A semantic segmentation method of multi-path feature fusion based on deep learning

A technology of feature fusion and semantic segmentation, applied in the direction of neural learning methods, instruments, biological neural network models, etc., can solve complex problems, achieve the effect of improving accuracy and reasonable design

Inactive Publication Date: 2019-01-11
ACADEMY OF BROADCASTING SCI STATE ADMINISTATION OF PRESS PUBLICATION RADIO FILM & TELEVISION +1
View PDF6 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Although the image semantic segmentation method has made good progress, but because of its complexity, there are still many problems to be solved

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
  • A semantic segmentation method of multi-path feature fusion based on deep learning
  • A semantic segmentation method of multi-path feature fusion based on deep learning
  • A semantic segmentation method of multi-path feature fusion based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0030] Aiming at the problem of how to make full use of global information and local information in image semantic segmentation, the present invention proposes a semantic segmentation using a multi-path feature fusion network. Such as Figures 1 to 3 As shown, the present invention changes the network structure. At the feature extraction end, that is, the encoder (Encoder), one path of each convolution layer in the network structure is changed into multiple paths. At the convolution output end of each layer, Add the features extracted by multiple paths and input them into the next layer of network. At the classification end, that is, the decoding end, the feature passes through the convolutional layer and the upsampling layer to restore the original resolution of the image, making the classification result more reliable. This method is equiva...

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 relates to a semantic segmentation method of multi-path feature fusion based on deep learning, comprising the following steps: extracting basic deep feature of an image by using a multi-path feature fusion method; passing the extracted basic deep features through the decoding end network, restoring the original image resolution information, and generating the segmentation result; using the cross-entropy loss function to train the network, and using the accuracy and mIoU to evaluate the performance of the network. The design of the invention is reasonable, which takes full accountof local information and global information. The output of the network is a segmentation map with the same resolution as the original image. The segmentation accuracy is calculated by using the existing labels of the image. The network is trained to minimize the cross-entropy loss function, which effectively improves the accuracy of image semantic segmentation.

Description

technical field [0001] The invention belongs to the technical field of semantic segmentation of computer vision images, in particular to a semantic segmentation method based on multi-path feature fusion based on 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 great ...

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): G06K9/34G06K9/42G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V10/32G06V10/267G06N3/045G06F18/253
Inventor 宋辉王东飞白伟黎政姜竹青门爱东
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 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