作物叶面积快速检测系统的构建及其检测效果的研究  

Construction of Crop Leaf Area Detection System And Its Detection Effect

作　　者：倪蕴琪 王笑语 王敏娟 Ni Yunqi;Wang Xiaoyu;Wang Minjuan(College of Food Science and Nutritional Engineering,China Agricultural University,Beijing 100083,China;College of Information and Electrical Engineering,China Agricultural University,Beijing 100083,China;College of Information Science and Engineering,Shandong Agriculture and Engineering University,Jinan 250100,Shandong,China)

机构地区：[1]中国农业大学食品科学与营养工程学院,北京100083 [2]中国农业大学信息与电气工程学院,北京100083 [3]山东农业工程学院信息科学与工程学院,山东济南250100

出　　处：《农业技术与装备》2020年第11期9-11,13,共4页Agricultural Technology & Equipment

摘　　要：作物叶面积指数是重要的植物信息,是一种重要的生理特征和物理参数。文章旨在设计一套快速图像采集系统及叶面积测定系统,使用Python和Open CV对图像进行处理,实现对叶面积的快速测定,并对叶面积的检测结果进行实验,实验表明:2种轮廓处理算子——Roberts算子和Scharr算子的测量误差均在3.00%之内。当手机和目标物的距离为300 mm时,测量误差大于5.00%;在400 mm时,测量误差在5.00%~3.00%;当超过500 mm时,误差稳定且小于3.00%。同时对多个拍摄偏转角度进行检测,并用多种形状的几何图像模拟了不同形状的叶片进行了面积测量,误差均在5.00%以内,可满足大多数情况下的叶面积测量应用。Leaf area index(LAI) is an important plant information, physiological characteristic and physical parameter. This paper aims to design a set of fast image acquisition system and leaf area measurement system. Using Python and Open CV to accept and process the image, the leaf area can be quickly measured. The experimental results show that the measurement errors of Roberts operator and Scharr operator are within 3%. When the distance between the mobile phone and the target is 300 mm, the measurement error is more than 5%;when the distance is 400 mm, the measurement error is between 5% and 3%;when the distance is more than 500 mm, the error is stable and less than 3%. At the same time, the measurement of the area of the blades with different shapes is simulated by the geometrical images of different shape, and the error is less than 5%. So it can meet the application of the measurement of the leaf area in most cases.

关 键 词：叶面积检测 OPENCV PYTHON 

分 类 号：S2[农业科学—农业工程]