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

Water level monitoring method and device, electronic device and storage medium

A water level monitoring and water gauge technology, applied in the field of image recognition, can solve the problems of low adaptability and accuracy

Active Publication Date: 2019-03-29
ZHEJIANG DAHUA TECH CO LTD
View PDF4 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The invention discloses a water level monitoring method, device, electronic equipment and storage medium, which are used to solve the technical problem of low adaptability and accuracy caused by environmental factors in water level monitoring in the prior art

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 level monitoring method and device, electronic device and storage medium
  • Water level monitoring method and device, electronic device and storage medium
  • Water level monitoring method and device, electronic device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0099]When the image recognition method is used in the prior art to directly calculate the water level value, its accuracy depends on the quality of the input image, and many image preprocessing steps are required, the operation is complicated and errors are easily caused, and the accuracy is relatively low. Therefore, the embodiment of the present invention has respectively trained the detection model (i.e. the first convolutional neural network model) based on the convolutional neural network to detect the water gauge in the image, and the recognition model (i.e. the second convolutional neural network model and The third convolutional neural network model) to accurately identify the numbers on the water level gauge, and then combine the digital colors to determine the water level height to improve the accuracy of water level monitoring.

[0100] Therefore, according to an aspect of an embodiment of the present invention, a water level monitoring method is provided, such as ...

Embodiment 2

[0116] In order to obtain the parameters that have been trained in the first convolutional neural network model, it is necessary to train the first convolutional neural network model. On the basis of the above-mentioned embodiments, in the embodiment of the present invention, pre-train the first volume The process of accumulating a neural network model includes:

[0117] Acquiring a first sample image, wherein the fourth position information of the water gauge prediction frame is marked in the first sample image;

[0118] Input the marked first sample image into the first convolutional neural network model, and train the first convolutional neural network model according to each output of the first convolutional neural network model .

[0119] In the embodiment of the present invention, the electronic equipment used for model training can be a commonly used computer, but due to the large amount of data in the model training process, the electronic equipment used for model tra...

Embodiment 3

[0126] In order to avoid that the second image is too small, resulting in false detection or missed detection of the digits in the second image when recognizing the digits, so in order to further improve the digit recognition rate, on the basis of the above-mentioned embodiments, the embodiment of the present invention Among them, before the second image is input into the pre-trained second convolutional neural network model, the method also includes:

[0127] scaling the second image to a preset size;

[0128] Said inputting the second image into the pre-trained second convolutional neural network model includes:

[0129] Inputting the scaled second image into the pre-trained second convolutional neural network model.

[0130] Specifically, a possible implementation method is: before inputting the second image into the second convolutional neural network model, perform a crop operation or a warp operation on the second image to scale the second image to a preset size, wherei...

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 water level monitoring method and device, an electronic device and a storage medium. The method comprises the following steps: inputting a first image including a water levelgauge into a first convolution neural network model trained in advance to determine first position information of a water level gauge prediction frame in the first image; In accordance with that firstlocation information, extracting a second image corresponding to the water level gauge from the first image, inputting the second image into a pre-trained second convolution neural network model, determining second position information of a digital prediction box on the water level gauge in the second image, and identifying digits in each digital prediction box according to the second position information; according to the recognized number, the target number corresponding to the water surface is determined, and the water level height is determined according to the target number and the colorof the target number. Because the water level monitoring does not need tedious configuration and is not affected by environmental factors, the adaptability and accuracy of water level monitoring canbe improved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a water level monitoring method, device, electronic equipment and storage medium. Background technique [0002] Water level monitoring is of great significance to the monitoring of rivers, rivers, reservoirs and other water bodies. At present, the methods commonly used by most domestic hydrological stations for water level monitoring include: manual monitoring of water gauges, sensor monitoring and image recognition monitoring. [0003] Among them, when using the method of manual monitoring of the water gauge, not only the personal safety of the measurer exists, but also it is easily affected by the weather. For example, in rainy or foggy days, the accuracy of the monitoring data is difficult to be guaranteed, and the real-time performance of the monitoring is not good. Strong, unable to give early warning of flood disasters in time. [0004] When using the sensor mon...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/32G06K9/46G06K9/62
CPCG06V20/00G06V20/63G06V10/56G06V30/10G06F18/214Y02A90/30
Inventor 任馨怡陈媛媛
Owner ZHEJIANG DAHUA TECH CO LTD
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