Automatic vehicle extraction from airborne LiDAR data of urban areas aided by geodesic morphology

In this study, we address one of the key issues in traffic monitoring of urban areas using airborne laser scanning (ALS) data - vehicle extraction. Our aim is to automatically segment point sets of single vehicles solely relying on the geometric components of ALS data. To tackle the complexity of vehicle appearance in ALS data, a context-guided approach based on geometric model of vehicle is proposed to accomplish the task. Ground level separation is firstly used to exclude the irrelevant objects and provide the ''Region of Interest''. The marker-controlled watershed transformation assisted by morphological reconstruction is then performed on the filled height raster of ground level to isolate vehicles. The results from different ALS datasets are evaluated with respect to the semantic and geometric accuracy, respectively. They clearly show the high potential of airborne LiDAR in outlining single vehicles in urban areas, which allows accurate 3D point retrieval of single vehicles. Based on moving object model, the examination of vehicle movement is becoming feasible when the extracted vehicle points undergo the shape parametrization.