From the paper "Persistent Monitoring and Analysis at a Corridor Scale with Lidar" Authors: William Barbour, Matthew Bunting, Derek Gloudemans, Daniel B. Work, Jonathan Sprinkle
This paper describes the persistent monitoring of a transportation corridor over the course of 120 uninterrupted days in Nashville, TN. The goal of this monitoring is to provide opportunities to design interventions for unsafe intersections, better understand traffic dynamics, and explore the potential for closed-loop control of vehicle signals and walk signs. The monitoring consisted of mounted lidar units with some overlapping, and some non-overlapping, fields of view, offering coverage of eight intersections across a span of two miles. Lidar provides a sensing modality that is becoming comparable with vision-based approaches in terms of cost. Unlike camera-based sensing, lidar is natively privacy preserving. This provides an opportunity for improved reception in communities. The paper provides a full description of the corridor, the types of classifications performed by each lidar installation, and the refresh rates and data types recorded. In addition, sample analyses are given to demonstrate the richness of the data. Sample results include hot spots for post-encroachment times between classified objects, daily turning count statistical analysis, and event heat maps such as out of crosswalk.
The data files may be found at the following public Box link: https://vanderbilt.app.box.com/folder/318559458570?s=owlbxr8z2qq5y09rkr8uvdy9drhhi08l
Follow the instructions in INSTALL.md to create a conda environment, load the required packages, and then start jupyter notebook.
conda activate laddms-persistent
jupyter notebook
Load the file reproduce_plots.ipynb and download the needed files, placing them in the correct directory structure. Then run all cells to see the produced plots.