Roadside LiDAR Sensing for Obtaining All-Traffic Trajectory and Traffic Performance Analysis

Case ID:

LiDAR technology, traditionally applied in autonomous vehicle navigation, has now expanded its footprint into roadside infrastructure. Roadside LiDAR aims to provide comprehensive traffic data, including behavior-level trajectory data for all road users. However, there exist challenges such as accurate differentiation between static and moving objects, as well as capturing data about unconnected entities, like pedestrians or wild animals. As our roads become smarter, there’s a growing need to optimize LiDAR capabilities for roadside applications.

Technology Overview
The technology, developed at the University of Nevada, Reno, introduces advancements in LiDAR-centric innovations tailored for roadside applications, presenting a comprehensive suite of solutions to optimize traffic monitoring and vehicle navigation. Beginning with an enhancement of roadside LiDAR capabilities, it prioritizes swiftly distinguishing between moving objects and static backgrounds. The incorporation of the Fast Spatial Clustering based on a Two-dimensional Map (FSCTD) enhances data processing, optimizing the detection and tracking of varied vehicles. This approach integrates traditional distance-based tracking with statistical mapping to provide a holistic environmental representation. Additionally, the technology introduces a transformative method to convert the standard x-y-z coordinates from roadside LiDAR into universally interpretable geographic coordinates. Leveraging GIS-based platforms, especially Google Earth™, it crafts an intersection of reference points between GIS and LiDAR datasets, leading to a refined, accessible, and user-friendly data representation.


  • Superior classification accuracy
  • Rapid and precise detection and differentiation between static and dynamic entities
  • Consistent precision in detecting and tracking all road participants
  • Superior traffic oversight with minimized computational demands relative to video systems
  • Accurate, cost-effective roadside LiDAR data mapping into easy-to-interpret geographic coordinates data

The innovations possess significant potential in enhancing autonomous vehicle navigation, pioneering traffic analysis solutions, instituting real-time threat detection systems, and reshaping data interpretation methods for the future of transportation infrastructure.




Patent Information:
For Information, Contact:
Ray Siripirom
Senior Licensing Associate
University of Nevada, Reno
Hao Xu