欢迎访问《图学学报》 分享到：
图学学报

图学学报 ›› 2021, Vol. 42 ›› Issue (3): 454-461.DOI: 10.11996/JG.j.2095-302X.2021030454

• 图像处理与计算机视觉 • 上一篇    下一篇

AR 辅助的基于 HOG-SVM 移动水稻病害智能分析与识别系统

  

  1. 1. 上海市农业科学院农业科技信息研究所，上海 201403； 2. 上海数字农业工程与技术研究中心，上海 201403；  3. 同济大学软件学院，上海 201804； 4. 南昌航空大学信息工程学院，江西 南昌 330063
  • 出版日期:2021-06-30 发布日期:2021-06-29
  • 基金资助:
    上海市农业科学院卓越团队建设项目(2017[B-09]) 

AR-assisted intelligent analysis and identification system for mobile rice diseases based on HOG-SVM 

  1. 1. Institute of Agricultural Information Science and Technology, Shanghai Academy of Agricultural Sciences, Shanghai 201403, China;  2. Shanghai Engineering and Technological Research Center for Digital Agriculture, Shanghai 201403, China;  3. School of Software Engineering, Tongji University, Shanghai 201804, China;  4. School of Information Engineering, Nanchang Hangkong University, Nanchang Jiangxi 330063, China
  • Online:2021-06-30 Published:2021-06-29
  • Supported by:
    Shanghai Academy of Agricultural Sciences for the Program of Excellent Research Team (2017[B-09])

PDF (PC)

163

摘要： 针对传统病害识别系统存在拍摄环境要求高、样本数量要求多的缺点，设计了一套增强现实（AR） 辅助的基于方向梯度直方图(HOG)-支持向量机(SVM)的识别方案。在较少素材量的前提下，由于诊断系统中引入 AR 技术辅助拍摄，在训练时长、识别速度以及平均精度上优于其他方法。以安卓终端为例，实现了 AR 辅助基 于 HOG-SVM 的移动水稻病害识别系统，能够快速识别病害指导用户提高拍摄图片的质量。通过对批量图片进行 病斑识别，分别从病害准确率、病害叶片检出率和病斑定位准确率 3 方面对病斑识别结果进行分析，最终得出， AR 技术与基于 HOG-SVM 快速识别方案的结合能够在小训练样本前提下给出更快的训练结果和识别结果，且平 均精度高于 YOLO v3，SSD 512 和 Fast R-CNN 等深度模型，是一种比较合适目前移动端病害识别的方法。

关键词: 增强现实, 方向梯度直方图, 支持向量机, 水稻, 病害识别

Abstract: For the shortcomings of traditional disease recognition systems that require high altitude in a shooting environment and large numbers of samples, this research designed a set of f augmented reality (AR)-assisted recognition schemes based on histograms of oriented gradient (HOG)-support vector machine (SVM). Under the premise of a small amount of materials, this solution, which introduced AR technology in the diagnostic system for shooting assistance, outperforms other methods in terms of training time, recognition speed, and average accuracy. Taking the Android terminal as an example, an AR-assisted HOG-SVM-based mobile rice disease identification system was implemented, which can quickly identify diseases and guide users to improve the quality of photographed pictures. Through the identification of disease spots in batches of images, the results of disease spot recognition were analyzed from three aspects: disease accuracy, diseased leaf detection rate, and disease spot location accuracy. Finally, AR technology and rapid identification scheme based on HOG-SVM were obtained. This combination can generate faster training results and recognition results under the premise of small training samples. The average accuracy of this system is also higher than that of deep models such as YOLO v3, SSD 512, and Fast R-CNN. The proposed method is more practicable for disease identification on the current mobile terminal. 

Key words: augmented reality, histograms of oriented gradient, support vector machine, rice, disease recognition 

中图分类号: