At present, there are three major challenges in the sophisticated vegetation classification using hyperspectral image. The first is that the accuracy of classification obtained simply by using spectral information is low. The second is that the presence of noise in the spectral data affects the final classification results, and the third is the lack of classification methods designed for specific application scenarios. To this end, a method for sophisticated vegetation classification based on multi-dimensional features of hyperspectral images is proposed. In this method, hyperspectral image data are analyzed and utilized firstly through three aspects of spectral data dimension reduction, texture feature extraction and vegetation index selection. And then, based on the distribution of ground vegetation obtained from previous field surveys, training samples are selected and Support Vector Machine (SVM) supervised classification is performed, which results in the sophisticated classification of ground vegetation at last. To verify the classification results, the overall accuracy can reach 99.6%. The result shows that vegetation classification based on multi-dimensional features of hyperspectral image can effectively reduce data noise and improve information utilization rate, and can provide more reliable data support for vegetation ecological monitoring work.