Building a program to automatically classify point cloud data

  • Affiliations:

    1 Hanoi University of Mining and Geology, Vietnam
    2 Research and Development of Geospatial Data Management and Analysis Techniques (GMA), Hanoi University of Mining and Geology, Vietnam
    3 Natural Resources and Environment One Member Co., Ltd, Hanoi, Vietnam
    4 GeoPro Ltd, Hanoi, Vietnam

  • *Corresponding:
    This email address is being protected from spambots. You need JavaScript enabled to view it.
  • Received: 1st-Apr-2023
  • Revised: 23rd-July-2023
  • Accepted: 17th-Aug-2023
  • Online: 31st-Aug-2023
Pages: 1 - 11
Views: 627
Downloads: 50
Rating: 5.0, Total rating: 1
Yours rating

Abstract:

Along with cartography science and technology development, data acquisition through aeronautical laser scanning systems has been developing. This is an essential and detailed data source for database construction, mapping, and city 3D modeling,... City 3D modeling requires processing many types of data, at which point cloud data processing and classification play an essential role in creating input data sources for the model. However, the processing and classification of point cloud data mainly depend on commercial software with very high costs; moreover, the algorithms and parameters of commercial software are locked. That makes it impossible for the user to intervene to improve product accuracy. Therefore, building a program to automatically classify point cloud data into different geographical objects helps us master data processing technology for creating 3D models. It makes an important contribution to building and developing smart cities. The article introduces the step-by-step classification of LiDAR point cloud data and the process of automatically building a program to classify point cloud data based on Visual Studio.Net language. The result is a bilingual program automatically classifying point cloud data (Vietnamese - English). The program can read and fully deploy algorithms to process LiDAR point cloud data containing information with four color bands (red, green, blue, and near-infrared). The primary processing is based on proposed classification steps and thresholds for point cloud data classification into eight feature classes, including hydrology, solar land, traffic, low plants, medium plants, high plants, houses, and other objects, to establish 3D city models.

How to Cite
., Q.Ngoc Bui, Le, H.Dinh, ., H.Van Pham, Vu, T.Son, ., Q.Anh Duong and Tran, T.Thu Thi 2023. Building a program to automatically classify point cloud data (in Vietnamese). Journal of Mining and Earth Sciences. 64, 4 (Aug, 2023), 1-11. DOI:https://doi.org/10.46326/JMES.2023.64(4).01.
References

Alexandre Boulch (2020). ConvPoint: Continuous Convolutions for Point Cloud Processing. Computers and Graphics, 88, 24-34. doi.org/10.1016/j.cag.2020.02.005

Arief, H. A. A., Indahl, U. G., Strand, G. H., and Tveite, H. (2019). Addressing overfitting on point cloud classification using Atrous XCRF. ISPRS Journal of Photogrammetry and Remote Sensing155, 90-101. doi.org/10.1016/j.isprsjprs.2019.07.002.

Bui, N. Q., Le, D. H., Duong, A. Q., Nguyen Q. L. (2021). Rule-based classification of Airborne Laser Scanner data for automatic extraction of 3D objects in the urban area. Journal of the Polish Mineral Engineering Society, 48(2), 103-114. DOI: doi.org/10.29227/IM-2021-02-09

Bui, N. Q., Le, Di. H., Nguyen, Q. L., Tong, S. S., Duong, A. Q., Pham, V. H., Phan, T. H., Pham, T. L. (2020). Method of defining the parameters for UAV point cloud classification algorithm. Journal of the Polish Mineral Engineering Society, 46(1) 49-56. DOI: doi.org/10. 29227/IM-2020-02-08.

Chenglu Wen, Xiaotian Sun, Jonathan Li, Cheng Wang, Yan Guo, Ayman Habib (2019). A Deep Learning Framework for Road Marking Extraction, Classification and Completion from Mobile Laser Scanning Point Clouds. ISPRS Journal of Photogrammetry and Remote Sensing, 147, 178-92. doi.org/10.1016/j.isprsjprs.2018.10.007

Dương, A. Q., Lê, Đ. H., Phạm, V. H., Nguyễn, Q. C., Bùi, N. Q. (2022). Xây dựng quy trình thu nhận, xử lý và phân loại dữ liệu đám mây điểm LiDAR phục vụ thành lập mô hình 3D thành phố. Tạp chí Khoa học Kỹ thuật Mỏ - Địa chất, 63(4), 1-12. doi:10.46326/JMES.2022.63(4).01  

Heidar Rastiveis, Alireza Shams, Wayne A. Sarasua, Jonathan Li (2020). Automated Extraction of Lane Markings from Mobile LiDAR Point Clouds Based on Fuzzy Inference. ISPRS Journal of Photogrammetry and Remote Sensing, 160, 149-66. doi.org/10.1016/j.isprsjprs.2019.12.009

Lê, Đ. H. (2019). Nghiên cứu quy trình xử lý dữ liệu thu nhận từ hệ thống bay chụp ảnh and quét Lidar Leica City Mapper trong thành lập mô hình Cyber City. Luận văn Thạc sĩ Kỹ thuật, Trường Đại học Mỏ - Địa chất. Hà Nội, 82 trang. (Việt Nam).

Lê, Đ. H. (2023). Nghiên cứu tối ưu hóa thuật toán tự động phân loại dữ liệu đám mây điểm hỗ trợ xây dựng mô hình 3D thành phố thông minh. Luận án Tiến sĩ Kỹ thuật, Trường Đại học Mỏ - Địa chất. Hà Nội, 135 trang. (Việt Nam).

Markus Gerke, Jing Xiao (2014). Fusion of Airborne Laserscanning Point Clouds and Images for Supervised and Unsupervised Scene Classification. ISPRS Journal of Photogrammetry and Remote Sensing, 87, 78-92. doi.org/10.1016/j.isprsjprs.2013.10.011.

Qiang Lu, Chao Chen, Wenjun Xie, Yuetong Luo (2020). “PointNGCNN: Deep Convolutional Networks on 3D Point Clouds with Neighborhood Graph Filters. Computers and Graphics, 86, 42–51. doi.org/10.1016/j.cag.2019.11.005.

Ronggang Huang, Bisheng Yang, Fuxun Liang, Wenxia Dai, Jianping Li, Mao Tian, Wenxue Xu (2018). A Top-down Strategy for Buildings Extraction from Complex Urban Scenes Using Airborne LiDAR Point Clouds. Infrared Physics and Technology, 92, 203-18. doi.org/10.1016/j.infrared.2018.05.021.

Wuzhao Li, Fu Dong Wang, Gui Song Xia (2020). A Geometry-Attentional Network for ALS Point Cloud Classification. ISPRS Journal of Photogrammetry and Remote Sensing, 164, 26-40. doi.org/10.1016/j.isprsjprs.2020.03.016.

Xudong Lai, Yifei Yuan, Yongxu Li, Mingwei Wang (2019). Full-Waveform LiDAR Point Clouds Classification Based on Wavelet Support Vector Machine and Ensemble Learning. Sensors, 19(14). doi.org/10.3390/s19143191.

Yangbin Lin, Cheng Wang, Dawei Zhai, Wei Li, Jonathan Li (2018). Toward Better Boundary Preserved Supervoxel Segmentation for 3D Point Clouds. ISPRS Journal of Photogrammetry and Remote Sensing, 143,  39-47. doi.org/10.1016/j.isprsjprs.2018.05.004

Yi Yang, Hairong Fang, Yuefa Fang, Shijian Shi (2020). Three-Dimensional Point Cloud Data Subtle Feature Extraction Algorithm for Laser Scanning Measurement of Large-Scale Irregular Surface in Reverse Engineering. Journal of Measurement, 151, 107-220. doi.org/10.1016/j.measurement.2019.107220

Yongguang Yang, Feng Chen, Fei Wu, Deliang Zeng, Yi-mu Ji, Xiao-Yuan Jing (2020). Multi-View Semantic Learning Network for Point Cloud-Based 3D Object Detection. Neurocomputing, doi.org/10.1016/j.neucom.2019.10.116.