Information fusion of Lidar range and intensity data for automatic building recognition

Lidar has proved to be a promising data source for various mapping and 3D modelling of buildings in urban areas. Therefore, many researchers have been trying to study and develop automatic building recognition algorithms based on Lidar data. But, according to the adjacency of buildings and other objects in urban areas, especially trees, the performance of obtained results from most of these algorithms is still dependent to several assumptions and simplifications. In this article, a multi-agent methodology has been proposed for automatic building recognition based on the decision level fusion of textural and spatial information extracted from Lidar range and intensity products. In this multi-agent methodology, two different groups of object recognition agents are defined for building and tree detection in parallel and the algorithm has two different operational levels based on the types of contextual information. In the first level, both object recognition agents decide about the types of objects in the study area based on textural information, and the candidates of building and tree regions will be generated. In the second operational level, building recognition and tree recognition agents perform some operations in macro level in order to modify the candidates of building and tree regions based on spatial information. The evaluation of obtained results confirms the high capabilities of proposed multi-agent algorithm to decrease the conflicts in the field of automatic building recognition in complex urban areas.