基于图像识别的无人机精准喷雾控制系统的研究 |
| |
引用本文: | 王林惠,甘海明,岳学军,兰玉彬,王健,刘永鑫,凌康杰,岑振钊. 基于图像识别的无人机精准喷雾控制系统的研究[J]. 华南农业大学学报, 2016, 37(6): 23-30 |
| |
作者姓名: | 王林惠 甘海明 岳学军 兰玉彬 王健 刘永鑫 凌康杰 岑振钊 |
| |
作者单位: | 1. 华南农业大学电子工程学院,广东广州510642; 国际农业航空施药技术联合实验室/农业航空应用技术国际联合实验室/广东省农业航空应用工程技术研究中心,广东广州510642;2. 国际农业航空施药技术联合实验室/农业航空应用技术国际联合实验室/广东省农业航空应用工程技术研究中心,广东广州510642; 华南农业大学工程学院,广东广州510642 |
| |
基金项目: | 国家自然科学基金(41471351);华南农业大学校长基金(4500-K14018) |
| |
摘 要: | 【目的】针对传统的植保无人机喷雾作业时化肥农药浪费大,利用率低,造成环境污染的问题,研制一种基于图像识别的无人机精准喷雾控制系统。【方法】利用中值滤波算法对田间航拍图像进行去噪,采用分层K_means硬聚类算法实现对农田航拍图像的分割,提取非作物区域的颜色、纹理特征空间的22个特征参数,设计支持向量机分类器进行分类识别。根据优选的17个特征参数,利用以径向基函数作为核函数的支持向量机对非作物区域图像进行识别,并根据识别结果控制喷头,实现精准喷雾。【结果】测试样本的识别率可达为76.56%,在无干扰风场情况下,当P_阀为10%时,减施率可达32.7%。【结论】本系统为农业航空精准喷雾控制技术的应用提供了参考方向和决策支持。
|
关 键 词: | 支持向量机 无人机 图像识别 精准喷雾 |
收稿时间: | 2016-07-22 |
Design of a precision spraying control system with unmanned aerial vehicle based on image recognition |
| |
Affiliation: | 1 College of Electronic Engineering, South China Agricultural University, 2 International Laboratory of Agricultural Aviation Pesticide Spraying Technology/International Laboratory of Agriculture Aviation Applied Technology/Engineering Research Center for Agricultural Aviation Application of Guangdong Province,,1 College of Electronic Engineering, South China Agricultural University, 2 International Laboratory of Agricultural Aviation Pesticide Spraying Technology/International Laboratory of Agriculture Aviation Applied Technology/Engineering Research Center for Agricultural Aviation Application of Guangdong Province,,1 College of Electronic Engineering, South China Agricultural University, 2 International Laboratory of Agricultural Aviation Pesticide Spraying Technology/International Laboratory of Agriculture Aviation Applied Technology/Engineering Research Center for Agricultural Aviation Application of Guangdong Province,,2 International Laboratory of Agricultural Aviation Pesticide Spraying Technology/International Laboratory of Agriculture Aviation Applied Technology/Engineering Research Center for Agricultural Aviation Application of Guangdong Province, 3 College of Engineering, South China Agricultural University,,1 College of Electronic Engineering, South China Agricultural University, 2 International Laboratory of Agricultural Aviation Pesticide Spraying Technology/International Laboratory of Agriculture Aviation Applied Technology/Engineering Research Center for Agricultural Aviation Application of Guangdong Province,,1 College of Electronic Engineering, South China Agricultural University, 2 International Laboratory of Agricultural Aviation Pesticide Spraying Technology/International Laboratory of Agriculture Aviation Applied Technology/Engineering Research Center for Agricultural Aviation Application of Guangdong Province,,1 College of Electronic Engineering, South China Agricultural University, 2 International Laboratory of Agricultural Aviation Pesticide Spraying Technology/International Laboratory of Agriculture Aviation Applied Technology/Engineering Research Center for Agricultural Aviation Application of Guangdong Province, and 1 College of Electronic Engineering, South China Agricultural University, 2 International Laboratory of Agricultural Aviation Pesticide Spraying Technology/International Laboratory of Agriculture Aviation Applied Technology/Engineering Research Center for Agricultural Aviation Application of Guangdong Province, |
| |
Abstract: | Objective]In order to improve the efficiency and utilization of conventional unmanned aerial vehicle ( UAV) spraying in fertilizer and pesticide applications, an variable rate UAV spraying system was developed based on image recognition.[Method]Median filter was applied to the images for denois-ing.K_means clustering algorithm was then used to segment the UAV images to extract 22 texture features and the color of non-crop region.Support vector machine ( SVM) classifier was designed for classification.According to the 17 selected characteristic parameters, the non-crop region was recognized through the SVM classifier with Radial basis function ( RBF) as the kernel function.Finally, precision spraying was achieved with controllable nozzles based on the recognition results.[Result]The recognition accuracy reached up to 76.56%.In undisturbed wind farm, the reduction rate reached 32.7%with the threshold P of 10%.[Conclusion]This research can serve as reference guides for application of precise spraying control technology in agricultural aviation. |
| |
Keywords: | support vector machine unmanned aerial vehicle image recognition precision spray |
本文献已被 CNKI 万方数据 等数据库收录! |
| 点击此处可从《华南农业大学学报》浏览原始摘要信息 |
|
点击此处可从《华南农业大学学报》下载全文 |
|