改进的YOLOv3常见鱼病检测算法  

Improved YOLOv3 Algorithm for Common Fish Disease Detection

作　　者：冼远清[1] XIAN Yuanqing(Faculty of Mathematics and Computer Science of Guangdong Ocean University,Zhanjiang,China,524088)

机构地区：[1]广东海洋大学数学与计算机学院,广东湛江524088

出　　处：《福建电脑》2022年第7期11-14,共4页Journal of Fujian Computer

基　　金：湛江市科技攻关计划项目(No.2019B01008);广东海洋大学教改项目(No.XJG202150)资助。

摘　　要：鱼病检测是水产养殖中一项重要技术,将人工智能与鱼病检测相结合具有重要现实意义。YOLOv3具有速度快、检测准确度高等特点,但存在小目标检测效果较差问题。本文提出一种改进的YOLOv3深度神经网络模型,该模型可应用于白点病等7种常见鱼病诊断。实验结果表明,模型可以满足鱼病诊断的时空要求。Fish disease detection is an important technology in aquaculture.The combination of artificial intelligence and fish disease detection has important practical significance.YOLOv3 has the characteristics of fast speed and high detection accuracy,but it has the problem of poor detection effect of small targets.This paper presents an improved yolov3 deep neural network model,which can be applied to the diagnosis of seven common fish diseases such as white spot disease.The experimental results show that the model can meet the space-time requirements of fish disease diagnosis.

关 键 词：鱼病 检测算法 模型 

分 类 号：TP311.52[自动化与计算机技术—计算机软件与理论]