Unlock instant, AI-driven research and patent intelligence for your innovation.

Depth measurement method based on combination of deep learning and structured light

A deep learning and depth measurement technology, applied in the field of 3D reconstruction, can solve the problem of low depth measurement accuracy

Active Publication Date: 2020-01-14
WUHAN UNIV OF SCI & TECH
View PDF28 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application solves the problem of low accuracy of depth measurement in the prior art by providing a depth measurement method based on the combination of deep learning and structured light

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
  • Depth measurement method based on combination of deep learning and structured light
  • Depth measurement method based on combination of deep learning and structured light
  • Depth measurement method based on combination of deep learning and structured light

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementations.

[0045] This embodiment provides a depth measurement method based on the combination of deep learning and structured light, using two branches to process separately, and finally combining each other to solve the depth value. The structure diagram is as follows: figure 1 Shown.

[0046] Specifically, it includes branch one, branch two, and the combined part.

[0047] Branch 1: calibrate the structured light system to obtain the reference phase, project multiple sine grating fringe patterns to the measured object, and collect them with a camera, then calculate the package phase, compare the package phase with the reference phase, and obtain the package deformation phase .

[0048] Branch 2: Use the depth estimation network to estimate the depth of the gray imag...

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 belongs to the technical field of three-dimensional reconstruction, and discloses a depth measurement method based on combination of deep learning and structured light. The method comprises the steps of obtaining a package deformation phase through structured light vision; obtaining an initial depth value through deep learning; obtaining a first phase compensation coefficient according to the initial depth value; and obtaining a real deformation phase according to the package deformation phase and the first phase compensation coefficient, and performing phase expansion on the real deformation phase to obtain a measured depth value. According to the invention, the problem of low precision of depth measurement in the prior art is solved, and the measurement precision can be effectively improved.

Description

Technical field [0001] The invention relates to the technical field of three-dimensional reconstruction, in particular to a depth measurement method based on the combination of deep learning and structured light. Background technique [0002] The traditional two-dimensional imaging technology can no longer meet the needs of people nowadays. Because the image is the projection of the three-dimensional space on the optical system, it is not enough to realize the recognition of the image level. The higher level of computer vision must accurately obtain the object in the three-dimensional space. The shape, position, and posture in the three-dimensional reconstruction technology realize the detection, recognition, tracking and interaction of objects in three-dimensional space. Now, more and more technologies based on 3D images are emerging. In order to obtain real 3D images, it is usually necessary to perform depth perception on scenes or objects. [0003] Among a series of technologie...

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): G01C11/30G06N3/04
CPCG01C11/30G06N3/045
Inventor 常婉向森邓慧萍吴谨
Owner WUHAN UNIV OF SCI & TECH