Fusion of lidar and imagery for reliable building extraction

We propose a new building detection and description algorithm for lidar data and photogrammetric imagery using directional histograms, splitting and merging segments, and line segments matching. Our algorithm consists of three steps In the first step, we extract initial building regions from lidar data. Here, we apply a modified local maxima technique coupled with directional histograms and the entropies of these histograms. In the second step, given the color segmentation results from the photogrammetric imagery, we extract coarse building boundaries based on the lidar results with region segmentation and merging from aerial imagery. In the third step, we extract precise building boundaries based on the coarse building boundaries using line segments matching and perceptual grouping. Experimental results on multisensor data demonstrate that the proposed algorithm produces accurate and reliable results.