English

中国农机化学报

中国农机化学报 ›› 2021, Vol. 42 ›› Issue (8): 169-176.DOI: 10.13733/j.jcam.issn.2095-5553.2021.08.23

• 中国农机化学报 • 上一篇    下一篇

基于深度学习的月季多叶片病虫害检测研究

李子茂;刘恋冬;夏梦;帖军;张玥;   

  1. 中南民族大学计算机科学学院;湖北省制造企业智能管理工程技术研究中心;
  • 出版日期:2021-08-15 发布日期:2021-08-15
  • 基金资助:
    湖北省技术创新专项重大项目(2019ABA101)

 Detection of rose diseases and insect pests based on deep learning

Li Zimao, Liu Liandong, Xia Meng, Tie Jun, Zhang Yue.    

  • Online:2021-08-15 Published:2021-08-15

摘要: 月季病虫害严重影响月季产量和观赏性,将目标检测算法应用到月季病虫害检测中有利于提高月季病虫害检测效率,对实现月季智能化种植培育起到重要支撑作用。针对实际种植场景中复杂背景对病虫害检测的影响,以及病虫害形状大小特点,提出两阶段月季病虫害检测方法TSDDP,首先添加调优后的Inception模块改进YOLOv3模型特征提取与融合能力对自然环境下拍摄的月季多叶片图像进行叶片检测,去除复杂背景中存在的影响因素,然后通过K-means聚类Anchor box优化Faster R-CNN以满足月季病虫害目标检测需求,基于叶片检测结果对叶片病虫害进行检测。通过比较YOLOv3、Faster R-CNN和TSDDP对自然环境下的月季多叶片病虫害检测效果,试验结果表明TSDDP的检测精度和定位准确度均高于其他算法,最终病虫害平均检测精度达到82.26%,有效减少复杂背景造成误检的同时改善小尺度病虫害的检测和定位效果。

关键词: 病虫害检测, YOLOv3, 特征融合, Faster R-CNN

Abstract:  Diseases and insect pests of roses seriously affect the yield and ornamental value. The application of a target detection algorithm in the detection of rose diseases and insect pests is conducive to improve the detection efficiency and plays an important role in the realization of the intelligent cultivation of roses. In view of the influence of complex background on the detection of diseases and insect pests in the actual planting scene, a twostage rose pest detection method TSDDP was proposed in this paper. Firstly, the optimized Inception module was added to improve the ability of feature extraction and fusion of YOLOv3 model. The leaf detection of multileaf images of roses in the natural environment was carried out to remove the shadow in the complex background. Then, Faster RCNN was optimized by Kmeans clustering Anchor box to meet the needs of target detection of rose diseases and insect pests. By comparing the detection effects of YOLOv3, Faster RCNN, and TSDDP in the natural environment, the results showed that the detection accuracy and positioning accuracy of TSDDP were higher than other algorithms, and the final average detection accuracy of pests and diseases reached 82.26%. This can effectively reduce the false detection caused by complex backgrounds and improve the detection and location effect of smallscale diseases and insect pests.

Key words: diseases and pests detection, YOLOv3, feature fusion, Faster RCNN

中图分类号: