Depth image denoising and enhancing method based on deep learning

A deep image and deep learning technology, applied in the field of image processing, can solve the problems of poor depth value restoration effect, slow depth image denoising and enhancement processing speed, etc., to achieve the effect of improving reconstruction ability, improving effectiveness, and improving learning efficiency

Inactive Publication Date: 2016-08-03
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, provide a depth image denoising and enhancement method that meet

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 denoising and enhancing method based on deep learning
  • Depth image denoising and enhancing method based on deep learning
  • Depth image denoising and enhancing method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with specific examples.

[0035] Such as figure 1 As shown, the depth image denoising and enhancement method based on deep learning described in this embodiment, its specific circumstances are as follows:

[0036] 1) Select 30 groups of images, each group of images is composed of a clean depth image and its corresponding visual image and a noisy depth image, 28 groups of the 30 groups of images are used as network training sets, and the remaining 2 groups are used as network training sets. Network test set. Next, construct the network training set. The specific steps are:

[0037] 1-1) The visual image is grayscaled into a grayscale image.

[0038] 1-2) Image preprocessing of enhancing boundary information and removing redundant information is performed on the grayscale image, specifically, histogram equalization, bilateral filter filtering, Sobel operator extracting boundary, segmentation based on ...

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 present invention discloses a depth image denoising and enhancing method based on deep learning. The method comprises the steps of establishing a depth image denoising and enhancing convolutional neural network, wherein the network is composed of three layers of convolution units which finish the functions of feature extraction, non-linear mapping and image reconstruction of the input images respectively; jointly using the depth and visual images as the input of the convolutional neural network, wherein firstly the visual images are processed into the grayscale images in a grayscale processing manner; and enhancing the edge information and taking out the redundant information by the image preprocessing; segmenting the depth images into the image blocks according to certain intervals, adding the effective data by a rotation and pixel overturning data amplification method, and discarding the interference blocks and the redundant blocks; and improving the learning efficiency of the network adaptively based on a loss training depth image enhancement convolutional neural network of a weight map. According to the method of the present invention, the black spot filling and the denoising operations can be carried out on the depth images with noise real-timely, and the good visual effect and depth value recovery effect can be realized.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for denoising and enhancing deep images based on deep learning. Background technique [0002] With the development of portable and affordable depth cameras, the basic research and application of depth images in the field of image processing has become more and more important. By applying information on depth images, the performance of related research and applications in the field of machine vision, such as image segmentation, object tracking, image recognition, and image reconstruction, can be improved. [0003] However, due to the limitations of existing depth camera technology principles, the quality of the depth image obtained from it is not as good as the visual image, and there is a lot of noise interference, usually some random noise and "black holes" of different shapes on the edges of objects and black surfaces. , that is, the area where the depth information is...

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): G06T5/00G06K9/62
CPCG06T5/002G06F18/214
Inventor 张鑫廖轩吴锐远
Owner SOUTH CHINA UNIV OF TECH
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