Presentation 2019-02-20
Detection of Improper Tactile Paving using Pedestrian Viewpoint video
Kento Watanabe, Hiroki Takahashi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Currently, there are 36 million blind people in the whole world. Furthermore, the number of blind people will be expected to increase to 150 million people by 2050. Tactile paving takes a very important role. Many tactile paving is, however, inappropriate. This paper describes a deficient tactile paving detection algorithm from a pedestrian view point video. In this method, firstly, for the first frame of the video, the tactile paving is detected using color thresholding and noise removal. In the subsequent frames, candidates of tactile paving regions are extracted by performing only on the tactile paving region obtained in the previous frame and its surroundings. Furthermore, the final tactile paving region is obtained by merging with the tactile paving extracted by using HOG(Histogram of Oriented Gradients) features with the candidates. Contour tracking and corner detection are performed on the obtained region. Finally, Inappropriate tactile paving is judged based on the contour and corner information. In the proposed method, tactile paving in six different states was judged.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Tactile Paving Surfaces / Visual Impairment / Region Detection / Corner Detection / HOG Feature
Paper # ITS2018-73,IE2018-94
Date of Issue 2019-02-12 (ITS, IE)

Conference Information
Committee ITS / IE / ITE-MMS / ITE-HI / ITE-ME / ITE-AIT
Conference Date 2019/2/19(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Hokkaido Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English) Image Processing, etc.
Chair Takayoshi Yokota(Tottori Univ.) / Takayuki Hamamoto(Tokyo Univ. of Science) / Norihiko Ishii(NHK) / Masayuki Sato(Kitakyushu Univ.) / Norio Tagawa(Tokyo Metropolitan Univ.) / Nobuhiko Mukai(Tokyo City Univ.)
Vice Chair Masahiro Fujii(Utsunomiya Univ.) / Tomotaka Wada(Kansai Univ.) / Hideaki Kimata(NTT) / Kazuya Kodama(NII) / / / Hiroyuki Arai(Nippon Institute of Technology) / Hisaki Nate(Tokyo Polytechnic Univ.)
Secretary Masahiro Fujii(Saitama Univ.) / Tomotaka Wada(Univ. of Tokyo) / Hideaki Kimata(KDDI Research) / Kazuya Kodama(Nagoya Univ.) / (NHK) / (NTT) / Hiroyuki Arai(NHK) / Hisaki Nate(Hokkaido Univ.)
Assistant Msataka Imao(Mitsubishi Electric) / Yanlei Gu(Univ. of Tokyo) / Kenshi Saho(Toyama Prefectural Univ.) / Kouichiro Hashiura(Akita Prefectural Univ.) / Kazuya Hayase(NTT) / Yasutaka Matsuo(NHK)

Paper Information
Registration To Technical Committee on Intelligent Transport Systems Technology / Technical Committee on Image Engineering / Technical Group on Multi-media Storage / Technical Group on Human Information / Technical Group on Media Engineering / Technical Group on Artistic Image Technology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Detection of Improper Tactile Paving using Pedestrian Viewpoint video
Sub Title (in English)
Keyword(1) Tactile Paving Surfaces
Keyword(2) Visual Impairment
Keyword(3) Region Detection
Keyword(4) Corner Detection
Keyword(5) HOG Feature
Keyword(6)
1st Author's Name Kento Watanabe
1st Author's Affiliation The University of Electro-Communications(UEC)
2nd Author's Name Hiroki Takahashi
2nd Author's Affiliation The University of Electro-Communications(UEC)
Date 2019-02-20
Paper # ITS2018-73,IE2018-94
Volume (vol) vol.118
Number (no) ITS-449,IE-450
Page pp.pp.141-146(ITS), pp.141-146(IE),
#Pages 6
Date of Issue 2019-02-12 (ITS, IE)