基于YOLOv3深度学习算法的桑椹菌核病严重度检测方法研究与应用
Research and application of detection method of mulberry fruit sclerotiniose disease severity based on YOLOv3 deep learning algorithm
朱志贤 1邱盼 2张成 1董朝霞 1张凤 1胡兴明 1于翠1
作者信息
- 1. 湖北省农业科学院经济作物研究所,武汉 430064
- 2. 飞卓科技(上海)股份有限公司,上海 201506
- 折叠
摘要
通过对5种不同发病级别的1万张桑椹果实图像进行训练,基于YOLOv3深度学习算法并结合迁移学习法,获得桑椹菌核病严重度目标检测模型.为了验证该模型的鲁棒性,与同样采用迁移学习的EfficientDet、Faster R-CNN和YOLOv4原始模型进行了对比.结果表明,YOLOv3模型对健康果实和菌核病果实检测的平均精确率均值为0.79,比其他模型提高6.76%～54.90%,其对不同发病级别菌核病果实检测的平均精确率比其他模型提高7.04%～80.95%,查准率和查全率为最优或者次优.采用Flask+Vue技术构建的检测识别系统可在1s内获取病害严重度、果实大小、置信度信息,也能实现对视频的动态识别,为桑椹种植中自动化病害监测和快速高效精准施药提供了可靠的软件处理平台.
Abstract
A target detection model for mulberry fruit sclerotiniose disease severity was constructed based on YOLOv3 deep learning algorithm combined with transfer learning by training on 10 000 images of mulberry fruit with five different disease severity levels.To verify the robustness of the YOLOv3 model,comparative experiments were conducted with the EfficientDet,Faster R-CNN and YO-LOv4 that also used transfer learning.The results showed that the average precision rate of the YOLOv3 model could reach 0.79 for de-tecting healthy fruits and sclerotinia fruit,which was 6.76%～54.90%higher than that of the other models.The average precision rate of the YOLOv3 model for detecting disease severity levels of sclerotinia fruit was 7.04%～80.95%higher than that of the other models.The detection precision rate and recall rate of the YOLOv3 model were optimal or sub-optimal.The detection and recognition system con-structed by Flask+Vue technology could obtain disease severity,fruit size and confidence information within 1 s,and could also real-ize dynamic recognition of video.This system could provide a reliable software processing platform for automated disease monitoring and fast,efficient,and precise fungicide application during mulberry cultivation.
关键词
桑椹菌核病/深度学习算法/迁移学习法/YOLOv3/病害严重度检测Key words
mulberry fruit sclerotiniose disease/deep learning algorithm/transfer learning/YOLOv3/detection of disease severity引用本文复制引用
出版年
2024
NETL
NSTL
万方数据