Semantic segmentation method based on feature pyramid attention and mixed attention cascading

A feature pyramid and semantic segmentation technology, applied in the field of pattern recognition, can solve the problems of low segmentation accuracy, difficult to meet the requirements of segmentation accuracy, poor processing of segmentation target edge details, etc., to achieve the effect of optimizing processing and ensuring the speed of inference

Active Publication Date: 2021-04-13
NANJING UNIV OF SCI & TECH
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing fast semantic segmentation algorithms usually only retain a simple codec structure for image feature extraction and restoration, and lack of full use of multi-scale feature information, res

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
  • Semantic segmentation method based on feature pyramid attention and mixed attention cascading
  • Semantic segmentation method based on feature pyramid attention and mixed attention cascading
  • Semantic segmentation method based on feature pyramid attention and mixed attention cascading

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0055]A semantic segmentation method based on feature pyramid attention and hybrid level, specific steps are:

[0056]Step 1, build a semantic segmentation training set, specifically:

[0057]The image is preprocessed in the CITYSCAPES road data set, according to the RGB mean (0.485, 0.456, 0.406) and variance of the data set (0.229, 0.224, 0.225), the 2975-sheet binding is not a training set, 500 Zhang Jing label image as a verification set.

[0058]Step 2, build a deep convolutional neural network, the overall structurefigure 2 Down:

[0059]The depth convolutional neural network includes an encoder portion, a feature pyramid focus module, a mixing focus module, a feature fusion portion, a decoding branch.

[0060]In a further embodiment, the encoder portion uses the structure in existing mobilenetv2, such asimage 3 A shows that the present invention has made adjustments to use as a semantic segmentation task, such asimage 3 b. In the table, the number of output channels, T represents the expans...

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 semantic segmentation method based on feature pyramid attention and mixed attention cascading. The method comprises the steps of building a semantic segmentation training set; constructing a deep convolutional neural network, wherein the deep convolutional neural network comprises an encoder part, two feature pyramid attention modules, a mixed attention module, a decoding branch, a feature fusion part and a deep separable convolutional layer; training the deep convolutional neural network by using the semantic segmentation training set, and correcting network parameters; and inputting the streetscape road scene image to be segmented into the trained deep convolutional neural network to obtain a segmentation result. The invention can better adapt to the requirements of unmanned vehicle equipment for precision and speed.

Description

technical field [0001] The invention belongs to pattern recognition technology, specifically a semantic segmentation method based on feature pyramid attention and mixed attention cascade. Background technique [0002] Image semantic segmentation (semantic segmentation), also known as scene parsing (scene parsing), is a basic and challenging research direction in computer vision at present. Its task is to assign semantic labels to each pixel in the image, and a scene image Segment and parse into distinct image regions that correspond to semantic categories, including continuous objects (e.g. sky, road, grass) and discrete objects (e.g. people, cars, bicycles), etc. [0003] Image semantic segmentation technology enables computers to understand complex images containing multi-category objects. Research in this area has a wide range of application values ​​in areas such as unmanned vehicles, robot perception, and medical images. In recent years, due to the emergence of GPU com...

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
IPC IPC(8): G06T7/10G06N3/08G06N3/04
CPCG06T7/10G06N3/08G06T2207/20081G06N3/045
Inventor 徐锦浩王琼陈涛陆建峰
Owner NANJING UNIV OF SCI & TECH
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