Combining Hyperspectral and LiDAR Data for Building Extraction using Machine Learning Technique

Abstract: In this study, the fusion of hyperspectral and LiDAR data was used to propose a new method to detect buildings using the machine learning algorithm. The data sets provided by the National Science Foundation (NSF) - funded by the Centre for Airborne Laser Mapping (NCALM)- over the University of Houston campus and the neighbouring urban area, were used. The objectives of this study were: 1) automatic buildings extraction using the hyperspectral and LiDAR fused data (automation), 2) detection of the maximum number of listed buildings in the study area (completeness), and 3) achieving high accuracy in building detection throughout the classification procedure (accuracy and precision). After classification of the buildings, a comparison was made between the results obtained by the proposed method and the reference method in this field (Debes et al., 2014). Our proposed method showed a better accuracy for buildings detection in a much shorter time compared to the reference method. The accuracy of the classification was assessed by four parameters of Precision, Completeness, Overall Accuracy and Kappa Coefficient, and the values of 96%, 100%, 99%, and 0.94 were obtained, respectively.