Robust Building-Based Registration of Airborne Lidar Data and Optical Imagery on Urban Scenes Article Swipe
YOU?
·
· 2019
· Open Access
·
· DOI: https://doi.org/10.1109/igarss.2019.8898612
· OA: W2988795680
The motivation of this paper is to address the problem of registering\nairborne LiDAR data and optical aerial or satellite imagery acquired from\ndifferent platforms, at different times, with different points of view and\nlevels of detail. In this paper, we present a robust registration method based\non building regions, which are extracted from optical images using mean shift\nsegmentation, and from LiDAR data using a 3D point cloud filtering process. The\nmatching of the extracted building segments is then carried out using Graph\nTransformation Matching (GTM) which allows to determine a common pattern of\nrelative positions of segment centers. Thanks to this registration, the\nrelative shifts between the data sets are significantly reduced, which enables\na subsequent fine registration and a resulting high-quality data fusion.\n
