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

A method for visual saliency extraction of stereoscopic images

A technology of stereoscopic images and extraction methods, which is applied in image analysis, image enhancement, image data processing and other directions, can solve the problems of simple expansion of the salient extraction method of staying plane images, and achieves improved extraction stability and extraction accuracy, strong stability , the effect of high extraction accuracy

Active Publication Date: 2019-07-26
牧野微(上海)半导体技术有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, a stereoscopic image is not a simple spatial extension of a planar image, so the process of human perception of a stereoscopic image to generate stereoscopic vision is not a simple process of superimposing left-viewpoint images and right-viewpoint images. force) is not a simple extension of the plane visual properties
However, the existing saliency map extraction methods for stereo images are still limited to the simple extension of the saliency extraction methods for planar images.

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
  • A method for visual saliency extraction of stereoscopic images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0021] A method for visually salient extraction of stereo images proposed by the present invention, its overall realization block diagram is as follows figure 1 As shown, it includes the following steps:

[0022] ① Order S RGB Indicates the visually salient stereo image to be extracted, the S RGB The left view image of is denoted as {L RGB (x,y)}, the S RGB The right view image of is denoted as {R RGB (x,y)}, the S RGB The depth image of is recorded as {D(x,y)}, where 1≤x≤W, 1≤y≤H, W means S RGB The width, H means S RGB height, L RGB (x,y) means {L RGB The pixel value of the pixel whose coordinate position is (x, y) in (x, y)}, R RGB (x,y) means {R RGB The pixel value of the pixel whose coordinate position is (x, y) in (x, y)}, D(x, y) means the pixel value of the pixel whose coordinate position is (x, y) in {D(x, y)} Pixel values....

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 discloses a method for extracting visual salience of a stereoscopic image, which first obtains the L channel image, a channel image, and b channel image of the left viewpoint image of the stereoscopic image, and obtains the image transformed from the depth image of the stereoscopic image to the interval [0, 255] ; Then implement log-Gabor low-pass filtering to the L channel map, a channel map and b channel map and the transformed depth image to obtain respective low-pass filter feature maps; then obtain left-viewpoint visual salience according to four low-pass filter feature maps Figure; then obtain the center preference map of the stereo image; finally fuse the left view visual saliency map and the center preference map to obtain the visual saliency map of the stereo image; the advantage is that it conforms to the salient semantic feature, and has strong extraction stability and high extraction accuracy.

Description

technical field [0001] The invention relates to a method for processing image signals, in particular to a method for extracting visually significant stereoscopic images. Background technique [0002] In human visual reception and information processing, due to limited brain resources and differences in the importance of external environmental information, the human brain does not treat external environmental information equally in the processing process, but shows selective characteristics. When people watch images or video clips, their attention is not evenly distributed to every area of ​​the image, but they pay more attention to certain salient areas. How to detect and extract salient regions with high visual attention in videos is an important research content in the field of computer vision and content-based video retrieval. With the rapid development of stereoscopic video display technology and high-quality stereoscopic video content acquisition technology, salient re...

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): G06K9/46G06K9/62G06T7/00G06T7/168
CPCG06T7/0002G06T2207/10021G06T2207/10012G06V10/449G06V10/462G06F18/213
Inventor 周武杰蔡星宇顾鹏笠张爽爽潘婷周扬邱薇薇
Owner 牧野微(上海)半导体技术有限公司