| Winter wheat is the main crop in my country.How to monitor its growth in real time and provide it with the best growth conditions in time and accurately is the main topic of today’s smart agriculture research.There are many varieties of winter wheat in my country.Different varieties of winter wheat have different requirements for water,soil fertility,climate,etc.in each phenological phase of their growth.Therefore,independent identification of winter wheat varieties and distinguishing different winter wheat categories are the basis for realizing winter wheat smart production.The spectral characteristics of different varieties of winter wheat are very similar,which is a typical problem of weak inter-class characteristics.It is quite challenging to classify them with remote sensing methods.UAV hyperspectral remote sensing organically combines high spatial resolution and high spectral resolution to truly realize ‘space-spectrum integration’,which provides the possibility to solve this problem.To this end,this paper aims at the refined classification of different varieties of winter wheat,integrates UAV and UHD185 hyperspectral camera into a hyperspectral remote sensing system,takes Henan Wuzhi Winter Wheat Research Base as the experimental area,and first obtains the hyperspectral data of the experimental area.Then conduct experimental research on the splicing and dimensionality reduction methods of the original hyperspectral data,and finally introduce the machine learning and deep learning theories to study the refined classification methods of different varieties of winter wheat,in order to provide reference for the precise management of winter wheat and the classification of weak feature differences..The main work and conclusions of this paper are as follows:(1)Integrating DJI M600 UAV and Cubert UHD185 hyperspectral camera to form a UAV hyperspectral remote sensing system.The UHD185 camera has a small frame,only50×50 pixels,which can be used effectively after stitching.In this research,through multiple loop experiments of drone flight photography and hyperspectral image stitching,it is finally determined that the route parameters that can meet the hyperspectral image stitching of the weak feature area of winter wheat and the optimal heading overlap and side overlap are 90%,85%.(2)Aiming at the stitching problem of UHD185 images,this article first uses Pansharpen algorithm to perform hyperspectral data fusion,and secondly extracts and matches image feature points based on the improved SIFT algorithm Photo Scan,and then uses IDL programming to realize the extraction and merging of hyperspectral sub-band images Finally,the geocoding of hyperspectral images is completed based on Arc GIS to realize the stitching of UHD185 images.The correlation coefficients of the spectral curves of typical ground objects before and after splicing all reached 0.970,and the image after splicing effectively retained the original spectral characteristic information.(3)Principal component analysis transform(PCA),minimum noise separation transform(MNF)and independent component transform(ICA)are used to reduce the dimensionality of UHD185 data.The results are respectively compared with different kernel function support vector machines in machine learning,The maximum likelihood method and the ENVINet5 model improved based on the U-net neural network are combined to carry out the winter wheat classification experiment.The results show that the MNF-ENVINet5 dimensionality reduction classification result is the best,and its overall accuracy OA and Kappa coefficients are 78.98% and 0.7555,respectively. |
