Method and device for acquiring image parallax

A parallax acquisition and image technology, applied in the field of computer vision, can solve the problems of large amount of calculation and long calculation time

Active Publication Date: 2019-11-08
BEIJING SAMSUNG TELECOM R&D CENT +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The above three types of technologies are all processed for pixels, that is, each pixel needs to be processed, which requires a large amount of calculation and takes a long time for calculation

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
  • Method and device for acquiring image parallax
  • Method and device for acquiring image parallax
  • Method and device for acquiring image parallax

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] In order to solve the problems existing in the prior art that need to be processed for each pixel, the amount of calculation required is relatively large, and the calculation time required is long, an embodiment of the present application provides an image parallax acquisition method, and a method that can An image parallax acquisition device applying the method.

[0071] DVS (Dynamic Vision Sensor, Dynamic Vision Sensor) generates events according to changes in the light intensity of the shooting scene. Usually, all events output by DVS within a certain period of time form an image, and some pixels in the image correspond to an event. Some pixels do not correspond to events. The image generated by DVS has the following characteristics:

[0072] (1) Event sparsity. DVS is a motion-sensitive sensor that only captures object boundary or contour events where there is relative motion and light intensity changes reach a certain threshold. Therefore, only a small number of...

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 application discloses an image parallax acquisition method and device. The method comprises the following steps: calculating the cost of an event in a predetermined parallax range for each event in a left eye image and a right eye image, and calculating an intermediate process parallax of the event according to the cost, wherein the left eye image and the right eye image are the images acquired based on a DVS; determining whether the event in a first image is a Robust event according to the intermediate process parallax of the event and an intermediate process parallax of a corresponding event in a second image for each event in the first image, and ensuring that when the first image is the left eye image, the second image is the right eye image, and when the first image is the right eye image, the second image is the left eye image; and estimating a global optimal parallax of all events in the first image according to the intermediate process parallax of the Robust event in the first image. According to the image parallax acquisition method and device disclosed by the application, the problem of relatively large calculation amount and relatively long calculation time needed for processing each pixel in the prior art can be solved.

Description

technical field [0001] The present application relates to the technical field of computer vision, and in particular to a method and device for acquiring image parallax. Background technique [0002] At present, image parallax computing technology has played a central role in many important application scenarios, such as object recognition, scene 3D modeling, and assisted driving. In recent years, image parallax calculation technology has achieved fruitful results. According to the different matching methods of binocular images (two images obtained by two sensors shooting the same scene at the same time, called left-eye images and right-eye images), they can be mainly divided into the following Three categories: [0003] 1) Techniques based on local feature similarity [0004] This type of technology matches each pixel of the binocular image and the feature distribution of pixels in its neighborhood to match each pixel of the left-eye image to the best pixel in the right-ey...

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 Patents(China)
IPC IPC(8): H04N13/128H04N5/213
CPCH04N5/213H04N2013/0081H04N13/128H04N13/239H04N13/246
Inventor 郭萍邹冬青王强朴根柱赵百焕
Owner BEIJING SAMSUNG TELECOM R&D CENT
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