High-efficiency phase unwrapping method based on deep convolutional neural network

A convolutional neural network and phase unwrapping technology, applied in the field of high-efficiency phase unwrapping, can solve problems such as degradation and difficult network training, and achieve high-precision and high-efficiency effects

Pending Publication Date: 2019-09-06
SOUTHEAST UNIV
View PDF3 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In theory, deeper convolutional neural networks have more powerful feature extraction and classification capabilities, but in practice, a

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
  • High-efficiency phase unwrapping method based on deep convolutional neural network
  • High-efficiency phase unwrapping method based on deep convolutional neural network
  • High-efficiency phase unwrapping method based on deep convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] refer to figure 1 , in order to solve the phase unwrapping problem, the technical solution adopted by the present invention is to provide a method based on a deep convolutional neural network, comprising the following steps:

[0029] Step 1: Build the dataset. In one plane, through the superposition of four two-dimensional Gaussian functions with random positions, standard deviations, and peak values, the absolute phase of the three-dimensional surface shape in the objective reality is simulated; the main value of the frequency phase is superimposed on the absolute phase, and The main value of the superimposed result is used to simulate the wrapped phase measured after the three-dimensional surface shape measurement; the number of phase wrapped corresponding to the wrapped phase is determined by the number of periods intercepted during the process of taking the main value of the absolute phase. The following codes based on Matlab language are important algorithm codes ...

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 a high-efficiency phase unwrapping method based on a deep convolutional neural network. The method comprises the following steps: step 1, acquiring data of wrapped phases and phase wrapping times through software simulation, and establishing a training sample database according to the data; step 2, constructing a deep convolutional neural network with a residual path by utilizing a convolutional layer, a pooling layer, batch normalization, an activation function ReLu, an upper sampling layer and a Softmax classifier; step 3, preprocessing the data set obtained in the step 1, taking the preprocessed image as training data, and training a deep convolutional neural network model to obtain network model parameters; and step 4, inputting a to-be-expanded wrapped phase, expanding the wrapped phase by using the convolutional neural network model in the step 3, and visualizing the wrapped phase. According to the method, the construction problem of the sample database issolved, and high-precision phase unwrapping is realized on the premise of ensuring the measurement efficiency.

Description

technical field [0001] The invention relates to a high-efficiency phase unwrapping method based on a deep convolutional neural network, which belongs to the technical fields of optics, computer vision and artificial intelligence. Background technique [0002] In recent years, with the development of computer technology, the three-dimensional surface measurement of objects has become an important branch of computer measurement and calculation, and is widely used in various fields, such as face recognition and reconstruction, satellite radar interferometry, etc. Among many 3D surface shape measurement methods, the optical 3D surface shape measurement method based on phase analysis has received extensive attention and research due to its advantages of non-contact, fast measurement speed, and high measurement accuracy. The optical measurement based on phase analysis can be roughly divided into three steps: phase recovery, phase unwrapping, and phase-to-3D surface depth mapping. ...

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): G06F17/50G06T17/00G06K9/62G06N3/04
CPCG06T17/00G06F30/20G06N3/045G06F18/241
Inventor 王辰星汪懋荣
Owner SOUTHEAST UNIV
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