Check patentability & draft patents in minutes with Patsnap Eureka AI!

Method and device for carrying out semantic segmentation on image

An image and image acquisition technology, which is applied in neural learning methods, instruments, biological neural network models, etc., can solve the problems of insufficient accuracy of class activation maps and inaccurate image semantic segmentation results, etc.

Pending Publication Date: 2022-05-13
TSINGHUA UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The accuracy of class activation maps generated by existing methods is not high enough, resulting in inaccurate semantic segmentation results of images

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
  • Method and device for carrying out semantic segmentation on image
  • Method and device for carrying out semantic segmentation on image
  • Method and device for carrying out semantic segmentation on image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The following description includes exemplary methods, systems, and storage media that embody the techniques of the present invention. However, it should be understood that the described invention may be practiced without these specific details in one or more aspects. In other instances, well-known protocols, structures and techniques have not been shown in detail in order not to obscure the present invention. Those of ordinary skill in the art will appreciate that the described techniques and mechanisms can be applied to systems, methods, and computer-readable storage media for training object detection models using image captions.

[0024] Embodiments of the present invention will be described below with reference to the drawings. In the following description, numerous specific details are set forth in order to provide a more complete understanding of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be prac...

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 method, a system and a computer program product for correcting an initial class activation graph of an image. The method comprises the following steps: acquiring superpixel information of the image; superpixel information of the image is utilized, the image is divided into a plurality of areas, and relevant information of each area of the areas comprises an area adjacent to the area and all pixels of the area; the initial class activation graph of the image is acquired, the class activation graph is a probability value of classifying all pixels in the image into each class in classes of objects contained in the image, and a specific class probability value is an activation value of a specific class; and correcting the initial class activation graph of the image based on the related information of each of the plurality of areas of the image. And the modified class activation graph can better perform semantic segmentation on the image.

Description

technical field [0001] The present invention relates to semantic segmentation in image processing, in particular, the present invention relates to a method and system for semantically segmenting images. Background technique [0002] In image processing, semantic segmentation of images has important applications in many fields, such as autonomous driving, human-computer interaction, and virtual reality. The main task of semantic segmentation is to classify each pixel of the input image. With the development of deep learning technology, the current semantic segmentation tasks are mainly completed by deep learning technology. In deep learning, the semantic segmentation of images using fully supervised or weakly supervised methods has attracted widespread attention. The fully supervised training segmentation network requires high labeling costs. Weakly supervised training segmentation network can overcome this problem. For example, in semantic segmentation of images using we...

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): G06V10/26G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/214
Inventor 张慧钱辰
Owner TSINGHUA UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com