Integrating Aerial LiDAR and Very-High-Resolution Images for Urban Functional Zone Mapping

This study presents a new approach for Urban Functional Zone (UFZ) mapping by integrating two-dimensional (2D) Structure Parameters (USPs), three-dimensional (3D) USPs, and the spatial patterns of land covers, which can be divided into two steps. Firstly, we extracted various features, i.e., spectral, textural, geometrical 3D USPs from very-high-resolution (VHR) images light detection ranging (LiDAR) point clouds. In addition, multi-classifiers (MLCs), Random Forest, K-Nearest Neighbor, Linear Discriminant Analysis classifiers were used to perform cover using optimized features. Secondly, based on classification results, 2D different covers MLCs classify UFZs. Results northern part Brooklyn, New York, USA, show that yielded an excellent accuracy UFZ with overall 91.9%. Moreover, have demonstrated could considerably improve accuracies UFZs 6.4% 3.0%, respectively.