Classifying tree species in the plantations of southern China based on wavelet analysis and mathematical morphology

摘要

It is essential to classify tree species accurately for the sustainable management of forest resources and effective monitoring of species diversity. Airborne hyperspectral images have high spatial and spectral resolution, and consequently, the large quantity of information on spectral and spatial structures is effective for tree species classification. In this research, Gaofeng Forest Farm in Nanning, Guangxi Province, China, was used as the study site, and the airborne hyperspectral images were used as the data source. The spectral and textural information extracted by wavelet analysis and edge information extracted by mathematical morphological analysis composed a feature set. The feature set was filtered through a random forest, and object-oriented methods were used to classify tree species through a support vector classifier. The results showed that spectral features extracted by wavelet analysis were highly effective in classifying tree species that had the greatest spectral separability. Horizontal and vertical textures had no positive effect on the classification accuracy, while diagonal textures improved the classification accuracy of tree species. Texture features were not sensitive to stands with small areas and broken distributions, while the edge structure features extracted from mathematical morphology were sensitive to the complex forests. The overall accuracy of tree species classification by combining spectral, textural, and edge structural features was 96.54%, with a Kappa coefficient of 0.96. In the comparative test, the first-derivative and second-derivative of the hyperspectral image and texture features composed a feature set. Using the same classification methods, the OA was 80.91% and Kappa was 0.7711. Therefore, the wavelet analysis and mathematical morphology can significantly improve the tree species classification accuracy of hyperspectral images. Accurate tree species classification can provide basic scientific data for forest resource monitoring and management measures.