Skip to content
akaturk Academic measurement

Article detail · 2023

Performance of unsupervised machine learning methods using chi-squared weights for LiDAR point cloud filtering in urban areas

Journal of Spatial Science

YÖKSİS OpenAlex SJR Q2 JCR Q4 Citations 1 Percentile 36.7% FWCI 0.08
Year
2023
ISSN
1449-8596
Type
article

Data source split

  • YÖKSİS YÖKSİS article record
  • OpenAlex OpenAlex enrichment (abstract, citations, topics)

Abstract

English (OpenAlex)

In this study, we compared the LiDAR filtering performances of unsupervised machine learning methods, such as linkage, K-means, and self-organizing maps, for urban areas to provide a practical guide to researchers. The input parameters (x-y-z and intensity) were normalized and weighted using a chi-squared independence test to improve the classification accuracy. The best successful results were obtained using the weighted linkage method in terms of the total error of 13.53%, 3.96%, and 1.07% for the three samples, respectively. In comparison with other approaches, methods weighted by chi-squared have significant potential for classification and filtering and outperform many popular approaches.

Topics

  • Remote Sensing and LiDAR Applications
  • Remote Sensing in Agriculture
  • 3D Surveying and Cultural Heritage

Primary topic Remote Sensing and LiDAR Applications

Authors

  1. ALPER ŞEN YILDIZ TEKNİK ÜNİVERSİTESİ
  2. BARIŞ SÜLEYMANOĞLU YILDIZ TEKNİK ÜNİVERSİTESİ
  3. METİN SOYCAN