MyJournals Home  

RSS FeedsRemote Sensing, Vol. 14, Pages 5934: Evaluation of LiDAR-Derived Features Relevance and Training Data Minimization for 3D Point Cloud Classification (Remote Sensing)

 
 

23 november 2022 15:15:23

 
Remote Sensing, Vol. 14, Pages 5934: Evaluation of LiDAR-Derived Features Relevance and Training Data Minimization for 3D Point Cloud Classification (Remote Sensing)
 


Terrestrial laser scanning (TLS) is a leading technology in data acquisition for building information modeling (BIM) applications due to its rapid, direct, and accurate scanning of different objects with high point density. Three-dimensional point cloud classification is essential step for Scan-to-BIM applications that requires high accuracy classification methods, running at reasonable processing time. The classification process is divided into three main steps: neighborhood definition, LiDAR-derived features extraction, and machine learning algorithms being applied to label each LiDAR point. However, the extraction of LiDAR-derived features and training data are time consuming. This research aims to minimize the training data, assess the relevance of sixteen LiDAR-derived geometric features, and select the most contributing features to the classification process. A pointwise classification method based on random forests is applied on the 3D point cloud of a university campus building collected by a TLS system. The results demonstrated that the normalized height feature, which represented the absolute height above ground, was the most significant feature in the classification process with overall accuracy more than 99%. The training data were minimized to about 10% of the whole dataset with achieving the same level of accuracy. The findings of this paper open doors for BIM-related applications such as city digital twins, operation and maintenance of existing structures, and structural health monitoring.


 
99 viewsCategory: Geology, Physics
 
Remote Sensing, Vol. 14, Pages 5933: A 3D Space-Time Non-Local Mean Filter (NLMF) for Land Changes Retrieval with Synthetic Aperture Radar Images (Remote Sensing)
Remote Sensing, Vol. 14, Pages 5923: Plant Density Estimation Using UAV Imagery and Deep Learning (Remote Sensing)
 
 
blog comments powered by Disqus


MyJournals.org
The latest issues of all your favorite science journals on one page

Username:
Password:

Register | Retrieve

Search:

Physics


Copyright © 2008 - 2024 Indigonet Services B.V.. Contact: Tim Hulsen. Read here our privacy notice.
Other websites of Indigonet Services B.V.: Nieuws Vacatures News Tweets Nachrichten