改进YOLOv5算法的多类苹果叶片病害检测

doi:10.13733/j.jcam.issn.20955553.2024.12.034

摘要/Abstract

摘要：

针对多类苹果叶片病害准确率差异大、检测精度不高的问题，提出一种改进YOLOv5准确判别苹果叶片病害的检测算法(YOLOv5-CSEP)。首先，引入C3Ghost模块替换原YOLOv5主干网络C3模块，减少模型的参数量与计算量；其次，将混合注意力模块C-SAM加入主干网络中，提高主干网络的特征提取能力，在颈部网络中加入CA注意力模块，抑制复杂背景干扰关注目标信息；最后，引入增强型路径聚合网络(E-PANet)充分融合多尺度特征，提升网络对多类苹果叶片病害检测的准确性与鲁棒性。试验表明，改进后算法的各项性能指标均有提升，精确率达到93.2%，平均精度均值mAP@0.5达到87.9%，与原YOLOv5算法相比分别提高3.4%与1.7%，计算量减少11%。

关键词: 苹果叶片, 病害检测, 注意力机制, 增强路径聚合网络, YOLOv5

Abstract:

Aiming at the problems of large difference in accuracy and low detection accuracy of various types of apple leaf diseases, an improved YOLOv5 detection algorithm for accurate identification of apple leaf diseases (YOLOV5-CSEP) was proposed. Firstly, C3Ghost module was introduced to replace the C3 module of YOLOv5 backbone network to reduce the number of parameters and calculation amount of the model. Secondly, the hybrid attention module C-SAM was added to the backbone network to improve the feature extraction capability of the backbone network, and the CA attention module was added to the neck network to suppress the interference of complex background information. Finally, an enhanced path aggregation network (E-PANet) was introduced to fully integrate multi-scale features and improve the accuracy and robustness of the network to detect various types of apple leaf diseases. Experiments showed that all performance indexes of the improved algorithm were improved, the accuracy rate reached 93.2%, and the average accuracy (mAP@0.5) reached 87.9%. Compared with the original YOLOv5 algorithm, it was improved by 3.4% and 1.7% respectively, and the calculation amount was reduced by 11%.

Key words: apple tree leaf, disease detection, attention mechanism, enhanced path aggregation network, YOLOv5

中图分类号:

李昱达, 吴正平, 孙水发, 林淼, 伍箴燎, 沈虹杜. 改进YOLOv5算法的多类苹果叶片病害检测[J]. 中国农机化学报, 2024, 45(12): 230-237.

Li Yuda, Wu Zhengping, Sun Shuifa, Lin Miao, Wu Zhenliao, Shen Hongdu. Multi-species apple leaf disease detection with improved YOLOv5 algorithm[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(12): 230-237.

参考文献

［1］　任佳佳, 张朦朦, 李巍. 我国苹果区域分布特征及其供需优化分析［J］. 中国果树, 2023(5): 123-126.
Ren Jiajia, Zhang Mengmeng, Li Wei. Analysis on the regional distribution characteristics and supply and demand optimization of apple in China ［J］. China Fruits, 2023(5): 123-126.
［2］　Khan A I, Quadri S M K, Banday S, et al. Deep diagnosis: A realtime apple leaf disease detection system based on deep learning ［J］. Computers and Electronics in Agriculture, 2022, 198: 107093.
［3］　陈聪, 于啸, 宫琪. 基于改进残差网络的苹果叶片病害识别研究［J］. 河南农业科学, 2023, 52(4): 152-161.
Chen Cong, Yu Xiao, Gong Qi. Apple leaf diseases identification based on improved residual network ［J］. Journal of Henan Agricultural Sciences, 2023, 52(4): 152-161.
［4］　夏小雨, 韩成浩. 基于无人机的低空图像处理技术在农业领域的应用［J］. 农业与技术, 2023, 43(1): 38-41.
［5］　陈超, 齐峰. 卷积神经网络的发展及其在计算机视觉领域中的应用综述［J］. 计算机科学, 2019, 46(3): 63-73.
Chen Chao, Qi Feng. Review on development of convolutional neural network and its application in computer vision ［J］. Computer Science, 2019, 46(3): 63-73.
［6］　刘颖, 雷研博, 范九伦, 等. 基于小样本学习的图像分类技术综述［J］. 自动化学报, 2021, 47(2): 297-315.
Liu Ying, Lei Yanbo, Fan Jiulun, et al. Survey on image classification technology based on small sample learning ［J］. Acta Automatica Sinica, 2021, 47(2): 297-315.
［7］　Dubey S R, Jalal A S. Detection and classification of apple fruit diseases using complete local binary patterns ［C］. 2012 Third International Conference on Computer and Communication Technology. IEEE, 2012: 346-351.
［8］　Chakraborty S, Paul S, RahatuzZaman M. Prediction of apple leaf diseases using multiclass support vector machine ［C］. 2021 2nd International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST). IEEE, 2021: 147-151.
［9］　Zhang Chuanlei, Zhang Shanwen, Yang Jucheng, et al. Apple leaf disease identification using genetic algorithm and correlation based feature selection method ［J］. International Journal of Agricultural and Biological Engineering, 2017, 10(2): 74-83.
［10］　Khan M A, Lali M I U, Sharif M, et al. An optimized method for segmentation and classification of apple diseases based on strong correlation and genetic algorithm based feature selection ［J］. IEEE Access, 2019, 7: 46261-46277.
［11］　Jiang P, Chen Y, Liu B, et al. Realtime detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks ［J］. IEEE Access, 2019, 7: 59069-59080.
［12］　赵嘉威, 田光兆, 邱畅, 等. 基于改进YOLOv4算法的苹果叶片病害检测方法［J］. 江苏农业科学, 2023, 51(9): 193-199.
Zhao Jiawei, Tian Guangzhao, Qiu Chang, et al. Detection method of apple leaf diseases based on improved YOLOv4 algorithm ［J］. Jiangsu Agricultural Sciences, 2023, 51(9): 193-199.
［13］　曾晏林, 贺壹婷, 蔺瑶, 等. 基于BCE-YOLOv5的苹果叶部病害检测方法［J］. 江苏农业科学, 2023, 51(15): 155-163.
Zeng Yanlin, He Yiting, Lin Yao, et al. An apple leaf disease detection method based on BCE-YOLOv5 ［J］. Jiangsu Agricultural Sciences, 2023, 51(15): 155-163.
［14］　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.
［15］　金鑫, 庄建军, 徐子恒. 轻量化YOLOv5s网络车底危险物识别算法［J］. 浙江大学学报(工学版), 2023, 57(8): 1516-1526.
Jin Xin, Zhuang Jianjun, Xu Ziheng. Lightweight YOLOv5s networkbased algorithm for identifying hazardous objects under vehicles ［J］. Journal of Zhejiang University (Engineering Science), 2023, 57(8): 1516-1526.
［16］　Han K, Wang Y, Tian Q, et al. GhostNet: More features from cheap operations ［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 1580-1589.
［17］　Liu G, Hu Y, Chen Z, et al. Lightweight object detection algorithm for robots with improved YOLOv5 ［J］. Engineering Applications of Artificial Intelligence, 2023, 123: 106217.
［18］　Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design ［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 13713-13722.
［19］　Yang L, Zhang R Y, Li L, et al. SimAM: A simple, parameterfree attention module for convolutional neural networks ［C］. International Conference on Machine Learning. PMLR, 2021: 11863-11874.

[1]	韩鹏飞, 宋其江, 贾梦实. 基于改进轻量化 EfficientNet-V2模型的小麦种子分类[J]. 中国农机化学报, 2024, 45(9): 111-117.
[2]	张传栋, 亓璐, 丁华立. 基于改进 YOLOv8n模型的多品种葡萄簇检测方法[J]. 中国农机化学报, 2024, 45(9): 220-226.
[3]	宋立航, 张屹, 时寅豪. 基于改进 YOLOv5s的自然环境下油桃成熟度检测方法[J]. 中国农机化学报, 2024, 45(9): 250-257.
[4]	赵晓霞, 程曼, 袁洪波. 基于StrongSORT算法的羊只多目标跟踪方法[[J]. 中国农机化学报, 2024, 45(8): 180-188.
[5]	李洁, 高尚兵, 余骥远, 陈新, 李士丛, 袁星星. 基于PMMS-Net和叶绿素荧光成像的绿豆叶斑病抗性鉴定方法[J]. 中国农机化学报, 2024, 45(8): 210-216.
[6]	许贞辉, 李晓娟. 果园树干检测与导航线拟合算法研究[J]. 中国农机化学报, 2024, 45(8): 217-222.
[7]	刘星, 顾寄南, 黄则栋, 张文浩, 张伟. 基于深度学习的苹果点云语义分割方法研究[J]. 中国农机化学报, 2024, 45(8): 223-227.
[8]	苏斐, 王光辉, 史艳霞, 贾然, 闫银发, 祖林禄, . 融合通道注意力机制的ResUnet作物病斑分割模型[J]. 中国农机化学报, 2024, 45(8): 228-233.
[9]	胡国玉, 刘广, 周星光, 董娅兰, 周建平, . 基于Swin-TDL算法的果园环境下葡萄病害检测方法[J]. 中国农机化学报, 2024, 45(8): 234-239.
[10]	冯晓, 张辉, 刘运超, 张微, 李小红, 马中杰, . 基于改进YOLOv5s的硬核期葡萄簇检测[J]. 中国农机化学报, 2024, 45(8): 240-245.
[11]	周思捷, 刘天奇, 陈天华. 基于改进YOLOv5算法的水稻病害识别研究[J]. 中国农机化学报, 2024, 45(8): 246-253.
[12]	王克涛, 陈世锋, 陈贵, 韦锦, 蒙丽雯, 陈泉成. 基于YOLOv5s的园林球形绿篱检测方法[J]. 中国农机化学报, 2024, 45(8): 262-269.
[13]	李显娜, 吴强, 张一丹, 周康. 自监督学习下小样本番茄叶片病害检测[J]. 中国农机化学报, 2024, 45(7): 172-179.
[14]	岳耀华, 张伟, 亓立强, . 基于改进YOLOv5的田间大豆花朵生长状态检测方法研究[J]. 中国农机化学报, 2024, 45(7): 188-193.
[15]	黄晓宇, 张聪, 陈晓玲. 融合多尺度特征的遮挡番茄病害图像识别研究[J]. 中国农机化学报, 2024, 45(7): 194-200.