基于深度学习的柑橘病虫害动态识别系统研发

doi:10.13733/j.jcam.issn.2095-5553.2021.09.27

摘要/Abstract

摘要： 柑橘是我国重要的经济林果之一,因种植区多在山区坡地,病虫害防治给管理带来了很大困难,在线监测与专家决策成为现代农业发展的方向。本文采用物联网技术和深度学习方法,基于尺度可变视频流信息,设计并构建了一套基于柑橘叶片的病虫害动态识别系统。该系统实现了全方位智能控制,解决了实时叶片图像变形和尺度缩放等问题,实现了柑橘图像的动态采集和智能识别。叶片检测的MAP达到87.72%,病害识别准确率达到95.46%,系统运行结果表明,该系统可有效实现柑橘智能监控的管理,为病虫害物联网监控提供参考。

关键词: 物联网, 视频监控, 深度学习, 叶片检测, 病害识别

Abstract: Citrus is one of the important economic trees in our country. Because planting areas are mostly on mountainous slopes, the prevention and control of diseases and insect pests have brought great difficulties to management. Online monitoring and expert decisionmaking have become the direction of modern agricultural development. In this paper, using the Internet of Things technology and deep learning methods, a set of dynamic identification systems of diseases and insect pests based on citrus leaves is designed and constructed based on the variablescale video stream information. The system realizes allround intelligent control, solves realtime leaf image deformation and scale scaling, and realizes the dynamic collection and intelligent recognition of citrus images. The map of leaf detection is 87.72%, and the accuracy of disease identification is 95.46%. The system operation results show that the system can effectively realize the management of intelligent citrus monitoring and provide a reference for the monitoring of diseases and insect pests.

Key words: Internet of Things, video monitoring, deep learning, leaf detection, disease recognition

中图分类号:

李昊, 刘海隆, 刘生龙, . 基于深度学习的柑橘病虫害动态识别系统研发[J]. 中国农机化学报, 2021, 42(9): 195-201+208.

Li Hao, Liu Hailong, Liu Shenglong.. Research on dynamic identification system of citrus diseases and pests based on deep learning ［[J]. Journal of Chinese Agricultural Mechanization, 2021, 42(9): 195-201+208.

参考文献

［１］　
施盛华. 基于物联网与图像识别的太阳能果园虫害监测系统研发［D］. 杭州: 浙江科技学院, 2019.

Shi Shenghua. Research and development of inseet pest monitoring system for solar garden based on Internet of Things and image recognition ［D］. Hangzhou: Zhejiang University of Science and Technology, 2019.

［2］　
苏一峰. 基于物联网的小麦病虫害动态气象模型和远程诊断方法研究［D］. 北京：中国农业科学院, 2016.

［3］　
赵洁. 基于图像处理的水培黄瓜叶片病斑识别系统设计［D］. 西安：陕西科技大学, 2019.

Zhao Jie. Design of hydroponic cucumber leaf spot recognition system based on image processing ［D］. Xian: Shaanxi University of Science and Technology, 2019.

［4］　
吴桐. 基于物联网与图像识别的玉米病虫害诊断与预防系统［D］. 长春: 吉林农业大学, 2013.

Wu Tong. Based on Internet of Things and image recognition of corn plant diseases and insect pests diagnosis and prevention system ［D］. Changchun: Jilin Agricultural University, 2013.

［5］　
韩文霆, 崔利华, 陈微, 等. 桁架式可移动作物生长远程监控系统设计［J］. 农业工程学报, 2014, 30(13): 160-168.

Han Wenting, Cui Lihua, Chen Wei, et al. Design of movable remote crop monitoring system on fixed truss ［J］. Transactions of the CSAE, 2014, 30(13): 160-168.

［6］　
廖煊龙. 面向智能视频监控的目标检测和行为识别技术研究［D］. 成都: 电子科技大学, 2019.

Liao Xuanlong. Research of object detection and behavior recognition technology in intelligent video surveillance ［D］. Chengdu: University of Electronic Science and Technology of China, 2019.

［7］　
马浚诚, 李鑫星, 温皓杰, 等. 面向叶类蔬菜病害识别的温室监控视频采集系统［J］. 农业机械学报, 2015, 46(3): 282-287.

［8］　
高蒙. 基于机智云平台的远程监控系统开发关键技术研究［D］. 西安: 西安理工大学, 2019.

Gao Meng. Research on key technologies of remote monitoring system development based on intelligent cloud platform ［D］. Xian: Xian University of technology, 2019.

［9］　
赵兵. 基于深度学习的葡萄叶片分割［D］. 兰州: 甘肃农业大学, 2018.

Zhao Bing. Grape Leaf Segmentation based on Deep Learning ［D］. Lanzhou: Gansu Agricultural University, 2018.

［10］　
端辉. 基于YOLO的多尺度快速行人检测算法研究与应用［D］. 大连: 大连理工大学, 2019.

Duan Hui. Research and application of multiscale fast pedestrian detection algorithm based on YOLO ［D］. Dalian: Dalian University of Technology, 2019.

［11］　
汪文强, 张国平, 徐洪波, 等. 基于云平台的远程监控系统的设计与实现［J］. 信息技术, 2019, 43(11): 72-77.

Wang Wenqiang, Zhang Guoping, Xu Hongbo, et al. Design and implementation of remote monitoring system based on cloud platform ［J］. Information Technology, 2019, 43(11): 72-77.

［12］　
曹静. 基于视频图像的大棚白菜叶部病害识别与预警系统设计与实现［D］. 保定: 河北农业大学, 2019.

Cao Jing. Design and implementation of leaf disease recognition and early warning system for Chinese cabbage in greenhouse based on video image ［D］. Baoding: Hebei Agricultural University, 2019.

［13］　
管军霖, 智鑫. 基于YOLOv4卷积神经网络的口罩佩戴检测方法［J］. 现代信息科技, 2020, 4(11): 9-12.

Guan Junlin, Zhi Xin. Mask wearing detection method based on YOLOv4 convolutional neural network ［J］. Modern Information Technology, 2020, 4(11): 9-12.

［14］　
李振东. 智能葡萄大棚监测系统设计［D］. 淮南: 安徽理工大学, 2019.

Li Zhendong. Design of intelligent grape greenhouse monitoring system ［D］. Huainan: Anhui University of Science & Technology, 2019.

［15］　
Zhao Z, Cui X, Zhang H. Cloud storage technology in video surveillance ［J］. Advanced Materials Research, 2012, 532-533: 1334-1338.

［16］　
Ahmadi M, Ouarda W, Alimi A M. Efficient and fast objects detection technique for intelligent video surveillance using transfer learning and finetuning ［J］. Arabian Journal for Science and Engineering, 2020.

［17］　
Huang G, Liu Z, Laurens V, et al. Densely connected convolutional networks ［C］. IEEE Computer Society. IEEE Computer Society, 2016.

［18］　
Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, realtime object detection ［J］. IEEE, 2016.

［19］　
Salih T A, Ali A J, Ahmed M N. Deep learning convolution neural network to detect and classify tomato plant leaf diseases ［J］. Open Access Library Journal, 2020, 7(5): 1-12.

［20］　
Xia C, Lee J M, Yan L, et al. Plant leaf detection using modified active shape models ［J］. Biosystems Engineering, 2013, 116(1): 23-35.

［21］　
Mattihalli C, Gedefaye E, Endalamaw F, et al. Plant leaf diseases detection and automedicine ［J］. Internet of Things, 2018, 1-2: 67-73.

[1]	李东升, 胡文泽, 兰玉彬, 范明洪, 李翠云, 朱俊科. 深度学习在杂草识别领域的研究现状与展望[J]. 中国农机化学报, 2022, 43(9): 137-144.
[2]	卞东超, 杨发展, 赵国栋, 郑凯瑞, 林海波. 蓝莓温室智能水肥一体化系统构建[J]. 中国农机化学报, 2022, 43(8): 55-61.
[3]	王晓婷, 赵展, 王阳, 李林, . 基于改进Mask R-CNN的植物表型智能检测算法[J]. 中国农机化学报, 2022, 43(8): 151-157.
[4]	孙逸飞, 柳平增, 张艳, 宋长青, 张大雷, 马学文. 基于Sentinel-2A遥感影像的潍坊市冬小麦种植面积提取研究[J]. 中国农机化学报, 2022, 43(7): 98-105.
[5]	张三林, 张立萍, 郑威强, 郭壮, 付子强. 基于YOLOv5的核桃品种识别与定位[J]. 中国农机化学报, 2022, 43(7): 167-172.
[6]	史方青, 王虎林, 黄华. 基于卷积神经网络的马铃薯芽眼检测识别研究[J]. 中国农机化学报, 2022, 43(6): 159-165.
[7]	曹金凤, 沈大港, 郭继鸿, 刘鹏, 李策, 兰添贺. 基于CNN和SVM分类优化的大蒜鳞芽朝向识别研究[J]. 中国农机化学报, 2022, 43(5): 134-139.
[8]	雷雪梅, 张光强, 姚旗, 刘伟渭, 邱帅. 基于卷积神经网络的农机图像自动识别研究[J]. 中国农机化学报, 2022, 43(5): 140-147.
[9]	陈国防, 陈兆英, 王玉亮, 王金星, 范国强, 李汉卿, . 基于数据增强深度学习的苹果花检测方法研究[J]. 中国农机化学报, 2022, 43(5): 148-155.
[10]	杨学坤, 郑士朝. 气雾栽培式家庭植物工厂设计[J]. 中国农机化学报, 2022, 43(4): 38-45.
[11]	张燕斌, 杜健民, 王圆, 皮伟强, 高新超. 基于无人机高光谱遥感和3D-ResNet的荒漠草原地物分类[J]. 中国农机化学报, 2022, 43(4): 66-73.
[12]	何颖, 陈丁号, 彭琳. 基于改进YOLOv5模型的经济林木虫害目标检测算法研究[J]. 中国农机化学报, 2022, 43(4): 106-115.
[13]	孙博瑞, 孙三民, 蒋敏, 薛山. 基于LSTM神经网络的智能灌溉系统设计与试验#br# #br# [J]. 中国农机化学报, 2022, 43(4): 116-123.
[14]	项新建, 宋晓敏, 郑永平, 王海波, 方政洋. 基于MobileNet-YOLO的嵌入式人脸检测研究#br# #br# [J]. 中国农机化学报, 2022, 43(4): 124-130.
[15]	董萍, 卫梦华, 时雷, 郭伟. 迁移学习在玉米叶片病害识别中的研究与应用[J]. 中国农机化学报, 2022, 43(3): 146-152.