Extracting suburban residential building zone from airborne streak tube imaging LiDAR data

In this paper, we proposed a novel method for extracting suburban residential building zone (SRBZ) from airborne streak tube imaging LiDAR (STIL) data. This method is implemented using a single data source, which avoids the collections of multi-source data and shortens the production cycle of LiDAR data products. The framework of the method is mainly composed of a prediction module, and a correction module. In the correction module, two correction algorithms were proposed, that is, k-nearest neighbor majority voting correction algorithm (k-NNMV) and Gaussian weight based k-nearest neighbor voting correction algorithm (GWk-NNV). Experiment tests show that the framework based on the GWk-NNV has a better SRBZ extraction effect than that of the k-NNMV. The F1 coefficient of the GWk-NNV-based framework reached 80.10%. That proves that the proposed method for extracting SRBZ from airborne STIL data is feasible.