Abstract
Thermal imaging, when coupled with deep-learning-based analysis, can significantly improve highway work zone management and safety, though data scarcity in this field has been a historical challenge. We collected over 440 hours of thermal footage from highway sites in Massachusetts and New Hampshire and created a vehicle segmentation dataset featuring over 14,000 vehicle instances. We implement effective training strategies for deep learning models and develop algorithms to analyze vehicle trajectories and merging behaviors. Various visualization techniques are illustrated to better understand the extensive analytics data generated for each site, which can lead to development of data-driven strategies to improve Traffic management and safety. GitHub repository: https://github.com/z00bean/SmartWorkZoneControl.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
