Exploring Image-based Classification to Detect Vehicle Make and Model
The goal of this work is to improve the understanding of the impact of carbon emissions caused by vehicular traffic on highway systems. In order to achieve this goal, this work obtains a novel pipeline for vehicle segmentation, tracking and classification by leveraging techniques in computer vision and machine learning using the existing Virginia Department of Transportation (VDOT) infrastructure on networked traffic cameras. This vehicle segmentation and classification data can be used to obtain a real-time estimation of carbon emissions. The VDOT traffic video is analyzed for vehicle detection and segmentation using an adaptive Gaussian mixture model algorithm. The segmented vehicles are tracked using speeded up reduced feature (SURF) methods. The morphological properties and histogram of oriented features are derived from the detected and segmented vehicles. Finally, vehicle classification is performed using a multiclass support vector machine classifier. The resulting classification scheme offers an average classification rate of 85% under good quality segmentation. This work constitutes the first step in estimating carbon emission for highway traffic. In the subsequent steps, additional vehicle information (e.g., type, model), speed, and other relevant parameters need to be extracted and used for the Environmental Protection Agency's Motor Vehicle Emissions Simulator (MOVES) or similar tools to estimate the carbon emission. More challenging weather conditions as well as nighttime scenarios also need to be included to make this tool applicable to real life application.
- Record URL:
- Summary URL:
-
Supplemental Notes:
- This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program. Cover date: December 2013.
-
Corporate Authors:
Old Dominion University
Department of Electrical Engineering
Norfolk, VA United StatesNational Institute for Advanced Transportation Technology
University of Idaho, Moscow
115 Engineering Physics Building
Moscow, ID United States 83844-0901Research and Innovative Technology Administration
1200 New Jersey Avenue, SE
Washington, DC United States 20590 -
Authors:
- Flora, Jeffrey B
- Alam, Mahbubul
- Yousef, Amr H
- Iftekharuddin, Khan M
- Publication Date: 2013-11
Language
- English
Media Info
- Media Type: Digital/other
- Edition: Final Report
- Features: Appendices; Figures; Photos; References; Tables;
- Pagination: 26p
Subject/Index Terms
- TRT Terms: Algorithms; Computer vision; Exhaust gases; Highway traffic; Image analysis; Pollutants; Real time information; Vehicle classification
- Identifier Terms: Virginia Department of Transportation
- Subject Areas: Data and Information Technology; Environment; Highways; Vehicles and Equipment; I15: Environment;
Filing Info
- Accession Number: 01505702
- Record Type: Publication
- Report/Paper Numbers: N13-03
- Contract Numbers: DTRT12GUTC17
- Files: UTC, TRIS, RITA, ATRI, USDOT
- Created Date: Jan 27 2014 11:27AM