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.

Document type: Article

Full document

The PDF file did not load properly or your web browser does not support viewing PDF files. Download directly to your device: Download PDF document

Original document

The different versions of the original document can be found in:

http://downloads.hindawi.com/journals/jat/2017/5142732.xml,
http://dx.doi.org/10.1155/2017/5142732
https://doaj.org/toc/0197-6729,
https://doaj.org/toc/2042-3195 under the license http://creativecommons.org/licenses/by/4.0/
http://downloads.hindawi.com/journals/jat/2017/5142732.pdf,
https://publications.polymtl.ca/3532,
[=citjournalarticle_551545_12 https://www.safetylit.org/citations/index.php?fuseaction=citations.viewdetails&citationIds[]=citjournalarticle_551545_12],
https://trid.trb.org/view/1479693,
https://core.ac.uk/display/88193415,
https://academic.microsoft.com/#/detail/2569164774
Back to Top

Document information

Published on 01/01/2017

Volume 2017, 2017
DOI: 10.1155/2017/5142732
Licence: Other

Document Score

0

Views 1
Recommendations 0

Share this document

claim authorship

Are you one of the authors of this document?