Multi-agent hyperspectral and lidar features fusion for urban vegetation mapping

Urban vegetation recognition based on remote sensing data is highly affected by the complexities of urban areas due to the existence of various kinds of objects and their relations. Spectral similarities between tree canopies and types of grass lands, spatial adjacency between houses and tall trees, shadow and occluded areas make some difficulties for recognition of the plant species. In this research, the capabilities of multi-agent systems are utilized for feature fusion of hyperspectral imagery and lidar data for improving the vegetation recognition results in urban areas. The proposed algorithm has two main steps composed of generating a knowledge base containing spectral and height features extracted from input hyperspectral and Lidar data, respectively, and performing the hierarchical classification process to generate vegetation classification map based on parallel processing by object recognition agents. Evaluation of the capabilities of the proposed methodology is performed on hyperspectral and lidar DSM over Houston University and its surrounding areas. According to the obtained results, fusion of hyperspectral and Lidar DSM with the capabilities of multi-agent processing can improve the overall accuracy of vegetation recognition results for about 15.53% and 6.58% comparing with performing multi-agent and maximum likelihood classifier only on hyperspectral image, respectively.