Abstract
Abstract. Information obtained from LiDAR data processing is considered in a variety of applications, among them urban planning. In this context, buildings play a substantial role, since a high percentage of the urban landscape is occupied by them. In the literature, many methodologies have been developed aiming at the detection of building using remote sensing data. The approaches can be developed by applying different ideas: regularity of cluster boundary, plane fitting, radiometric data and also in geometric attribute derived from LiDAR. This paper proposes a method of building detection based on the use of the entropy concept and the K-means algorithm in which the training step is dispensed with. The experiments were performed considering two LiDAR datasets with different densities (12.5 pts/m2 and 4 pts/m2). Visual and qualitative analysis enabled verification of the potential of the proposed method, which presented satisfactory results for both datasets.
Highlights
The point cloud derived from airborne LASER scanning (ALS) systems, known as LiDAR data, can be used to obtain and maintain accurate and up-to-date cartographic products
The geographic information system (GIS) is an example as it is applied in several contexts, for instance, urban planning, telecommunications networks planning, surveillance and transportation and evaluation of damage caused by natural disasters
The process explores the entropy concept to describe the cluster characteristics, and the K-means algorithm to separate the clusters into buildings and non-buildings
Summary
The point cloud derived from airborne LASER scanning (ALS) systems, known as LiDAR data, can be used to obtain and maintain accurate and up-to-date cartographic products. Buildings play a major role, since they occupy a high percentage of the urban area. Considering these aspects, automatic and semi-automatic building extraction have been explored by many authors (Kim and Habib, 2009, Dal Poz et al, 2009, Awrangjeb, 2016, Gavankar and Ghosh, 2018, Santos et al, 2019). An important task in this area is related to obtaining the set of points related to each building, which is usually performed by means of region growing and RANSAC. This is commonly carried out over non-ground points: buildings, vegetation, among other high objects. When the aim is detection, extraction and reconstruction of building, identifying which are the building clusters is essential
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
