Presentation 2013-03-15
Recognition of Blocks Worlds from Monocular Single Images Considering Spatial Relationship between Blocks
Daichi TANII, Hotaka TAKIZAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this report, we propose a method of recognizing block scenes from monocular images. Block-like objects are represented by 3-D object models. At each location in a scene, several promising models are generated. The fidelity of the object models to edges extracted from the images and the interrelations between the adjoining object models are evaluated by use of the Markov Random Field (MRF)model that is composed of the object models. The most likely state of the MRF model is obtained by minimizing its posteriori energy function with a primal-dual interior point method. The proposed method is applied to actual scenes including several block-like objects.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Scene understanding / Markov Random Field model / Block models / Interrelations / Edge images
Paper # PRMU2012-213
Date of Issue

Conference Information
Committee PRMU
Conference Date 2013/3/7(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) Recognition of Blocks Worlds from Monocular Single Images Considering Spatial Relationship between Blocks
Sub Title (in English)
Keyword(1) Scene understanding
Keyword(2) Markov Random Field model
Keyword(3) Block models
Keyword(4) Interrelations
Keyword(5) Edge images
1st Author's Name Daichi TANII
1st Author's Affiliation Graduate School of Systems and Information Engineering()
2nd Author's Name Hotaka TAKIZAWA
2nd Author's Affiliation Faculty of Engineering
Date 2013-03-15
Paper # PRMU2012-213
Volume (vol) vol.112
Number (no) 495
Page pp.pp.-
#Pages 6
Date of Issue