Estimating vehicle fuel economy from overhead camera imagery and application for traffic control

dc.contributor.authorKarnowski, Thomas
dc.contributor.authorTokola, Ryan
dc.contributor.authorOesch, T Sean
dc.contributor.authorEicholtz, Matthew R.
dc.contributor.authorPrice, Jeff
dc.contributor.authorGee, Tim
dc.date.accessioned2022-11-17T20:40:49Z
dc.date.available2022-11-17T20:40:49Z
dc.date.issued2020-01-01
dc.descriptionConference. Library patrons may search WorldCat to identify libraries that hold this conference proceeding. Public Access Policy Public access comprises the efforts of U.S. federal science agencies to increase access to unclassified scholarly publications and digital data resulting from federal research and development (R&D) funding. While OSTI has provided public access to DOE's unclassified R&D results throughout its history, the incremental change reflected in the DOE Public Access Plan is the addition of final accepted manuscripts/journal articles, which OSTI makes publicly available within 12 months of publication. Access is provided through both OSTI.GOV and the DOE Public Access Gateway for Energy and Science (DOE PAGES®).
dc.description.abstractIn this work, we explore the ability to estimate vehicle fuel consumption using imagery from overhead fisheye lens cameras deployed as traffic sensors. We utilize this information to simulate vision-based control of a traffic intersection, with a goal of improving fuel economy with minimal impact to mobility. We introduce the ORNL Overhead Vehicle Dataset (OOVD), consisting of a data set of paired, labeled vehicle images from a ground-based camera and an overhead fisheye lens traffic camera. The data set includes segmentation masks based on Gaussian mixture models for vehicle detection. We show the dataset utility through three applications: the estimate of fuel consumption based on segmentation bounding boxes, vehicle discrimination for those vehicles with largest bounding boxes, and a fine-grained classification on a limited number of vehicle makes and models using a pre-trained set of convolutional neural network models. We compare these results with estimates based on a large open-source data set based on web-scraped imagery. Finally, we show the utility of the approach using reinforcement learning in a traffic simulator using the open source Simulation of Urban Mobility (SUMO) package. Our results show the feasibility of the approach for controlling traffic lights for better fuel efficiency based solely on visual vehicle estimates from commercial, fisheye lens cameras.
dc.description.sponsorshipUSDOE Office of Energy Efficiency and Renewable Energy (EERE)
dc.description.urihttps://www.osti.gov/biblio/1607112
dc.identifier.citationKarnowski, Thomas, Tokola, Ryan, Oesch, T Sean, Eicholtz, Matthew, Price, Jeff, & Gee, Tim. Estimating vehicle fuel economy from overhead camera imagery and application for traffic control. United States.
dc.identifier.urihttp://hdl.handle.net/11416/915
dc.language.isoen_US
dc.publisherOSTI.GOV U.S. Department of Energy Office of Scientific and Technical Information
dc.subjectEnergy consumption
dc.subjectComputer science
dc.titleEstimating vehicle fuel economy from overhead camera imagery and application for traffic control
dc.typeOther

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Estimating vehicle fuel economy from overhead camera imagery and application for traffic control.pdf
Size:
759.88 KB
Format:
Adobe Portable Document Format
Description:

Collections