Digital terrain from a two-step segmentation and outlier-based algorithm

Abstract

We present a novel ground filter for remotely sensed height data. Our filter has two phases: the first phase segments the DSM with a slope threshold and uses gradient direction to identify candidate ground segments; the second phase fits surfaces to the candidate ground points and removes outliers. Digital terrain is obtained by a surface fit to the final set of ground points. We tested the new algorithm on digital surface models (DSMs) for a 9600km2 region around Perth, Australia. This region contains a large mix of land uses (urban, grassland, native forest and plantation forest) and includes both a sandy coastal plain and a hillier region (elevations up to 0.5km). The DSMs are captured annually at 0:2m resolution using aerial stereo photography, resulting in 1:2TB of input data per annum. Overall accuracy of the filter was estimated to be 89:6% and on a small semi-rural subset our algorithm was found to have 40% fewer errors compared to Inpho’s Match-T algorithm.