文献类型：期刊文献

英文题名：Design and Experimentation of Fish Feeding Intensity System Based on Binocular Cameras and Deep Learning; [基于双目相机和深度学习的鱼类摄食强度分析方法]

作者：Yu G.; Qian L.; Liu H.; He Z.

机构：[1]School of Mechanical Engineering, Guangdong Ocean University, Zhanjiang, 524088, China;[2]Guangdong Marine Equipment and Manufacturing Engineering Technology Research Center, Zhanjiang, 524088, China

年份：2025

卷号：56

期号：3

起止页码：403

外文期刊名：Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

收录：Scopus(收录号：2-s2.0-105001578774)

语种：英文

外文关键词：binocular camera; deep-sea cage aquaculture; fish feeding; lightweight; semantic segmentation ; YOLO v8n - seg

外文摘要：Assessing the feeding intensity of fish in large-scale cages is crucial for enhancing feed utilization and reducing farming costs. Traditional feeding methods heavily rely on the experience of aquaculture managers, often leading to overfeeding, which contaminates water quality, or underfeeding, and adversely affects fish health. To accurately determine fish feeding intensity in deep-sea cage farming and achieve precise feeding, focusing on the splashes generated by pompano during feeding, utilizing depth images captured by a binocular camera, a non-invasive feeding intensity analysis method was proposed, involving semantic segmentation and area calculation of the splash. Firstly, to enable the model's deployment on low-cost edge devices, the YOLO v8n - seg model was improved through the incorporation of StarNet, BiFPN, and a custom-designed SCD - Head shared convolutional detection head, resulting in the lightweight YOLO v8n - SBS model. This modification achieved a 3. 2 percentage points increase in accuracy while reducing the number of parameters and floating-point operations by 71% and 36% , respectively. Secondly, to minimize equipment costs, a binocular camera was employed, and PVC boards were used to simulate splash targets on land for experimental convenience. A linear regression model (DI) was proposed to calculate splash area based on depth information. The results of the DI model on the test set demonstrated an R value of 0. 977 , an RMSE of 0. 033 m , and an MAE of 0. 023 m , indicating robust performance. Ultimately, the two models were combined into YOLO v8n -SBS - DI, which can segment splashes and compute their area, allowing for the assessment of feeding intensity through the trend of splash area changes. Sea trial results showed that the calculated splash area yields an R? value of 0. 914, an RMSE of 0. 973 m , and an MAE of 0. 870 m . These experimental outcomes confirmed that the model exhibited strong robustness and met the demands for splash area calculations in complex environments, thereby providing technical support for determining fish feeding intensity. ? 2025 Chinese Society of Agricultural Machinery. All rights reserved.