• Home
  • Search
  • Evaluate the Impact of Class Granularity in Point Cloud Semantic Segmentation on DTM Accuracy
  • https://doi.org/10.5194/isprs-archives-xlviii-m-6-2025-243-2025Copy DOI Icon

Evaluate the Impact of Class Granularity in Point Cloud Semantic Segmentation on DTM Accuracy

  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • Similar Papers
Abstract

Abstract. The Digital Terrain Model (DTM) is considered an essential component in various applications, including road design, urban planning, terrain analysis, and, environmental monitoring. LiDAR data is known to have very high accuracy therefore it is considered the most reliable source for DTM generation. However, accurately filtering the LiDAR data for the ground classification remains a challenge. This study explores the impact of class granularity on semantic segmentation and its effect on the accuracy of DTM generation sourced to LiDAR data. The RandLA-Net has been used for semantic segmentation, and for the training, the DALAS dataset which comprises various terrains and structures is used. The process is comprised of training the deep learning models on datasets that are classified into two schemes. The first scheme is a course with 2-classes (ground and non-ground) and the second scheme is a finer one with 8-classes (ground, vegetation, cars, trucks, powerlines, fences, poles, and buildings). The trained models are applied to three datasets to evaluate the result of the granularity on the accuracy of the DTM. The results show that the accuracy of the DTM based on the 2-class model outperforms the accuracy of the DTM obtained via the 8-classes model, as indicated by the used statistical measures such as RMSE, mean and standard deviation (STD). The semantic segmentation of the 8-classes model shows more misclassification, especially in complex urban areas, especially in distinguishing the ground points from non-ground objects. The study emphasizes the trade-off between class granularity and DTM accuracy, which shows that simpler classification schemes will lead to a better result of the DTM generation results.

Loading PDF

Similar Papers
  • Research Article

Evaluating the Impact of Ground Control Network Type on UAV Photogrammetric Accuracy: NTRIP, Radio RTK, and GCP-Free P4-RTK

  • Dec 30, 2025
  • Journal of Geomatics and Environmental Research
  • Conference Article
  • Citations15

Large-Scale DTM Generation From Satellite Data

  • Jun 01, 2019
  • Liuyun Duan +4
  • Research Article
  • Citations26

Deep learning-based semantic segmentation of three-dimensional point cloud: a comprehensive review

  • Jan 17, 2024
  • International Journal of Remote Sensing
  • Dheerendra Pratap Singh +1
  • Research Article
  • Citations178

Combined analysis of digital terrain models and remotely sensed data in landscape investigations

  • Mar 01, 1998
  • Progress in Physical Geography: Earth and Environment
  • Igor V Florinsky
  • PDF
  • Research Article
  • Citations16

Semantic segmentation of large-scale point clouds based on dilated nearest neighbors graph

  • Jan 04, 2022
  • Complex & Intelligent Systems
  • Lei Wang +4
  • Research Article
  • Citations3

Real-Time DTM Generation with Sequential Estimation and OptD Method

  • Apr 07, 2025
  • Applied Sciences
  • Wioleta Błaszczak-Bąk +4
  • PDF
  • Research Article
  • Citations4

VALIDATION OF DEMs DERIVED FROM HIGH RESOLUTION SAR DATA: A CASE STUDY ON BARCELONA

  • Jul 16, 2012
  • ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • U G Sefercik +3
  • Conference Article
  • Citations1

Vertical Accuracy Assessment of TanDEM-X Global DEM over various Indian

  • Mar 01, 2019
  • Divya Sekhar Vaka +1
  • Research Article
  • Citations1

BEMF-Net: Semantic Segmentation of Large-Scale Point Clouds via Bilateral Neighbor Enhancement and Multi-Scale Fusion

  • Nov 13, 2023
  • Remote Sensing
  • Hao Ji +8
  • Research Article

Comparative Study of Digital Terrain Models (DTM) Using DRTK 2 Drone and GNSS Methods

  • Jan 01, 2025
  • International Journal of Geosciences
  • Mouhamadou Moustapha Mbacké Ndour +3
  • Research Article

Accuracy and hydrographic realism of an under-forest DEM derived from airborne P-band radar interferometry over a wide area in the Brazilian amazon

  • Jul 16, 2024
  • International Journal of Remote Sensing
  • Carlos Rodrigo Tanajura Caldeira +3
  • Research Article
  • Citations6

Accurate DTM generation in sand beaches using mobile mapping

  • May 24, 2013
  • Journal of Coastal Conservation
  • S Madeira +2
  • Research Article
  • Citations272

Archaeological prospection of forested areas using full-waveform airborne laser scanning

  • Aug 10, 2007
  • Journal of Archaeological Science
  • Michael Doneus +3
  • Conference Article

Generation of digital terrain models from digital surface models using a watershed transformation approach

  • Sep 19, 2025
  • Thomas Krauss
  • Research Article
  • Citations631

Airborne LiDAR for DEM generation: some critical issues

  • Feb 01, 2008
  • Progress in Physical Geography: Earth and Environment
  • Xiaoye Liu
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.