Title: Selection of an Optimal Set of Discriminative and Robust Local Features with Application to Traffic Sign Recognition
Authors: Höferlin, Benjamin
Heidemann, Gunther
Citation: WSCG 2010: Full Papers Proceedings: 18th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision in co-operation with EUROGRAPHICS, p. 9-16.
Issue Date: 2010
Publisher: Václav Skala - UNION Agency
Document type: konferenční příspěvek
URI: http://wscg.zcu.cz/WSCG2010/Papers_2010/!_2010_FULL-proceedings.pdf
ISBN: 978-80-86943-88-6
Keywords: diskriminační místní znaky;rozpoznávání dopravních značek
Keywords in different language: discriminative local features;traffic sign recognition
Abstract: Today, discriminative local features are widely used in different fields of computer vision. Due to their strengths, discriminative local features were recently applied to the problem of traffic sign recognition (TSR). First of all, we discuss how discriminative local features are applied to TSR and which problems arise in this specific domain. Since TSR has to cope with highly structured and symmetrical objects, which are often captured at low resolution, only a small number of features can be matched correctly. To alleviate these issues, we provide an approach for the selection of discriminative and robust features to increase the matching performance by speed, recall, and precision. Contrary to recent techniques that solely rely on density estimation in feature space to select highly discriminative features, we additionally address the question of features’ retrievability and positional stability under scale changes as well as their reliability to viewpoint variations. Finally, we combine the proposed methods to obtain a small set of robust features that have excellent matching properties.
Rights: © Václav Skala - UNION Agency
Appears in Collections:WSCG 2010: Full Papers Proceedings

Files in This Item:
File Description SizeFormat 
Hoferlin.pdfPlný text1,61 MBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/10857

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.