A template-based approach for real-time speed-limit-sign recognition on an embedded system using GPU computing

Authors:
Pinar Muyan-Özçelik;Vladimir Glavtchev;Jeffrey M. Ota;John D. Owens
Affiliations:
University of California, Davis, CA;University of California, Davis, and BMW Group Technology Office, Palo Alto, CA;BMW Group Technology Office, Palo Alto, CA;University of California, Davis, CA
Venue:
Proceedings of the 32nd DAGM conference on Pattern recognition
Year:
2010

Citing 6
Cited 0

Contrast limited adaptive histogram equalization

Graphics gems IV
Traffic Sign Recognition Revisited

Mustererkennung 1999, 21. DAGM-Symposium
Fast object recognition in noisy images using simulated annealing

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
OpenVIDIA: parallel GPU computer vision

Proceedings of the 13th annual ACM international conference on Multimedia
Road Signs Recognition by the Scale-Space Template Matching in the Log-Polar Domain

IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a template-based pipeline that performs realtime speed-limit-sign recognition using an embedded system with a lowend GPU as the main processing element. Our pipeline operates in the frequency domain, and uses nonlinear composite filters and a contrast-enhancing preprocessing step to improve its accuracy. Running at interactive rates, our system achieves 90% accuracy over 120 EU speed-limit signs on 45 minutes of video footage, superior to the 75% accuracy of a non-real-time GPU-based SIFT pipeline.