3D reconstruction method of optical building target based on deep neural network

A deep neural network and three-dimensional reconstruction technology, applied in neural learning methods, biological neural network models, neural architectures, etc., to achieve the effect of ensuring quality and improving accuracy

Active Publication Date: 2022-03-01
电子科技大学成都学院
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the development of modern technology, architectural 3D reconstruction technology has attracted more and more attention in today's society. People use computers to convert 2D images into 3D data. 3D data refers to the generated 3D images stored in the form of digital models in the computer However, traditional architecture can no longer meet people's needs, and 3D architecture plays an increasingly important role in neighborhoods or scenes such as urban planning, intelligent buildings, disaster monitoring, and digital cities.

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
  • 3D reconstruction method of optical building target based on deep neural network
  • 3D reconstruction method of optical building target based on deep neural network
  • 3D reconstruction method of optical building target based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0048] 1. Locally recursive optical image building segmentation based on OSTU criterion and image entropy

[0049] 1. Optical image preprocessing

[0050] The quality of the image processing effect often has a direct impact on the accurate segmentation rate and effect of the image. Image segmentation preprocessing usually needs to be completed before an image starts to be segmented. Image information preprocessing technology broadly refers to image recognition for each important part of the image input by the user, eliminates useless information in the input image information, restores the real and useful image information in the input image in time, and enhances the accuracy of the input image information. Accuracy, reliability and detection, and at the same time, the image data segmentation can be optimized and simplified, thereby...

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 provides a method for three-dimensional reconstruction of optical architectural objects based on deep neural network, constructing optical image building datasets by labeling, and constructing deep neural network to extract optical buildings; preprocessing the input image to enhance the optical image Quality, using the local recursive method based on OTSU criterion and image entropy to segment the processed optical image, and through the training of its data set, the deep neural network has a better extraction ability; through the SENSOR simulation software, the optical target light can be quickly simulated ‑The method of building a data set for the target 3D point cloud, using the 3D‑R2N2 network to conduct a centralized study on the 3D data of the optical target image obtained, so that the 2D image is mapped to the 3D model, so as to obtain the instance of the object in an end-to-end manner, Obtaining 3D reconstruction results from optical images provides good value for development in the field of architecture.

Description

technical field [0001] The invention relates to the technical field of three-dimensional reconstruction, in particular to a method for three-dimensional reconstruction of optical architectural objects based on a deep neural network. Background technique [0002] With the development of modern technology, architectural 3D reconstruction technology has attracted more and more attention in today's society. People use computers to convert 2D images into 3D data. 3D data refers to the generated 3D images stored in the form of digital models in the computer However, traditional architecture can no longer meet people's needs, and 3D architecture is playing an increasingly important role in neighborhoods or scenes such as urban planning, intelligent buildings, disaster monitoring, and digital cities. Up to now, in-depth research has been carried out at home and abroad on the three-dimensional feature signal detection, feature signal matching, and camera feature calibration of buildi...

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 Patents(China)
IPC IPC(8): G06T17/00G06T7/10G06N3/04G06N3/08
CPCG06T17/00G06T7/10G06N3/08G06T2207/20081G06T2207/20084G06N3/045
Inventor 邹倩颖郭雪喻淋蔡雨静
Owner 电子科技大学成都学院
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