论文部分内容阅读
为了快速准确地获取黄瓜叶片的含氮量和叶面积指数等生长信息,提出了采用多光谱图像技术对黄瓜生长信息进行检测的新方法。利用标定板建立黄瓜叶片光谱反射率同图像灰度值之间的线性公式。通过多光谱相机对样本在绿光、红光和近红外三个通道的图像进行处理,获得叶片样本在每一通道的灰度值,然后根据标定板所建立的灰度值与反射率间的经验线性公式将对应的灰度值转为反射率值,并由反射率值计算出黄瓜的植被指数。采用最小二乘-支持向量机(LS-SVM)建立植被指数同叶片含氮景以及叶面积指数问的拟合模型。结果表明植被指数同叶片含氮量和叶面积指数的拟合相关系数分别为0.8665和0.8553。表明植被指数与黄瓜的叶片含氮量和叶面积指数具有紧密的相关性,也为快速采集黄瓜生长信息提供了一种新方法。
In order to quickly and accurately obtain the growth information of cucumber leaves such as nitrogen content and leaf area index, a new method for detecting cucumber growth information using multispectral image technology was proposed. The linear formula between the spectral reflectance of cucumber leaves and the gray value of the image was established by using the calibration plate. The multi-spectral camera is used to process the samples in the green, red and near infrared channels, and the gray value of each sample in the leaf sample is obtained. Based on the gray value and reflectivity The empirical linear formula converts the corresponding gray values into reflectance values and the cucumber index of vegetation from the reflectance values. A fitting model of vegetation index with leaf nitrogen content and leaf area index was established by least square support vector machine (LS-SVM). The results showed that the correlation coefficients between vegetation index and leaf nitrogen content and leaf area index were 0.8665 and 0.8553, respectively. The results showed that there was a close correlation between vegetation index and leaf nitrogen content and leaf area index of cucumber, which provided a new method for rapid collection of cucumber growth information.