一种YOLOv5-DK的柠檬初期病虫害检测算法研究

doi:10.13733/j.jcam.issn.2095-5553.2024.07.037

摘要/Abstract

摘要： 为解决柠檬初期病虫害特征部位小难以检测和可以利用数据集较少的问题，提出一种YOLOv5-DK检测算法。该算法是以YOLOv5为基础，采用K-Means++重新聚类柠檬初期虫害部位锚框，缓解柠檬初期虫害特征小的问题；同时提出一种新的轻量化Denseneck-2模块，该模块是利用DenseNet网络中复用的思想，让检测算法每一层输入都有前面每一层的特征信息，使得YOLOv5-DK对柠檬初期病虫害样本量的需求下降。与原始的YOLOv5检测算法相比较，新的YOLOv5-DK检测算法在检测的平均精度上面提高3.4%，漏检率下降2.1%，算法模型的参数量减轻6.3%，表明该算法在小样本和小目标的应用场景下性能更优。

关键词: 柠檬, 初期病虫害, 轻量化, 小样本, 小目标

Abstract: In order to solve the problems that the characteristic parts of insect pests in the early stage of lemon were too small and difficult to detect along with the limited data sets, a YOLOv5-DK detection algorithm was proposed. The algorithm was based on YOLOv5, and adopted K-Means++ to recluster the anchor frame of the initial pest location of lemon, alleviating the problem of small pest characteristics at the initial stage of lemon. Meanwhile, a new lightweight Denseneck-2 module was proposed, which applied the idea of reuse in the DenseNet network, so that the input of each layer of the detection algorithm had the characteristic information of each layer in front of it, which decreased the YOLOv5-DK demand on the initial sample volume of insect pests of lemons. The new YOLOv5-DK detection algorithm demonstrated higher competencies than the original one, including an increase of 3.4% in the average accuracy of detection, a decrease of 2.1% in the missed detection rate, and a reduction of 6.3% in the number of parameters of the algorithm model. These results showed that the algorithm performed better in the application of small samples and small targets.

Key words: lemon, initial pests and diseases, lightweight, small sample, small target

中图分类号:

熊志刚, 陈为真. 一种YOLOv5-DK的柠檬初期病虫害检测算法研究[J]. 中国农机化学报, 2024, 45(7): 249-254.

Xiong Zhigang, Chen Weizhen. Study on a YOLOv5-DK algorithm for lemon initial pests and diseases detection[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(7): 249-254.

参考文献

［1］　朱春华, 周先艳, 李进学, 等. 中国柠檬主要营养功效及产品开发研究进展［J］.包装与食品机械, 2018, 36(3): 48-53.
［2］　Liu J, Wang X. Plant diseases and pests detection based on deep learning: A review ［J］. Plant Methods, 2021, 17: 1-18.
［3］　Kumar S, Kaur R. Plant disease detection using image processinga review ［J］. International Journal of Computer Applications, 2015, 124(16): 6-9.
［4］　刘洪江, 王懋, 刘丽华, 等. 基于深度学习的小目标检测综述［J］. 计算机工程与科学, 2021, 43(8): 1429-1442.
Liu Hongjiang, Wang Mao, Liu Lihua, et al.A survey of small object detection based on deep learning ［J］. Computer Engineering & Science, 2021, 43(8): 1429-1442.
［5］　Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, realtime object detection ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
［6］　Redmon J, Farhadi A. YOLO9000: Better, faster, stronger［C］.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.
［7］　Redmon J, Farhadi A. YOLOv3: An incremental improvement ［J］. ArXiv Preprint ArXiv: 1804.02767, 2018.
［8］　Bochkovskiy A, Wang C Y, Liao H Y M. Yolov4: Optimal speed and accuracy of object detection ［J］. ArXiv Preprint ArXiv: 2004.10934, 2020.
［9］　Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector ［C］. Proceedings of the 14th European Conference on Computer Vision. Berlin, Germany: Springer Verlag, 2016: 21-37.
［10］　Wang X, Liu J, Zhu X. Early realtime detection algorithm of tomato diseases and pests in the natural environment ［J］. Plant Methods, 2021, 17(1): 1-17.
［11］　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(09): 195-201， 208.
［12］　Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
［13］　Girshick R. Fast R-CNN ［C］. Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
［14］　Ren S, He K, Girshick R, et al. Faster R-CNN: Towards realtime object detection with region proposal networks ［J］. Advances in Neural Information Processing Systems, 2015, 28.
［15］　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, Zheng 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.
［16］　Liu S, Qi L, Qin H, et al. Path aggregation network for instance segmentation ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8759-8768.
［17］　Rezatofighi H, Tsoi N, Gwak Jy, et al. Generalized intersection over union: A metric and a loss for bounding box regression ［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 658-666.
［18］　He K, Zhang X, Ren S, et al. Deep residual learning for image recognition ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
［19］　Huang G, Liu Z, Maaten L, et al. Densely connected convolutional networks ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4700-4708.
［20］　Parraga Alava J, Alcivar Cevallos R, Morales Carrillo J, et al. LeLePhid: An image dataset for aphid detection and infestation severity on lemon leaves ［J］. Data, 2021, 6(5): 51.

[1]	吴利刚, 吕媛媛, 周倩, 陈乐, 张梁, 史建华. 基于改进YOLOv5的轻量级黄花成熟检测方法[J]. 中国农机化学报, 2024, 45(7): 235-242.
[2]	周康乔, 刘向阳, 郑特驹. 改进YOLOv5的小目标多类别农田害虫检测算法研究[J]. 中国农机化学报, 2024, 45(6): 235-241.
[3]	漆海霞, , , 李承杰, 黄桂珍. 基于轻量化YOLOv4的死淘鸡目标检测算法[J]. 中国农机化学报, 2024, 45(5): 195-201.
[4]	向浩, 高巧明, 韦增健, 许鹏, 曾俊豪, 赵鹏飞. 山地模块化电动底盘的同侧输出行星减速器设计[J]. 中国农机化学报, 2023, 44(8): 133-140.
[5]	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.
[6]	黄大伟, 郭成荣, 傅爱军, 田永康, 龚运息. 基于多工况的畜禽运输车车厢骨架优化设计[J]. 中国农机化学报, 2023, 44(10): 137-143.
[7]	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.
[8]	王江晴, 冀星, 莫海芳, 帖军, 刘畅, . 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.
[9]	苏斐, 张泽旭, 赵妍平, 李天华, 祖林禄, . 基于轻量化YOLO⁃v3的绿熟期番茄检测方法[J]. 中国农机化学报, 2022, 43(3): 132-137.
[10]	刘泽松, 王浩屹, 李骅, 王永健, 丁元庚, 曾晓萍. 基于有限元的大蒜播种机机架轻量化设计[J]. 中国农机化学报, 2022, 43(1): 27-32.
[11]	任帅阳, 高爱民, 张勇, 韩伟, . 六旋翼植保无人机旋翼折叠机构有限元分析及拓扑优化[J]. 中国农机化学报, 2021, 42(9): 53-58+194.
[12]	杨桃月;顾苑婷;舒成松;曹阳;张大斌;. 烟秆拔秆破碎机机架轻量化设计与随机振动疲劳分析[J]. 中国农机化学报, 2021, 42(5): 100-106.
[13]	冯叶陶;廖敏;张小军;张涛;潘群林;. 丘陵山地拖拉机前驱动桥壳组件轻量化设计与试验研究[J]. 中国农机化学报, 2021, 42(5): 107-113.
[14]	陆雅诺;陈炳才;. 基于注意力机制的小样本啤酒花病虫害识别[J]. 中国农机化学报, 2021, 42(3): 189-196.
[15]	肖伟, 冯全, 张建华, 杨森, 陈佰鸿. 基于小样本学习的植物病害识别研究^*[J]. 中国农机化学报, 2021, 42(11): 138-143.