<  Back to the Polytechnique Montréal portal

Automatic traffic data collection under varying lighting and temperature conditions in multimodal environments: thermal versus visible spectrum video-based systems

Ting Fu, Joshua Stipancic, Sohail Zangenehpour, Luis Miranda-Moreno and Nicolas Saunier

Article (2017)

[img]
Preview
Published Version
Terms of Use: Creative Commons Attribution.
Download (3MB)
Cite this document: Fu, T., Stipancic, J., Zangenehpour, S., Miranda-Moreno, L. & Saunier, N. (2017). Automatic traffic data collection under varying lighting and temperature conditions in multimodal environments: thermal versus visible spectrum video-based systems. Journal of Advanced Transportation, 2017, p. 1-15. doi:10.1155/2017/5142732
Show abstract Hide abstract

Abstract

Vision-based monitoring systems using visible spectrum (regular) video cameras can complement or substitute conventional sensors and provide rich positional and classification data. Although new camera technologies, including thermal video sensors, may improve the performance of digital video-based sensors, their performance under various conditions has rarely been evaluated at multimodal facilities. The purpose of this research is to integrate existing computer vision methods for automated data collection and evaluate the detection, classification, and speed measurement performance of thermal video sensors under varying lighting and temperature conditions. Thermal and regular video data was collected simultaneously under different conditions across multiple sites. Although the regular video sensor narrowly outperformed the thermal sensor during daytime, the performance of the thermal sensor is significantly better for low visibility and shadow conditions, particularly for pedestrians and cyclists. Retraining the algorithm on thermal data yielded an improvement in the global accuracy of 48%. Thermal speed measurements were consistently more accurate than for the regular video at daytime and nighttime. Thermal video is insensitive to lighting interference and pavement temperature, solves issues associated with visible light cameras for traffic data collection, and offers other benefits such as privacy, insensitivity to glare, storage space, and lower processing requirements.

Open Access document in PolyPublie
Subjects: 1000 Génie civil > 1000 Génie civil
1000 Génie civil > 1003 Génie du transport
Department: Département des génies civil, géologique et des mines
Research Center: Non applicable
Funders: McGill Engineering Doctoral Award, CRSNG/NSERC
Date Deposited: 14 Dec 2018 15:59
Last Modified: 15 Dec 2018 01:20
PolyPublie URL: https://publications.polymtl.ca/3532/
Document issued by the official publisher
Journal Title: Journal of Advanced Transportation (vol. 2017)
Publisher: Hindawi
Official URL: https://doi.org/10.1155/2017/5142732

Statistics

Total downloads

Downloads per month in the last year

Origin of downloads

Dimensions

Repository Staff Only