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

Object segmentation method and device based on cyclic convolution

A technology of object segmentation and circular convolution, which is applied in the computer field to achieve efficient feature learning and improve accuracy

Active Publication Date: 2020-04-28
ZHEJIANG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention is based on the curve deformation method for object segmentation

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
  • Object segmentation method and device based on cyclic convolution
  • Object segmentation method and device based on cyclic convolution
  • Object segmentation method and device based on cyclic convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the above objects, features and advantages of the present invention more comprehensible, specific implementations of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0026] In the following description, a lot of specific details are set forth in order to fully understand the present invention, but the present invention can also be implemented in other ways different from those described here, and those skilled in the art can do it without departing from the meaning of the present invention. By analogy, the present invention is therefore not limited to the specific examples disclosed below.

[0027] Such as figure 1 As shown, the present invention provides a feature learning method on a curve based on circular convolution, and performs curve deformation based on learned features. The specific steps are:

[0028] 1. Input a target picture and use an existing deep neural network to extract a picture...

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 object segmentation method and a device. Object segmentation is carried out by predicting the contour line of an object in an image. In order to predict the contour line ofan object, the invention provides a feature learning method based on cyclic convolution and a curve deformation method. The method comprises the steps of constructing a feature vector for each node ofa curve based on an initialized closed curve; performing feature learning on the feature vector sequence defined on the closed curve by using cyclic convolution; based on cyclic convolution, proposing a deep neural network for curve deformation; realizing object segmentation based on a curve deformation method; and processing a target object including a plurality of connected regions. According to the method, through cyclic convolution, efficient feature learning on the curve is realized, and the accuracy of the method for performing object segmentation based on the contour line is improved.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to an object segmentation method and device based on circular convolution. Background technique [0002] In the related object segmentation technology, the traditional image processing method obtains the object contour curve by optimizing the initial curve, but it is easy to fall into the local optimal point. Some recent deep learning methods directly return to the object contour curve, but the segmentation effect is not accurate enough. In addition, there is a way to predict the contour curve of the object by using graph convolution to perform feature learning on the initial curve. However, the use of generalized graph convolution does not make full use of the topological characteristics of the curve, making feature learning not necessarily very efficient. Contents of the invention [0003] The purpose of the present invention is to propose a feature learning meth...

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): G06T7/149G06T7/12
CPCG06T7/149G06T7/12G06T2207/20081G06T2207/20084
Inventor 周晓巍鲍虎军彭思达
Owner ZHEJIANG UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com