Exploring Airborne LiDAR and Aerial Photographs Using Machine Learning for Land Cover Classification

Airborne LiDAR is a popular measurement technology in recent years. Its feature that it can quickly acquire high precision and density 3D point coordinates on the surface. The reflective waveform of radar contains geometric structure roughness surface reflector. Combined with information from aerial photographs, help users to interpret various object types serve as basis for land cover classification. experiment divided into three phases. In phase 1, data decision tree classification method (DT) were used classify customize parameter elevation. 2, we combined DT improve accuracy 3, support vector machine (SVM) was compare different methods. results show customizing elevation overall accuracy. study showed SVM had better grass, building artificial ground, planted shrub bare ground.