Quantitative detection algorithm for deep-sea megabenthic organisms based on improved YOLOv5
Detecting deep-sea megabenthic organisms is of foremost importance for seabed resource surveys, typical habitat protection, and biodiversity surveys. However, the complexity of the deep-sea environment, uneven illumination, and small biological targets that are easily obscured all increase target de...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-02-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2024.1301024/full |
| _version_ | 1827340768010829824 |
|---|---|
| author | Wei Wang Wei Wang Yong Fu Sun Wei Gao WeiKun Xu YiXin Zhang YiXin Zhang DeXiang Huang DeXiang Huang |
| author_facet | Wei Wang Wei Wang Yong Fu Sun Wei Gao WeiKun Xu YiXin Zhang YiXin Zhang DeXiang Huang DeXiang Huang |
| author_sort | Wei Wang |
| collection | DOAJ |
| description | Detecting deep-sea megabenthic organisms is of foremost importance for seabed resource surveys, typical habitat protection, and biodiversity surveys. However, the complexity of the deep-sea environment, uneven illumination, and small biological targets that are easily obscured all increase target detection difficulty significantly. To address these, this paper proposes a deep-sea megabenthic detection algorithm, DS-YOLO, based on YOLOv5s. To improve the detection ability of the model for deep-sea megabenthic organisms, the space-to-depth module and the spatial pyramid pooling cross stage partial channel module are introduced in the Backbone layer to enlarge the receptive field and enhance the retention of small-scale features. Then, the space-to-depth and normalization-based attention modules and the Add and Concat functions of the bidirectional feature pyramid network are introduced in the Neck layer to increase the multiscale fusion ability of the model and highlight the insignificant features. Finally, the two branches of the decoupling header output the category and location of the target, which causes the model to utilize the feature information to the maximum extent. Experiments showed that DS-YOLO improved mAP0.5 from 89.6% to 92.4% and mAP0.5:0.95 from 65.7% to 72.3% compared to the original YOLOv5s on the homemade dataset and outperformed other algorithms in the YOLO series. DS-YOLO reaches 84.7 FPS for deployment on mobile platforms. In addition, the combined DS-YOLO and DeepSORT algorithm can be used to calculate the abundance and community structure of deep-sea megabenthos. The model outperforms general target detection models for deep-sea megabenthos detection and is suitable for use in complex deep-sea environments. |
| first_indexed | 2024-03-07T21:26:15Z |
| format | Article |
| id | doaj.art-d480ebc8ed0d46b09df2b3d803ae19a2 |
| institution | Directory Open Access Journal |
| issn | 2296-7745 |
| language | English |
| last_indexed | 2024-03-07T21:26:15Z |
| publishDate | 2024-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj.art-d480ebc8ed0d46b09df2b3d803ae19a22024-02-27T04:53:33ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452024-02-011110.3389/fmars.2024.13010241301024Quantitative detection algorithm for deep-sea megabenthic organisms based on improved YOLOv5Wei Wang0Wei Wang1Yong Fu Sun2Wei Gao3WeiKun Xu4YiXin Zhang5YiXin Zhang6DeXiang Huang7DeXiang Huang8Investigation Department, National Deep Sea Center (NDSC), Qingdao, ChinaQingdao Innovation Development Base, Harbin Engineering University, Qingdao, ChinaInvestigation Department, National Deep Sea Center (NDSC), Qingdao, ChinaInvestigation Department, National Deep Sea Center (NDSC), Qingdao, ChinaInvestigation Department, National Deep Sea Center (NDSC), Qingdao, ChinaInvestigation Department, National Deep Sea Center (NDSC), Qingdao, ChinaQingdao Innovation Development Base, Harbin Engineering University, Qingdao, ChinaInvestigation Department, National Deep Sea Center (NDSC), Qingdao, ChinaCollege of Ocean Science and Engineering, Shandong University of Science and Technology, Qingdao, ChinaDetecting deep-sea megabenthic organisms is of foremost importance for seabed resource surveys, typical habitat protection, and biodiversity surveys. However, the complexity of the deep-sea environment, uneven illumination, and small biological targets that are easily obscured all increase target detection difficulty significantly. To address these, this paper proposes a deep-sea megabenthic detection algorithm, DS-YOLO, based on YOLOv5s. To improve the detection ability of the model for deep-sea megabenthic organisms, the space-to-depth module and the spatial pyramid pooling cross stage partial channel module are introduced in the Backbone layer to enlarge the receptive field and enhance the retention of small-scale features. Then, the space-to-depth and normalization-based attention modules and the Add and Concat functions of the bidirectional feature pyramid network are introduced in the Neck layer to increase the multiscale fusion ability of the model and highlight the insignificant features. Finally, the two branches of the decoupling header output the category and location of the target, which causes the model to utilize the feature information to the maximum extent. Experiments showed that DS-YOLO improved mAP0.5 from 89.6% to 92.4% and mAP0.5:0.95 from 65.7% to 72.3% compared to the original YOLOv5s on the homemade dataset and outperformed other algorithms in the YOLO series. DS-YOLO reaches 84.7 FPS for deployment on mobile platforms. In addition, the combined DS-YOLO and DeepSORT algorithm can be used to calculate the abundance and community structure of deep-sea megabenthos. The model outperforms general target detection models for deep-sea megabenthos detection and is suitable for use in complex deep-sea environments.https://www.frontiersin.org/articles/10.3389/fmars.2024.1301024/fullcomputer visiondeep sea object detectionmegabenthosYOLOv5automatic counting |
| spellingShingle | Wei Wang Wei Wang Yong Fu Sun Wei Gao WeiKun Xu YiXin Zhang YiXin Zhang DeXiang Huang DeXiang Huang Quantitative detection algorithm for deep-sea megabenthic organisms based on improved YOLOv5 Frontiers in Marine Science computer vision deep sea object detection megabenthos YOLOv5 automatic counting |
| title | Quantitative detection algorithm for deep-sea megabenthic organisms based on improved YOLOv5 |
| title_full | Quantitative detection algorithm for deep-sea megabenthic organisms based on improved YOLOv5 |
| title_fullStr | Quantitative detection algorithm for deep-sea megabenthic organisms based on improved YOLOv5 |
| title_full_unstemmed | Quantitative detection algorithm for deep-sea megabenthic organisms based on improved YOLOv5 |
| title_short | Quantitative detection algorithm for deep-sea megabenthic organisms based on improved YOLOv5 |
| title_sort | quantitative detection algorithm for deep sea megabenthic organisms based on improved yolov5 |
| topic | computer vision deep sea object detection megabenthos YOLOv5 automatic counting |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2024.1301024/full |
| work_keys_str_mv | AT weiwang quantitativedetectionalgorithmfordeepseamegabenthicorganismsbasedonimprovedyolov5 AT weiwang quantitativedetectionalgorithmfordeepseamegabenthicorganismsbasedonimprovedyolov5 AT yongfusun quantitativedetectionalgorithmfordeepseamegabenthicorganismsbasedonimprovedyolov5 AT weigao quantitativedetectionalgorithmfordeepseamegabenthicorganismsbasedonimprovedyolov5 AT weikunxu quantitativedetectionalgorithmfordeepseamegabenthicorganismsbasedonimprovedyolov5 AT yixinzhang quantitativedetectionalgorithmfordeepseamegabenthicorganismsbasedonimprovedyolov5 AT yixinzhang quantitativedetectionalgorithmfordeepseamegabenthicorganismsbasedonimprovedyolov5 AT dexianghuang quantitativedetectionalgorithmfordeepseamegabenthicorganismsbasedonimprovedyolov5 AT dexianghuang quantitativedetectionalgorithmfordeepseamegabenthicorganismsbasedonimprovedyolov5 |