基于改进YOLOv5的草莓病害智能识别终端设计

doi:10.13733/j.jcam.issn.2095-5553.2024.03.028

摘要/Abstract

摘要： 为实现低成本、便捷、高效的草莓病害识别与检测，提升草莓种植与生产效益，在YOLOv5模型基础上，引入高效通道注意力(Efficient Channel Attention，ECA)机制，研究构建一种草莓病害识别模型，应用嵌入式与软件工程技术研发草莓病害识别终端设备。终端设备应用系统由图像采集、图像检测、检测结果展示和数据传输等模块组成，实现草莓图像实时采集和病害实时识别检测等功能。基于草莓病害检测数据集对系统开展测试，结果表明，该系统可以有效识别草莓白粉菌果病、角斑病、叶斑病等病害。与YOLOv5相比，AP0.5∶0.95、AP0.5、AP0.75、APM、APL都有比较大幅度提升。系统具有高效、便捷、实时等优点，可广泛应用于草莓生产领域，从而有效提升草莓病害识别与检测效率。

关键词: 草莓病害, YOLOv5, 图像检测, 嵌入式, 模型识别

Abstract: In order to achieve lowcost, convenient, and efficient identification and detection of strawberry diseases, and improve the efficiency of strawberry planting and production, based on YOLOv5 model, an efficient channel attention (ECA) mechanism was introduced to study and construct a strawberry disease recognition model. The embedded and software engineering technology was applied to develop and implement a strawberry disease recognition terminal device. The system consisted of modules such as image acquisition, image detection, display of detection results, and data transmission. The system realized realtime collection of strawberry images and disease identification and checking functions. The system was tested using Kaggles strawberry disease detection dataset, and the experimental results showed that the system could effectively identify diseases such as strawberry powdery mildew fruit, and strawberry corner spot, and leaf spot. And compared with YOLOv5, there is a significant improvement in AP0.5∶0.95、AP0.5、AP0.75、APM、APL. The system has the advantages of efficiency, convenience, and realtime online, which can be widely applied in the field of strawberry production, thereby effectively improving the efficiency of strawberry disease identification and detection.

Key words: strawberry diseases, YOLOv5, image detection, embedded, model identification

中图分类号:

乔珠峰, , 赵秋菊, , 郭建鑫, , 陈会娜, , 平阳, , 赵继春, . 基于改进YOLOv5的草莓病害智能识别终端设计[J]. 中国农机化学报, 2024, 45(3): 205-211.

Qiao Zhufeng, , Zhao Qiuju, , Guo Jianxin, , Chen Huina, , Ping Yang, , Zhao Jichun, . Design of strawberry disease intelligent identification terminal based on improved YOLOv5[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(3): 205-211.

参考文献

［1］　郭文娟, 冯全, 李相周. 基于农作物病害检测与识别的卷积神经网络模型研究进展［J］. 中国农机化学报, 2022, 43(10): 157-166.
Guo Wenjuan, Feng Quan, Li Xiangzhou. Research progress of convolutional neural network model based on crop disease detection and recognition ［J］. Journal of Chinese Agricultural Mechanization, 2022, 43(10): 157-166.
［2］　Pydipati R, Burks T F, Lee W S. Identification of citrus disease using color texture features and discriminant analysis ［J］. Computers and Electronics in Agriculture, 2006, 52: 49-59.
［3］　Simonyan K, Zisserman A. Very deep convolutional networks for large scale image recognition ［J］. ArXiv Preprint, 2014.
［4］　Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions ［C］. Computer Vision and Pattern Recognition, Boston, 2015: 1-9.
［5］　He K M, Zhang X Y, Ren S O, et al. Deep residual leaning for image recognition ［C］. Computer Vision and Pattem Recognition Las Vegas, 2016: 770-778.
［6］　Huang G, Liu Z, MaatenL V D, et al. Densely connected convolutional networks ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
［7］　宋中山, 汪进, 郑禄, 等. 基于二值化的Faster RCNN柑橘病虫害识别研究［J］. 中国农机化学报, 2022, 43(6):150-158.
Song Zhongshan, Wang Jin, Zhen Lu, et al. Research on citrus pest identification based on Binary Faster RCNN ［J］. Journal of Chinese Agricultural Mechanization, 2022, 43(6): 150-158.
［8］　牛冲. 基于图像处理的草莓病害识别方法研究［D］. 太原: 太原理工大学, 2016.Niu Chong. Research on recognition method of strawberry disease based on image processing ［D］. Taiyuan: Taiyuan University of Technology, 2016.
［9］　宋怀波, 马宝玲, 尚钰莹, 等. 基于YOLO v7ECA模型的苹果幼果检测［J］. 农业机械学报, 2023, 54(6): 233-242.
Song Huaibo, Ma Baoling, Shang Yuying, et al. Detection of young apple fruits based on YOLO v7ECA model ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(6): 233-242.
［10］　郭辉, 陈海洋, 高国民, 等. 基于YOLO v5m的红花花冠目标检测与空间定位方法［J］. 农业机械学报, 2023, 54(7): 272-281.
Guo Hui, Chen Haiyang, Gao Guomin, et al. Safflower corolla object detection and spatial positioning methods based on YOLO v5m ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(7): 272-281.
［11］　邵延华, 张铎, 楚红雨, 等. 基于深度学习的YOLO目标检测综述［J］. 电子与信息学报, 2022, 44(10): 3697-3708.〖JP2〗Shao Yanhua, Zhang Duo, Chu Hongyu, et al. A review of YOLO object detection based on deep learning ［J］.〖JP〗 Journal of Electronics & Information Technology, 2022, 44(10): 3697-3708.
［12］　李成跃, 姚剑敏, 林志贤, 等. 基于改进YOLO轻量化网络的目标检测方法［J］. 激光与光电子学进展, 2020, 57(14): 45-53.Li Chengyue, Yao Jianmin, Lin Zhixian, et al. Object detection method based on improved YOLO lightweight network ［J］. Laser & Optoelectronics Progress, 2020, 57(14): 45-53.
［13］　崔家华, 张云洲, 王争, 等. 面向嵌入式平台的轻量级目标检测网络［J］. 光学学报, 2019, 39(4): 307-313.〖JP2〗Cui Jiahua, Zhang Yunzhou, Wang Zheng, et al. Lightweight object detection networks for embedded platform ［J］. Acta Optica Sinica, 2019, 39(4): 307-313.
［14］　李建, 杜建强, 朱彦陈, 等. 基于Transformer的目标检测算法综述［J］. 计算机工程与应用, 2023, 59(10): 48-64.Li Jian, Du Jianqiang, Zhu Yanchen, et al. Survey of transformerbased object detection algorithms ［J］. Computer Engineering and Applications, 2023, 59(10): 48-64.
［15］　Wang Q L. Wu B G, Zhu P F, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks ［J］. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020: 11531-11539.
［16］　Zhu X K, Lyu S C, Wang X, et al. TPHYOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on dronecaptured scenarios ［C］. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021: 2778-2788.
［17］　宋怀波, 李嵘, 王云飞, 等. 基于ECAYOLO v5s网络的重度遮挡肉牛目标识别方法［J］. 农业机械学报, 2023, 54(3): 274-281.
Song Haibo, Li Rong, Wang Yunfei, et al. Recognition method of heavily occluded beef cattle targets based on ECAYOLO v5s ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(3): 274-281.
［18］　王江晴, 冀星, 莫海芳, 等. 基于轻量化VGG的植物病虫害识别［J］. 中国农机化学报, 2022, 43(4): 25-31.
Wang Jiangqing, Ji Xing, Mo Haifang, et al. Plant disease detection based on lightweight VGG ［J］. Journal of Chinese Agricultural Mechanization, 2022,43(4):25-31.
［19］　李书琴, 陈聪, 朱彤, 等. 基于轻量级残差网络的植物叶片病害识别［J］. 农业机械学报, 2022, 53(3): 243-250.
Li Shuqin, Chen Cong, Zhu Tong, et al. Plant leaf disease identification based on lightweight residual network ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(3): 243-250.
［20］　李功, 赵巍, 刘鹏, 等. 一种用于目标跟踪边界框回归的光滑IoU损失［J］. 自动化学报, 2023, 49(2): 288-306.
Li Gong, Zhao Wei, Liu Peng, et al. SmoothIoU loss for bounding box regression in visual tracking ［J］. Acta Automatica Sinica, 2023, 49(2): 288-306.

[1]	邱畅, 田光兆, 赵嘉威, 谢尚杰, 郑奎. 基于改进YOLOv5的草莓病害识别[J]. 中国农机化学报, 2024, 45(3): 198-204.
[2]	缪亚伦, 石美琦, 孟海涛, 梁旭升, 黄才贵, 李岩舟. 基于Stereo CameraYOLOv5自然环境下百香果检测与定位模型[J]. 中国农机化学报, 2024, 45(3): 233-241.
[3]	叶荣, 马自飞, 高泉, 李彤, 邵郭奇, 王白娟. 基于改进YOLOv5sECAASFF算法的茶叶病害目标检测[J]. 中国农机化学报, 2024, 45(1): 244-251.
[4]	林森, , 许童羽, 葛禹豪, 马璟, 孙添龙, 赵春江. 基于改进YOLOv5l的设施番茄3D信息检测方法[J]. 中国农机化学报, 2024, 45(1): 274-284.
[5]	杨波, 何金平, 张立娜. 基于改进SPP-x的YOLOv5神经网络水稻叶片病害识别检测[J]. 中国农机化学报, 2023, 44(9): 190-197.
[6]	陈维美, 刘馨蔚, 王铁伟, 徐文凯, 李娟. 基于两级融合深度学习的松材线虫病识别[J]. 中国农机化学报, 2023, 44(7): 214-219.
[7]	李明, 丁智欢, 赵靖暄, 陈思铭, 李文勇, 杨信廷. 基于改进YOLOv5s的日光温室黄瓜霜霉病孢子囊检测计数方法[J]. 中国农机化学报, 2023, 44(5): 63-70.
[8]	李光明, 弓皓斌, 袁凯. 基于轻量化YOLOv5s的花椒簇检测研究[J]. 中国农机化学报, 2023, 44(4): 153-158.
[9]	王宇博, 马廷淮, 陈光明. 基于改进YOLOv5算法的农田杂草检测[J]. 中国农机化学报, 2023, 44(4): 167-173.
[10]	肖章, 彭江, 刘俊杰, 孙二杰, 彭如恕. 基于YOLOv5-CP的复杂环境下油茶果检测[J]. 中国农机化学报, 2023, 44(12): 193-199.
[11]	杨霄, 王朕, , 赵伟, 徐晶, 文玲梅, 徐敏. 鱼病实时检测系统的研制与试验[J]. 中国农机化学报, 2023, 44(11): 130-137.
[12]	肖克辉, , 杨宏, , 苏章顺, , 杨小丹, . 基于改进YOLOv5的蝴蝶兰花朵识别与计数[J]. 中国农机化学报, 2023, 44(11): 155-161.
[13]	胡奕帆, 赵贤林, 李佩娟, 赵辰雨, 陈光明. 基于改进YOLOv5的自然环境下番茄果实检测[J]. 中国农机化学报, 2023, 44(10): 231-237.
[14]	杨文姬, 胡文超, 赵应丁, 钱文彬. 基于改进Yolov5植物病害检测算法研究[J]. 中国农机化学报, 2023, 44(1): 108-115.
[15]	汪颖, 王峰, 李玮, 王艳艳, 王应彪, 罗鑫. 用于复杂环境下果蔬检测的改进YOLOv5算法研究[J]. 中国农机化学报, 2023, 44(1): 185-191.