A Method for Recognizing Dead Sea Bass Based on Improved YOLOv8n
Deaths occur during the culture of sea bass, and if timely harvesting is not carried out, it will lead to water pollution and the continued spread of sea bass deaths. Therefore, it is necessary to promptly detect dead fish and take countermeasures. Existing object detection algorithms, when applied...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/14/4318 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849252051382435840 |
|---|---|
| author | Lizhen Zhang Chong Xu Sai Jiang Mengxiang Zhu Di Wu |
| author_facet | Lizhen Zhang Chong Xu Sai Jiang Mengxiang Zhu Di Wu |
| author_sort | Lizhen Zhang |
| collection | DOAJ |
| description | Deaths occur during the culture of sea bass, and if timely harvesting is not carried out, it will lead to water pollution and the continued spread of sea bass deaths. Therefore, it is necessary to promptly detect dead fish and take countermeasures. Existing object detection algorithms, when applied to the task of detecting dead sea bass, often suffer from excessive model complexity, high computational cost, and reduced accuracy in the presence of occlusion. To overcome these limitations, this study introduces YOLOv8n-Deadfish, a lightweight and high-precision detection model. First, the homemade sea bass death recognition dataset was expanded to enhance the generalization ability of the neural network. Second, the C2f-faster–EMA (efficient multi-scale attention) convolutional module was designed to replace the C2f module in the backbone network of YOLOv8n, reducing redundant calculations and memory access, thereby more effectively extracting spatial features. Then, a weighted bidirectional feature pyramid network (BiFPN) was introduced to achieve a more thorough integration of deep and shallow features. Finally, in order to compensate for the weak generalization and slow convergence of the CIoU loss function in detection tasks, the Inner-CIoU loss function was used to accelerate bounding box regression and further improve the detection performance of the model. The experimental results show that the YOLOv8n-Deadfish model has an accuracy, recall, and mean precision of 90.0%, 90.4%, and 93.6%, respectively, which is an improvement of 2.0, 1.4, and 1.3 percentage points, respectively, over the original base network YOLOv8n. The number of model parameters and GFLOPs were reduced by 23.3% and 18.5%, respectively, and the detection speed was improved from the original 304.5 FPS to 424.6 FPS. This method can provide a technical basis for the identification of dead sea bass in the process of intelligent aquaculture. |
| format | Article |
| id | doaj-art-042d8fda38034b32935da09d3de26fa4 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-042d8fda38034b32935da09d3de26fa42025-08-20T03:56:45ZengMDPI AGSensors1424-82202025-07-012514431810.3390/s25144318A Method for Recognizing Dead Sea Bass Based on Improved YOLOv8nLizhen Zhang0Chong Xu1Sai Jiang2Mengxiang Zhu3Di Wu4College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, ChinaCollege of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, ChinaCollege of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, ChinaCollege of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, ChinaCollege of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, ChinaDeaths occur during the culture of sea bass, and if timely harvesting is not carried out, it will lead to water pollution and the continued spread of sea bass deaths. Therefore, it is necessary to promptly detect dead fish and take countermeasures. Existing object detection algorithms, when applied to the task of detecting dead sea bass, often suffer from excessive model complexity, high computational cost, and reduced accuracy in the presence of occlusion. To overcome these limitations, this study introduces YOLOv8n-Deadfish, a lightweight and high-precision detection model. First, the homemade sea bass death recognition dataset was expanded to enhance the generalization ability of the neural network. Second, the C2f-faster–EMA (efficient multi-scale attention) convolutional module was designed to replace the C2f module in the backbone network of YOLOv8n, reducing redundant calculations and memory access, thereby more effectively extracting spatial features. Then, a weighted bidirectional feature pyramid network (BiFPN) was introduced to achieve a more thorough integration of deep and shallow features. Finally, in order to compensate for the weak generalization and slow convergence of the CIoU loss function in detection tasks, the Inner-CIoU loss function was used to accelerate bounding box regression and further improve the detection performance of the model. The experimental results show that the YOLOv8n-Deadfish model has an accuracy, recall, and mean precision of 90.0%, 90.4%, and 93.6%, respectively, which is an improvement of 2.0, 1.4, and 1.3 percentage points, respectively, over the original base network YOLOv8n. The number of model parameters and GFLOPs were reduced by 23.3% and 18.5%, respectively, and the detection speed was improved from the original 304.5 FPS to 424.6 FPS. This method can provide a technical basis for the identification of dead sea bass in the process of intelligent aquaculture.https://www.mdpi.com/1424-8220/25/14/4318dead sea basstarget detectiondeep learningYOLOv8 |
| spellingShingle | Lizhen Zhang Chong Xu Sai Jiang Mengxiang Zhu Di Wu A Method for Recognizing Dead Sea Bass Based on Improved YOLOv8n Sensors dead sea bass target detection deep learning YOLOv8 |
| title | A Method for Recognizing Dead Sea Bass Based on Improved YOLOv8n |
| title_full | A Method for Recognizing Dead Sea Bass Based on Improved YOLOv8n |
| title_fullStr | A Method for Recognizing Dead Sea Bass Based on Improved YOLOv8n |
| title_full_unstemmed | A Method for Recognizing Dead Sea Bass Based on Improved YOLOv8n |
| title_short | A Method for Recognizing Dead Sea Bass Based on Improved YOLOv8n |
| title_sort | method for recognizing dead sea bass based on improved yolov8n |
| topic | dead sea bass target detection deep learning YOLOv8 |
| url | https://www.mdpi.com/1424-8220/25/14/4318 |
| work_keys_str_mv | AT lizhenzhang amethodforrecognizingdeadseabassbasedonimprovedyolov8n AT chongxu amethodforrecognizingdeadseabassbasedonimprovedyolov8n AT saijiang amethodforrecognizingdeadseabassbasedonimprovedyolov8n AT mengxiangzhu amethodforrecognizingdeadseabassbasedonimprovedyolov8n AT diwu amethodforrecognizingdeadseabassbasedonimprovedyolov8n AT lizhenzhang methodforrecognizingdeadseabassbasedonimprovedyolov8n AT chongxu methodforrecognizingdeadseabassbasedonimprovedyolov8n AT saijiang methodforrecognizingdeadseabassbasedonimprovedyolov8n AT mengxiangzhu methodforrecognizingdeadseabassbasedonimprovedyolov8n AT diwu methodforrecognizingdeadseabassbasedonimprovedyolov8n |