Fusion of high resolution lidar and aerial images for object extraction

The aim of this research is to extract objects i.e. buildings, trees and roads important for noise mapping but also for applications such as 3D city modelling, land cover classification, change detection and many others. Earlier research has focused on the extraction of these objects independently either from aerial imagery or LIDAR (Light Detection and Ranging) data. This paper however, focuses on the extraction of these objects by fusing the information captured by two independent sensors. A workflow has been developed for the extraction of these objects automatically utilizing intensity and height values from LIDAR and the NDVI (Normalized Difference Vegetation Index) from multispectral images. Major tasks include LIDAR data classification, segmentation and its integration with the information extracted from aerial images. Buildings are extracted first and this facilitates the extraction of other objects by refining the classification of LIDAR data. Results are evaluated and incorporated into a GIS system for further analysis.