Unlock instant, AI-driven research and patent intelligence for your innovation.

Method of Obtaining Depth Map from Binocular Image

A technology of depth map and image, applied in the field of image processing, to achieve the effect of improving quality, rich information and clear outline

Active Publication Date: 2016-07-06
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current 3D movie video experience still cannot be separated from the mode of wearing glasses. While experiencing the 3D effect, wearing glasses has brought a lot of troubles to the audience, so the demand for glasses-free 3D equipment is imminent.

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 of Obtaining Depth Map from Binocular Image
  • Method of Obtaining Depth Map from Binocular Image
  • Method of Obtaining Depth Map from Binocular Image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Such as figure 1 The method for obtaining a depth map through a binocular image in the present invention is shown in the following steps:

[0024] a. Carry out sub-picture conversion to binocular original video image, divide it into left-eye view and right-eye view, and carry out median filtering to described left-eye view and right-eye view by CTMF algorithm, filter radius is 1 or 2;

[0025] b. For the filtered sub-graph, the pixel index number is used as the node, and the distance between the four neighbors or the eight neighbors between the pixels is calculated as the edge of the minimum spanning tree, and the minimum spanning tree of the left and right eye view is respectively established by the kruskal algorithm. If it is 3 Channel RGB image, calculate the difference for each channel, and finally calculate the average of the differences of the three channels to get the distance from the current point to the neighbor point, you can use the formula D...

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 relates to a method for obtaining a depth map through a binocular image, comprising: a. Median filtering of the converted left eye view and right eye view; b. Establish the minimum spanning tree of the left and right eye views, and then calculate the corresponding left and right eye gradient contour images; c. Translate to obtain 2n left and right eye disparity range sequence images and 2n left and right eye gradient disparity range images; d. Obtain the mean value of the left and right eye gradient contour image differences and the mean value of the left and right eye disparity range sequence image differences according to the weight, and obtain the 2n amplitude difference weighted difference table and weight coefficient table; e. Perform similarity aggregation filtering to obtain 2n aggregated disparity tables for left and right eyes. In the 2n aggregated disparity tables, take the minimum aggregated value table at the same pixel position. The invention can quickly and accurately obtain the sequence map position and the image depth map, and the foreground and background depth information of the image is rich and the outline is clear, which can effectively improve the quality of the naked-eye 3D image and further promote the development of the naked-eye 3D technology.

Description

technical field [0001] The invention relates to image processing, in particular to a method for obtaining a depth map through a binocular image. Background technique [0002] With the rapid development of film and video technology, when TV, film and video programs enter millions of households, 2D flat films and video programs can no longer satisfy people's strong demand for visual impact and layered experience. The rise of 3D movie video quietly at present has solved people's viewing demand for current stereoscopic movie video. However, the current 3D movie video experience still cannot be separated from the mode of wearing glasses. While experiencing the 3D effect, wearing glasses has brought a lot of troubles to the audience, so the demand for naked-eye 3D equipment is imminent. The key technology of naked-eye 3D is to find the depth map of the image. Contents of the invention [0003] The invention provides a method for obtaining a depth map through a binocular 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 Patents(China)
IPC IPC(8): G06T7/00
Inventor 李国超
Owner SICHUAN CHANGHONG ELECTRIC CO LTD