Neural network model for segmenting image and image segmentation method thereof

A neural network model and image segmentation technology, which is applied in the field of computer vision, can solve the problems of large model parameters, inability to run mobile devices, and large calculations, and achieve the effect of reducing calculations, small calculations, and few model parameters

Active Publication Date: 2020-04-28
LANGCHAO ELECTRONIC INFORMATION IND CO LTD
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of this application is to provide a neural network model, image segmentation method, device and readable storage medium for image segmentation, to solve the problem of large

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
  • Neural network model for segmenting image and image segmentation method thereof
  • Neural network model for segmenting image and image segmentation method thereof
  • Neural network model for segmenting image and image segmentation method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0092] The detailed structure of the neural network model of embodiment two is as Figure 4 As shown, follow the Figure 4 The order of the circle labels in the middle is to describe each network structure respectively.

[0093] 1. Firstly, the network input is shown as circle 0, and the input dimension is H×W×3. As a specific implementation mode, it can be set to 768×768×3 in this embodiment.

[0094] 2. The input image first enters circle 1. ConvBnPRelu represents a network composed of Conv (convolutional layer), BatchNormal (Bn) layer and Relu layer. ConvBnPRelu(3,32,3,2,1) represents the input is 3 channels. The output is 32 channels, the convolution kernel uses a 3×3 scale, the stride is set to 2, and the padding is set to a convolutional layer formed by 1.

[0095] Specifically, after the first ConvBnPRelu layer, the width and height of the feature map are reduced by half, and the output of this layer is 384×384×32; after the second ConvBnPRelu layer, the scale of the ...

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 neural network model for segmenting an image, an image segmentation method and device thereof, and a readable storage medium, the neural network model comprises an intelligent selection module, and the intelligent selection module further comprises a feature extraction unit and an intelligent selection unit. As the feature extraction unit adopts multi-scale cavity convolution, information of different scales of an input feature map is obtained, and a large amount of rich feature information is provided for subsequent feature screening; and the intelligent selection unit carries out intelligent screening on the input feature map channel by training a weight value according to the size of the weight value, so that the intelligent selection module can reduce the parameter quantity and the calculated quantity while ensuring the segmentation precision. Therefore, the neural network model provided by the invention can quickly extract effective features of the imageby adopting the intelligent selection module, is small in calculation amount and few in model parameters, and is suitable for a mobile terminal.

Description

technical field [0001] The present application relates to the technical field of computer vision, in particular to a neural network model for image segmentation, image segmentation method, device and readable storage medium. Background technique [0002] At present, solving computer vision problems such as image classification, image segmentation and object detection through deep learning has become popular and achieved great success. [0003] Among them, image segmentation technology is an important research direction in the field of computer vision and an important part of image semantic understanding. Image segmentation refers to the process of dividing an image into several regions with similar properties. In recent years, image segmentation technology has developed by leaps and bounds. This technology-related scene object segmentation, human body front and background segmentation, human face parsing, 3D reconstruction, etc. The technology has been widely used in unmann...

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): G06K9/34G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/267G06V10/464G06N3/045G06F18/253G06V10/82G06V10/26G06V10/454G06T7/11G06T2207/20084G06N3/0464
Inventor 王立郭振华赵雅倩
Owner LANGCHAO ELECTRONIC INFORMATION IND CO LTD
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