Title:
GENERATION DEVICE, GENERATION METHOD AND PROGRAM FOR THREE-DIMENSIONAL MODEL
Document Type and Number:
WIPO Patent Application WO/2019/116942
Kind Code:
A1
Abstract:
The purpose of the present invention is to prevent a defect from occurring in a three-dimensional model to be generated, even when a structure or the like that obstructs a part of a target object exists in a photographed scene. This generation device of a three-dimensional model is characterized by having: an acquisition means which acquires a first mask image that represents a region of a structure, which is a stationary object in each image photographed at a plurality of viewpoints, and a second mask image that represents a region of the foreground, which is an object of a moving body in each of the images photographed at the plurality of viewpoints; a synthesis means which synthesizes the acquired first mask images and second mask images, and generates a third mask image in which the structure regions and the foreground regions in the images photographed at the plurality of viewpoints are integrated; and a generation means which generates the three-dimensional model including the structure and the foreground by means of a visual cone intersection using the third mask image.
Inventors:
MORISAWA KEISUKE (JP)
KOBAYASHI KIWAMU (JP)
KOBAYASHI KIWAMU (JP)
Application Number:
PCT/JP2018/044373
Publication Date:
June 20, 2019
Filing Date:
December 03, 2018
Export Citation:
Assignee:
CANON KK (JP)
International Classes:
G06T7/55; G06T1/00; G06T5/50; H04N5/232; H04N7/18
Foreign References:
| JP2008191072A | 2008-08-21 | |||
| JP2012088114A | 2012-05-10 | |||
| JPH11149576A | 1999-06-02 | |||
| JP2014010805A | 2014-01-20 | |||
| JP2017239891A | 2017-12-14 | |||
| JP2018089467A | 2018-06-14 | |||
| JP2018209196A | 2018-11-06 |
Other References:
IWASHITA, YUMI ET AL.: "3D Tracking of Multiple moving objects using fast level set method", JOURNAL OF THE ROBOTICS SOCIETY OF JAPAN, vol. 23, no. 7, 1 October 2005 (2005-10-01), pages 47 - 54, XP055640845, DOI: 10.7210/jrsj.23.813
LAURENTINI A: "The Visual Hull Concept for Silhouette-Based Image Understanding", IEEE TRANSCRIPTIONS PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 16, no. 2, February 1994 (1994-02-01), pages 150 - 162, XP008103532, DOI: 10.1109/34.273735
LAURENTINI A: "The Visual Hull Concept for Silhouette-Based Image Understanding", IEEE TRANSCRIPTIONS PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 16, no. 2, February 1994 (1994-02-01), pages 150 - 162, XP008103532, DOI: 10.1109/34.273735
Attorney, Agent or Firm:
TANI & ABE, P.C. (JP)
Download PDF: