Object-Based Method for Urban Extraction through Using Quick Bird Satellite Imagery, LiDAR Data and Digital Urban Geomatics Techniques

Abstract

Urban extraction mapping has become increasingly important in recent years andparticularity extraction urban features based on remotely sensed data such as highresolution imagery and LiDAR data. Though the researchers used the high spatialresolution image to extract urban area but he methods are still complexand still there are challenges associated with combining data that were acquiredover differing time periods using inconsistent standards. So, this study will focuson the extraction of urban area based on an object-based classification method withintegration of Quickbird satellite image and digital surface elevation (DSM)extracted from LiDAR data for the Rusafa city of Baghdad, Iraq. All the processeswere done in eCognition and ArcGIS software for feature extraction and mapping,respectively. The overall methodological steps proposed in this research for theextraction of urban area using object-based method. In addition of that both theimage data and LiDAR-derived DSM were integrated based on the eCognitionsoftware for extraction urban map of Rusafa city, Baghdad. Finally, the resultsindicated that the Artificial Neural Networks (ANN) model achieved the highesttraining and testing accuracies and performed the best compared to RF and SupportVector Machines (SVM) methods. And also, the results showed that the ArtificialNeural Networks (ANN) had capability to extract the boundaries of the buildingsand other urban features more accurately than the other two methods. This couldbe interpreted as the Artificial Neural Networks (ANN) model can learn complexfeatures by the optimization process of the model and its multi-level featureextraction property.