ICPR, International Conference on Pattern Recognition (Japan, 2012.))

In this work the Distributed Event Analysis Research Laboratory have proposed a new object-based hierarchical model for joint probabilistic extraction of vehicles and coherent vehicle groups - called traffic segments - in airborne LIDAR point clouds collected from crowded urban areas. Firstly, the 3D point set is segmented into terrain, vehicle, roof, vegetation and clutter classes. Then the points with the corresponding class labels and intensity values are projected to the ground plane. In the obtained 2D class and intensity maps we approximate the top view projections of vehicles by rectangles. Since our tasks are simultaneously the extraction of the rectangle population which describes the position, size and orientation of the vehicles and grouping the vehicles into the traffic segments, we propose a hierarchical, Two-Level Marked Point Process model for the problem. The output vehicle and traffic segment configurations are extracted by an iterative stochastic optimization algorithm. We have tested the proposed method with real aerial LiDAR measurements on a data set containing 471 vehicles, and we have provided quantitative object and pixel level comparison results versus two state-of-the-art solutions.