Abstract
The automatic extraction of buildings from true color stereo aerial imagery in a dense built-up area is the main focus of this paper. Our approach strategy aimed at reducing the complexity of the image content by means of a three-step procedure combining reliable geospatial image analysis techniques. Even if it is a rudimentary first step towards a more general approach, the method presented proved useful in urban sprawl studies for rapid map production in flat area by retrieving indispensable information on buildings from scanned historic aerial photography. After the preliminary creation of a photogrammetric model to manage Digital Surface Model and orthophotos, five intermediate mask-layers data (Elevation, Slope, Vegetation, Shadow, Canny, Shadow, Edges) were processed through the combined use of remote sensing image processing and GIS software environments. Lastly, a rectangular building block model without roof structures (Level of Detail, LoD1) was automatically generated. System performance was evaluated with objective criteria, showing good results in a complex urban area featuring various types of building objects.
Highlights
Detailed information on urban sprawl is of great interest for town municipalities in the fields of urban planning, water and land resource management, etc
In light of the above issues, this paper focuses on a decision making strategy that combines various data mask layers in order to delineate buildings from true-color stereo aerial imagery automatically in a complex built-up area
Aerial or satellite images are employed as single data source for building extraction by means of auxiliary information such as shadow [13], perceptual grouping based on the line segment obtained from edge detection, which is useful in defining border pixels [14], or both of them [15]
Summary
Detailed information on urban sprawl is of great interest for town municipalities in the fields of urban planning, water and land resource management, etc For these purposes, analysis of spatial and temporal data, which help in quantifying growth trends on a spatial scale, are required. In light of the above issues, this paper focuses on a decision making strategy that combines various data mask layers in order to delineate buildings from true-color stereo aerial imagery automatically in a complex built-up area (one to three-floor residential housing with irregular shapes, heterogeneous materials of roofs and close vegetation). The aerial digital data used and the simplified procedure proposed in this study simulated the working processes of rapid map production and change detection analysis carried out comparing multi-temporal scanned historic aerial photography with the intent of identifying potential urban sprawl in peripheral areas.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
