YOLOv7-CHS: An Emerging Model for Underwater Object Detection
Underwater target detection plays a crucial role in marine environmental monitoring and early warning systems. It involves utilizing optical images acquired from underwater imaging devices to locate and identify aquatic organisms in challenging environments. However, the color deviation and low illu...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/11/10/1949 |
| _version_ | 1797573416885157888 |
|---|---|
| author | Liang Zhao Qing Yun Fucai Yuan Xu Ren Junwei Jin Xianchao Zhu |
| author_facet | Liang Zhao Qing Yun Fucai Yuan Xu Ren Junwei Jin Xianchao Zhu |
| author_sort | Liang Zhao |
| collection | DOAJ |
| description | Underwater target detection plays a crucial role in marine environmental monitoring and early warning systems. It involves utilizing optical images acquired from underwater imaging devices to locate and identify aquatic organisms in challenging environments. However, the color deviation and low illumination in these images, caused by harsh working conditions, pose significant challenges to an effective target detection. Moreover, the detection of numerous small or tiny aquatic targets becomes even more demanding, considering the limited storage and computing power of detection devices. To address these problems, we propose the YOLOv7-CHS model for underwater target detection, which introduces several innovative approaches. Firstly, we replace efficient layer aggregation networks (ELAN) with the high-order spatial interaction (HOSI) module as the backbone of the model. This change reduces the model size while preserving accuracy. Secondly, we integrate the contextual transformer (CT) module into the head of the model, which combines static and dynamic contextual representations to effectively improve the model’s ability to detect small targets. Lastly, we incorporate the simple parameter-free attention (SPFA) module at the head of the detection network, implementing a combined channel-domain and spatial-domain attention mechanism. This integration significantly improves the representation capabilities of the network. To validate the implications of our model, we conduct a series of experiments. The results demonstrate that our proposed model achieves higher mean average precision (mAP) values on the Starfish and DUO datasets compared to the original YOLOv7, with improvements of 4.5% and 4.2%, respectively. Additionally, our model achieves a real-time detection speed of 32 frames per second (FPS). Furthermore, the floating point operations (FLOPs) of our model are 62.9 G smaller than those of YOLOv7, facilitating the deployment of the model. Its innovative design and experimental results highlight its effectiveness in addressing the challenges associated with underwater object detection. |
| first_indexed | 2024-03-10T21:09:18Z |
| format | Article |
| id | doaj.art-da385b9f638043a38f72021e30468ee7 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-10T21:09:18Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-da385b9f638043a38f72021e30468ee72023-11-19T16:58:59ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-10-011110194910.3390/jmse11101949YOLOv7-CHS: An Emerging Model for Underwater Object DetectionLiang Zhao0Qing Yun1Fucai Yuan2Xu Ren3Junwei Jin4Xianchao Zhu5College of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, ChinaCollege of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, ChinaSchool of Mechanical and Electrical Engineering, Henan University of Technology, Zhengzhou 450001, ChinaCollege of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, ChinaSchool of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou 450001, ChinaSchool of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou 450001, ChinaUnderwater target detection plays a crucial role in marine environmental monitoring and early warning systems. It involves utilizing optical images acquired from underwater imaging devices to locate and identify aquatic organisms in challenging environments. However, the color deviation and low illumination in these images, caused by harsh working conditions, pose significant challenges to an effective target detection. Moreover, the detection of numerous small or tiny aquatic targets becomes even more demanding, considering the limited storage and computing power of detection devices. To address these problems, we propose the YOLOv7-CHS model for underwater target detection, which introduces several innovative approaches. Firstly, we replace efficient layer aggregation networks (ELAN) with the high-order spatial interaction (HOSI) module as the backbone of the model. This change reduces the model size while preserving accuracy. Secondly, we integrate the contextual transformer (CT) module into the head of the model, which combines static and dynamic contextual representations to effectively improve the model’s ability to detect small targets. Lastly, we incorporate the simple parameter-free attention (SPFA) module at the head of the detection network, implementing a combined channel-domain and spatial-domain attention mechanism. This integration significantly improves the representation capabilities of the network. To validate the implications of our model, we conduct a series of experiments. The results demonstrate that our proposed model achieves higher mean average precision (mAP) values on the Starfish and DUO datasets compared to the original YOLOv7, with improvements of 4.5% and 4.2%, respectively. Additionally, our model achieves a real-time detection speed of 32 frames per second (FPS). Furthermore, the floating point operations (FLOPs) of our model are 62.9 G smaller than those of YOLOv7, facilitating the deployment of the model. Its innovative design and experimental results highlight its effectiveness in addressing the challenges associated with underwater object detection.https://www.mdpi.com/2077-1312/11/10/1949underwater object detectionYOLOv7-CHSHOSI moduleCT moduleSPFA module |
| spellingShingle | Liang Zhao Qing Yun Fucai Yuan Xu Ren Junwei Jin Xianchao Zhu YOLOv7-CHS: An Emerging Model for Underwater Object Detection Journal of Marine Science and Engineering underwater object detection YOLOv7-CHS HOSI module CT module SPFA module |
| title | YOLOv7-CHS: An Emerging Model for Underwater Object Detection |
| title_full | YOLOv7-CHS: An Emerging Model for Underwater Object Detection |
| title_fullStr | YOLOv7-CHS: An Emerging Model for Underwater Object Detection |
| title_full_unstemmed | YOLOv7-CHS: An Emerging Model for Underwater Object Detection |
| title_short | YOLOv7-CHS: An Emerging Model for Underwater Object Detection |
| title_sort | yolov7 chs an emerging model for underwater object detection |
| topic | underwater object detection YOLOv7-CHS HOSI module CT module SPFA module |
| url | https://www.mdpi.com/2077-1312/11/10/1949 |
| work_keys_str_mv | AT liangzhao yolov7chsanemergingmodelforunderwaterobjectdetection AT qingyun yolov7chsanemergingmodelforunderwaterobjectdetection AT fucaiyuan yolov7chsanemergingmodelforunderwaterobjectdetection AT xuren yolov7chsanemergingmodelforunderwaterobjectdetection AT junweijin yolov7chsanemergingmodelforunderwaterobjectdetection AT xianchaozhu yolov7chsanemergingmodelforunderwaterobjectdetection |