| work_keys_str_mv | AT puwang ashipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms AT shenhuayang ashipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms AT guoquanchen ashipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms AT weijunwang ashipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms AT zeyanghuang ashipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms AT yuanliangjiang ashipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms AT puwang shipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms AT shenhuayang shipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms AT guoquanchen shipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms AT weijunwang shipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms AT zeyanghuang shipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms AT yuanliangjiang shipsmaritimecriticaltargetidentificationmethodbasedonlightweightandtripleattentionmechanisms |