Automatic change detection and incremental updating for accurate 3D urban cartography

In this paper, we present a new method of automatic change detection for 3D urban cartography which then progressively incorporates these changes by incremental updating, exploiting the concept of multiple passages. In the proposed method the 3D point clouds, obtained in each passage, are first classified into 2 main object classes: Permanent and Temporary using a voxel-segmentation based classification method and inference based on basic characteristics. The Temporary objects are removed from the 3D point clouds which are then merged together to leave behind a unified perforated 3D point cloud of the urban scene. These perforated 3D point clouds obtained from different passages (in the same place) at different days and times are matched together to complete the 3D urban landscape by incremental updating. Different man-made or natural changes occurring in the urban landscape over this period of time are detected and analyzed using cognitive functions of similarity and the resulting 3D cartography is progressively modified accordingly. The results, evaluated on real data, not only demonstrate the efficacy of the change detection method but also show that these changes are effectively incorporated ensuring that the resulting 3D cartography is updated and contains only the exact permanent features. It is also shown that the proposed method is easily applicable and well suited for handling large urban scenes.