Roadside Asset Extraction from Mobile LiDAR Point Cloud

Abstract:

Mobile LiDAR systems are powerful tools that help us map roads and their surroundings in 3D with great speed and precision.The data provided by these systems support urban planning efforts, digital mapping, transportation infrastructure maintenance, and more. This report presents a comprehensive workflow for roadside asset extraction using Mobile Terrestrial Laser Scanning (MTLS) data, focusing on road lane detection, cross-section slope analysis, and point cloud classification. Roadside asset extraction is the identification and classification of roadside features like signs and poles. The dataset, acquired using a high-resolution mobile LiDAR system, contains over 5.7 billion points (pieces of data) across 68 LAS files. Preprocessing of the data involved tiling, merging, and denoising processes to enhance data quality. This research used two types of image-like maps— one showing elevation and one showing how reflective the surface is—to model the road and identify lane markings. Furthermore, the team developed and trained an AI-driven deep learning-based classifier program using a PointNet-style architecture implemented in PyTorch to segment ground and non-ground features. The classifier was trained using over 500 million labeled points and applied to new LAS files for inference. The model achieved effective binary classification performance and produced classified LAS outputs compatible with downstream GIS workflows. This means the program was able to successfully sort features into two categories—like ground vs. non-ground—and produce files that work with common mapping software. This work demonstrates the feasibility of combining traditional feature extraction with modern deep learning approaches to enhance automation and accuracy in infrastructure mapping.

Publications:

Roadside Asset Extraction from Mobile LiDAR Point Cloud (Full Report)

Research Brief

Authors:

Yushin Ahn
Yushin Ahn is an Associate Professor of the Department of Civil and Geomatics Engineering, California State University (CSU) at Fresno, CA. He received a B. Eng. Degree in civil engineering and an M.Sc. degree in surveying and digital photogrammetry from Inha University, Korea in 1998 and 2000, and an M.sc. and PhD degree in geodetic science from the Ohio State University, Columbus, in 2005 and 2008 respectively. His research interests include digitalphotogrammetry, feature tracking, and sensor calibration and integration. Dr. Ahn received the Robert E. Altenhofen Memorial Scholarship from American Society of Photogrammetry and Remote Sensing. He has been a certified photogrammetrist since 2014.

Riadh Munjy
Dr. Riadh Munjy received his BS in Civil Engineering in 1978 from the University of Baghdad, Iraq, an MSCE in civil Engineering in 1979, an MS in Applied Mathematics in 1981, and a PhDin Civil Engineering in 1982 from the University of Washington. He has been a faculty member and an active researcher at CSU, Fresno since 1982 and has been a Professor of Civil and Geomatics Engineering since 1988 and the Chair of the Civil and Geomatics EngineeringDepartment since 2014. He has over forty years of experience in teaching courses in photogrammetry, digital mapping, GIS, and least squares adjustment. He was awarded the Meritorious Service Award by ASPRS in 1997, the Fairchild Photogrammetric Award in 2014, the Fellow Award in 2020, and the Lifetime Achievement Award in 2023.

Steven Choi
Dr. Stephen Choi is an Associate Professor of Information Systems at CSU, Fresno. He received his PhD in Information Systems from the College of Computing Sciences, New Jersey Institute of Technology. His research interests focus on the Artificial Intelligence domain where machine learning, deep learning, and reinforcement learning with business data are emphasized. Dr. Choi stays active with AI education where he is the AI certificate program coordinator and is involved with AI course development and pedagogies. Before joining college academics, Dr. Choi worked as a business professional and manager for over ten years with leading companies such as Pfizer Pharmaceuticals, Johnson & Johnson Pharmaceuticals, and Covance.

Published:

August 2025

Keywords:

Artificial intelligence

Deep learning

Spatial analysis

Intelligent transportation systems (ITS)

Laser Radar