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

Image Semantic Segmentation Method Based on Global Features and Local Features of Deep Learning

A technology of global features and local features, applied in the field of semantic segmentation of computer vision images, can solve problems such as the difficulty of widely representing image features, achieve the effects of reducing noise, clear boundaries, and improving accuracy

Active Publication Date: 2021-07-23
ACADEMY OF BROADCASTING SCI STATE ADMINISTATION OF PRESS PUBLICATION RADIO FILM & TELEVISION +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods rely too much on manually annotated feature libraries, and it is difficult to widely represent image features, which has great limitations in practical applications.

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
  • Image Semantic Segmentation Method Based on Global Features and Local Features of Deep Learning
  • Image Semantic Segmentation Method Based on Global Features and Local Features of Deep Learning
  • Image Semantic Segmentation Method Based on Global Features and Local Features of Deep Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0035] An image semantic segmentation method based on global features and local features of deep learning, such as Figure 1 to Figure 3 As shown, at the encoding end, the deep convolutional neural network model is used to extract the global and local features of the image; at the decoding end, the two features are fused to obtain complementary image discriminant features for image semantic segmentation. At the same time, in order to restore the original resolution of the image more accurately at the decoding end, a stacked pooling layer is proposed. The image features are stacked through the maximum pooling layer, the convolutional layer, and finally the anti-pooling layer. The feature is fused with the previous convolution feature to reduce the noise in the feature map, make the boundary of the segmentation map clearer, and also reduce the cl...

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 present invention relates to an image semantic segmentation method based on global features and local features of deep learning, comprising the following steps: at the encoding end, using a convolutional neural network model based on deep learning to extract the basic depth features of the image, and simultaneously according to the Depth divides features into low-level features and high-level features; apply feature fusion module to fuse low-level features and high-level features into enhanced deep features; after obtaining deep features, input them to the decoder; use cross-entropy loss function as the target training Network, using mIoU to evaluate network performance. The invention is reasonably designed, it uses the deep convolutional neural network model to extract the global and local features of the image, fully utilizes the complementarity of the global features and local features, and uses the stacked pooling layer to further improve the performance, effectively improving the image semantics segmentation accuracy.

Description

technical field [0001] The invention belongs to the technical field of computer vision image semantic segmentation, in particular to an image semantic segmentation method based on global features and local features of deep learning. Background technique [0002] Image semantic segmentation refers to dividing each pixel in the image into different semantic categories by a certain method, realizing the reasoning process from the bottom layer to the high-level semantics, and finally obtaining a pixel-by-pixel semantically labeled segmentation map showing different segmentation regions. Image semantic segmentation is widely used in many computer vision tasks such as street scene recognition and target detection in automotive autonomous driving, drone landing point detection, scene understanding, robot vision, etc. From the machine learning method based on computer vision to the current method based on deep learning, the research of image semantic segmentation algorithm has made ...

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): G06N3/04G06N3/08G06K9/46G06K9/62
CPCG06N3/084G06V10/462G06N3/045G06F18/24
Inventor 宋辉解伟郭晓强周芸姜竹青门爱东
Owner ACADEMY OF BROADCASTING SCI STATE ADMINISTATION OF PRESS PUBLICATION RADIO FILM & TELEVISION
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