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

Water flow speed measuring method based on convolutional neural network image identification

A convolutional neural network and image recognition technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of inconvenient measurement and the inability to guarantee the safety of the measurement personnel, and achieve the effect of saving manpower

Active Publication Date: 2016-11-23
ZHEJIANG UNIV OF TECH
View PDF4 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is inconvenient to measure during the high flood period, and the life safety of the surveyors cannot be guaranteed

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
  • Water flow speed measuring method based on convolutional neural network image identification
  • Water flow speed measuring method based on convolutional neural network image identification
  • Water flow speed measuring method based on convolutional neural network image identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention will be further described below in conjunction with the accompanying drawings.

[0018] A kind of water flow velocity measurement method based on convolutional neural network image recognition of the present invention, specifically comprises the following steps:

[0019] Step 1 (equipment installation phase): such as figure 1 As shown, select the target river and survey. If the river has a bridge or a pier, install the camera on the bridge or pier. If the river has no bridge or pier, choose a flat river bank to set up a bracket and install the camera. The camera is connected to the host of the hydropower station through a video cable, and the host needs to be installed with a video capture card. The dome camera is selected as the camera to adjust the camera angle to align with the river surface, and the camera is adjusted so that the images captured are only images of the river surface without river bank debris. If necessary, install lights with ...

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

Provided is a water flow speed measuring method based on convolutional neural network image identification. The method comprises the following steps of equipment installing, sample picture collecting, sample data establishing, classifier training and actual measuring. According to the method, a non-contact camera is adopted to acquire surface images of a large quantity of rivers in the different states, the flow speed corresponding to each image is measured in advance, and the images are preprocessed to generate sample data for training and adjusting a convolutional neural network; when the flow speed needs to be measured again, the picture of the surface of a river at that time only needs to be shot by the camera and classified through the trained convolutional neural network, and the flow speed corresponding to the obtained category is the flow speed of the river at that time.

Description

technical field [0001] The invention relates to a method for measuring water flow speed by using images, in particular to a method for using a convolutional neural network algorithm to identify and classify river surface pictures, and obtain the corresponding river flow velocity in the state of the picture, which belongs to computer vision and river detection field. Background technique [0002] There are many rivers in our country, and it is of great significance to measure the flow velocity of rivers to prevent floods and protect the property safety of the country and the people. The traditional method of measuring flow velocity with buoys often faces the problem of buoys being washed away in the face of floods, which increases the instability of the measurement process. During the measurement process, it is often necessary to manually place buoys, and multiple people cooperate to calculate the distance and time of the buoys to calculate the flow rate of the river. It is...

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): G06K9/00G06K9/62
CPCG06V20/52G06F18/24G06F18/214
Inventor 王万良鞠振宇邱虹李卓蓉杨平郑建炜
Owner ZHEJIANG UNIV OF TECH
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