Semantic Image Segmentation Method Using Convolutional Neural Networks

A convolutional neural network and image segmentation technology, which is applied in the direction of instruments, computing, character and pattern recognition, etc., can solve the problems of information loss, failure to make good use of information, and failure to consider pixel connection, etc., to achieve accurate results and Smoothing, accuracy-enhancing effects

Active Publication Date: 2021-10-29
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] (1) To a certain extent, the information between the upper and lower layers is not well utilized, resulting in the loss of information;
[0005] (2) The connection between pixels is not considered

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 Image Segmentation Method Using Convolutional Neural Networks
  • Semantic Image Segmentation Method Using Convolutional Neural Networks
  • Semantic Image Segmentation Method Using Convolutional Neural Networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0023] The designer of the present invention has devoted himself to the research of semantic image segmentation, summed up and aimed at the deficiencies and drawbacks of the current existing technology, and innovatively proposed a semantic image segmentation method of convolutional neural network, by combining partial layered feature fusion and Fully connected conditional random field processing for semantic image segmentation. The overview steps include: 1. Construct a network architecture model consisting of convolutional layers, pooling layers, upsampling layers, and loss functions, and the step size, convolution kernel size, and output characteristics of each layer in the model The number of graphs is customized according to the specifications; 2. Fusion of sh...

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 convolutional neural network semantic image segmentation method, which realizes semantic image segmentation by combining partial layered feature fusion in the network architecture and fully connected conditional random field processing. The specific steps include: constructing a network architecture model consisting of convolutional layers, pooling layers, upsampling layers, and loss functions, and the step size of each layer in the model, the size of the convolution kernel, and the number of output feature maps by Specification customization; fuse the shallow and deep information in the network architecture, and upsample the fused features to the resolution of the original image; use the fully connected conditional random field to optimize the post-processing of the feature image output by the upsampling segmentation. The application of the scheme of the present invention makes full use of the information of each layer through the feature fusion of different layers, and improves the final accuracy rate; combined with the fully connected CRF, the network output result is post-processed, and the connection between each pixel is processed. , making the result of image segmentation more accurate and smooth.

Description

technical field [0001] The invention belongs to the field of semantic image segmentation, and specifically refers to the implementation of semantic image segmentation by using a deep learning method. Background technique [0002] With the continuous breakthrough of deep learning, it has been widely used in various fields, such as computer vision, speech recognition, natural language processing, etc. The proposal of convolutional neural network (CNN) has made deep learning a hot word to some extent, and the proposal of fully convolutional neural network (FCN) has made a great breakthrough in semantic image segmentation. Semantic image segmentation can It is said to be the cornerstone technology of image understanding, and it plays a pivotal role in applications such as autonomous driving and drones. As we all know, an image is composed of many pixels, and semantic image segmentation, as the name implies, is to classify each pixel in the picture, that is, to realize the posit...

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): G06K9/34G06K9/62
CPCG06V10/267G06F18/253
Inventor 周全杨文斌从德春王雨卢竞男
Owner NANJING UNIV OF POSTS & TELECOMM
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