Unlock instant, AI-driven research and patent intelligence for your innovation.

Semantic segmentation method and device by suppressing non-interested information and storage device

A semantic segmentation, non-interesting technology, applied in neural learning methods, image analysis, image data processing, etc., can solve problems such as unfavorable model deployment, multiple computing resources, etc.

Active Publication Date: 2020-05-29
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the process of building a neural network, the stacking of simple neural network layers cannot suppress non-interesting information; to achieve better generalization effects, it is necessary to expand the receptive field of the model, but it requires a lot of computing resources. Not conducive to the deployment of the model on mobile devices

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 and device by suppressing non-interested information and storage device
  • Semantic segmentation method and device by suppressing non-interested information and storage device
  • Semantic segmentation method and device by suppressing non-interested information and storage device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described in detail with reference to the accompanying drawings.

[0029] refer to figure 1 , figure 1 is a flowchart of the semantic segmentation method by suppressing non-interesting information. The semantic segmentation method by suppressing non-interest information of the present invention comprises the following steps:

[0030] Step 1), optimize the neural network based on the deep learning library, and use tensorflow to build the basic image semantic segmentation model Unet, including two stages of encoding and decoding: the encoding stage is serially down-sampled 4 times, and each down-sampling passes through 2 layers of space A 3×3 convolutional layer and a pooling layer with gradually increasing dimensions and constant feature map size, the convolutional layer uses the conv...

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 provides a semantic segmentation method and device for suppressing non-interested information and a storage device, a neural network is optimized based on a deep learning library, the precision of a semantic segmentation result is improved. The method mainly comprises the following steps: 1) constructing a basic Unet model; 2) adding an attention mechanism, 3) multiplying a gate feature map by a current layer result, 4) adding a new output result and a multi-loss function, and 5) carrying out image semantic segmentation on an image to be subjected to semantic segmentation. The method can improve the precision of the semantic segmentation neural network and effectively inhibit non-interested information.

Description

technical field [0001] The present invention relates to the field of semantic segmentation, and more specifically, relates to a semantic segmentation method, device and storage device by suppressing non-interesting information. Background technique [0002] In the process of semantic segmentation of images using neural networks, it is necessary to build neural networks first. In the process of building a neural network, the stacking of simple neural network layers cannot suppress non-interesting information; to achieve better generalization effects, it is necessary to expand the receptive field of the model, but it requires a lot of computing resources. It is not conducive to the deployment of the model on mobile devices. The present invention is a solution proposed based on the above problems. Contents of the invention [0003] The purpose of the present invention is to address the defects in the prior art, propose a high-precision semantic segmentation method that supp...

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): G06T7/11G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06T7/11G06N3/082G06T2207/10004G06V10/44G06N3/045G06F18/25
Inventor 刘恒郭明强黄颖吴亮谢忠关庆锋韩成德宋振振
Owner CHINA UNIV OF GEOSCIENCES (WUHAN)