Hierarchical Image Object-based Structural Analysis toward Urban Land Use Classification Using High-resolution Imagery and Airborne Lidar Data

High-resolution remotely sensed imagery and airborne laser altimetry data offer exciting possibilities for feature extraction and spatial modelling in urban areas. In this study, hierarchical image objects have been generated by image segmentation based on IKONOS imagery and laser scanning data using semantically meaningful thresholds. Delaunay triangulation and morphological image analysis technique have been applied in deriving spatial relations between image objects and for structural analysis. Land use objects can be inferred at a higher level based on land cover objects and structural information. In this paper, an overview is given of an urban land use classification schema based on hierarchical image objects. The image objects at each level are described, their spatial properties mentioned and the derivation of structural information is outlined. The focus of this paper is on the higher level of spatial clusters and spatial units: land use functions through structural analysis of related features, spatial relations and associated measurements. Finding discriminant functions for identifying land use and its spatial units is a major concern. A number of measurements are introduced and experimental results are compared and evaluated. These experiments are based on different types of data from a study area in southeast Amsterdam.