Building Extraction from Laser Scanning Data

Laser scanning systems are frequently used to provide the digital surface models, DSM, of the earth surface. Laser scanning is a fast and precise technique to extract information related with various objects (terrain and non-terrain). Automatic extraction of objects from laser scanner data and images has recently been an important subject. Buildings are the objects of the highest interest in 3D city modeling. Urban areas are rapidly changing due to human activities in construction, destruction or extension of topographic elements such as buildings and roads. This mandates the availability of fast data acquisition technique and automatic method for detecting and extracting 3D topographic objects from the data. In this paper, building details were extracted from laser scanning data. We used data which were produced by ISPRS III commission to be evaluated the filtering techniques belonging to Stuttgart city center. We produced an efficient algorithm with Hough transform technique by using MATLAB software. We present a sequential Hough transform for detection of building in point clouds. Our algorithm consists of two sequential steps of low dimensional Hough transforms. The first step, called Orientation Estimation, uses the Gaussian sphere of the input data and performs a 2D Hough Transform for finding strong hypotheses for the direction of building axis. The second step of Position and Radius Estimation consists of a 3D Hough transform for estimating building position and radius. This sequential breakdown reduces the space and time complexity while retaining the advantages of robustness against outliers and multiple instances. The results of applying this algorithm to real data sets from two industrial sites are presented that demonstrate the effectiveness of this procedure for building detection. * Corresponding author.