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

Convolutional neural network (CNN) based rain measurement identification of marine radar

A technology of convolutional neural network and marine radar, which is applied in the field of marine radar rain measurement and recognition based on convolutional neural network, can solve the problems of complex equipment, high requirements for installation and site selection, and high cost of weather radar, and achieve a good convergence and stable state Effect

Active Publication Date: 2019-12-13
DALIAN MARITIME UNIVERSITY
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditionally, weather radars used for rain measurement are expensive, complex equipment, and require high installation and site selection.

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
  • Convolutional neural network (CNN) based rain measurement identification of marine radar
  • Convolutional neural network (CNN) based rain measurement identification of marine radar

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0041] As a preferred implementation, the model optimization process includes the following steps:

[0042] Step S21: Input the radar rain echo image P with a size of 100×100×3, pass through the Conv_1 convolution layer with a kernel size of 5×5, the number of convolution kernels is 32, and the sliding step size is 2 Convolution, to obtain a feature image P' whose size is 50×50×32;

[0043] Step S22: performing feature merging on the feature image P' as the input of the optimization process;

[0044] Step S23: The output feature map P obtained by the conv4 layer 7 By zero-padded convolution, the feature map P 7 with the feature image P 1 Keeping 50×50, the feature map P 7 with the feature image P 1 The number of channels is merged and appended to obtain a joint feature image P with a size of 50×50×160 2 ;

[0045] Step S24: The combined feature image P 2 The output sets the first short path, and at the same time the joint feature image P 2 Enter the feature extraction...

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 CNN based rain measurement identification of a marine radar. The method comprises a model building process, a model optimization process and a model training process. The method is based on a classical LeNet-5 CNN model. A multi-level residual CNN model is established, a training set is established by using samples of light rain, medium rain and heavy rain, and input intothe multi-level residual CNN to train the network model, the loss rate is calculated by using a cross entropy loss function, the minimum loss is obtained rapidly, and achieving a very good convergencestable state by using a batch training mode.

Description

technical field [0001] The present invention relates to the technical field of radar identification, in particular, to a method for identification of marine radar rain measurement based on convolutional neural network. Background technique [0002] Meteorological disasters occur frequently in my country, causing serious economic losses. Rainfall is one of the important elements. Accurate and quantitative estimation of rainfall is of great importance in preventing flood disasters and reducing secondary disasters caused by short-term sudden rainfall. significance. With the development of meteorological technology, radar can well meet the needs of rainfall observation in terms of real-time and detection range of rainfall detection. Traditionally, meteorological radars used for rain measurement are expensive, complicated equipment, and have high requirements for installation and site selection. In this paper, considering the cost performance, the marine radar is selected, and t...

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): G01S13/95G01S7/41G06N3/04G06N3/08
CPCG01S13/956G01S7/417G01S7/418G06N3/084G06N3/045Y02A90/10
Inventor 陈晓楠赵欢欢索继东彭勇
Owner DALIAN MARITIME UNIVERSITY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com