Presentation 1999/1/22
Automatic Recognition of Road Signs
Takamitsu AWAKURA, Kazuyuki SASAKI, Masato NAKAJIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper we proposed a new method for detecting and recognizing road signs using sequence of color road images. We detect the shapes of road signs that are circle and triangle using generalized Hough Transform. In order to detect them efficiently, we estimate the parameters, which are the location and the size of the object in the next frame, when an object is detected. Therefore we can detect the object in limited parameter space. We use the principle of Motion stereo for estimating the parameters. After detecting objects, the meaning of objects are recognized by Matched filtering as an information retrieval operation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Road sign / generalized Hough Transform / Motion stereo / Matched filtering
Paper # PRMU98-201
Date of Issue

Conference Information
Committee PRMU
Conference Date 1999/1/22(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic Recognition of Road Signs
Sub Title (in English)
Keyword(1) Road sign
Keyword(2) generalized Hough Transform
Keyword(3) Motion stereo
Keyword(4) Matched filtering
1st Author's Name Takamitsu AWAKURA
1st Author's Affiliation Faculty Science and Technology, Keio University()
2nd Author's Name Kazuyuki SASAKI
2nd Author's Affiliation Faculty Science and Technology, Keio University
3rd Author's Name Masato NAKAJIMA
3rd Author's Affiliation Faculty Science and Technology, Keio University
Date 1999/1/22
Paper # PRMU98-201
Volume (vol) vol.98
Number (no) 528
Page pp.pp.-
#Pages 8
Date of Issue