A Denoising Method Based on Multi-Branch Selective Kernel Nested Connection Residual Networks

A nested connection and selective technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as noise suppression of complex seismic data that cannot be adaptively processed, and achieve high computing efficiency and denoising performance. The effect of reducing residual connections and improving computational efficiency

Active Publication Date: 2022-03-15
SOUTHWEST PETROLEUM UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a denoising method based on a multi-branch selective kernel nested connection residual network, which solves the problem that the traditional method cannot adaptively process complex seismic data noise suppression

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
  • A Denoising Method Based on Multi-Branch Selective Kernel Nested Connection Residual Networks
  • A Denoising Method Based on Multi-Branch Selective Kernel Nested Connection Residual Networks
  • A Denoising Method Based on Multi-Branch Selective Kernel Nested Connection Residual Networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0037] Such as Figure 1-5 As shown, a denoising method based on a multi-branch selective kernel nested connection residual network. It should be noted that the residual network is a network architecture proposed for the difficulty of training deep convolutional neural networks. The problem of network degradation caused by the increase of depth, but the number of network layers is large, and the calculation efficiency needs to be improved; the residual network consists of a series such as figure 2 The Residual Module (Residual Module, ResM) in b is composed, which is in figure 2 Add identity mapping (Identity Mapping, IM) on the basis of the Convolution Neural Network Module (CNNM) in a, that is, f(x)=x; when the netwo...

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 relates to the technical field of seismic data processing, and discloses a denoising method based on multi-branch selective kernel nested connection residual network, which includes the following processing steps: nesting and connecting multi-layer residual modules to obtain residual nesting Network; add a multi-branch selective kernel, and use the residual nested network as the input of the multi-branch selective kernel. Each branch uses convolutions of different scales for feature extraction, calculation and output of the final image. The present invention adopts nested residual connection, which can reduce residual connection and improve calculation efficiency. The nested residual connection of the present invention is combined with the multi-branch selective kernel, and the feature map output by the nested connection residual network can be used as the input of the multi-branch selective kernel module, and convolution kernels of different sizes are used for multi-branch fusion. In order to obtain feature maps with rich content, it is suitable for complex data processing. The invention has high computing efficiency and denoising performance, and can be widely used in random noise processing of actual seismic data.

Description

technical field [0001] The invention relates to the technical field of seismic data processing, in particular to a denoising method based on a multi-branch selective kernel nested connection residual network. Background technique [0002] Random noise is formed by the comprehensive action of various factors, has no fixed frequency and propagation direction, and is distributed in all time and all frequency bands, so it is difficult to effectively separate it from seismic records. Traditional seismic data noise suppression methods such as wavelet transform, f-x domain filtering, curvelet transform, and Gaussian filtering are mainly based on the predictability and sparsity of seismic data, and their noise suppression effects are limited by factors such as model assumptions and parameter settings. Adaptively processing seismic data in complex areas, the denoising effect needs to be improved. [0003] In recent years, in view of the good performance of deep learning in computer ...

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): G06V10/30G06V10/77G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/213G06F18/214
Inventor 曾梦张固澜罗一梁梁晨曦段景李勇詹熠宗杨志红
Owner SOUTHWEST PETROLEUM UNIV
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