Login

A Template-Based Approach for Real-Time Speed-Limit-Sign Recognition on an Embedded System using GPU Computing

@inproceedings{Muyan-Ozcelik:2010:ATA,
title="A Template-Based Approach for Real-Time Speed-Limit-Sign Recognition on an Embedded System using GPU Computing",
booktitle="DAGM (The German Association for Pattern Recognition) Symposium",
author="Pinar Muyan-Ozcelik AND Vladimir Glavtchev AND Jeffrey M. Ota AND John D. Owens ",
year="2010",
keywords="GPU computing, computer vision, embedded systems, real-time automotive computing applications",
pages="162–171",
organization="DAGM (The German Association for Pattern Recognition) Symposium",
publisher="Springer Series on Lecture Notes in Computer Science (LNCS)",
location="Darmstadt, Germany",
eventtime="September 22-24, 2010",
abstract="We present a template-based pipeline that performs real-time speed-limit-sign recognition using an embedded system with a low-end 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.",
}
back to publication