Local Validation and Evaluation of Pedestrian Detection Using Thermal Imaging Technology is Needed, Especially in Areas with Complex Traffic Conditions and Road User Activities.

NYCDOT Assessed the Available and Potential Data Sources for the Applicability of Cooperative Driving for Advanced Connected Vehicles in New York City.

Date Posted
11/28/2022
TwitterLinkedInFacebook
Identifier
2022-L01158

Connected Vehicle Pilot Deployment Program Phase 3, Understanding and Enabling Cooperative Driving for Advanced Connected Vehicles in New York City – New York City Department of Transportation (NYCDOT)

Summary Information

Cooperative Driving (CD) is a means of sharing information to support vehicle movements to improve traffic safety and traffic flow. Vehicle-to-Everything (V2X) communication services enable the synchronization of vehicles via information exchange to coordinate, validate, and support drivers’ actions. As a part of the USDOT Connected Vehicle Pilot Deployment (CVPD), this project explored the applicability of cooperative driving for advanced connected vehicles (CD for ACV) on urban roadways and identified three testable use cases for New York City (NYC): 

  1. Pedestrian and bicyclist safety through cooperation
  2. Cooperative work zones
  3. Cooperative intersection management. 

This project identified data needs and assessed the existing and potential data sources that may contribute to CD for ACV. Specifically, Forward Looking Infrared (FLIR) thermal-based pedestrian detection technology that was used for the Pedestrian in Crosswalk application in the CVPD was evaluated.

Several lessons learned were captured during the evaluation of FLIR pedestrian detection, particularly from the detection accuracy of the FLIR sensors under different conditions.

  • Perform the validation and evaluation of FLIR technologies locally. The detection accuracy of FLIR thermal sensors was found to vary in different scenarios and locations, and could be affected by complex traffic patterns or certain road user activities. However, FLIR sensors are not affected by the level of ambient light, so time of day should not be constraining for usage and testing.
  • Consider real-time evaluation and monitoring of pedestrian detection devices. It is important to identify feasible evaluation methods, such as local printouts or network portal, at the time the pedestrian detection devices are purchased and installed. Different thermal-based sensors can have different functionality and software characteristics. The export options of the detected events may limit how the performance is evaluated.
  • Consider anomalous pedestrian movements. The FLIR sensor used in this project required designating a primary axis for pedestrian movements, but in some cities like New York City, pedestrians may cross at a significant angle with respect to the crosswalk. These movements are important to consider when developing a CD pedestrian safety application.
  • Synchronize the thermal sensor’s local time during configuration. Synchronizing the sensor’s local time during the initial configuration is important, however, agencies should also be aware of the possibility for time to become desynched over a period. For example, in this project, one FLIR sensor was found to have a 6-second delay with respect to a reference clock after three days had elapsed.

Connected Vehicle Pilot Deployment Program Phase 3, Understanding and Enabling Cooperative Driving for Advanced Connected Vehicles in New York City – New York City Department of Transportation (NYCDOT)

Connected Vehicle Pilot Deployment Program Phase 3, Understanding and Enabling Cooperative Driving for Advanced Connected Vehicles in New York City – New York City Department of Transportation (NYCDOT)
Source Publication Date
12/29/2021
Author
Talas, Mohamad; Kaan Ozbay; Jingqin Gao; Abhinav Bhattacharyya; Robert Rausch; David Benevelli; and Samuel Sim
Publisher
Prepared by C2SMART, NYCDOT, and Transcore for USDOT Federal Highway Administration
Other Reference Number
Report No. FHWA-JPO-21-920
System Engineering Elements

Keywords Taxonomy: