Investigation of Emerging Sensing and AI/ML Technologies to Enhance the Safety of Vulnerable Roadway Users at Signalized Intersection

Term Start:

June 1, 2024

Term End:

May 31, 2026

Budget:

$371,410

Keywords:

LiDAR Technology, Safety, Vulnerable Roadway Users

Thrust Area(s):

Data Collection Mechanisms, Equity and Understanding User Needs

University Lead:

City College of New York

Researcher(s):

Yiqiao Li; Jie Wei; Camille Kamga

Accurately identifying and analyzing vulnerable roadway users (VRUs) such as pedestrians, bicyclists, and other non-vehicle occupants, are a crucial yet difficult undertaking. VRUs’ behavior is influenced by localized factors such as land use, and their movements are not confined to predefined paths. This study will investigate the use of emerging technologies such as LiDAR, network cameras, and AI/ML algorithms to capture the movements and behaviors of vulnerable road users (VRUs). By evaluating pedestrian demand, including the volume and characteristics of pedestrian traffic, this research aims to assess and improve the safety of intersections. 

This project will start with a comprehensive study of the state-of-the-art methods of VRU data collection, image- and LiDAR-based VRU object detection and classification, and dynamic VRU trajectory estimation methods. Next, a candidate study intersection will be reviewed and selected for the sensor installation and data collection. The LiDARs and Cameras will be synchronized with the field processing unit and the retrieved data will be transferred and saved to be further analyzed.  

In the model development process, three traffic data collection framework will be designed: a roadside LiDAR-based VRU data collection, video-based VRU data collection, and an integrated framework. 

Project scope

Scroll to Top