Depth information acquisition method based on binocular framework

A technology of depth information and acquisition method, applied in the field of depth information acquisition based on binocular architecture, can solve the problems of consistency, inability to achieve the brightness of two channels, and the brightness of left and right channels to be consistent, so as to improve accuracy, avoid the problem of consistent brightness, The effect of improving reliability

Inactive Publication Date: 2012-05-09
ZHEJIANG ICARE VISION TECH
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012]2. Consistent brightness of the left and right channels
Because there are always individual differences in the camera, the brightness of the two channels cannot be consistent;
[0013]3. Live Questions

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 information acquisition method based on binocular framework
  • Depth information acquisition method based on binocular framework
  • Depth information acquisition method based on binocular framework

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Further explain below in conjunction with accompanying drawing:

[0037] Such as figure 1 As shown, a depth information acquisition method based on binocular architecture,

[0038] 1 The synchronization signal transmitted to the right channel through the left channel ensures the frame synchronization of the left and right channels;

[0039] 2 Using Census transformation to avoid the problem of consistent brightness;

[0040] The figure shows the Census transformation template, and the right side shows the original dense template. The calculation formula is as (1-3), and all neighboring points are compared with the central point to form a 256-bit number. In order to simplify the calculation and speed up, we use the sparse template as shown on the left, and only take part of the neighborhood points to compare with the center point. On the one hand, because the repeated comparison is omitted, the amount of information is less reduced; on the other hand, the template 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 relates to a depth information acquisition method based on a binocular framework, which comprises the following steps of: by utilizing the frame synchronous input and output interface of a camera chip, outputting a sampling signal from a left passage into a right passage for the frame synchronism of the left passage and the right passage; adopting Census transformation result as a characteristic to avoid the problem of inconsistent brightness of the left passage and a right passage; by the arrangement of a reasonable algorithm to enable the real-rime to be realized on an embedded platform; giving out depth information reliability by the algorithm so as to provide richer information for the following processing; and adopting the embedded platform to enable a camera structure to be small and further to be conveniently installed.

Description

technical field : [0001] The invention relates to the field of stereo vision, in particular to a depth information acquisition method based on binocular architecture. Background technique [0002] The current depth cameras mainly include three architectures: femtosecond, structured light and stereo vision. Compared with the previous two architectures, stereo vision has low precision and poor accuracy, but it has the advantages of simple structure, low price, and little environmental interference, and is suitable for some occasions with low requirements. [0003] Stereo vision is based on the principle of parallax, and depth information is obtained through stereo matching. The binocular stereo vision is shown in the figure below, where the baseline distance B=the distance between the projection centers of the two cameras; the focal length of the camera is f. [0004] Let the two cameras watch the same feature point of the space object at the same time , obtained images of...

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): H04N13/00
Inventor 尚凌辉高勇余天明贺磊盈张兆生
Owner ZHEJIANG ICARE VISION 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