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

Water flow velocity measurement method based on motion enhancement feature

A water flow speed measurement and motion technology, which is applied in image enhancement, fluid velocity measurement, neural learning methods, etc., can solve the problems of high lighting requirements and difficult image to achieve the expected effect, and achieve the effect of low lighting requirements

Pending Publication Date: 2021-12-21
中科厦门数据智能研究院
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In general, the existing methods put forward strict requirements on the applicable environment, such as requiring manual placement of tracers, or requiring turbulent water flow with splash eddies, or requiring the water body itself to have a certain amount of sand, or requiring a large number of different scenarios Water velocity calibration sample data set, or more natural floating objects are required to be prominently displayed in the image
In addition, for methods such as template matching, optical flow, and general-purpose corner detection and matching, it is found in practice that the measurement features that these methods rely on have high requirements for lighting. It is difficult to achieve the expected effect on the images collected under

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 velocity measurement method based on motion enhancement feature
  • Water flow velocity measurement method based on motion enhancement feature
  • Water flow velocity measurement method based on motion enhancement feature

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Such as Figure 1-7 As shown, a water flow speed measurement method based on motion enhancement features, including the following steps:

[0043] Step 1: collect and divide the water flow video data into frames, and obtain the water surface pictures at time t, t+△t, and t+2△t;

[0044] Step 2, use the frame difference method to calculate the frame difference map of T1 and the frame difference map of T2 respectively, where T1 is the time between t time and t+△t time, and T2 is the time between t+△t time and t+2△t time;

[0045] Step 3: Statistical disturbance noise, perform frame difference processing on the water flow video, count the fluctuation range of its non-zero value, and draw a distribution map, the highest point is used as the vertex of the normal distribution, and the noise points are counted on the left half, and the right is recorded as Maximum noise threshold, and fit a normal distribution curve;

[0046]Step 4, filter the disturbance noise, on the frame ...

Embodiment 2

[0053] Such as Figure 1-7 As shown, a water flow speed measurement method based on motion enhancement features, including the following steps:

[0054] Step 1: collect and divide the water flow video data into frames, and obtain the water surface pictures at time t, t+△t, and t+2△t;

[0055] Step 2, use the frame difference method to calculate the frame difference map of T1 and the frame difference map of T2 respectively, where T1 is the period from time t to t+△t, and T2 is the period from time t+△t to time t+2△t. In use, △t is the reciprocal of the frame rate of the camera, for example, for a video with 25 frames per second, △t is 40ms. Such as Figure 1 As shown, the left half of the figure is the image at time t, and the right half is the image at time t+△t;

[0056] Step 3: Statistical disturbance noise, perform frame difference processing on the water flow video, count the fluctuation range of its non-zero value, and draw a distribution map, the highest point is used...

Embodiment 3

[0072] Such as Figure 1-9 As shown, a water flow velocity measurement method based on motion-enhanced features, this method can automatically mark the natural tracers in the water flow, that is, it can generate a classification data set at low cost. Figure 8 An illustration of a tree leaf as a natural tracer of water flow, Figure 9 An illustration of a splash that is a natural tracer of water flow.

[0073] In this example, the natural tracer binary classification data set based on deep learning-based cross-water flow velocity estimation: positive samples include natural floating objects such as water splashes, vortexes, bubbles, etc. caused by flow, and floating objects such as mud Sand, dead branches and leaves; negative samples include non-physical light and shadow movement effects such as wind blown shade spots, lights at night, and small creatures that can change their speed, such as fish, birds, and insects in the picture.

[0074] In this embodiment, the tracer cla...

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 water flow velocity measurement method based on a motion enhancement feature, and the method comprises the following steps: collecting and framing water flow video data, calculating a frame difference image through employing a frame difference method, counting disturbance noise, filtering the disturbance noise, enhancing the filtered image through employing a histogram equalization method, generating a water flow feature displacement, dynamically filtering water flow vector outliers, estimating a water flow velocity value, performing filtering, enhancement and secondary difference on continuous multiple frames of continuous water flow images to obtain an intermediate result after motion is remarkably amplified, performing corner detection and constrained matching on the intermediate result, and performing optimization on a continuous statistical result. A good real-time measurement effect can be obtained, and finally, a classification model trained by a collected reference object data set is utilized to further ensure the reliability of a reference point selected for flow velocity estimation. The method can play a role in a more universal water body environment and a weaker light environment, and is easy for landing use of hydrological intelligent monitoring engineering.

Description

technical field [0001] The invention relates to the field of water flow monitoring, in particular to a method for measuring water flow velocity based on motion enhancement features. Background technique [0002] Water flow velocity measurement plays an important role in water resource allocation, agricultural precision irrigation, flood and drought disaster prevention and control. In my country, where there are many water bodies, many rivers, reservoirs, irrigation canals, and diverse geological conditions, finding a more suitable method for measuring water flow velocity will be of great help to the implementation of actual hydrological real-time monitoring projects. The non-contact video analysis and measurement method has many advantages such as high safety for users, convenient information connection with the background system, not easy to be damaged, and more comprehensive information such as images and sounds, and good real-time performance. An important part of intell...

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): G06T7/246G06T5/00G06T5/40G06K9/40G06K9/46G06K9/62G01P5/18G06N3/04G06N3/08
CPCG06T7/246G06T5/40G01P5/18G06N3/08G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/20224G06N3/045G06F18/241G06T5/70Y02A90/30
Inventor 钟剑斌徐勇军程坦安竹林
Owner 中科厦门数据智能研究院
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