Extraction of maize lodging range from remote sensing image based on canopy height model
Accurate extraction of maize lodging area is the basis of accurate field management and estimation of maize yield loss, and the remote sensing image acquired by UAV is flexible, which is a popular method for crop lodging measurement. However, most of the existing researches use spectral and texture features, which are easily affected by shooting time, terrain, angle and so on. The method of extracting maize lodging range based on canopy height difference is developed by using unmanned technology. Firstly, the background soil distribution is extracted by the visible light band differential vegetation index. And then the height of maize is extracted. Finally, the maize lodging range is extracted based on SVM and OSTU automatic threshold method. The experimental results show that the classification accuracy of SVM for three samples is 88. 84％,89. 52％ and 90. 80％,respectively, and for OSTU automatic threshold method is 94. 61％,89. 74％ and 97. 20％,respectively, which is slightly better than the former. In this study, crop lodging is extracted based on crop height as a structural parameter. The mechanism is clear and the effect of UAV imaging instability is eliminated to some extent.
万方数据
维普
