Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Filling method and device for missing pixels of depth image

A technology of depth image and filling method, which is applied in the field of visual image and can solve the problem of underutilization of effective pixel depth information

Pending Publication Date: 2020-11-24
BEIJING LUSTER LIGHTTECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present application provides a method and device for filling missing pixels in a depth image to solve the technical problem of not fully utilizing the depth information of effective pixels in the neighborhood of missing pixels in the filling method

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
  • Filling method and device for missing pixels of depth image
  • Filling method and device for missing pixels of depth image
  • Filling method and device for missing pixels of depth image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] For the acquired depth image, due to the influence of the acquisition equipment and the acquisition environment, noise data will inevitably be introduced into the acquired depth image. When the data with large noise cannot pass the conventional filtering algorithm, such as: Gaussian filtering , mean filter, median filter, etc., the position information of the noise in the depth image can be obtained through the abnormal data detection algorithm of the depth image, and then the pixel at the corresponding position in the depth image is set as an invalid pixel, that is, where the noise is Pixel is an invalid pixel.

[0055] Below in conjunction with accompanying drawing, the application is described in further detail:

[0056] An embodiment of the present application provides a method for filling missing pixels in a depth image, which is used in the field of visual images. The depth image consists of depth data ( figure 1 ) and data validity ( figure 2 ) consists of two...

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 filling method and device for missing pixels of a depth image. The method comprises the steps of determining a to-be-filled pixel region, a strip-shaped region and an effective pixel region according to the data effectiveness of the depth image, wherein the to-be-filled pixel region comprises a missing pixel part and / or a pixel invalid part caused by noise; obtaining a mapping value from an effective pixel to a boundary distance in the strip-shaped region to form a priority queue; when the number of the pixels in the priority queue is greater than zero, obtaining the pixels of the priority queue, and adding the pixels to the effective pixel region; acquiring four neighborhood pixels of the pixel, dividing the region where the four neighborhood pixels are located, when the number of the pixels in the priority queue is equal to zero, obtaining a depth image which is completely filled, achieving the quick and effective filling of the depth image, setting a regionneeding to be filtered as an invalid pixel region while the missing pixels are filled, and achieving the filling of the invalid pixels in the filtering region.

Description

technical field [0001] The present application relates to the field of visual images, in particular to a method and device for filling missing pixels in a depth image. Background technique [0002] In the field of visual images, the depth image can reflect the depth information of the captured object. By processing the acquired depth image, the height measurement, volume measurement and related detection operations of the object can be realized. At present, due to the limited viewing angle of the laser light source or the camera, the laser cannot scan some areas of the object, or the camera cannot observe part of the light stripe information of the laser, so the depth values ​​of some pixels in the image cannot be calculated, which eventually leads to the existence of Due to the lack of pixels, and due to the influence of the acquisition equipment and the acquisition environment, noise data will inevitably be introduced into the acquired depth image, which will affect the pr...

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): G06T5/30G06T5/00
CPCG06T5/30G06T5/70
Inventor 柯俊山
Owner BEIJING LUSTER LIGHTTECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products