Depth recovery method, electronic device and computer readable storage medium

A depth recovery and algorithm technology, applied in the field of image processing, can solve the problems of low depth recovery accuracy and increase chip cost, and achieve the effect of reducing the amount of calculation, improving efficiency and reducing cost.

Active Publication Date: 2022-05-31
合肥的卢深视科技有限公司
View PDF23 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, as the demand for the output resolution of the depth camera continues to increase, the computing resources required by the depth camera have also doubled. The depth restoration method based on the stereo vision binocular matching algorithm can no longer meet the actual needs of the depth camera. The precision of the depth camera is relatively low, and the optimization and upgrading of the computing unit of the depth camera will greatly increase the cost of the chip

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 recovery method, electronic device and computer readable storage medium
  • Depth recovery method, electronic device and computer readable storage medium
  • Depth recovery method, electronic device and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] An embodiment of the present application relates to a deep recovery method, applied to an electronic device; wherein the electronic device can

[0026] The specific flow of the depth recovery method of the present embodiment can be shown in Figure 1, including:

[0031] In step 102, multi-value processing is performed on the speckle image corresponding to the infrared image to obtain a multi-valued speckle image.

[0034] In an example, the server performs multi-value processing on the speckle image corresponding to the infrared image.

[0037] In an example, after obtaining the infrared image and the speckle image corresponding to the infrared image, the server can obtain the speckle image corresponding to the infrared image.

[0038] In one example, the server may combine the mask with the multi-valued speckle map to obtain only foreground regions

[0039] Step 104, according to the disparity value, determine the depth value of each point in the foreground area.

[0042] ...

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 embodiment of the present application relates to the technical field of image processing, and discloses a depth recovery method, electronic equipment, and a computer-readable storage medium. The above-mentioned depth recovery method includes: segmenting the filtered infrared image according to a preset image segmentation algorithm, and determining the foreground area of ​​the infrared image, and generate a mask for the foreground area; perform multivalued processing on the speckle image corresponding to the infrared image to obtain a multivalued speckle image; according to the multivalued The speckle map, the preset multi-valued reference speckle map and the mask, determine the parallax value of each point in the foreground area; determine the parallax value of each point in the foreground area according to the parallax value depth value. The depth restoration method provided by the embodiment of the present application can greatly reduce the calculation amount while ensuring the high precision of the depth restoration, avoid increasing the cost of the chip, and effectively improve the efficiency of the depth restoration.

Description

Deep recovery method, electronic device and computer readable storage medium technical field Embodiments of the present application relate to the technical field of image processing, in particular to a depth recovery method, electronic equipment and Computer-readable storage medium. Background technique [0002] With the rapid development of 3D technology, a 3D structure that projects on three-dimensional space and obtains three-dimensional imaging based on structured light Optical technology is becoming more and more mature, different from pure passive 3D measurement technology including binocular stereo vision technology, 3D structure Optical technology mainly emits light with certain structural characteristics through near-infrared lasers, projects it on the object to be photographed, and then emits light with certain structural characteristics. Collected by a special infrared camera, because this light with a certain structure is in different depth areas of the sub...

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 & AuthorityPatents(China)
IPC IPC(8): G06T7/593G06T7/194
CPCG06T7/593G06T7/194G06T2207/10048
Inventor化雪诚户磊王海彬刘祺昌李东洋
Owner合肥的卢深视科技有限公司