基于改进YOLOv4算法的苹果叶部病害缺陷检测研究

doi:10.13733/j.jcam.issn.2095-5553.2022.11.025

摘要/Abstract

摘要： 针对苹果叶部病害缺陷检测效率低下、误检率高、实时性差等问题，以苹果叶部的灰斑病、黑星病、锈病、斑点落叶病作为研究对象，提出一种基于改进YOLOv4算法的苹果叶部病害缺陷检测算法。首先通过数据扩增对数据集扩充提升鲁棒性，算法通过二分K均值聚类算法确定锚框以解决预设锚框不适用苹果叶部病害的问题，引入DenseNet121作为特征提取网络，提升对苹果叶部病害缺陷的检测性能，并且减小模型大小，降低存储开销。将模型与YOLOv4模型进行对比验证，试验结果表明，改进后的YOLOv4模型平均精度均值（mAP）达到97.52%，与改进前相比提升0.89%，模型大小为62.71 MB，与改进前相比减小182.82 MB，检测速度为26.33 FPS，与改进前相比提升6.78 FPS。能够满足实际生活中对苹果叶部病害检测的需求。

关键词: 苹果叶部病害, 缺陷检测, YOLOv4, 二分K均值聚类, DenseNet121

Abstract: Aiming at the problems of low efficiency, high error detection rate and poor realtime detection of apple leaf disease defects, taking gray spot, scab, rust and leaf spot disease of apple leaves as the research objects. An apple leaf disease detection algorithm based on improved yolov4 was proposed. Firstly, data amplification was used to expand the data set to improve the robustness. The algorithm determined the anchor frame by binary kmeans clustering algorithm to solve the problem that the preset anchor frame was not suitable for apple leaf diseases. DenseNet121 was introduced as a feature extraction network to improve the detection performance of apple leaf disease defects, and reduce the model size, reduce the storage overhead. The model in this paper was compared with YOLOV4 model. The results showed that the mean accuracy (mAP) of the improved YOLOv4 model reached 97.52%, which was 089% higher than before. The size of the model was 62.71 MB, which decreased 182.82 MB compared with that before improvement. The detection speed was 26.33 FPS, which increased 6.78 FPS compared with that before improvement. It can meet the demand of apple leaf disease detection in real life.

Key words: apple leaf diseases, defect detection, YOLOv4, binary K-means clustering, DenseNet121

中图分类号:

TP391.4:S436.611.1

王权顺, 吕蕾, 黄德丰, 付思琴, 余华云. 基于改进YOLOv4算法的苹果叶部病害缺陷检测研究[J]. 中国农机化学报, 2022, 43(11): 182-187.

Wang Quanshun, Lü Lei, Huang Defeng, Fu Siqin, Yu Huayun.. Research of apple leaf disease defect based on improved YOLOv4 algorithm[J]. Journal of Chinese Agricultural Mechanization, 2022, 43(11): 182-187.

参考文献

［1］　
常倩, 李瑾. 2000年以来中国苹果产业发展趋势分析［J］. 北方园艺, 2021(3): 155-160.

Chang Qian, Li Jin. Development trend of apple industry in China since 2000［J］. Northern Horticulture, 2021(3): 155-160.

［2］　
王树桐, 王亚南, 曹克强. 近年我国重要苹果病害发生概况及研究进展［J］. 植物保护, 2018, 44(5): 13-25, 50.

Wang Shutong, Wang Yanan, Cao Keqiang. Occurrence of and research progress in important apple diseases in China in recent years ［J］. Plant Protection, 2018, 44(5): 13-25， 50.

［3］　
乔社茹. 苹果叶部病害的识别与防治［J］. 山西林业科技, 2020, 49(2): 55-57.

Qiao Sheru. Identification and control of apple leaf diseases ［J］. Shanxi Forestry Science and Technology, 2020, 49(2): 55-57.

［4］　
魏杨, 毕秀丽, 肖斌. 基于区域卷积神经网络的农业害虫检测方法［J］. 计算机科学, 2018, 45(z2): 226-229, 233.

Wei Yang, Bi Xiuli, Xiao Bin. Agricultural insect pest detection method based on regional convolutional neural network ［J］. Computer Science, 2018, 45(z2): 226-229, 233.

［5］　
张振华, 陆金桂. 基于改进卷积神经网络的混凝土桥梁裂缝检测［J］. 计算机仿真, 2021, 38(11): 490-494.

Zhang Zhenhua, Lu Jingui. Concrete bridge crack detection based on improved convolution neural network ［J］. Computer Simulation, 2021, 38(11): 490-494.

［6］　
娄茹珍, 徐丽, 蒋正乾, 等. 基于卷积神经网络的眼疾识别算法［J］. 无线电工程, 2021, 51(11): 1202-1207.

Lou Ruzhen, Xu Li, Jiang Zhengqian, et al. Eye disease recognition algorithm based on convolution neural network ［J］. Radio Engineering, 2021, 51(11): 1202-1207.

［7］　
傅云龙, 梁丹, 梁冬泰, 等. 基于机器视觉与YOLO算法的马铃薯表面缺陷检测［J］. 机械制造, 2021, 59(8): 82-87.

Fu Yunlong, Liang Dan, Liang Dongtai, et al. Potato surface defect detection based on machine vision and YOLO algorithm ［J］. Machinery, 2021, 59(8): 82-87.

［8］　
宋中山, 刘越, 郑禄, 等. 基于改进YOLOV3的自然环境下绿色柑橘的识别算法［J］. 中国农机化学报, 2021, 42(11): 159-165.

Song Zhongshan, Liu Yue, Zheng Lu, et al. Identification of green citrus based on improved YOLOV3 in natural environment ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(11): 159-165.

［9］　
Redmon J, Farhadi A. Yolov3: An incremental improvement ［J］. arXiv preprint arXiv: 1804.02767, 2018.

［10］　
周宏威, 沈恒宇, 袁新佩, 等. 基于迁移学习的苹果树叶片病虫害识别方法研究［J］. 中国农机化学报, 2021, 42(11): 151-158.

Zhou Hongwei, Shen Hengyu, Yuan Xinpei, et al. Research on identification method of apple leaf diseases based on transfer learning ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(11): 151-158.

［11］　
王云露, 吴杰芳, 兰鹏, 等. 基于改进Faster R-CNN的苹果叶部病害识别方法［J］. 林业工程学报, 2022, 7(1): 153-159.

Wang Yunlu, Wu Jiefang, Lan Peng, et al. Apple disease identification using improved Faster R-CNN ［J］. Journal of Forestry Engineering, 2022, 7(1): 153-159.

［12］　
伍济钢, 成远, 邵俊, 等. 基于改进YOLOv4算法的PCB缺陷检测研究［J］. 仪器仪表学报, 2021, 42(10): 171-178.

Wu Jigang, Cheng Yuan, Shao Jun, et al. A defect detection method for PCB based on the improved YOLOv4 ［J］. Chinese Journal of Scientific Instrument, 2021, 42(10): 171-178.

［13］　
Huang G, Liu Z, Van DerMaaten L, et al. Densely connected convolutional networks ［C］. IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4700-4708.

［14］　
郭玥秀, 杨伟, 刘琦, 等. 残差网络研究综述［J］. 计算机应用研究, 2020, 37(5): 1292-1297.

Guo Yuexiu, Yang Wei, Liu Qi, et al. Survey of residual network ［J］. Application Research of Computers, 2020, 37(5): 1292-1297.

［15］　
He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition ［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 37(9): 1904-1916.

［16］　
Liu S, Qi L, Qin H, et al. Path aggregation network for instance segmentation ［C］. IEEE Conference on Computer Vision and Pattern Recognition. 2018: 8759-8768.

［17］　
Dubey S R, Singh S K, Chaudhuri B B. A Comprehensive Survey and Performance Analysis of Activation Functions in Deep Learning［J］. arXiv preprint arXiv:2109.14545, 2021.

［18］　
杨俊闯, 赵超. K-Means聚类算法研究综述［J］. 计算机工程与应用, 2019, 55(23): 7-14, 63.

Yang Junchuang, Zhao Chao. Survey on K-Means clustering algorithm ［J］. Computer Engineering and Applications, 2019, 55(23): 7-14, 63.

［19］　
钱小梅, 刘嘉勇, 程芃森. 基于密集连接卷积神经网络的远程监督关系抽取［J］. 计算机科学, 2020, 47(2): 157-162.

Qian Xiaomei, Liu Jiayong, Cheng Pengsen. Distant supervised relation extraction based on densely connected convolutional networks ［J］. Computer Science, 2020, 47(2): 157-162.

[1]	陈文, 余康, 李岩舟, 陈远玲, 胡珊珊, 乔曦. 基于网络瘦身算法的YOLOv4-tiny的甘蔗茎节识别[J]. 中国农机化学报, 2023, 44(2): 172-181.
[2]	韦锦, 李正强, 许恩永, 蒙艳玫, 韦和钧, 武豪. 基于DA2-YOLOv4算法绿篱识别研究[J]. 中国农机化学报, 2022, 43(9): 122-130.
[3]	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.
[4]	张磊, 刘琪芳, 聂红玫, 王晨, 牛帆. 基于改进YOLOV4网络模型的番茄果实检测[J]. 中国农机化学报, 2022, 43(12): 162-169.
[5]	李威, 李尚平, 潘家枫, 李凯华, 闫昱晓. 基于机器学习的中耕期甘蔗幼苗识别定位^*[J]. 中国农机化学报, 2021, 42(11): 130-137.