Depth image restoration algorithm based on composite adaptive region growth criterion

A technology of depth image and region growth, applied in image enhancement, image analysis, image data processing and other directions, can solve problems such as difficult actual scenes, complex pre-work, high time complexity, etc., to improve repair accuracy and repair order. Reasonable and ensure the effect of correct dissemination

Active Publication Date: 2019-09-10
CHENGDU UNIVERSITY OF TECHNOLOGY
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods are either not suitable for dynamic scenes, or the pre-work is very complicated, or it is difficult to apply to actual scenes due to high time complexity

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 image restoration algorithm based on composite adaptive region growth criterion
  • Depth image restoration algorithm based on composite adaptive region growth criterion
  • Depth image restoration algorithm based on composite adaptive region growth criterion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Attached below figure 1 to attach figure 2 , the present invention will be described in further detail.

[0024] Reference attached figure 1 , the present invention first needs to obtain the depth image and the corresponding registered RGB image, and perform priority calculation on all the hollow pixels in the depth image to obtain the pixel with the highest priority as the point to be repaired, through the compound adaptive area The growth criterion obtains the neighborhood of the point to be repaired, and estimates the depth value of the point to be repaired by bilateral weighting of the pixels in the neighborhood of the repaired point, and finally updates the hole area and repeats the steps until the repair is completed.

[0025] The algorithm includes the following steps:

[0026] S1: Calibrate the RGB-D camera, obtain the internal and external parameters of the RGB camera and the depth camera, and use the pinhole imaging principle to complete the registration o...

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 depth image restoration algorithm based on a composite adaptive region growth criterion, the algorithm provides a confidence item and a weighted priority calculation method, and the restoration sequence of depth images is determined by the weighted priority; under the guidance of the weighted priority, a pixel point more similar to the feature of the to-be-repaired point is found through a composite adaptive region growth criterion, and a neighborhood of the to-be-repaired point is constructed; and under the guidance of the RGB image, the depth estimation of the to-be-repaired point is determined according to the linear weighted combination of the pixel points in the neighborhood of the to-be-repaired point. According to the algorithm, high repair precision can beobtained under the condition that boundary information is kept complete.

Description

technical field [0001] The present invention relates to depth image restoration, which adopts weighted priority to guide the restoration order of depth images, uses RGB image information to find the neighborhood of the point to be repaired, and obtains the depth estimation of the point to be repaired by bilateral weighting of pixels in the neighborhood of the repaired point , so as to repair the missing pixels of the depth image. Background technique [0002] With the continuous progress and development of the times, digital image technology has been widely used in many fields. As an important part of computer graphics and machine vision, accurate image information often determines the accuracy of the final results, and most images usually have problems such as blurring or even damage, so image restoration technology has become the current Research hotspots. The emergence of depth information has further enriched the neighborhood involved in machine vision. The depth image...

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): G06T5/00G06T7/187G06T7/33G06T7/80
CPCG06T5/001G06T7/187G06T7/33G06T7/85G06T2207/10028G06T2207/10024G06T2207/20192
Inventor 陈光柱陈正阳侯睿
Owner CHENGDU UNIVERSITY OF TECHNOLOGY
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