Indoor automatic drawing and modeling method based on planar image

A technology of automatic mapping and modeling methods, which is applied in neural learning methods, biological neural network models, special data processing applications, etc., and can solve problems such as low room detection rate and difficulty in topology repair.

Active Publication Date: 2019-12-03
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, the room detection rate is low, the topology repair is difficult, and it can only deal with the floor plan in Manhattan form, or it needs to manually design a large number of special icon symbol extraction rules, which is difficult to generalize to other types of floor plan image recognition.

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
  • Indoor automatic drawing and modeling method based on planar image
  • Indoor automatic drawing and modeling method based on planar image
  • Indoor automatic drawing and modeling method based on planar image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described in detail with reference to the accompanying drawings.

[0067] An embodiment of the present invention provides an indoor automatic drawing and modeling method based on a plan image, the input of which is a plan image, and the output is an indoor map and model. The floor plan data used in this embodiment comes from the public dataset CVC-FP.

[0068] Please refer to figure 1 , figure 1 It is a flow chart of an indoor automatic drawing and modeling method based on a plan image in an embodiment of the present invention, specifically including the following steps:

[0069] S1: Manually annotate the true value of several floor plan images. The labeling of the true value refers to labeling the type, detection frame and segmented area for each indoor building element in each floo...

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 invention provides an indoor automatic drawing and modeling method based on a planar image. A planar image is used as a data source, instance segmentation is carried out on the planar image, semantic types and geometric contours of various indoor building elements such as walls and doors and windows are extracted, and a two-dimensional indoor map and a three-dimensional simple model which areconsistent in topology are generated through post-processing steps such as topological optimization and restoration. The method does not need to manually design a large number of image processing rules, directly obtains the image features through learning, and can be used for the recognition of various types of plane images. The method has the beneficial effects that the one-to-one detection rateof the indoor navigable space is effectively improved, inclined building elements on a plane image can be processed, and the requirements of indoor position service for maps and models of public places are met.

Description

technical field [0001] The invention relates to the technical field of indoor drawing and modeling, in particular to an indoor automatic drawing and modeling method based on planar images. Background technique [0002] In recent years, indoor positioning technology and indoor location services have developed rapidly, and the demand for basic data such as indoor maps and spatial models has also developed rapidly. Architectural floor plan images are a very popular type of data source in interior mapping and modeling production. Compared with surveying and modeling methods such as laser point cloud, floor plan is an easier data source to obtain and process. However, in the current indoor drawing and modeling production, the indoor drawing and modeling using the floor plan image as the data source requires professional draftsmen to extract vector space elements such as walls, rooms, doors and windows in the plan view. The process is very cumbersome and inefficient. Low, it is ...

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
IPC IPC(8): G06F17/50G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 尚建嘎吴怡洁陈攀
Owner CHINA UNIV OF GEOSCIENCES (WUHAN)
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