Ahmed, Fahim (General Motors), Grimm, Donald (General Motors), Bai, Fan (Research and Development, General Motors)

Traffic Sign Health Quality Assessment

Scheduled for presentation during the Regular Session "Data Management and Geographic Information Systems" (FrBT2), Friday, September 27, 2024, 14:50−15:10, Salon 5

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 7, 2024

Abstract

Modern Advanced Driver Assistance Systems (ADAS) provide emerging capabilities for detecting the quality of roadway infrastructure assets to enable new customer features and analytics capabilities for road management authorities. This paper proposes measures to assess traffic sign health based on crowd sourced vehicle perception data, which to our knowledge has not been previously explored and for which there are no existing measures. We propose the following measures: (1) Euclidean Distance measurement of paint color deviation compared to the ideal condition, (2) Contrast Ratio assessment of visibility contrast of detected traffic signs colors and (3) Environmental Contrast Ratio to assess visibility contrast of detected traffic signs with respect to the background. We validated our approach against FHWA recommendation guidelines and the federally recommended CIE Chromacity diagram.