Unlock instant, AI-driven research and patent intelligence for your innovation.

River surface flow velocity detection method based on deep learning

A technology of surface velocity and deep learning, which is applied in the field of image processing, can solve problems such as detection accuracy that needs to be improved, and achieve the effect of high detection accuracy

Pending Publication Date: 2020-12-29
CHINA INST OF WATER RESOURCES & HYDROPOWER RES
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This technology uses an unmanned vehicle (UV) equipped with cameras or radars for capturing realistic pictures from various waterways during navigation without physically touching them. These photos help identify specific areas where there may have rapid changes in speed such as rivers or streams. By analyzing these photo sequences over multiple hours it becomes possible to predict how fast they move through certain parts of their path based on factors like current speeds. Overall, this technology allows UAVs navigating underwater channels more accurately than previously done manually.

Problems solved by technology

Technological Problem: Current methods for detecting stream movement by analyzing changes over time require manual placement or expensive equipment that may lead to potential hazards such as damaging wildlife or human health due to their exposure to waves hitting them.

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
  • River surface flow velocity detection method based on deep learning
  • River surface flow velocity detection method based on deep learning
  • River surface flow velocity detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0047] Such as figure 1 As shown, a method for detecting river surface velocity based on deep learning, the specific steps are as follows:

[0048] S1. Obtain the image data of the river surface with the training result label;

[0049] S2. Preprocessing the data to generate a training set and a verification set;

[0050] S3. Using convolutional neural network to build a neural network for image classification of river surface velocity images:

[0051] S4, training and testing the neural network for image classification of river surface velocity;

[0052] S5. Using a computer vision algorithm to detect the flow velocity on the surface of a single river.

[0053] The river surface velocity data acquisition steps used in step S1 are:

[0054]Step S1.1 Select the target river and investigate. If the river has a bridge or a dock, install the camera on the bri...

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 river surface flow velocity detection method based on deep learning. The river surface flow velocity detection method comprises the following steps: S1, acquiring image dataof a river surface with a training result label; S2, preprocessing the data to generate a training set and a verification set; S3, building a river surface flow velocity image classification neural network by using a convolutional neural network; S4, training and testing the river surface flow velocity image classification neural network; and S5, detecting the flow velocity of a single river surface by using a computer vision algorithm. The river surface flow velocity image classification neural network constructed by the method has high detection precision, a camera is used to shoot the current river surface picture, the flow velocity detection model is used to classify the picture, and the flow velocity of the class picture with the highest probability as the picture is the surface flowvelocity of the river at the moment.

Description

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

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
Owner CHINA INST OF WATER RESOURCES & HYDROPOWER RES