Performance analysis of different classifiers in segmenting point cloud data

Abstract

3D point clouds are a set of point coordinates that can be obtained by using sensing device such as the Terrestrial Laser Scanner (TLS). Due to its high capability in collecting data and produce a strong density point cloud surrounding it, segmentation is needed to extract information from the massive point cloud containing different types of objects, apart from the object of interest. Bell Tower of Tawau, Sabah has been chosen as the object of interest to study the performance of different types of classifiers in segmenting the point cloud data. A state-of-the-art TLS was used to collect the data. This research’s aim is to segment the point cloud data of the historical building from its scene by using two different types of classifier and to study their performances. Two main classifiers commonly used in segmenting point cloud data of interest like building are tested here, which is Random Forest (RF) and k-Nearest Neighbour (kNN). As a result, it is found out that Random Forest classifier performs better in segmenting the existing point cloud data that represent the historic building compared to k-Nearest Neighbour classifier.