Stationary LiDAR for Traffic and Safety Applications – Vehicles Interpretation and Tracking

The goal of the Traffic Scanning (T-Scan) project is to develop a data processing module for a novel Light Detection and Ranging (LiDAR)-based traffic scanner to collect highly accurate microscopic traffic data at road intersections. T-Scan uses LiDAR technology that can detect and track various types of road users, including buses, cars, pedestrians, and bicycles; and, unlike video detection, it does not experience the well-known occlusion problem. Moreover, LiDAR data has a one-to-one correspondence with the physical world, which makes it possible in principle to produce the positions and velocities of road users in real-time as needed for traffic and safety applications, with the errors of estimation dependent only on the resolution and accuracy of the LiDAR sensor. This report presents a research project that is the first step towards evaluating the feasibility and developing a practical tool of T-Scan for counting turning vehicles at intersections, measuring traffic interactions for the purpose of safety estimation, and conducting other traffic studies. The presented first phase of this research includes: 1) the integration and evaluation of a data acquisition system, 2) the development of basic pre-processing functions for data reduction, storing, and retrieval, 3) recognition and extraction of the fixed background, 4) correction of the measurements for the sensor motion, and 5) development of a concept for tracking and classifying moving objects.