A proposed new approach for extracting complex building boundaries from segmented LiDAR data

Many studies have been conducted on extracting building boundaries from LiDAR (Light Detectino And Ranging) data. In these studies, points are first segmented, then are further generalized or regularized to acquire straight boundary lines that better approximate the real boundaries. In most research in this area, such generalization or regularization assumes that buildings have only right angles, i.e., all the line segments of the building boundaries are either parallel or perpendicular to each other. However, this assumption is not valid for many buildings, and restricts wider applications of this type of study. We present a new approach consisting of three steps that is applicable to more complex building boundaries. The three steps consist of boundary tracing, generalization, and regularization. Each step contains algorithms that range from slight modifications of conventional algorithms to entirely new concepts. Four typical building shapes were selected to test the performance of our new approach. Our results show that our proposed approach has good potential for extracting building boundaries of various shapes.