Automatic Building Extraction with Multi-sensor Data Using Rule-based Classification

Abstract

This paper presents a new approach for automatic building extraction using a rule-based classification method with a multi-sensor system that includes light detection and ranging (LiDAR), a digital camera, and a GPS/IMU positioned on the same platform. The LiDAR data (elevation and intensity) and ortho-image are used to develop a rule set defined by parameter analyses during the segmentation and fuzzy classification processes to improve the building extraction results. The proposed approach was tested using the data derived from a multi-sensor system in Sivas, Turkey. Moreover, analyses of completeness (81.71%) and correctness (87.64%) were performed by automatic comparison of the extracted buildings and reference data.