Presentation 2003/1/9
Detection of Pedestrian Crossing from An Image
Sugruru KITAWAKI, Tadayoshi SHIOYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) For the purpose of assisting for the blind to cross a pedestrian crossing alone in safety, we have estimated the distance between an endline of the pedestrian crossing and the observer by using the image data under the assumption that the blind is in front of the pedestrian crossing. This presents a method for detecting the pedestrian crossing as pre-processing of length estimation. First, segmentation is performed by using gabor energy in a grayscale image and the color information of the input image, and a candidate region of the pedestrian crossing is extracted. Next, in order to detect the pedestrian crossing, we check the periodicity of the white line at the pedestrian crossing by calculating a projective invariant in extracted candidate region. Experimental results based on this proposal method are given by using many real images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Detection of pedestrian crossing / Image data / The blind / Gabor energy / Projective invariant
Paper # PRMU2002-174
Date of Issue

Conference Information
Committee PRMU
Conference Date 2003/1/9(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) Detection of Pedestrian Crossing from An Image
Sub Title (in English)
Keyword(1) Detection of pedestrian crossing
Keyword(2) Image data
Keyword(3) The blind
Keyword(4) Gabor energy
Keyword(5) Projective invariant
1st Author's Name Sugruru KITAWAKI
1st Author's Affiliation Graduate School of Science and Technology, Kyoto Institute of technology()
2nd Author's Name Tadayoshi SHIOYAMA
2nd Author's Affiliation Graduate School of Science and Technology, Kyoto Institute of Technology
Date 2003/1/9
Paper # PRMU2002-174
Volume (vol) vol.102
Number (no) 554
Page pp.pp.-
#Pages 6
Date of Issue