Title:
DEVICE AND METHOD FOR GENERATING BUILDING IMAGE
Document Type and Number:
WIPO Patent Application WO/2022/131720
Kind Code:
A1
Abstract:
A device and a method for generating a building image, according to one embodiment of the present invention, comprises: a wireless communication unit; a database for storing a plurality of pieces of material data; and a control unit, which receives image data and a building material identifier from a portable terminal through the wireless communication unit, uses predetermined first weight data to separate an object, to which a material is to be applied, from the image data and generate a probability map, detects an edge from the image data to generate an edge map, uses the probability map, the edge map and predetermined second weight data to clearly separate the object, to which the material is to be applied, from the image data and generate an improved probability map, uses the pieces of material data, the improved probability map and the building material identifier to apply, to the image data, perspective and a material desired by a user of the portable terminal and generate actual building image data, and transmits, to the portable terminal, the actual building image data through the wireless communication unit.
More Like This:
Inventors:
HAN SANG KOOK (KR)
Application Number:
PCT/KR2021/018884
Publication Date:
June 23, 2022
Filing Date:
December 13, 2021
Export Citation:
Assignee:
DEEPBUILD CO LTD (KR)
International Classes:
G06T19/20; G06Q50/10; G06T3/00; G06T7/13; G06T15/04
Foreign References:
| KR20190065933A | 2019-06-12 | |||
| KR102224691B1 | 2021-03-09 |
Other References:
KAPTAN EFE ÇAĞIN: "IMAGE SEGMENTATION AND TEXTURE MAPPING ON PILLOWS USING FULLY CONVOLUTIONAL NEURAL NETWORKS", MASTER'S THESIS, THE REPUBLIC OF TURKEY BAHCESEHIR UNIVERSITY, 1 January 2018 (2018-01-01), XP055943056, Retrieved from the Internet
CHENG DONGCAI; MENG GAOFENG; XIANG SHIMING; PAN CHUNHONG: "FusionNet: Edge Aware Deep Convolutional Networks for Semantic Segmentation of Remote Sensing Harbor Images", IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, IEEE, USA, vol. 10, no. 12, 1 December 2017 (2017-12-01), USA, pages 5769 - 5783, XP011674695, ISSN: 1939-1404, DOI: 10.1109/JSTARS.2017.2747599
SULTANA MARYAM, KIM IN, JUNG SOON: "Deep Matting for AR Based Interior Design", METHODS AND APPLICATIONS FOR MODELING AND SIMULATION OF COMPLEX SYSTEMS : 18TH ASIA SIMULATION CONFERENCE, ASIASIM 2018, KYOTO, JAPAN, OCTOBER 27–29, 2018, PROCEEDINGS, SPRINGER SINGAPORE, SINGAPORE, vol. 1212, 31 January 2020 (2020-01-31), Singapore, pages 31 - 42, XP009538268, ISSN: 1865-0929, ISBN: 978-981-1328-53-4, DOI: 10.1007/978-981-15-4818-5_3
CHENG DONGCAI; MENG GAOFENG; XIANG SHIMING; PAN CHUNHONG: "FusionNet: Edge Aware Deep Convolutional Networks for Semantic Segmentation of Remote Sensing Harbor Images", IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, IEEE, USA, vol. 10, no. 12, 1 December 2017 (2017-12-01), USA, pages 5769 - 5783, XP011674695, ISSN: 1939-1404, DOI: 10.1109/JSTARS.2017.2747599
SULTANA MARYAM, KIM IN, JUNG SOON: "Deep Matting for AR Based Interior Design", METHODS AND APPLICATIONS FOR MODELING AND SIMULATION OF COMPLEX SYSTEMS : 18TH ASIA SIMULATION CONFERENCE, ASIASIM 2018, KYOTO, JAPAN, OCTOBER 27–29, 2018, PROCEEDINGS, SPRINGER SINGAPORE, SINGAPORE, vol. 1212, 31 January 2020 (2020-01-31), Singapore, pages 31 - 42, XP009538268, ISSN: 1865-0929, ISBN: 978-981-1328-53-4, DOI: 10.1007/978-981-15-4818-5_3
Attorney, Agent or Firm:
KO, Young Kap (KR)
Download PDF:
Previous Patent: METHOD FOR AUTHENTICATING ACCESS LAYER ON BASIS OF PUBLIC KEY INFRASTRUCTURE IN CONSIDERATION OF HAN...
Next Patent: REFRIGERATOR
Next Patent: REFRIGERATOR