Building inside structure recognition system and building inside structure recognition method

Patent metadata

Field	Value
Publication number	US-2025384675-A1
Application number	US-202218705195-A
Country	US
Kind code	A1
Filing date	Sep 5, 2022
Priority date	Oct 28, 2021
Publication date	Dec 18, 2025
Grant date	—

Abstract

Provided is a building inside structure recognition system for recognizing a structure in a building by using a machine learning model. A building inside structure recognition system according to the present invention comprises: a machine learning model generation device that generates a machine learning model by executing machine learning in which a correct image generated from building information modeling (BIM) data is set as correct data and a virtually observed image generated by rendering the BIM data is set as observation data; and a building inside structure recognition device that recognizes a structure in a building by using the machine learning model generated by the machine learning model generation device.

First claim

1 . A machine learning model generation device that generates a machine learning model for recognizing a structure in a building, the machine learning model generation device comprising:
a correct image generation unit that generates a correct image from building information modeling (BIM) data; a virtually observed image generation unit that generates a virtually observed image by rendering the BIM data; a machine learning model generation unit that generates a machine learning model by executing machine learning in which the correct image generated by the correct image generation unit is set as correct data and the virtually observed image is set as observation data; and a reinforcing image generation unit that generates a reinforcement image to be used as part of input data when generating the machine learning model, wherein the correct image is a mask image having a mask region indicating a structure, and the reinforcement image is an image obtained by extracting a center line of the mask region of the correct image.

2 . (canceled)

3 . (canceled)

4 . The machine learning model generation device according to claim 1 , further comprising a virtually observed image processing unit that generates an enhanced virtually observed image by performing, on the virtually observed image generated by the virtually observed image generation unit, image processing for bringing the virtually observed image closer to a real image.

5 . The machine learning model generation device according to claim 4 , wherein the image processing performed by the virtually observed image processing unit includes at least one or more of filtering of a spectral frequency, addition of a light source, addition of illumination light, or addition of a shadow.

6 . The machine learning model generation device according to claim 4 , wherein the virtually observed image processing unit generates a texture-added image by adding texture of the structure to the enhanced virtually observed image.

7 . The machine learning model generation device according to claim 1 , wherein the machine learning model generation unit generates the machine learning model by deep learning using a neural network.

8 . A building inside structure recognition device that recognizes a structure in a building by using a machine-learned model for recognizing a structure in a building, the building inside structure recognition device comprising
a recognition unit that when an image of inside of a real building is input to the machine-learned model as input data, recognizes a structure in the image to output a recognition result image indicating a region of the structure in the image as output data, wherein the machine-learned model is generated by executing machine learning in which a correct image generated from building information modeling (BIM) data is set as correct data and a virtually observed image generated by rendering the BIM data is set as observation data, and wherein a reinforcement image is used as part of input data when generating the machine learning model, and the correct image is a mask image having a mask region indicating a structure, and the reinforcement image is an image obtained by extracting a center line of the mask region of the correct image.

9 . The building inside structure recognition device according to claim 8 , wherein the recognition unit recognizes a structure in the image by further using a structure selection image indicating a region of the structure as input data in addition to the image of inside of the real building.

10 . The building inside structure recognition device according to claim 8 , wherein the recognition unit removes text included in the image of inside of the real building, and recognizes a structure in the image by using the image after text removal as input data.

11 . The building inside structure recognition device according to of claim 8 , wherein the machine-learned model is generated by deep learning using a neural network.

12 . A building inside structure recognition system for recognizing a structure in a building by using a machine learning model, the building inside structure recognition system comprising:
a machine learning model generation device that generates a machine learning model by executing machine learning in which a correct image generated from building information modeling (BIM) data is set as correct data and a virtually observed image generated by rendering the BIM data is set as observation data; and a building inside structure recognition device that recognizes a structure in a building by using the machine learning model generated by the machine learning model generation device, and wherein a reinforcement image is used as part of input data when generating the machine learning model, and the correct image is a mask image having a mask region indicating a structure, and the reinforcement image is an image obtained by extracting a center line of the mask region of the correct image.

13 . A building inside structure management system that manages a structure in a building recognized by using a machine-learned model for recognizing a structure in a building, the building inside structure management system comprising
a database that stores data on the structure recognized in the building inside structure recognition device according to claim 8 or data on a member of the structure.

14 . A building inside structure recognition system for recognizing a structure in a building by using a machine learning model, the building inside structure recognition system comprising:
the machine learning model generation device according to claim 1 ; and the building inside structure recognition device according to claim 8 .

15 . A building inside structure recognition method, comprising:
a step of generating a machine learning model by executing machine learning in which a correct image generated from building information modeling (BIM) data is set as correct data and a virtually observed image generated by rendering the BIM data is set as observation data; and a step of recognizing a structure in a building by using the machine learning model, and wherein a reinforcement image is used as part of input data when generating the machine learning model, and the correct image is a mask image having a mask region indicating a structure, and the reinforcement image is an image obtained by extracting a center line of the mask region of the correct image.

16 . A program that causes a computer to execute each step of the method according to claim 15 .

Assignees

• Topcon Corp
• Riken

Inventors

• Fukuma Yasufumi
• Mao Zaixing
• Tsukada Hisashi
• Ito Toru
• Wada Satoshi
• Yanobe Satoshi

Classifications

• G06V10/7715

  Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods · CPC title

• G06V10/462

  Salient features, e.g. scale invariant feature transforms [SIFT] · CPC title

• G06V10/82 Primary

  using neural networks · CPC title

• G06V10/774

  Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06T7/00

  Image analysis · CPC title