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

Image semantic segmentation method and system and computer storage medium

A semantic segmentation and image technology, applied in the field of computer vision, can solve the problems of low image resolution, difficult to correctly identify image details, difficult to segment multi-scale objects, etc. degree of effect

Pending Publication Date: 2020-08-11
HUNAN UNIV
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide an image semantic segmentation method, system and computer storage medium to improve Accuracy of Image Semantic Segmentation

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 and system and computer storage medium
  • Image semantic segmentation method and system and computer storage medium
  • Image semantic segmentation method and system and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0079] refer to figure 1 , the present invention provides a semantic segmentation method based on an attention model for street view understanding, which includes the following steps:

[0080] Step S1: Preprocessing the input training set images, first uniformly adjust the size of the input images, and then perform standardization processing, that is, subtract the average pixel value of the adjusted image.

[0081] Step S2: Use a convolutional neural network (CNN) to capture general features, and embed a spatial CNN (SCNN) and an attention model in appropriate positions in the CNN network, respectively. Adding SCNN and attention model to the appropriate position of the CNN network will help to extract richer feature information and improve segmentation accuracy. The specific implementation process of this step inclu...

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 an image semantic segmentation method and system and a computer storage medium. The method comprises the steps of preprocessing an input image; capturing general features by using a convolutional neural network, and respectively embedding a spatial CNN and an attention model into proper positions of the general features; utilizing an SCNN algorithm to mine the general features to obtain deep feature information; extracting multi-scale feature information of the obtained general features and deep features through an attention model; and the fusion network fuses results obtained by the SCNN algorithm and the attention model to generate a final predicted semantic segmentation result. The method is used for solving the problems that in the prior art, the image resolution is reduced, and a multi-scale object is difficult to correctly identify and segment, and is beneficial to improving the accuracy of a semantic segmentation network.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to an image semantic segmentation method, system and computer storage medium. Background technique [0002] Image semantic segmentation is a very important field in computer vision. It can group pixels according to the semantic meaning existing in the image, that is, mark which object category each pixel belongs to in the image. Image semantic segmentation has a wide range of applications, such as street scene recognition and understanding in autonomous driving, robot vision, and environment modeling. At present, the semantic segmentation method based on deep learning is the mainstream technology in the field of image semantic segmentation, especially the semantic segmentation method based on Convolutional Neural Networks (CNN for short) has achieved remarkable success. [0003] However, the convolutional neural network structure itself has inherent defects: repeated poolin...

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): G06K9/34G06K9/62G06N3/04G06N3/08G06T3/40G06T7/10G06T5/50
CPCG06T3/4038G06T7/10G06T5/50G06N3/084G06T2207/20081G06T2207/20084G06T2207/20221G06V10/267G06N3/045G06F18/253Y02T10/40
Inventor 张大方范海博刁祖龙
Owner HUNAN UNIV
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