Hybrid 3D Segmentation Technique for 3D City Models

Abstract

Abstract3D city model is a virtual representation of a city or urban environment, where in GIS related context, represents existing cities in the world. Initially, they are used only as presentations that complement the results of 2D analyses and bear no analytical capabilities. The advancement in computer graphics technology has effectively sparked the effort towards realizing 3D GIS where the 3D models can be used directly in analyses rather than just purely visual enhancement. A lot of research has been conducted in an effort to provide analytical capabilities to the 3D models. Rapid developments in computer-related industries have led to cutting edge technologies that enable analyses to be conducted on the 3D models. The ability of 3D city models to represent real world objects more accurately have boosted its efficiency and usability in geospatial related analyses. Now, it has become the new trend in building and urban management while modelling 3D objects are getting easier with the emergence of user-friendly tools for 3D modelling available in the market. The Open Geospatial Consortium (OGC) has accepted City Geography Markup Language CityGML specifications as one of the international standards for representing and exchanging spatial data, making it easier to visualize, store and manage 3D city models data efficiently. CityGML represents the semantics, geometry, topology and appearance of 3D city models in five well-defined Level-of-Details (LoD), namely LoD0 to LoD4. However, complex building structures are making the 3D models unsuitable for analyses as it takes a lot of time to process large data. Thus, it is only logical to breakdown the complex building into manageable segments. Segmentation is basically a method to break down an object into simpler parts. This chapter introduces a hybrid 3D segmentation method based on semantic and geometric decomposition for 3D buildings in CityGML. The proposed method deals with segmentation of a 3D building based on its semantic value and surface characteristics, fitted by one of the predefined primitives. For future work, the segmentation method will be implemented as part of the change detection module that can detect any changes on the 3D buildings, store and retrieve semantic information of the changed structure.Keywords3D city models3D model segmentationCityGML