A method of building component extraction based on a Faster-RCNN model

A technology of building components and extraction methods, which is applied in the fields of deep learning and image target detection, and can solve the problems of missing building components, wrong identification of building component categories, and large manpower.

Active Publication Date: 2018-12-14
HUAIYIN INSTITUTE OF TECHNOLOGY
View PDF6 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0016] For the building component information in manual architectural engineering drawings, the traditional method is to identify and count through human eyes. There are problems in the identification of building component categories, missing building components and requiring a lot of manpower.

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
  • A method of building component extraction based on a Faster-RCNN model
  • A method of building component extraction based on a Faster-RCNN model
  • A method of building component extraction based on a Faster-RCNN model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] Below in conjunction with specific embodiment, further illustrate the present invention, should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various equivalent forms of the present invention All modifications fall within the scope defined by the appended claims of the present application.

[0064] Such as Figure 1-4 As shown, a method for extracting building components based on the Faster-RCNN model of the present invention comprises the following steps:

[0065] Step 1: Perform grayscale, binarization, and segmentation preprocessing on the preprocessing drawing data set Drawing for construction engineering to obtain the preprocessing drawing image block data set DrawingBlock, specifically as figure 2 Shown:

[0066] Step 1.1: Define preprocessing drawing dataset Drawing, preproc...

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 discloses a method of building component extraction based on a Faster-RCNN model. The method includes: firstly, binarizing and segmenting the building engineering drawing image to obtainthe image block data set; then, using the labelImg tool to label the building elements in the dataset, and obtaining a building component recognition model is obtained by Faster-RCNN training, and storing the building component information extracted from the model in the drawings in a structured form. The method of the invention effectively extracts the building component information in the manual building engineering drawings, so that the utilization ratio of the manual building engineering drawings is improved, and the use value of the manual building engineering drawings is increased.

Description

technical field [0001] The invention belongs to the technical field of deep learning and image target detection, in particular to a method for extracting building components based on the Faster-RCNN model. Background technique [0002] The method for extracting building components in the present invention has an important function and significance for the utilization of manual building engineering drawings. When facing the problem of image target detection, researchers will choose traditional feature extraction technology or target detection technology based on deep learning, and use the above technology to detect image targets. Using image target detection technology to extract building components from manual architectural drawings, thereby improving the utilization rate of manual architectural drawings and providing a solution for the utilization of manual architectural drawings. [0003] The existing research bases of Feng Wanli, Zhu Quanyin and others include: Wanli Fen...

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): G06K9/62G06K9/34G06K9/32
CPCG06V10/267G06V10/25G06F18/214G06F18/24
Inventor 朱全银许康宗慧冯万利周泓李翔严云洋高尚兵
Owner HUAIYIN INSTITUTE OF TECHNOLOGY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap