Recommended Citation
Bandaru, V. K., Romero, M. A., Lizarazo, C., & Tarko, A. P. (2021). TScan–Stationary LiDAR for traffic and safety applications: Vehicle interpretation and tracking (Joint Transportation Research Program Publication No. FHWA/IN/JTRP-2021/31). West Lafayette, IN: Purdue University. https://doi.org/10.5703/1288284317402
DOI
10.5703/1288284317402
Abstract
To improve traffic performance and safety, the ability to measure traffic accurately and effectively, including motorists and other vulnerable road users, at road intersections is needed. A past study conducted by the Center for Road Safety has demonstrated that it is feasible to detect and track various types of road users using a LiDAR-based system called TScan. This project aimed to progress towards a real-world implementation of TScan by building two trailer-based prototypes with full end-user documentation. The previously developed detection and tracking algorithms have been modified and converted from the research code to its implementational version written in the C++ programming language. Two trailer-based TScan units have been built. The design of the prototype was iterated multiple times to account for component placement, ease of maintenance, etc. The expansion of the TScan system from a one single-sensor unit to multiple units with multiple LiDAR sensors necessitated transforming all the measurements into a common spatial and temporal reference frame. Engineering applications for performing traffic counts, analyzing speeds at intersections, and visualizing pedestrian presence data were developed. The limitations of the existing SSAM for traffic conflicts analysis with computer simulation prompted the research team to develop and implement their own traffic conflicts detection and analysis technique that is applicable to real-world data. Efficient use of the development system requires proper training of its end users. An INDOT-CRS collaborative process was developed and its execution planned to gradually transfer the two TScan prototypes to INDOT’s full control. This period will be also an opportunity for collecting feedback from the end user and making limited modifications to the system and documentation as needed.
Report Number
FHWA/IN/JTRP-2021/31
Keywords
LiDAR-based tracking, intersection traffic analysis, traffic conflicts, TScan
SPR Number
4102
Performing Organization
Joint Transportation Research Program
Sponsoring Organization
Indiana Department of Transportation
Publisher Place
West Lafayette, IN
Date of this Version
2021