Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image segmentation and multithread fusion-based method and system for evaluating depth of single image

A technology of depth estimation and single image, applied in the fields of computer vision and image processing, it can solve the problems that there is no good solution and the performance of the calculation needs to be further improved, and achieve the effect of algorithm robustness and accuracy

Active Publication Date: 2010-06-16
BEIJING SHENRUI BOLIAN TECH CO LTD
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method needs to collect training data and establish a sample library, and the calculation performance needs to be further improved.
[0005] In short, the current single-view depth estimation methods still have their own limitations, and there is no good solution to this problem.

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
  • Image segmentation and multithread fusion-based method and system for evaluating depth of single image
  • Image segmentation and multithread fusion-based method and system for evaluating depth of single image
  • Image segmentation and multithread fusion-based method and system for evaluating depth of single image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0028] refer to figure 1 , figure 1 It is a flow chart of the steps of the method for estimating the depth of a single image based on image segmentation and multi-cue fusion in the present invention, including the following steps:

[0029] Primitive matching step 110, given an input image and a primitive template, using shape and texture matching, occlusion estimation and simultaneous image segmentation methods, to achieve one-to-many primitive matching and detection, and find the corresponding template in the input image. Match all the primitives, including the occluded and incompletely displayed primitives, and obtain the 3D pose estimation of the primitives by shape matching;

[0030] The depth cue extraction step 120 is to e...

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 an image segmentation and multithread fusion-based method and an image segmentation and multithread fusion-based system for evaluating depth of a single image. The method comprises the following steps: setting an input image and an element template, and finding all elements matched with the template in the input image by using the match of shape and texture, shielding evaluation and an image segmentation method which is simultaneously performed on the basis of an image model; extracting depth cue parameters of each element, wherein the depth cue parameters comprise the size of the element, a shielding relationship and the blur length of each element in the image obtained by the computation; according to the depth cue parameters, evaluating a depth value of each element and using an area in the image except the elements as a background; performing depth fitting on an inner area of each element according to a three-dimensional pose of the element obtained by matching the shape; and finally obtaining an optimized depth map. By comprehensively utilizing the depth cue parameters such as the imaging sizes of objects, the shielding relationship and the blur length, the relative depth map of the single image is obtained.

Description

technical field [0001] The invention relates to the fields of computer vision and image processing, in particular to a single image depth estimation method and system based on image segmentation and multi-cue fusion. Background technique [0002] In order to meet the development needs of the new generation of digital media and further promote the update of stereoscopic display technology, the research on 3D information restoration and scene reconstruction in computer vision and other related fields has become one of the hot spots. With the rapid development and widespread popularization of digital image acquisition equipment, a large number of two-dimensional data sources, image libraries, and photo collections have become media materials commonly owned by people. How to restore the stereoscopic information of the real world (that is, the depth information perpendicular to the image plane in the third dimension) based on a two-dimensional image is one of the classic problems...

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): G06T7/00
Inventor 王亦洲郭歌王威高文
Owner BEIJING SHENRUI BOLIAN TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products