Related Experiment Video
Updated: Sep 11, 2025

Photorealistic Learned Landscapes for Augmented Reality
Published on: June 27, 2025
Research on Ground Point Cloud Segmentation Algorithm Based on Local Density Plane Fitting in Road Scene
Tao Wang1,2, Yiming Fu1,2, Zhi Zhang3
1School of Information and Communication Engineering, Beijing Information Science and Technology University, Beijing 100101, China.
This study presents a novel ground point cloud segmentation algorithm for road scenes. The method effectively reduces ground interference in 3D point cloud data, improving recognition and prediction.
Area of Science:
- Computer Vision
- Robotics
- Geospatial Data Analysis
Background:
- 3D point cloud data in road scenes suffers from ground interference and uneven density.
- This interference complicates subsequent recognition and prediction tasks.
Purpose of the Study:
- To develop an effective ground point cloud segmentation algorithm for road scenes.
- To address challenges posed by uneven density and ground interference in 3D point cloud data.
Main Methods:
- Density segmentation to balance point cloud density.
- Candidate sample selection and plane validity detection.
- Modified DBSCAN clustering for plane fitting and segmentation.
- Abnormal inspection for result refinement.
Main Results:
- The algorithm effectively segments ground point clouds.
- Demonstrated advantages over existing advanced algorithms.
- Significantly reduced ground interference in 3D point cloud data.
Conclusions:
- The proposed algorithm improves scalability, reduces training costs, and enhances deployment efficiency and universality.
- The method offers a robust solution for processing noisy 3D road scene data.
Related Concept Videos
Plane Potential Flows
Uniform...
Design Example: Alignment of a Road Line Using GIS
Topographic Surveying and Contours
Plotting of Topographic Maps
Uniform Depth Channel Flow: Problem Solving
Methods of Obtaining Topography

