House map parameterization and re-editing modeling method

A modeling method and technology of floor plan, applied in the field of image recognition, can solve the problems of multiple memory, single display effect, no support for re-editing, etc., and achieve the effect of simplifying data calculation, improving accuracy, and reducing data volume

Active Publication Date: 2017-09-01
广州乐家数字科技有限公司
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing house-type map recognition technology or method does not have a complete recognition method for the basic characteristics of the house type, such as: walls, doors, windows, balconies, etc., resulting in a lack of a large amount of foundation for the final display effect, and the display effect is not good. good
In addition, some feature vector databases are pre-established and processed by matching with the database. The huge database will occupy more memory, which is not enough for mobile terminals with small memory such as mobile phones.
At the same time, the obtained feature data does not support the re-editing function. The type, material, and size of the features in the displayed 3D model cannot be changed, and the display effect is single, which cannot meet the actual needs of users.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • House map parameterization and re-editing modeling method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] Such as figure 1 As shown, a parametric re-editable modeling method for floor plan, which specifically includes the following steps:

[0045] Step 1: Preprocessing the floor plan provided by the user;

[0046] Step 2: Obtain the coordinates of the two ends of the centerline of the wall and the data of the thickness of the wall;

[0047] Step 3: Cutting the doors, windows and balconies in specific areas;

[0048] Step 4: Feature matching and recognition, obtain the feature type and the coordinates of the starting and ending ends;

[0049] Step 5: Whether to re-edit the identification data according to the user's requirements;

[0050] Step 6: 3D reconstruction of the floor plan, displaying from multiple angles and directions.

[0051] Described step one pretreatment method comprises the following steps:

[0052] 11) Grayscale processing is performed on the data after copying the original image data;

[0053] 12) Binarize the grayscale data;

[0054] 13) Expand the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention relates to the technical field of image recognition, and more particularly to a house map parameterization and re-editing modeling method. The method comprises the following steps: preprocessing a house map provided by a user; obtaining coordinates of two points of the beginning and the end of the center line of the wall and wall thickness data; carrying out cutting processing on the specific area of the door, the window, and the balcony; carrying out feature matching recognition to obtain a feature type and the coordinates of two points of the beginning and the end; according to user requirements, determining whether carrying out re-editing processing on recognition data; and carrying out three-dimensional reconstruction of the house map, and displaying the house map in a multi-angle and multi-dimension manner. The house map parameterization and re-editing modeling method provided by the present invention is a complete recognition method for basic features such as the wall, the door, the window, the balcony and so on of the house, and the re-editing function of each feature is supported; and the user can change the feature type, the material, and the size at will, so that the final display effect is more comprehensive, and actual requirements of the user are more in line with.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a parameterized and re-editable modeling method for a floor plan. Background technique [0002] The parameterized and re-editable modeling method of floor plans can be applied to standard browsers and mobile terminals. It is based on image recognition technology to parameterize the features of walls, doors, windows, balconies, etc. Or the mobile terminal can edit the parameters to create a three-dimensional display model, which supports multi-angle viewing of the three-dimensional effect of the house type. [0003] The existing house-type map recognition technology or method does not have a complete recognition method for the basic characteristics of the house type, such as: walls, doors, windows, balconies, etc., resulting in a lack of a large amount of foundation for the final display effect, and the display effect is not good. good. In addition, some feature vector...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/50G06T17/00
CPCG06T17/00G06F30/13
Inventor 陈煜
Owner 广州乐家数字科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products