Data integration of high resolution orbital image and airborne LiDAR system for semi-automatic buildings detection in urban areas

Abstract:

Currently, the high spatial and radiometric resolution sensors are able to acquire images where features on the surface are represented by submeter pixels. Along with, the ALS ( Airborne LiDAR System, an active remote sensing technology embedded in aircrafts ( is able of collecting elevation data from thousands of coordinate points on the Earth's surface. This integration is desirable, because it can generate complementary or additional data. Therefore, this research presents a methodology to detect buildings in an urban area, using a GeoEye(r) image and ALS data, based on an object-based analysis and classification rules generated by decision trees. The ALS data enable the production of the digital models, such as the DSM (Digital Surface Model), DTM (Digital Terrain Model) and NDSM (Normalized Digital Terrain Model). The image was orthorectified by means of the DSM, and the image segmentation process relied on the NDSM using the so-called FLSA (Full Lambda Schedule Algorithm). Representative samples of the classes of interest were used to train the classification process, set parameters and create the decision rules. After training, the complete dataset was subjected to a classification process. The experiments sought to verify which attributes most contributed to building detection

Keywords:
Data Integration; High resolution; GeoEye; ALS