LiDAR point cloud classification using point elevation and reflection intensity
- Authors: Phuong Huu Thi Nguyen 1*, Duc Van Dang 2, Xuan Truong Nguyen 3, Loi Huu Pham 1, Thang Minh Nguyen 4
1 Hanoi Univeristy of Mining and Geology, Hanoi, Vietnam
2 Institute of Information Technology - VAST, Hanoi, Vietnam
3 Scientific and technical development support center - HUMG, Hanoi, Vietnam
4 General Department of Geology and Minerals – MONRE, Hanoi, Vietnam
- Received: 9th-June-2022
- Revised: 29th-Sept-2022
- Accepted: 4th-Oct-2022
- Online: 31st-Oct-2022
The data obtained from LiDAR includes a lot of valuable information and is applied in many different fields such as geodesy - cartography, and antiques. information transmission, etc. LiDAR point cloud contains a lot of information about the object such as high point, point reflection intensity, nominal distance (NPS), and grayscale value, etc., each information is used in different problems. to clarify the three-dimensional spatial distribution, the zoning surface, or the features of the topography and features in the survey area. In the article, the authors use information altitude and reflection intensity, two typical symbols of data LiDAR, to implement a mathematical layer application to set digital elevation (DEM), model the face number (DSM), and 3D model to verify the partition of address, address at the area of testing. Pitch information is used by the author to separate groups of ground (ground) and non-ground (non-ground) points. Value reflection will be used to enhance accuracy when performing groundless classification into vegetative strata, and tall buildings. The use of point intensity reflection enhances the accuracy of previous high point-based geometry processing methods. With the accuracy of the problem analysis class reaching (ground (93.8%), building (91%), and vegetation (93,7%)), the models are set up just out of the partition of the required answer surface of the problem application.
Gao, Y. and Li, M.C., (2020). Airborne lidar point cloud classification based on multilevel point cluster features. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 42, 1231-1237.
Rodríguez-Cuenca, B., García-Cortés, S., Ordóñez, C., and Alonso, M.C., (2015). Automatic detection and classification of pole-like objects in urban point cloud data using an anomaly detection algorithm. Remote Sensing, 7(10), 12680-12703.
Rodriguez-Perez, R., Vogt, M., and Bajorath, J., (2017). Support vector machine classification and regression prioritize different structural features for binary compound activity and potency value prediction. ACS omega, 2(10), 6371-6379.
Yunfei, B., Guoping, L., Chunxiang, C., Xiaowen, L., Hao, Z., Qisheng, H., Linyan, B. and Chaoyi, C., (2008). Classification of LIDAR point cloud and generation of DTM from LIDAR height and intensity data in forested area. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 37(7), 313-318.