Presentation 2022-12-05
A Method of Automatic Wall Detection from Room Images by Deep Neural Networks
Shunya Shimegi, Kaoru Arakawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In order to design interior renovation easily,a method of automatic wall area detection is proposed using deep neural networks.This method detects only wall area from images of wall front view which involve furniture.Such images of wall front view are obtained from omnidirectional camera,and after changing the color and pattern of the wall area,this proposed method can simulate the reformed room more realistically by reconstructing the images of walls,a floor,and a ceiling into an omnidirectional image on a head-mount display.Deep neural networks are applied to detect the wall area.Especially,a method for more precise detection is proposed by controlling the size of the input image by the value of the local variance,since the precision of wall detection depends on the image size.Computer simulations verified high performance of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Deep learning / Semantic segmentation / Image area extraction / Interior design
Paper # SIS2022-27
Date of Issue 2022-11-28 (SIS)

Conference Information
Committee SIS
Conference Date 2022/12/5(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tomoaki Kimura(Kanagawa Inst. of Tech.)
Vice Chair Naoto Sasaoka(Tottori Univ.) / Hakaru Tamukoh(Kyushu Inst. of Tech.)
Secretary Naoto Sasaoka(NTT) / Hakaru Tamukoh(Kansai Univ.)
Assistant Yoshiaki Makabe(Kanagawa Inst. of Tech.) / Yosuke Sugiura(Saitama Univ.)

Paper Information
Registration To Technical Committee on Smart Info-Media Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Method of Automatic Wall Detection from Room Images by Deep Neural Networks
Sub Title (in English)
Keyword(1) Deep learning
Keyword(2) Semantic segmentation
Keyword(3) Image area extraction
Keyword(4) Interior design
1st Author's Name Shunya Shimegi
1st Author's Affiliation Meiji University(Meiji Univ.)
2nd Author's Name Kaoru Arakawa
2nd Author's Affiliation Meiji University(Meiji Univ.)
Date 2022-12-05
Paper # SIS2022-27
Volume (vol) vol.122
Number (no) SIS-293
Page pp.pp.21-25(SIS),
#Pages 5
Date of Issue 2022-11-28 (SIS)