Segmentation method for image with deep image information

A technology of depth image and image segmentation, applied in the field of image analysis, it can solve the problem that API is not suitable

Active Publication Date: 2013-01-30
NINGBO UNIV
View PDF2 Cites 67 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Since the launch of Kinect in June 2010, it has become easier to obtain images with depth image information, and the segmentation based on depth image information will gradually become more important. The Kinect supporting API also uses some preliminary depth image information. The image is segmented, but it is relatively simple. The main reason is that the indoor environment is relatively simple. Through threshold segmentation, and using plane matching to cut out the interference of the ground, the indoor characters can be well segmented. For complex or close distances between the front and background In the case of Kinect supporting API is not suitable

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
  • Segmentation method for image with deep image information
  • Segmentation method for image with deep image information
  • Segmentation method for image with deep image information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described below in conjunction with specific examples.

[0041] The invention provides a method for segmenting an image with depth image information, comprising the following steps:

[0042] ① Obtain an image with depth image information through Kinect, the data structure of this image is RGBD, where RGB is three channels of color space, D is the depth image information corresponding to the pixel captured by Kinect, and then drag out on the image A circle or box for the first image segmentation, the circle or box completely falls within the object to be segmented, or the circle or box at least intersects the object to be segmented;

[0043] ②Probabilistic modeling is performed on the color information and depth image information of the foreground and background. data is o = {o 1 ,...,o i ,...,o N}, o i =(c i , d i ) is the image segmentation information of depth image information, N is the number of image pixels, c i is a ve...

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 segmentation method for an image with deep image information, which is high in segmentation accuracy, and capable of still achieving a good segmentation effect under the condition of a very similar front background. The segmentation method comprises the steps of: (1) obtaining the image with deep image information via Kinect; (2) performing probability modelling on the colour information of the front background and the deep image information; (3) performing parameter estimation on the model by EM (Expectation-Maximization) algorithm; and (4) performing segmentation after the first image segmentation on the image by adopting an image segmentation algorithm, wherein an energy function is formula shown in the abstract, and according to the energy function, the smallest segmentation is evaluated by a maximum flow algorithm, so as to obtain the final segmentation object.

Description

technical field [0001] The invention relates to the technical field of image analysis, in particular to a method for segmenting images with depth image information. Background technique [0002] In the technology of image analysis, image segmentation is a very important underlying processing technology. It is the basis of many high-level applications. Simply take license plate recognition as an example, where the vehicle license plate in the image can be regarded as the foreground (useful information), The part other than the vehicle license plate is regarded as the background. Image segmentation is to distinguish the foreground from the background, or image segmentation is to divide the image into several specific regions with unique properties and extract the target of interest. Technologies and processes, such as: vehicle license plate recognition, medical image analysis, face recognition, human flow detection, object tracking and recognition, the function of the magic wa...

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 赵杰煜俞江明
Owner NINGBO UNIV
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