CN117831035B - Water gate safety identification method, system and storage medium - Google Patents

Abstract

The present application provides a sluice safety identification method, system and storage medium, which are applied to the field of water conservancy project safety monitoring. It can solve the problem of weak accuracy of sluice safety identification by manually identifying water flow patterns. The method obtains a to-be-processed image containing tracer particles of the water flow under the sluice, and determines the planar two-dimensional flow field corresponding to the to-be-processed image according to a preset cross-correlation window and a cross-correlation algorithm. That is to say, the flow velocity vector of each cross-correlation window in the to-be-processed image is determined, and further, the vorticity value of each cross-correlation window is determined. Based on the preset judgment strategy and vorticity value, the water flow pattern under the sluice and the position corresponding to the water flow pattern are identified. The present application can accurately and efficiently identify the water flow pattern under the sluice through image analysis and processing, thereby improving the safety monitoring of the sluice.

Description

Water gate safety identification method, system and storage medium

Technical Field

The present application relates to the field of water conservancy project safety monitoring, and in particular to a sluice safety identification method, system and storage medium.

Background technique

In water conservancy projects, sluice gates are used for flood control, drainage, tide blocking, irrigation, water supply, navigation and hydropower generation; closing the gates can block floods, tide blocking, store water to raise the upstream water level, etc., to meet the needs of upstream water intake or navigation; opening the gates can discharge floodwater, drain water, flush sand, intake water, etc., or adjust the flow according to the needs of downstream water use.

After the gate of the sluice is opened, if the structure of the sluice is partially damaged or aged, or if there are changes in scouring and silting under the gate, the flow pattern of the water will change, such as vortex flow, zigzag flow, etc. In the relevant technology, the staff mainly observes the changes in the flow pattern of the water flow, and determines whether the sluice has safety hazards based on the observed changes in the flow pattern of the water flow.

However, the above method of judging the potential safety hazard of the sluice by manually identifying the flow pattern of water has poor accuracy and timeliness in identifying the safety of the sluice.

Summary of the invention

The present application provides a sluice safety identification method, system and storage medium, which can solve the problem of low accuracy of sluice safety identification in the method of judging sluice safety hazards by manually identifying water flow patterns.

The embodiment of the present application is implemented as follows:

A first aspect of an embodiment of the present application provides a sluice safety identification method, comprising:

Obtaining an image to be processed of the water flow under the sluice gate, wherein the image to be processed contains tracer particles;

According to the preset cross-correlation window and cross-correlation algorithm, the planar two-dimensional flow field corresponding to the image to be processed is determined, wherein the planar two-dimensional flow field is determined by the flow velocity vectors of each cross-correlation window in the image to be processed; the vorticity value of each cross-correlation window is determined; based on the preset judgment strategy and vorticity value, the water flow state under the gate and the position corresponding to the water flow state are identified.

In the above method, by using the cross-correlation algorithm on the image to be processed of the water flow under the gate, the flow velocity vector of each cross-correlation window in the image to be processed can be determined, and then the vorticity value of each cross-correlation window can be determined. In this way, on the basis of the vorticity value, combined with the preset judgment strategy, the flow state of the water flow under the gate and the corresponding position of the water flow state can be identified. In other words, through the analysis and processing of the image, the flow state of the water flow under the gate can be accurately and efficiently identified, thereby improving the safety monitoring of the sluice.

In conjunction with the first aspect, in some implementations of the first aspect, determining the vorticity value of each cross-correlation window includes:

The velocity vector of the cross-correlation window is decomposed into a horizontal velocity and a vertical velocity; the horizontal velocity gradient and the vertical velocity gradient of the cross-correlation window are determined; and the vorticity value of the cross-correlation window is determined based on the horizontal velocity gradient and the vertical velocity gradient of the cross-correlation window.

In conjunction with the first aspect, in certain implementations of the first aspect, based on a preset determination strategy and a vorticity value, identifying a flow pattern under a gate and a position corresponding to the flow pattern includes:

If the vorticity value is greater than a preset vorticity threshold, the first cross-correlation window corresponding to the vorticity value is marked as a vortex flow, wherein the first cross-correlation window is a cross-correlation window in the image to be processed, and the preset judgment strategy includes judging the cross-correlation window whose vorticity value is greater than the preset vortex threshold as a vortex flow; the position corresponding to the first cross-correlation window is the position of the vortex flow.

In the above method, on the basis of determining the vorticity value, different flow states of the water flow under the gate are identified through different preset judgment strategies, that is, the cross-correlation window with a vorticity value greater than the preset vorticity threshold can be judged as a vortex flow.

In conjunction with the first aspect, in certain implementations of the first aspect, based on a preset determination strategy and a vorticity value, identifying a flow pattern under a gate and a position corresponding to the flow pattern includes:

Calculating the arctangent value of the flow velocity vector of the second cross-correlation window in the cross-correlation window, where the second cross-correlation window is a window other than the first cross-correlation window in the cross-correlation window; determining a second angle between each second cross-correlation window and the horizontal direction based on the arctangent value;

If the absolute value of the difference between the second angle and the first angle is greater than the preset angle threshold, the third cross-correlation window corresponding to the second angle is marked as a breakaway flow, wherein the first angle is the angle between the smooth flow direction of the water flow under the gate and the horizontal direction, and the preset judgment strategy includes judging the cross-correlation window whose absolute value of the difference between the second angle and the first angle is greater than the preset angle threshold as a breakaway flow; the position corresponding to the third cross-correlation window is the position of the breakaway flow.

In the above method, on the basis of determining the vorticity value, different flow states of the water flow under the gate are identified through different preset judgment strategies. That is to say, the cross-correlation window in which the absolute value of the difference between the second angle and the first angle is greater than the preset angle threshold can be judged as a zigzag flow.

In addition, the identification of vortex flow and offset flow can be combined to further identify other flow patterns, such as lateral circulation.

In combination with the first aspect, in some implementations of the first aspect, determining the planar two-dimensional flow field corresponding to the image to be processed according to a preset cross-correlation window and a cross-correlation algorithm includes:

According to the size of the preset cross-correlation window, the first moment image in the image to be processed is divided into a plurality of cross-correlation windows;

Determine the cross-correlation value corresponding to each cross-correlation window in the image at the second moment in the image to be processed, wherein the image at the first moment and the image at the second moment are two images at adjacent moments in the image to be processed;

Based on the cross-correlation value, a second position in the image at the second moment that matches the first position in the image at the first moment is determined; and according to the first position and the second position, a planar two-dimensional flow field corresponding to the image to be processed is determined.

In the above method, by converting the image to be processed into the flow velocity vector of each cross-correlation window in the image to be processed, it is convenient to further identify the flow state of the water flow under the gate by means of the flow velocity vector, thereby improving the image recognition capability. In combination with the first aspect, in some implementations of the first aspect, before determining the planar two-dimensional flow field corresponding to the image to be processed according to the preset cross-correlation window and the cross-correlation algorithm, it also includes:

A conversion relationship between the image coordinate system of the image to be processed and the world coordinate system is established; based on the conversion relationship, the world coordinates corresponding to the image to be processed are determined.

In the above method, the data in the image coordinate system is converted into the world coordinate system, thereby improving the applicability of the sluice safety identification method in actual sluice scenarios.

A second aspect of an embodiment of the present application provides a sluice safety identification system, the system comprising an image acquisition module and a water flow state identification module, wherein:

An image acquisition module, used for acquiring an image to be processed of the water flow under the sluice gate;

The water flow pattern recognition module is used to determine the planar two-dimensional flow field corresponding to the image to be processed according to the preset cross-correlation window and the cross-correlation algorithm, wherein the planar two-dimensional flow field is determined by the flow velocity vectors of each cross-correlation window in the image to be processed; it is also used to determine the vorticity value of each cross-correlation window; it is also used to identify the water flow pattern under the gate and the position corresponding to the water flow pattern based on the preset judgment strategy and vorticity value.

In combination with the second aspect, in some implementations of the second aspect, the system further includes: a correction module, configured to locate the world coordinates corresponding to the image to be processed.

A third aspect of an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the sluice safety identification method in the first aspect are implemented.

A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor executes the steps of the sluice safety identification method in the first aspect.

It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

The present application provides a method, system and storage medium for identifying the safety of a sluice gate. The method obtains an image to be processed containing tracer particles of the water flow under the sluice gate, and determines the planar two-dimensional flow field corresponding to the image to be processed according to a preset cross-correlation window and a cross-correlation algorithm. That is to say, the flow velocity vector of each cross-correlation window in the image to be processed is determined, and further, the vorticity value of each cross-correlation window is determined. Based on the preset judgment strategy and vorticity value, the flow state of the water flow under the sluice gate and the position corresponding to the flow state of the water flow are identified. The present application can achieve accurate and efficient identification of the water flow state under the sluice gate through analysis and processing of the image, thereby improving the safety monitoring of the sluice gate.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

FIG1 is a schematic structural diagram of a sluice safety identification system provided by an embodiment of the present application;

FIG2 is a schematic diagram of the structure of another water gate safety identification system provided by an embodiment of the present application;

FIG3 is a schematic flow chart of a sluice safety identification method provided in an embodiment of the present application;

FIG4 is an image of an image to be processed provided by an embodiment of the present application;

FIG5 is a schematic diagram of a process for determining a planar two-dimensional flow field corresponding to an image to be processed provided by an embodiment of the present application;

FIG6 is a schematic diagram of an image at a first moment and an image at a second moment provided by an embodiment of the present application;

FIG7 is a schematic diagram showing displacement of the position of the cross-correlation window in the image at two corresponding moments in FIG6 ;

FIG8 is a schematic diagram of the smooth flow of one of the gated images to be processed according to an embodiment of the present application;

FIG9 is a schematic diagram of vorticity discretization of a cross-correlation window provided in an embodiment of the present application;

FIG10 is a schematic diagram of a first angle provided by an embodiment of the present application;

FIG11 is a schematic diagram of the position of the vortex flow identified corresponding to the image to be processed in FIG8;

FIG. 12 is a schematic diagram of the position of the identified bending flow corresponding to the image to be processed in FIG. 8 .

Detailed ways

In order to make the purpose, implementation mode and advantages of the present application clearer, the exemplary implementation mode of the present application will be clearly and completely described below in conjunction with the drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only part of the embodiments of the present application, rather than all the embodiments.

It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and common meanings.

The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

In water conservancy projects, sluices are used for flood control, drainage, tide blocking, irrigation, water supply, shipping and hydropower generation; they are mostly built in rivers, canals, reservoirs, lakes and coastal areas, and play an important role in flood control, drainage, tide blocking, irrigation, water supply, shipping and hydropower generation.

It should be pointed out that the sluice gate can be an estuary gate, a headwater gate, etc. For example, the estuary gate is located at the confluence of the city's inland river and rivers such as the Yangtze River or the Yellow River. It is an arc gate used to raise the water level of the inland river during the dry season and discharge flood water during the flood season. The top of the gate is divided into several fine lower holes for overflow. The headwater gate is located in the irrigation channel. It is a flat vertical steel gate used to control the amount of irrigation water.

Closing the gates can block floods, prevent tides, store water to raise the upstream water level, etc., to meet the needs of upstream water intake or navigation; opening the gates can release floodwaters, drain waterlogging, flush sand, intake water, etc., or adjust the flow according to the water needs of downstream.

Due to the long-term effects of factors such as load, freeze-thaw, wind, waves, rain, and snow, the structures of various parts of the buildings will inevitably age. After the gate of the sluice is opened, if the building of the sluice is partially damaged or aged, collapse on both sides of the gate, or scouring and siltation changes occur under the gate, the flow pattern of the water will change, such as vortex flow, offset flow, etc.

In the related art, the staff mainly observes the changes in the flow pattern of the water flow, and determines whether the sluice has safety hazards based on the observed changes in the flow pattern of the water flow. However, the above method of judging the safety hazards of the sluice by manually identifying the flow pattern of the water flow has poor accuracy and timeliness in identifying the safety hazards of the sluice.

In view of the above problems, the embodiments of the present application can provide a sluice safety identification method, system, computer equipment and storage medium. The sluice safety identification method is applied to the sluice safety identification system. The image acquisition module in the sluice safety identification system collects the processed image containing tracer particles of the water flow under the gate. The water flow state identification module in the sluice safety identification system determines the planar two-dimensional flow field corresponding to the image to be processed according to the preset cross-correlation window and cross-correlation algorithm, and then determines the flow velocity vector of each cross-correlation window in the image to be processed, and further determines the vorticity value of each cross-correlation window. Based on the preset judgment strategy and vorticity value, the water flow state under the gate and the position corresponding to the water flow state are identified. The present application can realize accurate and efficient identification of the water flow state under the gate by analyzing and processing the image.

A sluice safety identification method, system and storage medium of an embodiment of the present application are described in detail below in conjunction with the accompanying drawings.

Figure 1 shows a structural schematic diagram of a sluice safety identification system provided in an embodiment of the present application. As shown in Figure 1 , an embodiment of the present application provides a sluice safety identification system, which includes an image acquisition module 10 and a water flow state identification module 20.

The image acquisition module is communicatively connected with the water flow pattern recognition module, so as to facilitate the transmission of the image data collected by the image acquisition module to the water flow pattern recognition module so as to facilitate the water flow pattern recognition module to analyze and process.

Among them, the image acquisition module is set at a position for photographing the water flow under the gate, so as to collect images of the water flow under the gate through the image acquisition module. Its position can be set on the sluice, on the river bank or assumed to be above the water flow.

The image acquisition module may be composed of a shooting device with a lens, such as a camera, a still camera, a drone, or other device with a shooting function.

It should be pointed out that, in some embodiments, the image acquisition module may also be called a camera module, a shooting module, etc., which is not limited in the embodiments of the present application.

It should be noted that the image acquisition module and the water flow pattern recognition module may share a power supply device, or each may have its own power supply.

Among them, the water flow state recognition module can be implemented by a device with computing power. It can determine the planar two-dimensional flow field corresponding to the image to be processed according to the preset cross-correlation window and cross-correlation algorithm, and then determine the flow velocity vector of each cross-correlation window in the image to be processed. Further, determine the vorticity value of each cross-correlation window, and then identify the water flow state under the gate and the position corresponding to the water flow state based on the preset judgment strategy and vorticity value.

For example, the water flow pattern recognition module can be a laptop computer, a desktop computer, a tablet computer, a smart TV, a mobile phone, a robot, etc.

It should be pointed out that, in some embodiments, the water flow state identification module may also be called a data processing module, a data analysis and prediction module, etc., and the embodiments of the present application do not limit this.

It should be noted that the specific contents executable by the water flow pattern recognition module are described in detail in the following description of the sluice safety recognition method. Please refer to the description of Figures 3 to 12.

For the sake of convenience of explanation, in FIG2 , the image acquisition module is taken as a camera 11 as an example, and the water flow state recognition module is taken as a desktop computer 21 as an example for schematic illustration.

The camera includes a lens, an image sensor, a power supply, a controller and a communication submodule. The camera is connected to the desktop computer through the communication submodule, and the communication data between the two can be mutual.

In some embodiments, the communication between the camera and the desktop computer can be a one-way transmission from the camera to the desktop computer.

In some embodiments, a preset time interval may be used so that the camera can continuously capture images to be processed at an interval of Δt. It should be noted that the preset time interval may be set in the camera or sent to the camera via a desktop computer.

The image to be processed may contain one or more images. As the acquisition time continues, the image data in the image to be processed will increase, which can be stored through a database or other means, or image data with identification features can be screened out for storage to improve the data processing efficiency of the desktop computer.

In some embodiments, the water gate safety identification system further includes a correction module for calibrating the world coordinates corresponding to the image to be processed.

It should be understood that the turbulent water flow under the sluice gate will produce bubbles, etc. These bubbles are naturally formed floating objects, which are convenient for being used as tracer particles to be obtained in the image to be processed.

Through the correction module, the captured image is linked to the world coordinates, improving the recognition of the water flow pattern recognition system in the sluice application scenario.

In some embodiments, the correction module may be a plurality of calibration control points set on the water surface. For example, the calibration control points may be equipped with a real-time kinematic (RTK) device.

As shown in FIG. 2 , four sensors 31 equipped with RTK may be deployed on the water surface. The four sensors are not on the same straight line, and adjacent connecting lines are distributed in a quadrilateral.

By placing the four calibration control points on the same horizontal plane, the two-dimensional coordinates of the real world plane can be determined.

In addition, if the world coordinates are , the corresponding image coordinates of the image to be processed are/> , the conversion relationship between world coordinates and image coordinates is established as follows:

Where the coefficient λ is used to normalize the transformed coordinates, that is, to scale the value of the third dimension to 1. The homography matrix has 9 elements, but only 8 degrees of freedom, which can be divided by Normalize. Therefore, 8 equations can be established from 4 calibration control points to solve the parameters in the homography matrix/> , where i=0,2; j=0,2. That is, for any point in the image coordinates/> , can be converted to the real world coordinates of the water flow scene under the sluice by the above formula.

An embodiment of the present application provides a sluice safety identification system. By building this system, an image acquisition module can be used to collect images to be processed containing tracer particles of the water flow under the sluice. A water flow pattern identification module can determine the planar two-dimensional flow field corresponding to the image to be processed based on preset cross-correlation windows and cross-correlation algorithms, and then determine the flow velocity vectors of each cross-correlation window in the image to be processed, and further determine the vorticity values of each cross-correlation window. Based on the preset judgment strategy and vorticity values, the water flow pattern under the sluice and the position corresponding to the water flow pattern are identified. The sluice safety identification system provided by the embodiment of the present application can accurately and efficiently identify the water flow pattern under the sluice by analyzing and processing images.

Figure 3 shows a schematic flow chart of a sluice safety identification method provided in an embodiment of the present application. As shown in Figure 3, an embodiment of the present application provides a sluice safety identification method, which is applied to a sluice safety identification system.

The sluice safety identification method comprises the following steps:

S110, obtaining an image to be processed of the water flow below the sluice gate.

The image to be processed contains tracer particles, which refer to natural floating objects generated by the turbulence of water flow under the sluice. Floating objects refer to objects floating on the water and moving with the water flow. The natural floating objects here can be bubbles, leaves, etc.

It should be understood that the image to be processed refers to a continuous image acquired by the image acquisition module, and the acquisition of continuous images makes it easier to determine the flow state change of the water flow.

S120 , determining a planar two-dimensional flow field corresponding to the image to be processed according to a preset cross-correlation window and a cross-correlation algorithm.

The planar two-dimensional flow field is determined by the flow velocity vectors of each cross-correlation window in the image to be processed.

It should be understood that the size of the image to be processed is W*H pixels, and the size of the preset cross-correlation window is M*N, wherein M may be equal to N, or may not be equal to N, and both M and N are smaller than W and H.

That is to say, each image in the to-be-processed images can be divided into a plurality of cross-correlation windows.

FIG4 shows an image among the images to be processed in an embodiment of the present application, wherein a cross-correlation window and the size of the window are marked. It should be noted that the black dots in the image represent tracer particles.

In some embodiments, the planar two-dimensional flow field corresponding to the image to be processed can be determined by a cross-correlation algorithm or a fast cross-correlation algorithm. FIG5 shows a schematic diagram of a process for determining the planar two-dimensional flow field corresponding to the image to be processed in an embodiment of the present application. As shown in FIG5, the process of determining the planar two-dimensional flow field corresponding to the image to be processed is as follows:

S210 . Divide the first moment image in the image to be processed into a plurality of cross-correlation windows according to a preset cross-correlation window size.

The first moment image and the second moment image are two images at adjacent moments, and the position of the tracer particles in the first moment image and the second moment image has changed. FIG6 shows a schematic diagram of the first moment image and the second moment image, wherein (A) in FIG6 is the first moment image, and (B) in FIG6 is the second moment image. The same cross-correlation window is marked in both the first moment image and the second moment image, and FIG6 shows that the position of the cross-correlation window in the image to be processed has shifted.

FIG. 7 shows that the positions of the cross-correlation windows in the corresponding images at two moments in FIG. 6 are displaced, and the coordinates corresponding to the cross-correlation windows move by (Δx, Δy).

In some embodiments, in the first moment image, the first moment image is divided into a plurality of cross-correlation windows of a size of M*N.

S220, determining the cross-correlation values corresponding to each cross-correlation window in the image at the second moment in the image to be processed.

In the second moment image, the cross-correlation value R(i, j) corresponding to each cross-correlation window is calculated.

In some embodiments, the cross-correlation value may be determined by a normalized cross-correlation algorithm, and its corresponding expression is as follows:

Where R(i, j) is the cross-correlation value at the coordinate (i, j) in the image at the second moment, where i is the distance extending from the upper left corner to the right in each cross-correlation calculation window; j is the distance extending from the upper left corner to the bottom in each cross-correlation calculation window;

(m, n) are the coordinates of each pixel in the image at the first moment in the cross-correlation window constructed with the fixed feature point as the corner point, where the fixed feature point is any pixel that can be used as the corner point of the cross-correlation window;

is the average gray value of all pixels in the cross-correlation window in the image at the second moment;

G(i, j) is the gray value at the coordinate (i, j) in the image at the second moment;

G(i+m, j+n) is the gray value at the coordinate (i+m, j+n) in the image at the second moment;

It is the average grayscale value of the pixel in the window constructed with the fixed feature points as corner points in the image at the first moment;

T(m, n) is the grayscale value at coordinate (m, n) in the window constructed with (i0, j0) as the corner point in the image at the first moment.

S230: Determine, based on the cross-correlation value, a second position in the image at the second moment that matches the first position in the image at the first moment.

For a first position of the cross-correlation window at any position in the image at the first moment, in the image at the second moment, the maximum value of the cross-correlation values can be determined as the corresponding matching second position in the image at the second moment.

S240: Determine a planar two-dimensional flow field corresponding to the image to be processed according to the first position and the second position.

The displacement of the position of the cross-correlation window may be determined by using the first position and the second position, such as the corresponding (Δx, Δy) in FIG. 7 .

In some embodiments, the shift in the cross-correlation window position is determined by the following equation:

Δx=(i-i0)

Δy= (j-j0)

Δt=(T2-T1)

Wherein, (i0, j0) is the coordinate of the corner point of the cross-correlation window in the image at the first moment; (i, j) is the coordinate of the corner point of the cross-correlation window in the image at the second moment corresponding to (i0, j0) in the image at the first moment; T2 is the time when the image at the second moment is obtained; T1 is the time when the image at the second moment is obtained;

Δx is the horizontal displacement, Δy is the vertical displacement, and Δt is the time interval between the image at the second moment and the image at the first moment.

Then, through the above displacement, the planar two-dimensional flow field corresponding to the image to be processed is determined.

In some embodiments, the displacement of the cross-correlation window position corresponding to the above formula can be converted from image coordinates to world coordinates through the conversion relationship between the world coordinates and the image coordinates, which can be converted by the following formula:

Where vx is the horizontal displacement, vy is the vertical displacement, and V is the displacement of the cross-correlation window.

Furthermore, through the above displacement, the planar two-dimensional flow field in the world coordinates corresponding to the image to be processed is determined.

It should be understood that after the conversion relationship between the image coordinate system of the image to be processed and the world coordinate system is established, the world coordinates corresponding to the image to be processed can be determined based on the conversion relationship.

That is to say, the flow velocity vectors of each cross-correlation window in the image at the first moment are first determined, and after the flow velocity vectors of all cross-correlation windows are calculated, a planar two-dimensional flow field is obtained.

As shown in FIG. 3 , after step 120 , step S130 is executed to determine the vorticity value of each cross-correlation window.

Figure 8 shows a schematic diagram of an image in the image to be processed under the gate of an embodiment of the present application. As shown in Figure 8, in the smooth schematic diagram corresponding to the image to be processed, the image to be processed is divided into multiple areas by cross-correlation windows, and the flow field corresponding to each cross-correlation window is indicated at the marked position.

The vorticity value of the cross-correlation window can be obtained by decomposing the flow velocity vector of the cross-correlation window into horizontal flow velocity and vertical flow velocity; determining the horizontal flow velocity gradient and the vertical flow velocity gradient of the cross-correlation window; and determining the vorticity value of the cross-correlation window based on the horizontal flow velocity gradient and the vertical flow velocity gradient of the cross-correlation window.

In some embodiments, the vorticity value of each cross-correlation window can be obtained by calculating:

du(i,j)=(u(i+1,j)-u(i-1,j))

dv(i,j)=(v(i,j+1)-v(i,j-1))

w(i, j) = dv(i, j) - du(i, j)

Where du(i, j) is the horizontal velocity gradient at (i, j), dv(i, j) is the vertical velocity gradient at (i, j), and w(i, j) is the vorticity value of the corresponding cross-correlation window.

Figure 9 shows a schematic diagram of the vorticity discretization of the cross-correlation window. As shown in Figure 9, the cross-correlation window above the cross-correlation window (i, j) is (i, j-1), the cross-correlation window below is (i, j+1), the cross-correlation window on the left is (i-1, j), and the cross-correlation window on the right is (i+1, j).

It should be understood that the flow velocity vector within each cross-correlation window (i, j) can be decomposed into the horizontal flow velocity u(i, j) and the vertical flow velocity v(i, j), and then the vorticity value w(i, j) of the corresponding cross-correlation image can be calculated.

S140. Based on a preset determination strategy and vorticity value, identify the flow pattern of the water flow under the gate and the position corresponding to the flow pattern.

It should be understood that there are different flow forms for water flow, such as vortex flow, zigzag flow, transverse circulation, etc., wherein the transverse circulation can also exist in the form of vortex flow or zigzag flow on the water flow surface. Therefore, in the embodiment of the present application, the identification of vortex flow and zigzag flow is mainly used.

There are also different preset judgment strategies corresponding to different forms of water flow states. Among them, the preset judgment strategy includes judging the cross-correlation window whose vorticity value is greater than the preset vorticity threshold as vortex flow, and the preset judgment strategy also includes judging the cross-correlation window whose absolute value of the difference between the second angle and the first angle is greater than the preset angle threshold as impingement flow; wherein the first angle is the angle between the initial direction and the horizontal direction, and the second angle is the angle between the cross-correlation window and the horizontal direction.

It should be understood that, according to the position of the sluice gate, the smooth flow direction of the water flow is selected as the initial direction of the water flow under the sluice gate in advance, and there is an angle θ between the initial direction and the horizontal direction, that is, the first angle. FIG10 shows a schematic diagram of the first angle.

If the vorticity value is greater than a preset vorticity threshold, the first cross-correlation window corresponding to the vorticity value is marked as a vortex flow, wherein the first cross-correlation window is a cross-correlation window in the image to be processed, and the position corresponding to the first cross-correlation window is the position of the vortex flow.

Among them, all the cross-correlation windows whose vorticity values are greater than the preset vorticity threshold value Tw, that is, w(i, j)>Tw, are marked as vortex six, and the position of the vortex flow is identified. Figure 11 is a schematic diagram of the position of the vortex flow corresponding to the image to be processed in Figure 8, as shown in Figure 11, the diagram shows the position of the vortex flow.

Further, the inverse tangent value of the flow velocity vector of the second cross-correlation window in the cross-correlation window is calculated, and the second cross-correlation window is the window other than the first cross-correlation window in the cross-correlation window; based on the inverse tangent value, the second angle between each second cross-correlation window and the horizontal direction is determined; if the absolute value of the difference between the second angle and the first angle is greater than a preset angle threshold, the third cross-correlation window corresponding to the second angle is marked as a breakaway flow, wherein the first angle is the angle between the smooth flow direction of the water flow under the gate and the horizontal direction, the position corresponding to the third cross-correlation window is the position of the breakaway flow, and the third cross-correlation window is a cross-correlation window in the second cross-correlation window.

Among them, u(i, j) is positive along the X direction and negative otherwise, and v(i, j) is positive along the Y direction and negative otherwise.

The arc tangent value of the velocity vector of the second cross-correlation window in the cross-correlation window can be calculated using the following function:

atan2(u(i，j),v(i，j))

When atan2(u(i, j), v(i, j))>0,Φ=atan2(u(i, j), v(i, j))

When atan2(u(i, j), v(i, j))<0,Φ=2π+atan2(u(i, j), v(i, j))

Where Φ is the second angle.

All third cross-correlation windows with |Φ-θ|>Ta are marked as the folding flow, wherein the position corresponding to the third cross-correlation window is the position of the folding flow.

FIG. 12 is a schematic diagram of the position of the zigzag flow identified corresponding to the image to be processed in FIG. 8 . As shown in FIG. 12 , the diagram shows the position of the zigzag flow.

In some embodiments, the water flow state can be automatically identified based on the image, and a safety warning can be issued. The safety warning can be sent to the staff through the sluice safety identification system, or a warning sound can be prompted by the sluice safety identification system. The warning sound can be the same or different warning music or voice, etc.

An embodiment of the present application provides a method for safety identification of a sluice gate, which obtains an image to be processed containing tracer particles of the water flow under the gate, and determines the planar two-dimensional flow field corresponding to the image to be processed according to a preset cross-correlation window and a cross-correlation algorithm. That is to say, the flow velocity vector of each cross-correlation window in the image to be processed is determined, and further, the vorticity value of each cross-correlation window is determined. Based on the preset judgment strategy and vorticity value, the flow state of the water flow under the gate and the position corresponding to the water flow state are identified. The present application can achieve accurate and efficient identification of the water flow state under the gate through analysis and processing of the image, thereby improving the safety monitoring of the sluice gate.

In some embodiments, an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the aforementioned sluice safety identification method when executing the computer program.

In some embodiments, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor executes the steps of the aforementioned sluice safety identification method.

The following paragraphs will compare and list the Chinese terms involved in this application specification and their corresponding English terms to facilitate reading and understanding.

For the convenience of explanation, the above description has been made in conjunction with specific embodiments. However, the above discussion in some embodiments is not intended to be exhaustive or limit the embodiments to the specific forms disclosed above. According to the above teachings, various modifications and variations can be obtained. The selection and description of the above embodiments are to better explain the principles and practical applications, so that those skilled in the art can better use the embodiments and various different variations of the embodiments suitable for specific use considerations.

Claims (8)

1. A method for identifying water gate safety, characterized in that the method comprises: Acquire an image to be processed of water flow under the sluice gate, wherein the image to be processed contains tracer particles; Determine the planar two-dimensional flow field corresponding to the image to be processed according to a preset cross-correlation window and a cross-correlation algorithm, wherein the planar two-dimensional flow field is determined by the flow velocity vectors of each cross-correlation window in the image to be processed; Determining the vorticity value of each of the cross-correlation windows; Based on the preset determination strategy and the vorticity value, the flow pattern of the water under the gate and the position corresponding to the flow pattern of the water are identified, wherein: If the vorticity value is greater than a preset vorticity threshold, marking a first cross-correlation window corresponding to the vorticity value as a vortex flow, wherein the first cross-correlation window is a cross-correlation window in the image to be processed, and the preset determination strategy includes determining a cross-correlation window whose vorticity value is greater than a preset vortex threshold as a vortex flow; and the position corresponding to the first cross-correlation window is the position of the vortex flow; Calculating an arctangent value of a flow velocity vector of a second cross-correlation window in the cross-correlation window, wherein the second cross-correlation window is a window other than the first cross-correlation window in the cross-correlation window; and determining a second angle between each of the second cross-correlation windows and the horizontal direction based on the arctangent value; If the absolute value of the difference between the second angle and the first angle is greater than a preset angle threshold, the third correlation window corresponding to the second angle is marked as a breakaway flow, wherein the first angle is the angle between the smooth flow direction of the water flow under the gate and the horizontal direction, and the preset judgment strategy includes judging the correlation window whose absolute value of the difference between the second angle and the first angle is greater than a preset angle threshold as a breakaway flow, and the third correlation window is a correlation window in the second correlation window; the position corresponding to the third correlation window is the position of the breakaway flow. 2. The sluice safety identification method according to claim 1, characterized in that the determining of the vorticity value of each cross-correlation window comprises: Decomposing the flow velocity vector of the cross-correlation window into a horizontal flow velocity and a vertical flow velocity; Determining a horizontal velocity gradient and a vertical velocity gradient of the cross-correlation window; The vorticity value of the cross-correlation window is determined based on the horizontal flow velocity gradient and the vertical flow velocity gradient of the cross-correlation window. 3. The sluice safety identification method according to claim 1 is characterized in that the step of determining the planar two-dimensional flow field corresponding to the image to be processed according to a preset cross-correlation window and a cross-correlation algorithm comprises: According to a preset size of the cross-correlation window, dividing the first moment image in the image to be processed into a plurality of the cross-correlation windows; Determine the cross-correlation value corresponding to each cross-correlation window in the image at the second moment in the image to be processed, wherein the image at the first moment and the image at the second moment are two images at adjacent moments in the image to be processed; Based on the cross-correlation value, determining a second position in the image at the second moment that matches the first position in the image at the first moment; A planar two-dimensional flow field corresponding to the image to be processed is determined according to the first position and the second position. 4. The method for identifying water gate safety according to claim 1 is characterized in that, before determining the planar two-dimensional flow field corresponding to the image to be processed according to the preset cross-correlation window and the cross-correlation algorithm, it also includes: Establishing a conversion relationship between the image coordinate system and the world coordinate system of the image to be processed; Based on the conversion relationship, the world coordinates corresponding to the image to be processed are determined. 5. A water gate safety identification system, characterized in that the system comprises: An image acquisition module, used for acquiring an image to be processed of the water flow under the sluice gate; A water flow pattern recognition module, used to determine the planar two-dimensional flow field corresponding to the image to be processed according to a preset cross-correlation window and a cross-correlation algorithm, wherein the planar two-dimensional flow field is determined by the flow velocity vectors of each cross-correlation window in the image to be processed; The water flow pattern recognition module is also used to determine the vorticity value of each of the cross-correlation windows; The water flow state recognition module is further used to identify the water flow state under the gate and the position corresponding to the water flow state based on a preset judgment strategy and the vorticity value, wherein if the vorticity value is greater than a preset vorticity threshold, a first cross-correlation window corresponding to the vorticity value is marked as a vortex flow, wherein the first cross-correlation window is a cross-correlation window in the image to be processed, and the preset judgment strategy includes judging a cross-correlation window whose vorticity value is greater than a preset vortex threshold as a vortex flow; the position corresponding to the first cross-correlation window is the position of the vortex flow; Also used to calculate the arctangent value of the flow velocity vector of the second cross-correlation window in the cross-correlation window, the second cross-correlation window being a window other than the first cross-correlation window in the cross-correlation window; based on the arctangent value, determine the second angle between each of the second cross-correlation windows and the horizontal direction; If the absolute value of the difference between the second angle and the first angle is greater than a preset angle threshold, the third correlation window corresponding to the second angle is marked as a breakaway flow, wherein the first angle is the angle between the smooth flow direction of the water flow under the gate and the horizontal direction, and the preset judgment strategy includes judging the correlation window whose absolute value of the difference between the second angle and the first angle is greater than a preset angle threshold as a breakaway flow, and the third correlation window is a correlation window in the second correlation window; the position corresponding to the third correlation window is the position of the breakaway flow. 6. The water gate safety identification system according to claim 5, characterized in that the system further comprises: The correction module is used to locate the world coordinates corresponding to the image to be processed. 7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein the processor implements the steps of the water gate safety identification method according to any one of claims 1 to 4 when executing the computer program. 8. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor executes the steps of the water gate safety identification method according to any one of claims 1 to 4.