Superresolution of License Plates in Real Traffic Videos

In this paper, a novel method to enhance license plate numbers of moving vehicles in real traffic videos is proposed. A high-resolution image of the number plate is obtained by fusing the information derived from multiple, subpixel shifted, and noisy low-resolution observations. The image to be supe...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on intelligent transportation systems 2007-06, Vol.8 (2), p.321-331
Main Authors: Suresh, K.V., Kumar, G.M., Rajagopalan, A.N.
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Cameras
Computational efficiency
Computer science
control theory
systems
Control theory. Systems
Degradation
Exact sciences and technology
Gibbs distribution (GD)
graduated nonconvexity (GNC)
Ground, air and sea transportation, marine construction
Histograms
Image resolution
intelligent transport system
license plate text
Licenses
Markov random field (MRF)
Markov random fields
Mathematical models
Pattern recognition. Digital image processing. Computational geometry
Plates
Robotics
Robustness
Spatial resolution
superresolution
Traffic control
Traffic engineering
Traffic flow
Vehicles
Videos
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a novel method to enhance license plate numbers of moving vehicles in real traffic videos is proposed. A high-resolution image of the number plate is obtained by fusing the information derived from multiple, subpixel shifted, and noisy low-resolution observations. The image to be superresolved is modeled as a Markov random field and is estimated from the observations by a graduated nonconvexity optimization procedure. A discontinuity adaptive regularizer is used to preserve the edges in the reconstructed number plate for improved readability. Experimental results are given on several traffic sequences to demonstrate the robustness of the proposed method to potential errors in motion and blur estimates. The method is computationally efficient as all operations can be implemented locally in the image domain
ISSN:1524-9050
1558-0016
DOI:10.1109/TITS.2007.895291