Detection of Ground in Point-clouds Generated from Stereo-pair Images

Domen Mongus, Borut Žalik


This paper proposes a new approach for constructing digital terrain models (DTM) from the point-clouds
generated from airborne stereo-pair images. The method uses data decomposition based on the differential
attribute profiles and -mapping for the extraction of the most-contrasted connected-components. Their
filtering is achieved based on multicriterion threshold function. The method is evaluated by comparing the
output DTM with the reference Light Detection and Ranging data (LiDAR).

Full Text:


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.