Depth map-based automatic image segmentation method

An automatic image and depth map technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of low algorithm interaction efficiency and inability to effectively integrate depth information, and achieve the effect of reducing interaction time and improving segmentation accuracy

Active Publication Date: 2018-09-28
CHONGQING UNIV OF POSTS & TELECOMM +1
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims at the problem that the interaction efficiency of the existing algorithm is not high a

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 map-based automatic image segmentation method
  • Depth map-based automatic image segmentation method
  • Depth map-based automatic image segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0063] The technical solutions in the embodiments of the present invention will be described clearly and in detail below in conjunction with the drawings in the embodiments of the present invention. The described embodiments are only a part of the embodiments of the present invention.

[0064] The technical solutions of the present invention to solve the above technical problems are:

[0065] The execution flow chart of the present invention is as figure 1 As shown, the specific technical solutions are as follows:

[0066] 1. Obtain the original image and depth image, such as figure 2 with image 3 As shown, SLIC super pixel segmentation is performed on the original image. SLIC segmentation is completed as follows:

[0067] 1) Initialize the cluster center C by setting the number of super pixels K k , The distance between cluster centers

[0068] 2) Move the cluster center to the pixel with the smallest gradient in the 3×3 spatial neighborhood to prevent the cluster center from bei...

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 depth map-based automatic image segmentation method, and discloses an improved GrabCut image segmentation algorithm for solving the problem that images cannot be effectivelysegmented by GrabCut when images have close-background image regions, shadow regions or low-contrast regions. According to the algorithm, depth information is fused on the basis of realizing GrabCut automatic segmentation via significance, so that the segmentation correctness of the algorithm is improved. The method comprises the following steps of: firstly, initializing the GrabCut algorithm by guiding significant information through the depth information; secondly, fusing the depth information into an energy formula of the algorithm; and finally, constructing a network flow map by using theimproved energy formula and a superpixel, and carrying out maximum flow/minimum flow segmentation. Compared with traditional image segmentation method, the method has the effect of effectively combining depth information with a GrabCut automatic segmentation framework so as to improve the correctness of the segmentation algorithm.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and in particular relates to an automatic image segmentation method based on a depth map. Background technique [0002] The purpose of image segmentation is the process of dividing an image into several parts through automatic or user interaction. It is one of the basic problems in the fields of image processing, human-computer interaction, etc. It is widely used in many fields to simplify subsequent operations, such as object Dataset construction, image editing and image retrieval, etc. Among many image segmentation methods, graph theory-based segmentation has attracted much attention due to its advantages of considering global information, fusing color and region information well, and requiring only a small amount of user interaction. Traditional graph-cut refers to manually annotating some pixels as foreground objects and backgrounds with user interaction, and using Graph-cut...

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
IPC IPC(8): G06T7/11G06K9/46
CPCG06T7/11G06V10/462
Inventor 刘辉石小龙郭晖翁小莉董昊
Owner CHONGQING UNIV OF POSTS & TELECOMM
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