CN118865265A - A method and system for quality control of side-scan flow radar data - Google Patents

Abstract

The present invention provides a side-scanning current radar data quality control method and system, wherein the method comprises the following steps: data collection is performed on each monitoring area of the monitored water area to obtain current point cloud data, current image data and current flow rate data; based on the current point cloud data and current image data, the water state of the water area corresponding to the monitored area is determined, and the abnormal time corresponding to the abnormal state is determined; data collection with the same duration as the abnormal time is performed to obtain supplementary point cloud data, supplementary image data and supplementary flow rate data; in response to determining that the corresponding monitoring area is in a normal state based on the supplementary point cloud data and supplementary image data, the abnormal flow rate portion corresponding to the abnormal time is replaced by the supplementary flow rate data; based on each current flow rate data, the water flow rate corresponding to the monitored water area is determined. The present invention at least improves the measurement accuracy of the water flow rate.

Description

A method and system for quality control of side-scan flow radar data

Technical Field

The invention relates to data processing technology, and in particular to a side-scan current measurement radar data quality control method and system.

Background Art

Water velocity usually refers to the speed of water flow, which can be expressed in different units, such as meters per second (m/s) or centimeters per second (cm/s). Flow rate depends on the nature of the water flow and the environmental conditions. For example, the flow rate in rivers, streams, and oceans may be different.

In the prior art, the measurement of water flow velocity often uses professional scanning radar to complete the corresponding measurement process. However, since the water area is often in different water states due to different natural or human factors, for example, when there are large vortex areas, ripple areas and noise areas in the water area, it will affect the measurement accuracy of the water flow velocity, and it is impossible to achieve accurate measurement of the water flow velocity, thereby reducing the corresponding measurement efficiency.

Summary of the invention

Based on the above problems, the present invention is proposed to provide a method and system for quality control of side-scan current radar data that overcomes the above problems or at least partially solves the above problems.

According to one aspect of the present invention, a method for controlling the quality of side-scan flow radar data is provided, comprising the following steps:

The water area to be monitored is gridded, and each grid point is determined as each monitoring area;

Collect data for each monitoring area at a preset time to obtain the current point cloud data, current image data and current flow velocity data of the corresponding monitoring area;

Determine the state of the water area corresponding to the monitoring area within the preset time based on the current point cloud data and the current image data, and determine the abnormal time corresponding to the abnormal state;

Performing data collection for a supplementary time having the same duration as the abnormal time to obtain supplementary point cloud data, supplementary image data and supplementary flow velocity data corresponding to the monitoring area;

In response to determining that the water area corresponding to the monitoring area is in a normal state during the supplementary time based on the supplementary point cloud data and the supplementary image data, replacing the abnormal flow velocity portion corresponding to the abnormal time in the current flow velocity data with the supplementary flow velocity data;

The water area flow velocity corresponding to the water area to be monitored is determined based on each current flow velocity data corresponding to each monitoring area.

Optionally, in the method according to the present invention, data collection is performed for each monitoring area for a preset time to obtain current point cloud data, current image data and current flow velocity data of the corresponding monitoring area, including:

The point cloud radar, image radar and flow velocity radar are triggered to collect data for each monitoring area for a preset time based on a preset collection frequency;

Determine the number of acquisitions based on the preset acquisition frequency and the preset time, and obtain secondary point cloud data, secondary image data, and secondary flow velocity data corresponding to each number of acquisitions;

Grouping each secondary point cloud data, each secondary image data and each secondary flow velocity data based on each time node corresponding to each acquisition number, to obtain each node data group of the secondary point cloud data, the secondary image data and the secondary flow velocity data corresponding to the same time node;

Each node data group is determined to be the current point cloud data, current image data and current flow velocity data corresponding to the monitoring area.

Optionally, in the method according to the present invention, determining the water state of the water area corresponding to the monitoring area within the preset time based on the current point cloud data and the current image data, and determining the abnormal time corresponding to the abnormal state, includes:

A two-dimensional plane is established based on the monitoring area, and point clouds of each region corresponding to the height of each point cloud are established on the two-dimensional plane based on the secondary point cloud data located in any node data group;

Acquire a region height corresponding to the monitoring region, compare the height of each point cloud with the region height, and determine a first morphological attribute of the monitoring region at a time node corresponding to the node data group based on the comparison result;

Retrieving secondary image data located in the same node data group as the secondary point cloud data, and determining a second morphological attribute of the monitoring area at a time node corresponding to the node data group based on the secondary image data;

Determine the water state of the monitoring area at the time node based on the first morphological attribute and the second morphological attribute corresponding to the monitoring area;

All time nodes corresponding to the abnormal state are summed up to obtain the abnormal time corresponding to the abnormal state.

Optionally, in the method according to the present invention, determining the first morphological attribute of the monitoring area at the time node corresponding to the node data group based on the comparison result includes:

Determine all regional point clouds whose corresponding point cloud heights are less than the regional height as a vortex point cloud group, and determine all regional point clouds whose corresponding point cloud heights are greater than the regional height as a ripple point cloud group;

Connecting point clouds of each region located in the vortex point cloud group and in adjacent position in the two-dimensional plane to obtain each vortex region located in the two-dimensional plane;

Connecting point clouds of the respective regions in the ripple point cloud group that are in an adjacent position relationship in the two-dimensional plane to obtain ripple regions in the two-dimensional plane;

Based on the preset merging strategy, each vortex area is merged based on the encirclement relationship;

After the merging process, the first area sizes and the number of first areas corresponding to each vortex area, and the second area sizes and the number of second areas corresponding to each ripple area are determined as the first morphological attributes of the monitoring area at the time node corresponding to the node data group.

Optionally, in the method according to the present invention, the vortex regions are merged based on the encirclement relationship based on a preset merging strategy, including:

Performing coordinate processing on the two-dimensional plane, obtaining vortex coordinate points located in each vortex area, and obtaining vortex coordinate groups corresponding to each vortex area;

The vortex coordinate groups are compared in pairs, and based on the comparison results, it is determined whether the vortex coordinate groups have an enclosing relationship, and the vortex areas corresponding to the vortex coordinate groups having an enclosing relationship are merged into one vortex area.

Optionally, in the method according to the present invention, determining the second morphological attribute of the monitoring area at the time node corresponding to the node data group based on the secondary image data includes:

Binarizing the secondary image data to obtain a binary image, wherein the binary image includes water area pixel points corresponding to the first pixel value and noise pixel points corresponding to the second pixel value;

Connecting the noise pixels in adjacent positions in the secondary image data to obtain noise regions in the secondary image data;

The sizes of the third regions and the number of the third regions corresponding to the noise regions are determined as the second morphological attributes of the monitoring region at the time node corresponding to the node data group.

Optionally, in the method according to the present invention, determining the water state of the monitoring area at the time node based on the first morphological attribute and the second morphological attribute corresponding to the monitoring area includes:

Performing a sum calculation based on the sizes of each first area to obtain a first size total value, and performing a ratio calculation based on the first size total value and a monitoring size corresponding to the monitoring area to obtain a first size ratio;

Normalizing the first size ratio and the first area quantity respectively to obtain a first size coefficient and a first quantity coefficient, and performing a sum calculation based on the first size coefficient and the second quantity coefficient to obtain a swirl coefficient;

Performing a sum calculation based on the sizes of the second regions to obtain a second size total value, and performing a ratio calculation based on the second size total value and a monitoring size corresponding to the monitoring region to obtain a second size ratio;

Normalizing the second size ratio and the second area quantity respectively to obtain a second size coefficient and a second quantity coefficient, and performing a sum calculation based on the second size coefficient and the second quantity coefficient to obtain a ripple coefficient;

Performing a sum calculation based on the sizes of the third regions to obtain a total third size value, and performing a ratio calculation based on the total third size value and a monitoring size corresponding to the monitoring region to obtain a third size ratio;

Normalizing the third size ratio and the third area quantity respectively to obtain a third size coefficient and a third quantity coefficient, and performing a sum calculation based on the third size coefficient and the third quantity coefficient to obtain a noise coefficient;

The water state of the monitoring area at the time node is determined based on the vortex coefficient, ripple coefficient and noise coefficient.

Optionally, in the method according to the present invention, determining the water state of the monitoring area at the time node based on the vortex coefficient, the ripple coefficient and the noise coefficient includes:

Call up the vortex weight, ripple weight and noise weight;

Calculate the product of the vortex coefficient and the vortex weight to obtain a vortex evaluation value;

Calculate the product of the ripple coefficient and the ripple weight to obtain a ripple evaluation value;

Calculate the product of the noise coefficient and the noise weight to obtain a noise evaluation value;

When the vortex evaluation value is greater than a first preset value, determining that the water state of the monitoring area at the time node is an abnormal state;

When the ripple evaluation value is greater than a second preset value, determining that the water state of the monitoring area at the time node is an abnormal state;

When the noise evaluation value is greater than a third preset value, determining that the water state of the monitoring area at the time node is an abnormal state;

When the vortex evaluation value is less than or equal to a first preset value, the ripple evaluation value is less than or equal to a second preset value, and the noise evaluation value is less than or equal to a third preset value, the vortex evaluation value, the ripple evaluation value, and the noise evaluation value are summed to obtain a comprehensive evaluation value;

When the comprehensive evaluation value is greater than a fourth preset value, it is determined that the water state of the monitoring area at the time node is abnormal.

Optionally, in the method according to the present invention, the actual state determination data corresponding to any time node sent by the management terminal based on any monitoring area is obtained, and the water state corresponding to the monitoring area is compared with the actual state determination data;

If the state is actually determined to be a normal state and the water state is an abnormal state, the vortex weight, ripple weight and noise weight are reduced by training;

If the state actually determines that the data is in an abnormal state and the water state is in a normal state, the vortex weight, ripple weight and noise weight are increased and trained;

The trained vortex weight, ripple weight, and noise weight are obtained through the following formula:

in, Vortex Weight Increase the number of training sessions. Vortex Weight The training constant value of Vortex Weight Reduce the number of training sessions. is the trained vortex weight, is the ripple weight Increase the number of training sessions. is the ripple weight The training constant value of is the ripple coefficient weight Reduce the number of training sessions. is the trained ripple weight, is the noise weight Increase the number of training sessions. is the noise weight The training constant value of is the noise weight Reduce the number of training sessions. is the trained vortex weight.

According to another aspect of the present invention, there is provided a side-scan flow radar data quality control system, comprising:

A grid processing module is configured to perform grid processing on the water area to be monitored, and determine each grid point obtained as each monitoring area;

The data acquisition module is configured to collect data for each monitoring area for a preset time to obtain current point cloud data, current image data and current flow velocity data of the corresponding monitoring area;

A state determination module is configured to determine the state of the water area corresponding to the monitoring area within the preset time based on the current point cloud data and the current image data, and determine the abnormal time corresponding to the abnormal state;

A supplementary acquisition module is configured to collect data for a supplementary time having the same duration as the abnormal time, and obtain supplementary point cloud data, supplementary image data and supplementary flow velocity data corresponding to the monitoring area;

A data replacement module is configured to replace the abnormal flow velocity portion corresponding to the abnormal time in the current flow velocity data with the supplementary flow velocity data in response to determining that the water area corresponding to the monitoring area is in a normal state during the supplementary time based on the supplementary point cloud data and the supplementary image data;

The flow rate determination module is configured to determine the water area flow rate corresponding to the water area to be monitored based on each current flow rate data corresponding to each monitoring area.

According to the solution of the present invention, by gridding the monitored water area, corresponding data collection is carried out based on each obtained monitoring area, and the current flow velocity data corresponding to each monitoring area is statistically calculated, the water flow velocity of the corresponding water area to be monitored can be obtained, and the flow velocity measurement of the monitored water area is refined to improve the corresponding measurement accuracy; at the same time, when measuring the flow velocity of each monitoring area, the water state of each monitoring area is also determined based on the vortex dimension, ripple dimension and noise dimension. When the water state of the corresponding monitoring area is abnormal, it is necessary to carry out corresponding supplementary collection for the monitoring area, thereby eliminating the interference of natural or human factors on the flow velocity measurement, and further improving the corresponding measurement accuracy.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 shows a flow chart of a method for controlling the quality of side-scan flow radar data according to an embodiment of the present invention;

FIG2 is a schematic diagram showing the scanning radar in this embodiment measuring the flow velocity in the monitoring area;

FIG3 shows a system block diagram of a side-scan flow radar data quality control system according to another embodiment of the present invention.

DETAILED DESCRIPTION

The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

Water velocity usually refers to the speed of water flow, which can be expressed in different units, such as meters per second (m/s) or centimeters per second (cm/s). Flow rate depends on the nature of the water flow and the environmental conditions. For example, the flow rate in rivers, streams, and oceans may be different.

In the prior art, the measurement of water flow velocity often uses professional scanning radar to complete the corresponding measurement process. However, since the water area is often in different water states due to different natural or human factors, for example, when there are large vortex areas, ripple areas and noise areas in the water area, it will affect the measurement accuracy of the water flow velocity, and it is impossible to achieve accurate measurement of the water flow velocity, thereby reducing the corresponding measurement efficiency.

In order to solve the problems existing in the above-mentioned prior art, the solution of the present invention is proposed. One embodiment of the present invention provides a side-scanning current radar data quality control method, which can be executed in a computing device, wherein the computing device can be understood as a terminal with data processing function, such as a mobile phone or a computer.

As shown in FIG1 , the purpose of this embodiment is to implement a side-scan flow radar data quality control method, which starts at step S102. In step S102, the following contents are included:

The water area to be monitored is gridded, and each grid area obtained is determined as each monitoring area.

For example, in this embodiment, the flow velocity measurement of the water area is generally carried out by using a corresponding scanning radar. As shown in FIG2 , the scanning radar forms a corresponding scanning surface when scanning. The scanning radar is controlled to move the scanning surface to the water surface of the water area to be monitored, so as to realize the flow velocity scanning of the water surface area overlapping with the scanning surface for a preset time, so as to determine the water flow velocity of the water surface area. In reality, since the water area to be monitored generally has a large water area, that is, the water area may be much larger than the area corresponding to the scanning surface, the water area to be monitored will be gridded accordingly to obtain a plurality of corresponding grid areas, and the plurality of grid areas will be respectively determined as monitoring areas, so that in subsequent steps, the corresponding flow velocity measurement can be performed based on each monitoring area, and then the water flow velocity corresponding to the water area to be monitored is determined according to the measurement result of each monitoring area, thereby improving the corresponding measurement accuracy.

In step S104, the following contents are included:

Data is collected for each monitoring area at a preset time to obtain the current point cloud data, current image data and current flow velocity data of the corresponding monitoring area.

It should be noted that, in the embodiment, when a scanning radar is used to measure the flow velocity of the water area to be monitored, the bad water surface conditions in the water area to be monitored may affect the corresponding measurement accuracy. For example, when there are corresponding larger ripples, larger vortices and larger floating objects on the water surface, the measurement accuracy of the water area to be monitored will be reduced accordingly. In order to reduce the impact of these bad water surface conditions on the flow velocity measurement, it is first necessary to identify these bad water surface conditions accordingly. It is well known that when there are no ripples and vortices on the water surface of any monitoring area, the area height corresponding to the monitoring area should remain consistent. That is, it is in a horizontal state, and when corresponding ripples and vortices appear on the water surface, the area height corresponding to the monitored area may change accordingly, that is, when ripples appear, the area height at the position of the corresponding ripples will increase, and when vortices appear, the area height at the position of the corresponding vortex will decrease; based on this characteristic, while measuring the flow velocity in the monitored area, the current point data can be obtained to determine whether there are corresponding ripples and vortices; and for floating objects, the current image data can be obtained to further determine whether large floating objects have appeared in the corresponding monitored area based on the current image data.

Further, in this embodiment, the above-mentioned “collecting data for each monitoring area for a preset time to obtain current point cloud data, current image data and current flow velocity data of the corresponding monitoring area” may also include the following steps:

The point cloud radar, image radar and flow velocity radar are triggered to collect data for each monitoring area for a preset time based on a preset collection frequency;

Determine the number of acquisitions based on the preset acquisition frequency and the preset time, and obtain secondary point cloud data, secondary image data, and secondary flow velocity data corresponding to each number of acquisitions;

Grouping each secondary point cloud data, each secondary image data and each secondary flow velocity data based on each time node corresponding to each acquisition number, to obtain each node data group of the secondary point cloud data, the secondary image data and the secondary flow velocity data corresponding to the same time node;

Each node data group is determined to be the current point cloud data, current image data and current flow velocity data corresponding to the monitoring area.

For example, in this embodiment, the acquisition of current point cloud data can be based on the corresponding point cloud radar, the acquisition of current image data can be based on the corresponding image radar, and the acquisition of current flow velocity data can be based on the corresponding flow velocity radar; and because the corresponding preset time will be continued to ensure the accuracy of the corresponding flow velocity measurement when collecting data for the monitored water area, and water generally has corresponding fluidity, therefore, for the same monitoring area, different water surface conditions may correspond to different times. For example, when the preset time is 30s, only the corresponding larger ripples appear in the 15th second, and the corresponding larger vortex and floating objects appear at the same time in the 16th second, and only smaller floating objects may appear in the 17th second. In this case, it can be seen that the accuracy of the flow velocity measurement for 17s is relatively high. In order to be able to divide the point cloud data, image data and flow velocity data at the same time to determine the water surface state corresponding to any monitoring area at that time, it can be achieved in the following way:

First, the point cloud radar, image radar and flow velocity radar are triggered to collect data for each monitoring area for a preset time based on the same preset collection frequency;

Next, the number of acquisitions corresponding to the preset time can be determined based on the preset acquisition frequency. For example, when the preset time is 30s and the preset acquisition frequency is 2s/time, the corresponding number of acquisitions is 15 times. After the corresponding number of acquisitions is determined, the point cloud radar, image radar and flow velocity radar can be controlled to simultaneously collect data for the monitoring area in the corresponding number of acquisitions, so as to obtain secondary point cloud data, secondary image data and secondary flow velocity data corresponding to the same number of acquisitions.

Then, the secondary point cloud data, secondary image data and secondary flow velocity data corresponding to the same number of acquisition times can be divided into the same node data group to obtain each node data group corresponding to the monitoring area;

Finally, each node data group may be determined as the current point cloud data, current image data, and current flow velocity data obtained after data collection in the corresponding monitoring area within a preset time.

In step S106, the following contents are included:

The state of the water area corresponding to the monitoring area within the preset time is determined based on the current point cloud data and the current image data, and the abnormal time corresponding to the abnormal state is determined.

For example, in this embodiment, after obtaining the corresponding current point cloud data and current image data, the water state of the corresponding monitoring area within the preset time can be determined based on the two; and from the above content, it can be seen that when the water surface conditions of any monitored water area show at least one of large ripples, vortices or floating objects, the measurement accuracy of the flow velocity measurement corresponding to the time node is low, that is, the water state corresponding to the time node can be determined as an abnormal state; in order to improve the corresponding measurement accuracy, it is necessary to locate these time nodes and determine the abnormal time when the corresponding monitoring area is in an abnormal state, so as to conduct supplementary monitoring of the monitoring area with the same duration as the abnormal time in the future.

Further, in this embodiment, the above-mentioned “determining the water state of the water area corresponding to the monitoring area within the preset time based on the current point cloud data and the current image data, and determining the abnormal time corresponding to the abnormal state” may also include the following steps:

A two-dimensional plane is established based on the monitoring area, and point clouds of each region corresponding to the height of each point cloud are established on the two-dimensional plane based on the secondary point cloud data located in any node data group;

Acquire a region height corresponding to the monitoring region, compare the height of each point cloud with the region height, and determine a first morphological attribute of the monitoring region at a time node corresponding to the node data group based on the comparison result;

Retrieving secondary image data located in the same node data group as the secondary point cloud data, and determining a second morphological attribute of the monitoring area at a time node corresponding to the node data group based on the secondary image data;

Determine the water state of the monitoring area at the time node based on the first morphological attribute and the second morphological attribute corresponding to the monitoring area;

All time nodes corresponding to the abnormal state are summed up to obtain the abnormal time corresponding to the abnormal state.

For example, in this embodiment, the acquisition of abnormal time can be specifically implemented through the following scheme:

First, a corresponding two-dimensional plane can be established based on a horizontal plane in a static state without external influence in the monitoring area, and regional point clouds corresponding to the heights of each point cloud can be established on the two-dimensional plane based on the secondary point cloud data in the node data group; it should be noted that since the point cloud radar can obtain the height information of the corresponding point cloud, that is, the height information is obtained based on the generated regional point cloud in the corresponding monitoring area, so as to obtain the corresponding secondary point cloud data, and further generate the regional point clouds corresponding to the heights of each point cloud on the two-dimensional plane according to the secondary point cloud data;

Next, in order to determine the ripples and/or vortices located in the monitoring area based on the point clouds of each area, it is necessary to obtain the area height corresponding to the monitoring area. Here, the area height can be understood as the height of the horizontal plane of the monitoring area in a static state without external influences; since the point cloud height at the area corresponding to the ripples will be greater than the area height, and the point cloud height at the area corresponding to the vortex will be less than the area height, therefore, based on this characteristic, the point cloud heights of each area point cloud located in the same monitoring area can be compared with the area height, and the first morphological attribute of the monitoring area at the time node of the corresponding node data group can be determined based on the corresponding comparison results;

Then, in order to determine the floating objects in the monitoring area, the secondary image data in the same node data group as the secondary point cloud data can be retrieved, and the second morphological attribute of the monitoring area at the time node of the corresponding node data group can be determined based on the corresponding secondary image data;

Then, after determining the corresponding first morphological attribute and second morphological attribute, the water state of the monitoring area at the time node can be determined based on the first morphological attribute and the second morphological attribute;

Finally, the time nodes corresponding to the abnormal state are summed up to obtain the abnormal time corresponding to the abnormal state.

It should be noted that, in this implementation, the first morphological attribute is determined based on whether corresponding ripples and vortices exist in the monitoring area, that is, it is determined by the point cloud height, and the second morphological attribute is determined based on whether corresponding floating objects exist in the monitoring area, that is, it is determined by image recognition.

Furthermore, in this embodiment, the above-mentioned “determining the first morphological attribute of the monitoring area at the time node corresponding to the node data group based on the comparison result” may also include the following steps:

Determine all regional point clouds whose corresponding point cloud heights are less than the regional height as a vortex point cloud group, and determine all regional point clouds whose corresponding point cloud heights are greater than the regional height as a ripple point cloud group;

Connecting point clouds of each region located in the vortex point cloud group and in adjacent position in the two-dimensional plane to obtain each vortex region located in the two-dimensional plane;

Connecting point clouds of the respective regions in the ripple point cloud group that are in an adjacent position relationship in the two-dimensional plane to obtain ripple regions in the two-dimensional plane;

Based on the preset merging strategy, each vortex area is merged based on the encirclement relationship;

After the merging process, the first area sizes and the number of first areas corresponding to each vortex area, and the second area sizes and the number of second areas corresponding to each ripple area are determined as the first morphological attributes of the monitoring area at the time node corresponding to the node data group.

For example, in the present embodiment, in the monitoring area, all regional point clouds whose corresponding point cloud height is less than the regional height can be determined as a vortex point cloud group, and all regional point clouds whose corresponding point cloud height is greater than the regional height can be determined as a ripple point cloud group; by connecting the regional point clouds located in the vortex point cloud group and in adjacent positional relationship, the vortex regions located in the two-dimensional plane can be obtained. Similarly, by connecting the regional point clouds located in the ripple point cloud group and in adjacent positional relationship, the ripple regions located in the two-dimensional plane can be obtained. Here, since the ripple regions and vortex regions generally present an array Column state, that is, there may be an encirclement relationship between each ripple area, and there may also be a corresponding encirclement relationship between each vortex area. Therefore, in order to be able to determine the number of ripple areas and vortex areas respectively, it is necessary to determine whether each ripple area and each vortex area can be merged separately based on the preset merging strategy; after completing the corresponding merging processing, the first area size and the number of first areas corresponding to each vortex area respectively, the second area size and the number of second areas corresponding to each ripple area respectively can be obtained, and further determined as the first morphological attribute of the monitoring area at the time node of the corresponding node data group.

Here, the above-mentioned “merging the vortex regions based on the encirclement relationship based on the preset merging strategy” may also include the following steps:

Performing coordinate processing on the two-dimensional plane, obtaining the vortex coordinate points located in each vortex area, and obtaining the vortex coordinate groups corresponding to the vortex areas;

The vortex coordinate groups are compared in pairs, and based on the comparison results, it is determined whether the vortex coordinate groups have an enclosing relationship, and the vortex areas corresponding to the vortex coordinate groups having an enclosing relationship are merged into one vortex area.

For example, in this embodiment, in order to determine whether the vortex areas have a corresponding enclosing relationship, the following process can be used:

First, the two-dimensional coordinates can be processed into coordinates, so as to obtain the vortex coordinate points constituting each vortex area, and form vortex coordinate groups corresponding to each vortex area respectively;

Next, based on the characteristics of the vortex, it can be known that the vortex is generally a spiral water vortex, that is, it radiates outward in an array from the center point of the vortex. Therefore, each vortex coordinate group can be compared two by two, and based on the comparison result, it can be determined whether there is an encirclement relationship between the vortex coordinate groups. When at least two have an encirclement relationship, it can be determined that at least two should belong to the same vortex area. At this time, the vortex areas with an encirclement relationship can be merged into one vortex area, thereby completing the merged screening of each vortex area, so that the first area number and the first area size of the vortex area can be accurately obtained in the subsequent method steps.

Here, after the first morphological attribute of the monitoring area within the preset time is determined based on the corresponding current point cloud data, the second morphological attribute of the monitoring area within the preset time can be determined based on the corresponding current image data. That is, in this embodiment, the above-mentioned "determining the second morphological attribute of the monitoring area at the time node corresponding to the node data group based on the secondary image data" can also include the following steps:

Binarizing the secondary image data to obtain a binary image, wherein the binary image includes water area pixel points corresponding to the first pixel value and noise pixel points corresponding to the second pixel value;

Connecting the noise pixels in adjacent positions in the secondary image data to obtain noise regions in the secondary image data;

The sizes of the third regions and the number of the third regions corresponding to the noise regions are determined as the second morphological attributes of the monitoring region at the time node corresponding to the node data group.

For example, in this embodiment, in order to determine the second morphological attribute at the time node of the corresponding node data group, the floating objects located in the monitoring area can be identified based on the image recognition method. Here, the area formed by the floating objects can be called a noise area, and the floating objects can include leaves, branches or other objects;

In order to quickly identify floating objects floating on the monitoring area, the acquired secondary image data can be binarized to obtain a corresponding binary image; here, the binarization process can be understood as setting the grayscale value of the pixel points on the image to 0 or 255, so that the entire image presents an obvious black and white effect; since the pixel values of the water area pixels of the corresponding monitoring area are the same, other pixel points with different pixel values from the water area pixels are noise pixel points of the corresponding floating objects. By binarizing the secondary image data, the corresponding water area pixels can be converted into the first pixel value, and the corresponding noise pixels can be converted into the second pixel value, so as to complete the identification of floating objects. Compared with the existing method of using image recognition models for identification, it has a lower data processing amount and can also ensure the corresponding identification accuracy;

After completing the determination of each noise pixel point, the noise pixel points in adjacent position relationships are further connected to obtain each noise area in the secondary image data, and the third area size and the number of third areas corresponding to each noise area are determined as the second morphological attribute of the monitoring area at the time node of the corresponding node data group.

For example, in this embodiment, after the first morphological attribute and the second morphological attribute are determined, the water state at the corresponding time node can be determined based on the first morphological attribute and the second morphology of the corresponding monitoring area, wherein the specific method steps may include the following contents:

Performing a sum calculation based on the sizes of the first regions to obtain a first size total value, and performing a ratio calculation based on the first size total value and a monitoring size corresponding to the monitoring region to obtain a first size ratio;

Normalizing the first size ratio and the first area quantity respectively to obtain a first size coefficient and a first quantity coefficient, and performing a sum calculation based on the first size coefficient and the second quantity coefficient to obtain a swirl coefficient;

Performing a sum calculation based on the sizes of the second regions to obtain a second size total value, and performing a ratio calculation based on the second size total value and a monitoring size of the corresponding monitoring region to obtain a second size ratio;

Normalizing the second size ratio and the second area quantity respectively to obtain a second size coefficient and a second quantity coefficient, and performing a sum calculation based on the second size coefficient and the second quantity coefficient to obtain a ripple coefficient;

Performing a sum calculation based on the sizes of the third regions to obtain a total third size value, and performing a ratio calculation based on the total third size value and a monitoring size corresponding to the monitoring region to obtain a third size ratio;

Normalizing the third size ratio and the third area quantity respectively to obtain a third size coefficient and a third quantity coefficient, and performing a sum calculation based on the third size coefficient and the third quantity coefficient to obtain a noise coefficient;

The water state of the monitoring area at the time node is determined based on the vortex coefficient, ripple coefficient and noise coefficient.

For example, in this embodiment, the corresponding swirl coefficient, ripple coefficient and noise coefficient can be determined respectively based on the first morphological attribute obtained above, wherein the determination of the swirl coefficient includes the following process:

First, the monitoring size of the corresponding monitoring area is obtained, and at the same time, the first area sizes of the corresponding vortex areas are summed up to obtain the corresponding total value of the first size;

Next, the first dimension ratio is obtained by calculating the ratio of the first dimension total value to the monitoring dimension;

Finally, the first size ratio and the first area quantity are normalized to obtain the corresponding first size coefficient and first quantity coefficient, and the vortex coefficient of the corresponding vortex area is obtained by summing them up.

Furthermore, the determination of the ripple coefficient includes the following process:

First, the monitoring size of the corresponding monitoring area is obtained, and at the same time, the second area sizes of the corresponding corrugated areas are summed up to obtain the corresponding second size total value;

Next, the second dimension ratio is obtained by calculating the ratio of the second dimension total value to the monitoring dimension;

Finally, the second size ratio and the second area quantity are normalized to obtain the corresponding second size coefficient and second quantity coefficient, and the corrugation coefficient of the corresponding corrugation area is obtained by summing them up.

Furthermore, the determination of the noise figure includes the following process:

First, the monitoring size of the corresponding monitoring area is obtained, and at the same time, the third area sizes of the corresponding noise areas are summed up to obtain the corresponding total value of the third size;

Next, the third dimension ratio is obtained by calculating the ratio of the total value of the third dimension to the monitored dimension;

Finally, the third size ratio and the third area quantity are normalized to obtain the corresponding third size coefficient and third quantity coefficient, and the noise coefficient of the corresponding noise area is obtained by summing them up.

For example, in this embodiment, when a large ripple, vortex or floating object appears in the monitoring area at a certain time node, it will affect the corresponding measurement accuracy. In this case, it is necessary to determine the water state of the monitoring area at the corresponding time node based on the vortex coefficient, ripple coefficient and noise coefficient obtained above. The specific method process may include the following contents:

Call up the vortex weight, ripple weight and noise weight;

Calculate the product of the vortex coefficient and the vortex weight to obtain a vortex evaluation value;

Calculate the product of the ripple coefficient and the ripple weight to obtain a ripple evaluation value;

Calculate the product of the noise coefficient and the noise weight to obtain a noise evaluation value;

When the vortex evaluation value is greater than a first preset value, determining that the water state of the monitoring area at the time node is an abnormal state;

When the ripple evaluation value is greater than a second preset value, determining that the water state of the monitoring area at the time node is an abnormal state;

When the noise evaluation value is greater than a third preset value, determining that the water state of the monitoring area at the time node is an abnormal state;

When the vortex evaluation value is less than or equal to a first preset value, the ripple evaluation value is less than or equal to a second preset value, and the noise evaluation value is less than or equal to a third preset value, the vortex evaluation value, the ripple evaluation value, and the noise evaluation value are summed to obtain a comprehensive evaluation value;

When the comprehensive evaluation value is greater than a fourth preset value, it is determined that the water state of the monitoring area at the time node is abnormal.

For example, in this embodiment, by calling the corresponding vortex weight, ripple weight and noise weight, and multiplying each weight with the corresponding coefficient, the corresponding vortex evaluation value, ripple evaluation value and noise evaluation value are obtained. Through the above calculation process, it can be known that the larger the vortex evaluation value, the larger the corresponding vortex size and the number of vortices may be; the larger the ripple evaluation value, the larger the corresponding ripple size and the number of ripples may be; the larger the noise evaluation value, the larger the corresponding noise size and the number of noise may be; based on this, it can be determined that when any evaluation value is greater than the corresponding preset value, the water state of the monitored area at the time node can be determined as an abnormal state; and when all evaluation values are less than or equal to the corresponding preset values, in order to further determine the water state, it is necessary to judge the comparison result between the comprehensive evaluation value obtained by summing the vortex evaluation value, the ripple evaluation value and the noise evaluation value and the corresponding preset value. When the comprehensive evaluation value is greater than the corresponding preset value, it can also indicate that the water state of the corresponding monitored area at the time node is an abnormal state.

It should be noted that, in this embodiment, each of the above-mentioned weights and preset values can be set by the corresponding management terminal, and the specific values are not limited in this embodiment.

Furthermore, in the present embodiment, since the determination of the water state is based on the corresponding numerical comparison results, the water state determined by the numerical comparison results may deviate from the actual situation to a certain extent. In order to improve the corresponding determination accuracy, the corresponding weights can be updated and trained in real time to realize the process of iteratively updating the weights, thereby continuously improving the corresponding determination accuracy.

Here, the update iteration of each weight can be achieved through the following steps:

Obtaining actual state determination data corresponding to any time node sent by the management end based on any monitoring area, and comparing the water state corresponding to the monitoring area with the actual state determination data;

If the state is actually determined to be a normal state and the water state is an abnormal state, the vortex weight, ripple weight and noise weight are reduced by training;

If the state actually determines that the data is in an abnormal state and the water state is in a normal state, the vortex weight, ripple weight and noise weight are increased and trained;

The trained vortex weight, ripple weight, and noise weight are obtained through the following formula:

in, Vortex Weight Increase the number of training sessions. Vortex Weight The training constant value of Vortex Weight Reduce the number of training sessions. is the trained vortex weight, is the ripple weight Increase the number of training sessions. is the ripple weight The training constant value of is the ripple coefficient weight Reduce the number of training sessions. is the trained ripple weight, is the noise weight Increase the number of training sessions. is the noise weight The training constant value of is the noise weight Reduce the number of training sessions. is the trained vortex weight.

In step S108, the following contents are included:

Data collection is performed for a supplementary time having the same duration as the abnormal time to obtain supplementary point cloud data, supplementary image data and supplementary flow velocity data corresponding to the monitoring area.

For example, in this embodiment, by counting the time nodes in the abnormal state, the abnormal time within the preset time can be determined. Since the abnormal time corresponds to the time nodes that affect the measurement accuracy, it is necessary to remove the corresponding time nodes and collect data with supplementary time of the same length as the abnormal time, so as to obtain supplementary point cloud data, supplementary image data and supplementary flow velocity data corresponding to the monitored area.

In step S110, the following contents are included:

In response to determining that the water area corresponding to the monitoring area is in a normal state during the supplementary time based on the supplementary point cloud data and the supplementary image data, the supplementary flow velocity data replaces the abnormal flow velocity portion corresponding to the abnormal time in the current flow velocity data.

For example, since the supplementary point cloud data and supplementary image data are obtained based on supplementation, it is necessary to ensure that the corresponding water area state is normal before the corresponding supplementary flow velocity data can be used to replace the abnormal flow velocity part of the corresponding abnormal time in the current flow velocity data, thereby improving the corresponding measurement accuracy; and if the water area state corresponding to the corresponding supplementary point cloud data and supplementary image data is abnormal, it is necessary to perform corresponding supplementation again to ensure that the current flow velocity data after supplementation has higher measurement accuracy.

In step S112, the following contents are included:

The water area flow velocity corresponding to the water area to be monitored is determined based on each current flow velocity data corresponding to each monitoring area.

For example, after completing the data supplement for each monitoring area, the water area flow velocity corresponding to the water area to be monitored can be determined based on the current flow velocity data corresponding to each monitoring area; here, the water area flow velocity can be obtained based on the mean calculation, that is, when there are three monitoring areas, the current flow velocity data corresponding to the three monitoring areas can be averaged, and the corresponding mean result can be determined as the water area flow velocity.

According to the scheme of the present embodiment, by gridding the monitored water area, corresponding data collection is performed based on each obtained monitoring area, and the current flow velocity data corresponding to each monitoring area is statistically calculated, so the water flow velocity of the corresponding water area to be monitored can be obtained, and the flow velocity measurement of the monitored water area is refined to improve the corresponding measurement accuracy; at the same time, when measuring the flow velocity of each monitoring area, the water state of each monitoring area is also determined based on the vortex dimension, ripple dimension and noise dimension. When the water state of the corresponding monitoring area is abnormal, it is necessary to perform corresponding supplementary collection on the monitoring area, thereby eliminating the interference of natural or human factors on the flow velocity measurement, and further improving the corresponding measurement accuracy.

Another embodiment of the present invention provides a side-scan flow radar data quality control system, and FIG3 is a corresponding system block diagram thereof. The system includes:

A grid processing module is configured to perform grid processing on the water area to be monitored, and determine each grid point obtained as each monitoring area;

The data acquisition module is configured to collect data for each monitoring area for a preset time to obtain current point cloud data, current image data and current flow velocity data of the corresponding monitoring area;

A state determination module is configured to determine the state of the water area corresponding to the monitoring area within the preset time based on the current point cloud data and the current image data, and determine the abnormal time corresponding to the abnormal state;

A supplementary acquisition module is configured to collect data for a supplementary time having the same duration as the abnormal time, and obtain supplementary point cloud data, supplementary image data and supplementary flow velocity data corresponding to the monitoring area;

A data replacement module is configured to replace the abnormal flow velocity portion corresponding to the abnormal time in the current flow velocity data with the supplementary flow velocity data in response to determining that the water area corresponding to the monitoring area is in a normal state during the supplementary time based on the supplementary point cloud data and the supplementary image data;

The flow rate determination module is configured to determine the water area flow rate corresponding to the water area to be monitored based on the current flow rate data corresponding to each monitoring area.

In the description provided herein, algorithms and displays are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the examples of the present invention. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages can be utilized to implement the content of the present invention described herein, and the above description of specific languages is for the purpose of disclosing the preferred embodiment of the present invention.

In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof.

Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in the devices described in the embodiment, or alternatively may be located in one or more devices different from the devices in the examples. The modules in the foregoing examples may be combined into one module or may be divided into multiple submodules.

Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of submodules or subunits or subcomponents.

Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features from different embodiments is meant to be within the scope of the present invention and to form different embodiments.

In addition, some of the embodiments are described herein as methods or combinations of method elements that can be implemented by a processor of a computer system or by other devices that perform the functions. Therefore, a processor with necessary instructions for implementing the method or method elements forms a device for implementing the method or method elements. In addition, the elements described herein of the device embodiments are examples of devices for implementing the functions performed by the elements for the purpose of implementing the invention.

As used herein, unless otherwise specified, the use of ordinal numbers "first," "second," "third," etc. to describe common objects merely indicates that different instances of similar objects are involved, and is not intended to imply that the objects so described must have a given order in time, space, order, or in any other manner.

Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is primarily selected for readability and instructional purposes, rather than for explaining or limiting the subject matter of the present invention.

Claims (10)

1. A method for controlling the quality of side-scan current radar data, comprising the following steps: The water area to be monitored is gridded, and each grid area obtained is determined as each monitoring area; Collect data for each monitoring area at a preset time to obtain the current point cloud data, current image data and current flow velocity data of the corresponding monitoring area; Determine the state of the water area corresponding to the monitoring area within the preset time based on the current point cloud data and the current image data, and determine the abnormal time corresponding to the abnormal state; Performing data collection for a supplementary time having the same duration as the abnormal time to obtain supplementary point cloud data, supplementary image data and supplementary flow velocity data corresponding to the monitoring area; In response to determining that the water area corresponding to the monitoring area is in a normal state during the supplementary time based on the supplementary point cloud data and the supplementary image data, replacing the abnormal flow velocity portion corresponding to the abnormal time in the current flow velocity data with the supplementary flow velocity data; The water area flow velocity corresponding to the water area to be monitored is determined based on each current flow velocity data corresponding to each monitoring area. 2. The method for controlling the quality of side-scan flow radar data according to claim 1, characterized in that: Data is collected for each monitoring area at a preset time to obtain the current point cloud data, current image data and current flow rate data of the corresponding monitoring area, including: The point cloud radar, image radar and flow velocity radar are triggered to collect data for each monitoring area for a preset time based on a preset collection frequency; Determine the number of acquisitions based on the preset acquisition frequency and the preset time, and obtain secondary point cloud data, secondary image data, and secondary flow velocity data corresponding to each number of acquisitions; Grouping each secondary point cloud data, each secondary image data and each secondary flow velocity data based on each time node corresponding to each acquisition number, to obtain each node data group of the secondary point cloud data, the secondary image data and the secondary flow velocity data corresponding to the same time node; Each node data group is determined to be the current point cloud data, current image data and current flow velocity data corresponding to the monitoring area. 3. The method for controlling the quality of side-scan flow radar data according to claim 2, characterized in that: Determining the water state of the water area corresponding to the monitoring area within the preset time based on the current point cloud data and the current image data, and determining the abnormal time corresponding to the abnormal state, including: A two-dimensional plane is established based on the monitoring area, and point clouds of each region corresponding to the height of each point cloud are established on the two-dimensional plane based on the secondary point cloud data located in any node data group; Acquire a region height corresponding to the monitoring region, compare the height of each point cloud with the region height, and determine a first morphological attribute of the monitoring region at a time node corresponding to the node data group based on the comparison result; Retrieving secondary image data located in the same node data group as the secondary point cloud data, and determining a second morphological attribute of the monitoring area at a time node corresponding to the node data group based on the secondary image data; Determine the water state of the monitoring area at the time node based on the first morphological attribute and the second morphological attribute corresponding to the monitoring area; All time nodes corresponding to the abnormal state are summed up to obtain the abnormal time corresponding to the abnormal state. 4. The method for controlling the quality of side-scan flow radar data according to claim 3, characterized in that: Determining a first morphological attribute of the monitoring area at a time node corresponding to the node data group based on the comparison result includes: Determine all regional point clouds whose corresponding point cloud heights are less than the regional height as a vortex point cloud group, and determine all regional point clouds whose corresponding point cloud heights are greater than the regional height as a ripple point cloud group; Connecting point clouds of each region located in the vortex point cloud group and in adjacent position in the two-dimensional plane to obtain each vortex region located in the two-dimensional plane; Connecting point clouds of the respective regions in the ripple point cloud group that are in an adjacent position relationship in the two-dimensional plane to obtain ripple regions in the two-dimensional plane; Based on the preset merging strategy, each vortex area is merged based on the encirclement relationship; After the merging process, the first area sizes and the number of first areas corresponding to each vortex area, and the second area sizes and the number of second areas corresponding to each ripple area are determined as the first morphological attributes of the monitoring area at the time node corresponding to the node data group. 5. The method for controlling the quality of side-scan flow radar data according to claim 4, characterized in that: Based on the preset merging strategy, each vortex area is merged based on the encirclement relationship, including: Performing coordinate processing on the two-dimensional plane, obtaining the vortex coordinate points located in each vortex area, and obtaining the vortex coordinate groups corresponding to the vortex areas; The vortex coordinate groups are compared in pairs, and based on the comparison results, it is determined whether the vortex coordinate groups have an enclosing relationship, and the vortex regions corresponding to the vortex coordinate groups having an enclosing relationship are merged into one vortex region. 6. The method for controlling the quality of side-scan flow radar data according to claim 5, characterized in that: Determining a second morphological attribute of the monitoring area at a time node corresponding to the node data group based on the secondary image data includes: Binarizing the secondary image data to obtain a binary image, wherein the binary image includes water area pixel points corresponding to the first pixel value and noise pixel points corresponding to the second pixel value; Connecting the noise pixels in adjacent positions in the secondary image data to obtain noise regions in the secondary image data; The sizes of the third regions and the number of the third regions corresponding to the noise regions are determined as the second morphological attributes of the monitoring region at the time node corresponding to the node data group. 7. The method for controlling the quality of side-scan flow radar data according to claim 6, characterized in that: Determining the water state of the monitoring area at the time node based on the first morphological attribute and the second morphological attribute corresponding to the monitoring area includes: Performing a sum calculation based on the sizes of each first area to obtain a first size total value, and performing a ratio calculation based on the first size total value and a monitoring size corresponding to the monitoring area to obtain a first size ratio; Normalizing the first size ratio and the first area quantity respectively to obtain a first size coefficient and a first quantity coefficient, and performing a sum calculation based on the first size coefficient and the second quantity coefficient to obtain a swirl coefficient; Performing a sum calculation based on the sizes of the second regions to obtain a second size total value, and performing a ratio calculation based on the second size total value and a monitoring size corresponding to the monitoring region to obtain a second size ratio; Normalizing the second size ratio and the second area quantity respectively to obtain a second size coefficient and a second quantity coefficient, and performing a sum calculation based on the second size coefficient and the second quantity coefficient to obtain a ripple coefficient; Performing a sum calculation based on the sizes of the third regions to obtain a total third size value, and performing a ratio calculation based on the total third size value and a monitoring size corresponding to the monitoring region to obtain a third size ratio; Normalizing the third size ratio and the third area quantity respectively to obtain a third size coefficient and a third quantity coefficient, and performing a sum calculation based on the third size coefficient and the third quantity coefficient to obtain a noise coefficient; The water state of the monitoring area at the time node is determined based on the vortex coefficient, ripple coefficient and noise coefficient. 8. The method for controlling the quality of side-scan flow radar data according to claim 7, characterized in that: Determining the water state of the monitoring area at the time node based on the vortex coefficient, the ripple coefficient, and the noise coefficient includes: Call up the vortex weight, ripple weight and noise weight; Calculate the product of the vortex coefficient and the vortex weight to obtain a vortex evaluation value; Calculate the product of the ripple coefficient and the ripple weight to obtain a ripple evaluation value; Calculate the product of the noise coefficient and the noise weight to obtain a noise evaluation value; When the vortex evaluation value is greater than a first preset value, determining that the water state of the monitoring area at the time node is an abnormal state; When the ripple evaluation value is greater than a second preset value, determining that the water state of the monitoring area at the time node is an abnormal state; When the noise evaluation value is greater than a third preset value, determining that the water state of the monitoring area at the time node is an abnormal state; When the vortex evaluation value is less than or equal to a first preset value, the ripple evaluation value is less than or equal to a second preset value, and the noise evaluation value is less than or equal to a third preset value, the vortex evaluation value, the ripple evaluation value, and the noise evaluation value are summed to obtain a comprehensive evaluation value; When the comprehensive evaluation value is greater than a fourth preset value, it is determined that the water state of the monitoring area at the time node is abnormal. 9. The method for controlling the quality of side-scan flow radar data according to claim 8, characterized in that: Obtaining actual state determination data corresponding to any time node sent by the management end based on any monitoring area, and comparing the water state corresponding to the monitoring area with the actual state determination data; If the state is actually determined to be a normal state and the water state is an abnormal state, the vortex weight, ripple weight and noise weight are reduced by training; If the state actually determines that the data is in an abnormal state and the water state is in a normal state, the vortex weight, ripple weight and noise weight are increased and trained; The trained vortex weight, ripple weight, and noise weight are obtained through the following formula: in, Vortex Weight Increase the number of training sessions. Vortex Weight The training constant value of Vortex Weight Reduce the number of training sessions. is the trained vortex weight, is the ripple weight Increase the number of training sessions. is the ripple weight The training constant value of is the ripple coefficient weight Reduce the number of training sessions. is the trained ripple weight, is the noise weight Increase the number of training sessions. is the noise weight The training constant value of is the noise weight Reduce the number of training sessions. is the trained vortex weight. 10. A side-scan flow radar data quality control system, characterized by comprising: A grid processing module is configured to perform grid processing on the water area to be monitored, and determine each grid point obtained as each monitoring area; The data acquisition module is configured to collect data for each monitoring area for a preset time to obtain current point cloud data, current image data and current flow velocity data of the corresponding monitoring area; A state determination module is configured to determine the state of the water area corresponding to the monitoring area within the preset time based on the current point cloud data and the current image data, and determine the abnormal time corresponding to the abnormal state; A supplementary acquisition module is configured to collect data for a supplementary time having the same duration as the abnormal time, and obtain supplementary point cloud data, supplementary image data and supplementary flow velocity data corresponding to the monitoring area; A data replacement module is configured to replace the abnormal flow velocity portion corresponding to the abnormal time in the current flow velocity data with the supplementary flow velocity data in response to determining that the water area corresponding to the monitoring area is in a normal state during the supplementary time based on the supplementary point cloud data and the supplementary image data; The flow rate determination module is configured to determine the water area flow rate corresponding to the water area to be monitored based on the current flow rate data corresponding to each monitoring area.