Object segmentation method and device based on circular 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: 2022-07-15
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 circular convolution
  • Object segmentation method and device based on circular convolution
  • Object segmentation method and device based on circular 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 clearly understood, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0026] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention can also be implemented in other ways different from those described herein, and those skilled in the art can do so without departing from the connotation of the present invention. Similar promotion, therefore, the present invention is not limited by the specific embodiments disclosed below.

[0027] like 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 the learned features. The specific steps are:

[0028] 1. Input a target image and use an existing deep neural netwo...

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 device. The object segmentation is performed by predicting the outline of the object in the image. In order to predict the outline of an object, the present invention provides a feature learning method based on circular convolution and a curve deformation method. The implementation of the present invention includes: constructing a feature vector for each node of the curve based on the initialized closed curve; using circular convolution to perform feature learning for the feature vector sequence defined on the closed curve; based on the circular convolution, a deep neural network is proposed. Perform curve deformation; realize object segmentation based on curve deformation method; process target objects containing multiple connected regions. The invention realizes efficient feature learning on the curve through circular convolution, and improves the accuracy of the method for object segmentation based on contour lines.

Description

technical field [0001] The invention belongs to the field of computer technology, and in particular relates to a method and device for object segmentation 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 optimum point. Some recent deep learning methods directly return to the contour curve of the object, but the segmentation effect is not accurate enough. In addition, there is also an implementation of using graph convolution to perform feature learning on the initial curve to predict the contour curve of the object. But using generalized graph convolutions does not fully exploit the topological features of curves, making feature learning not necessarily very efficient. SUMMARY OF THE INVENTION [0003] The purpose of the present invention is to propose a feature learning ...

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): 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 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