冬小麦病虫害的高光谱识别方法研究

为探讨冬小麦病虫害的高光谱遥感识别的可行性,在冬小麦白粉病、条锈病人工接种诱发和麦长管蚜自然危害条件下,利用ASD手持式高光谱仪,测定了冬小麦的田间光谱反射率,并经一阶微分、对数及归一化等数据变换,通过逐步判别、线性判别和分层聚类等方法时不同病虫害进行识别.结果表明,利用逐步判别分析法选择的重要波段主要位于蓝绿区和红边区及近红外区;分层聚类法选择的波段除了常规波段外,还有红、绿波段边缘区.利用上述方法选择的波段对病虫害进行识别比原始波段具有更高的精度(90.6%),边缘区波段对病虫害的识别有重要作用,用对教-微分变换处理较其他方法处理对病虫害识别有更好的效果.

Identification of Damage by Diseases and Insect Pests in Winter Wheat

Crop diseases and insect pests were an important factors in crop growth, yield and quality. Non destructive monitoring of crop diseases and insect pests was a basis of dynamic management by remote sensing technology. The canopy reflectance of wheat powdery mildew, wheat stripe rust and aphid were measured by using ASD hand held spectroradiometers. The reflectance data was transformed by the method of the first differential coefficient, logarithm and normalization, then stepwise discriminate analysis and hierarchical clustering were used to identify the difference in plant diseases and insect pests. The results suggested that bands selected from stepwise discrimination analysis mainly lied along the blue, green, red and near infrared bands. In addition to the blue, green, red and near infrared bands, the spectral bands along the blue green edge, green red edge and red curves were selected by the hierarchical clustering. Plant diseases and insect pests could be identified more accurately by using selected bands than the original data, with maximum identification accurate up to 90.6%, and the bands lying along the edges had important information for discrimination of plant diseases and pests. The spectral data, dealt with the transformation of logarithm and differential coefficient, could achieve better accuracy than others.