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

Convolutional neural network rainfall intensity classification method for rainy day pictures

A convolutional neural network and rainfall intensity technology, applied in the field of real-time rainwater measurement in municipal engineering, can solve problems such as rare data sets, insufficient accuracy, and high price, and achieve excellent feature extraction performance, improved classification performance, and fast computing speed. Effect

Inactive Publication Date: 2019-12-24
ZHEJIANG UNIV
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current weather forecast cannot reflect the spatial inhomogeneity of rainfall, and the accuracy is not enough to meet the needs of real-time scheduling
Existing rain intensity measurement tools such as rain gauges can measure rain intensity more accurately, but they are expensive, difficult to transmit data in real time, and unable to reflect the spatial inhomogeneity of rainfall in real time, etc.
[0003] The convolutional neural network has the characteristics of sparse connection and weight sharing, which can effectively reduce the number of parameters of the neural network model, but the training of the convolutional neural network still requires a large amount of data, and it is difficult to obtain real rainfall pictures, which is difficult to obtain on a large scale Real rainfall pictures
However, there are few similar datasets in the existing public datasets
This greatly hinders the application of convolutional neural networks in the classification of rainfall intensity in rainy day images

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 rainfall intensity classification method for rainy day pictures
  • Convolutional neural network rainfall intensity classification method for rainy day pictures
  • Convolutional neural network rainfall intensity classification method for rainy day pictures

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] The present invention extracts rainy day picture features through the convolutional neural network, and completes the training of the convolutional neural network in two steps, that is, training in the synthetic data set and the real data set respectively, can effectively extract the rainfall information in the picture, and can ignore the background at the same time, Interference factors such as light and shade, rain mark angle, distribution, etc., have high classification accuracy.

[0037] Specifically, a convolutional neural network rainfall intensity classification method for rainy day pictures, such as figure 1 shown, including the following steps:

[0038] (1) Synthesize rainfall pictures through image processing software to obtain a synthetic data set;

[0039] (2) Build a convolutional neural network (CNN), and use the synthetic data set in step (1) to pre-train the convolutional neural network;

[0040] (3) Collect actual rainfall pictures to obtain real data...

Embodiment 2

[0067] Such as Figure 7 As shown, the convolutional neural network rainfall intensity online quantification method for rainy pictures provided by the present invention comprises the following steps:

[0068] (1) Synthesize rainfall pictures through image processing software to obtain a synthetic data set;

[0069] (2) Build and modify the structure of the convolutional neural network (CNN), and use the synthetic data set in step (1) to pre-train the convolutional neural network;

[0070](3) Collect actual rainfall pictures to obtain real data sets;

[0071] (4) Fine-tune the pre-trained model using the real data set in step (3) to obtain a trained model;

[0072] (5) Use the model trained in step (4) for online quantification of real-time rainfall intensity.

[0073] In some preferred modes, the specific process of step (1) is: adding different rainfall intensities to the original image by image processing software to obtain a synthetic rainfall image;

[0074] In some pr...

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 convolutional neural network rainfall intensity classification method for rainy day pictures. The method comprises the following steps: (1), synthesizing rainfall pictures through image processing software, and obtaining a synthesized data set; (2) establishing a convolutional neural network, and pre-training the convolutional neural network by using the synthetic data set in the step (1); (3) collecting an actual rainfall picture to obtain a real data set; (4) finely adjusting the pre-trained model by using the real data set in the step (3) to obtain a trained model;and (5) using the trained model in the step (4) for real-time rainfall intensity classification. The classification method provided by the invention has a good effect and a low error rate for classification of the rainfall intensity of the real rainfall picture and the synthetic rainfall picture, and can greatly improve the accuracy of real-time weather information in space.

Description

technical field [0001] The invention belongs to the field of real-time measurement of rainwater in municipal engineering, and in particular relates to a convolutional neural network rainfall intensity classification method for rainy day pictures. Background technique [0002] At present, urban waterlogging occurs frequently in our country, causing huge economic property losses and even casualties. Heavy rain has obvious spatial inhomogeneity, resulting in obvious differences in the degree of disaster among different parts of the city. Accurately obtaining real-time rainfall levels in various regions is of fundamental significance for urban waterlogging monitoring, prevention and emergency response. The current weather forecast cannot reflect the spatial inhomogeneity of rainfall, and the accuracy is not enough to meet the needs of real-time scheduling. Although existing rain intensity measurement tools such as rain gauges can measure rain intensity more accurately, they ar...

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/2431
Inventor 郑飞飞尹航陶若凌申永刚张清周
Owner ZHEJIANG 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

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