SAFETYLIT WEEKLY UPDATE

We compile citations and summaries of about 400 new articles every week.
RSS Feed

HELP: Tutorials | FAQ
CONTACT US: Contact info

Search Results

Journal Article

Citation

Saturnino MB, Lafuente-Arroyo S, Gil-Jimenez P, Gomez-Moreno H, Lopez-Ferreras F. IEEE Trans. Intel. Transp. Syst. 2007; 8(2): 264-278.

Copyright

(Copyright © 2007, IEEE (Institute of Electrical and Electronics Engineers))

DOI

unavailable

PMID

unavailable

Abstract

In this paper the authors present an automated method for road-sign detection and recognition that relies on support vector machines (SVM) for applications in automatic traffic sign maintenance as well as in visual driver assistance systems. The presented system employs classification and detection in three steps. The first is segmentation from the color of the pixel to be analyzed using hue saturation intensity (HSI). The next step is the determination of traffic sign shape through linear SVM and, lastly, content recognition is established through Gaussian-kernel SVM. Of these two steps, the first is designed to classify the candidate blob as a specific shape among the types of traffic signs stored in the vehicle?s database. The second, which uses the Gaussian kernel, is used to determine what shapes and content is printed on the sign itself.

NEW SEARCH


All SafetyLit records are available for automatic download to Zotero & Mendeley
Print