Presentation 2022-06-09
Quantification of the danger of arbitrary walking scenes based on outdoor walking collision simulation within a 3DCG map space
Yukihiro Matsunaga, Masato Matsuoka, Hiromu Tanaka, Hideaki Kawano,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) One of the problems that visually impaired people face when they go out is an accident caused by collision with an obstacle. In order to avoid collisions with obstacles when walking outdoors, this study used models learned by CNN and LSTM to calculate the degree of risk for time-series images of collision scenes with multiple patterns of obstacles in a 3DCG map space, and verified whether the appropriate degree of risk could be quantified. As a result, it was confirmed that the model was able to quantify the appropriate risk level for not only stationary obstacles but also moving obstacles according to each scene, enabling the visually impaired to recognize the danger in various collision scenes.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Walking assistance / 3DCG map space / risk quantification / CNN / LSTM
Paper # SIS2022-2
Date of Issue 2022-06-02 (SIS)

Conference Information
Committee SIS / IPSJ-AVM
Conference Date 2022/6/9(2days)
Place (in Japanese) (See Japanese page)
Place (in English) KIT(Wakamatsu Campus)
Topics (in Japanese) (See Japanese page)
Topics (in English) Intelligent Multimedia Systems, Applied Embedded Systems, Three-Dimensional Image Technology (3DIT), etc.
Chair Noriaki Suetake(Yamaguchi Univ.) / Sei Naito(KDDI Research, Inc.)
Vice Chair Tomoaki Kimura(Kanagawa Inst. of Tech.) / Naoto Sasaoka(Tottori Univ.)
Secretary Tomoaki Kimura(NTT) / Naoto Sasaoka(National Inst. of Tech., Ube College) / (NTT)
Assistant Soh Yoshida(Kansai Univ.) / Yoshiaki Makabe(Kanagawa Inst. of Tech.)

Paper Information
Registration To Technical Committee on Smart Info-Media Systems / Special Interest Group on Audio Visual and Multimedia Information Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Quantification of the danger of arbitrary walking scenes based on outdoor walking collision simulation within a 3DCG map space
Sub Title (in English)
Keyword(1) Walking assistance
Keyword(2) 3DCG map space
Keyword(3) risk quantification
Keyword(4) CNN
Keyword(5) LSTM
1st Author's Name Yukihiro Matsunaga
1st Author's Affiliation Kyushu Institute of Technology(Kyutech)
2nd Author's Name Masato Matsuoka
2nd Author's Affiliation Kyushu University(Kyushu Univ.)
3rd Author's Name Hiromu Tanaka
3rd Author's Affiliation Kyushu Institute of Technology(Kyutech)
4th Author's Name Hideaki Kawano
4th Author's Affiliation Kyushu Institute of Technology(Kyutech)
Date 2022-06-09
Paper # SIS2022-2
Volume (vol) vol.122
Number (no) SIS-62
Page pp.pp.7-11(SIS),
#Pages 5
Date of Issue 2022-06-02 (SIS)