Abstract
Abstract: Building roof extraction has been studied for more than thirty years and it generates models that provide important information for many applications, especially urban planning. The present work aimed to model roofs only from point clouds using genetic algorithms (GAs) to develop a more automatized and efficient method. For this, firstly, an algorithm for edge detection was developed. Experiments were performed with simulated and real point clouds, obtained by LIDAR. In the experiments with simulated point clouds, three types of point clouds with different complexities were created, and the effects of noise and scan line spacing on the results were evaluated. For the experiments with real point clouds, five roofs were chosen as examples, each with a different characteristic. GAs were used to select, among the points identified during edge detection, the so-called ‘significant points’, those which are essential to the accurate reconstruction of the roof model. These points were then used to generate the models, which were assessed qualitatively and quantitatively. Such evaluations showed that the use of GAs proved to be efficient for the modeling of roofs, as the model geometry was satisfactory, the error was within an acceptable range, and the computational effort was clearly reduced.
Highlights
The extraction of building roofs has been studied for more than thirty years and it generates models that provide important information for the registration and leasing of radio/phone antennas, urban planning and solar energy studies, for example
In late 1990s, a new data source emerged: LIDAR (Light Detection and Ranging) which has significantly contributed with new data to the field (Awrangjeb, Zhang and Fraser, 2013). 3D modeling LIDAR proved to be more effective than aerial imaging in some applications
When it comes to detecting roof planes and their orientation, the point clouds obtained with LIDAR present better results due to the availability of a large number of points on the surface
Summary
The extraction of building roofs has been studied for more than thirty years and it generates models that provide important information for the registration and leasing of radio/phone antennas, urban planning and solar energy studies, for example. The most commonly applied principles in building extraction and modeling using LIDAR data assume that the roof is composed by planar surfaces and are based on the detection of planar regions, as in Ercolin Filho, Centeno and Mitishita (2016), or edges (Xiao et al 2015). These approaches are based on the estimation of the planes that compose the roof to model the intersections that define its shape. A different approach was proposed in this project: genetic algorithms (GAs) were used as an optimization tool to automatically find significant points in a particular roof’s point cloud, so that there would be no need to indicate the number of planes to be modeled beforehand
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
