Census adaptive transformation algorithm based on multiple codes

A transformation algorithm and adaptive technology, applied in the field of Census adaptive transformation algorithm based on multi-coding, can solve the problems of noise sensitivity, indistinct difference between similar areas, loss of brightness information, etc., and achieve the effect of noise reduction

Inactive Publication Date: 2017-05-10
DALIAN UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] Although the traditional Census transform weakens the luminance information, its weakening of the luminance information is too rough and does not make full use of the luminance information in the

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
  • Census adaptive transformation algorithm based on multiple codes
  • Census adaptive transformation algorithm based on multiple codes
  • Census adaptive transformation algorithm based on multiple codes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Refer to the content of the invention and the attached figure 2 . The present invention selects and divides into four groups, and under the situation of adding a redundant code, the specific operation process is as follows:

[0050] 1) Manually input window size 5×5, input σ=100 for noise judgment.

[0051] 2) Encode each pixel according to the transformation strategy of the present invention.

[0052] Refer to attached figure 2 .For the encoding method of a certain point in the image:

[0053] 3) Read the luminance data with a size of 5×5 for point p of the original image and point p′ of the reference image respectively. Let the read matrix be w p with w p '

[0054] 4) Group the read data according to the luminance value i(p) of point p and the luminance value i(p') of point p', assuming that each window has two groups: group 1 and group 2.

[0055] 5) Calculate the threshold ε for the grouped data 1 with ε 2 . With reference to the threshold calculation su...

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 field of binocular stereoscopic vision technology and relates to a Census adaptive transformation algorithm based on multiple codes. According to the adaptive transformation algorithm, traditional Census transformation is improved mainly from the two aspects of coding mode and noise control, and a new coding strategy is used. Brightness information is utilized more sufficiently while local information in a window is considered, and noise is weakened, so that the algorithm has higher robustness.

Description

technical field [0001] The invention belongs to the technical field of binocular stereo vision, and relates to a multi-coding-based Census adaptive transformation algorithm. Background technique [0002] Stereo matching has always been an important technical link in binocular stereo vision. Stereo matching is to find the conjugate point in the two images, that is, the position of the same point in space projected on different pixels in the left and right images, and finally generate a disparity map. . However, there are always problems of accuracy and efficiency in stereo matching. Due to the increasing parallelism of computers in recent years, researchers have been devoting themselves to finding a parallel high-precision stereo matching method. [0003] Generally, the stereo matching process can be divided into four parts: matching cost calculation, matching cost aggregation, initial disparity calculation, and disparity optimization. The current research on stereo matchi...

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): G06T9/00
CPCG06T9/007
Inventor 卢志茂朱世宇范冬梅
Owner DALIAN 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