Wave intensity detection method and related device, electronic device and storage medium

Abstract

The application discloses a wave intensity detection method and related device, electronic equipment and storage medium, wherein the wave intensity detection method comprises: fitting a numerical mapping relationship between wave intensity and echo intensity of a radar in advance; based on the measurement data of the wave scanning of the radar, a wave line is detected; whether each frame of measurement data successively detects a wave line crossing a detection line, and the wave line crossing the detection line is taken as a target line, and a clustering set of the target line detected by a straight line is taken as a target set; wherein the detection line is parallel to the end line of the wave, and is away from the radar relative to the end line; based on the numerical mapping relationship, the echo intensity of each measurement point in the target set is mapped respectively, and the wave intensity when the target line crosses the line is obtained. The above scheme can improve the accuracy, stability and scene adaptability of wave intensity detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent monitoring, in particular to a wave intensity detection method and related device, electronic equipment and storage medium. BACKGROUND

[0002] Wave intensity detection has a very high research value in application scenarios such as disaster warning. For example, in coastal areas, by detecting the wave intensity of the sea surface near the sea, timely warning can be provided before the disaster comes.

[0003] At present, the existing wave intensity detection usually relies on a camera, which continuously photographs the water area and detects the wave intensity of the photographed picture. However, this method is easily affected by natural factors such as light and weather, which greatly limits the accuracy, stability and scene adaptability of wave intensity detection. Therefore, how to improve the accuracy, stability and scene adaptability of wave intensity detection has become a problem to be solved. SUMMARY

[0004] The technical problem solved by the present application is to provide a wave intensity detection method and related device, electronic equipment and storage medium, which can improve the accuracy, stability and scene adaptability of wave intensity detection.

[0005] In order to solve the above problems, the first aspect of the present application provides a wave intensity detection method, comprising: fitting a numerical mapping relationship between wave intensity and radar echo intensity in advance; detecting a wave line based on the measurement data of the radar scanning of the wave; wherein the measurement data includes sub-data of a plurality of measurement points, and the sub-data includes at least two dimensions of point position and echo intensity, and the wave line is obtained by straight line detection on the clustering set obtained by clustering a plurality of measurement points based on the clustering threshold related to the point position; sequentially detecting whether each frame of measurement data crosses the detection line, and taking the wave line crossing the detection line as the target line, and taking the clustering set of the target line obtained by straight line detection as the target set; wherein the detection line is parallel to the end point line of the wave, and is away from the radar relative to the end point line; mapping the echo intensity of each measurement point in the target set based on the numerical mapping relationship to obtain the wave intensity when the target line crosses the line.

[0006] To solve the above problems, the second aspect of the present application provides a wave intensity detection device, comprising: a relationship fitting module, a wave detection module, a crossing line detection module and an intensity mapping module, the relationship fitting module is used for fitting the numerical mapping relationship between the wave intensity and the echo intensity of the radar in advance; the wave detection module is used for detecting the wave line based on the measurement data of the radar scanning the wave; wherein the measurement data comprises sub-data of a plurality of measurement points, the sub-data comprises at least two dimensions of point position and echo intensity, and the wave line is obtained by straight line detection on the clustering set obtained by clustering a plurality of measurement points based on the clustering threshold related to the point position; the crossing line detection module is used for detecting whether each frame of measurement data crosses the detection line in turn, and taking the wave line crossing the detection line as the target line, and taking the clustering set of the target line obtained by straight line detection as the target set; wherein the detection line is parallel to the end point line of the wave, and is away from the radar relative to the end point line; the intensity mapping module is used for mapping the echo intensity of each measurement point in the target set based on the numerical mapping relationship, to obtain the wave intensity when the target line crosses the line.

[0007] To solve the above problems, the third aspect of the present application provides an electronic device, comprising a memory and a processor coupled with each other, the memory stores program instructions, and the processor is used to execute the program instructions to realize the wave intensity detection method in the first aspect.

[0008] To solve the above problems, the fourth aspect of the present application provides a computer readable storage medium, which stores program instructions capable of being executed by a processor, and the program instructions are used for the wave intensity detection method in the first aspect.

[0009] The above scheme pre-fits a numerical mapping relationship between wave intensity and radar echo intensity. Based on this, wave lines are detected using radar wave scanning measurement data. The measurement data includes sub-data from several measurement points, each sub-data containing at least two dimensions: point location and echo intensity. The wave lines are obtained by performing straight line detection on the clustered sets of measurement points obtained by clustering these clustered sets based on a clustering threshold related to the point location. Then, it sequentially checks whether wave lines cross the detection line in each frame of measurement data. Wave lines that cross the detection line are designated as target lines, and the clustered sets of target lines obtained through straight line detection are designated as target sets. The detection line is parallel to the wave's endpoint line and is farther from the radar relative to the endpoint line. Thus, the echo intensity of each measurement point in the target set is mapped based on the numerical mapping relationship. Obtaining the wave intensity when the target line crosses is achieved through several advantages. Firstly, wave intensity detection relies solely on radar scanning, eliminating the need for visual imaging and minimizing the impact of natural factors like lighting and weather. Secondly, setting clustering thresholds based on point locations allows for variable thresholding of target points, improving accuracy compared to constant thresholding. Thirdly, pre-fitting a numerical mapping between wave intensity and echo intensity allows for mapping the echo intensity of each measurement point across the detection line using this pre-fitted mapping, resulting in a wave intensity that closely approximates the true intensity. Therefore, this method enhances the accuracy, stability, and scene adaptability of wave intensity detection. Attached Figure Description

[0010] Figure 1 This is a schematic flowchart of an embodiment of the wave intensity detection method of this application;

[0011] Figure 2 This is a schematic diagram of an embodiment of measurement data;

[0012] Figure 3 This is a schematic diagram of one embodiment of the finish line;

[0013] Figure 4 This is a schematic diagram of one embodiment of the detection line;

[0014] Figure 5 yes Figure 1 A flowchart illustrating an embodiment of step S12;

[0015] Figure 6 This is a schematic diagram showing the distribution of target points when the destination is chosen as the target direction;

[0016] Figure 7 This is a schematic diagram showing the distribution of target points when the direction of arrival is chosen as the target direction;

[0017] Figure 8 is a schematic diagram of an embodiment of a wave line;

[0018] Figure 9 is a flowchart of another embodiment of the wave intensity detection method of the present application;

[0019] Figure 10 is a frame diagram of an embodiment of the wave intensity detection device of the present application;

[0020] Figure 11 is a frame diagram of an embodiment of the electronic device of the present application;

[0021] Figure 12 is a frame diagram of an embodiment of the computer readable storage medium of the present application. DETAILED DESCRIPTION

[0022] The scheme of the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0023] In the following description, for the purpose of explanation and not limitation, specific details are set forth, such as particular system configurations, interfaces, techniques, in order to provide a thorough understanding of the present application.

[0024] The terms "system" and "network" are often used interchangeably herein. The term "and / or" herein is merely an associative relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases: A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents an "or" relationship between the associated objects. In addition, "multiple" in this paper means two or more than two.

[0025] Please refer to Figure 1 , Figure 1 is a flowchart of an embodiment of the wave intensity detection method of the present application. Specifically, it can include the following steps:

[0026] Step S11: Pre-fitting the numerical mapping relationship between the wave intensity and the echo intensity of the radar.

[0027] It should be noted that in actual application, the water surface oscillation to generate waves can be affected by many reasons. Among them, the most important is gravity and wind force. Generally, the water surface change caused by gravity is called tide, and the change caused by wind force is called wave. The "wave" referred to in the embodiments disclosed in the present application includes but is not limited to the "tide" caused by gravity and the "wave" caused by wind force, etc. Here, it is not limited to what causes the water surface oscillation. In addition, the wave intensity represents the intensity of the water surface oscillation. Taking the sea waves caused by sea wind in the sea as an example, it mainly includes wind wave, swell and offshore wave. Under different wind speed, wind direction and terrain conditions, the wave intensity changes greatly. For the intensity of the sea wave, the wave level is usually used to describe the intensity, and the wave level can be divided into 0-9 levels according to the effective wave height, in turn: no wave, slight wave, small wave, light wave, medium wave, large wave, giant wave, storm wave, storm wave and angry wave. Please refer to Table 1, Table 1 is an international wave level table, as shown in Table 1, 0-9 levels correspond to wave height interval, median, wind wave name, swell name and corresponding wind level.

[0028] Table 1 International wave level table

[0029]

[0030]

[0031] In one implementation scenario, as a possible implementation manner, in order to improve the accuracy of the numerical mapping relationship, sample data collected on site for the wave can be obtained. Specifically, sample data can be collected on site in advance at the place where the wave intensity needs to be detected. In addition, the sample data can specifically include: when the radar scans the wave, the echo intensity value of the wave at a plurality of sample points and the wave intensity value. It should be noted that the sample point is a measurement point of radar scanning, in order to facilitate the distinction, the measurement point in the sample data used in the fitting numerical mapping relationship stage is called a sample point, and its meaning can be referred to the measurement point, which will not be repeated here. On this basis, function fitting is performed based on the sample data, and the numerical mapping relationship between the wave intensity and the echo intensity is obtained. The above-mentioned manner, the sample data collected on site for the wave is obtained, and the sample data includes: when the radar scans the wave, the echo intensity value of the wave at a plurality of sample points and the wave intensity value, on this basis, function fitting is performed based on the sample data, and the numerical mapping relationship is obtained, so that the numerical mapping relationship suitable for the place where the wave intensity needs to be detected as much as possible can be fitted according to local conditions, which helps to improve the accuracy of the on-site wave intensity detection.

[0032] In a specific implementation scenario, the echo intensity represents the signal strength of the echo signal of the radar at the measurement point. It should be noted that in order to facilitate subsequent calculation, the unit of echo intensity can be dB.

[0033] In a specific implementation scenario, the wave intensity value can be represented by the actual wave height measured at the sample point.

[0034] In a specific implementation scenario, the wave intensity value can also be represented by a discrete wave level value as shown in Table 1. In this case, the actual wave height at the sample point can be obtained first, and then converted into a wave level according to Table 1 as the wave intensity value.

[0035] In a specific implementation scenario, after obtaining the sample data, the sample data can be fitted by using a nonlinear function fitting. The specific process of data fitting can be referred to the technical details of nonlinear function fitting, which will not be described here.

[0036] In another implementation scenario, unlike the foregoing implementation, in order to improve the generality of the numerical mapping relationship, sample data can be obtained at different locations. The specific meaning of the sample data can be referred to the foregoing related description, which will not be described here. Then, the sample data obtained at different locations can be classified according to the geographical model (such as near sea, lower reaches of a river, open sea, etc.) to which the location belongs. For example, the sample data obtained at different locations belonging to the near sea can be classified into one category, the sample data obtained at different locations belonging to the lower reaches of a river can be classified into one category, and the sample data obtained at different locations belonging to the open sea can be classified into one category, and so on. The numerical mapping relationship between the wave intensity and the echo intensity at the location (i.e., the geographical model) can be obtained by fitting each category of sample data with a function. Thus, when it is necessary to deploy a wave intensity detection to a target location, only the geographical model to which the target location belongs needs to be determined, and the numerical mapping relationship corresponding to the geographical model can be directly applied.

[0037] It should be noted that, since the detection relies on radar detection, the influence of natural factors such as light and weather can be reduced as much as possible, thereby improving the support for all-weather and all-time detection.

[0038] Step S12: detecting a wave line based on the measurement data of the radar wave scanning.

[0039] In the embodiments of the present disclosure, the measurement data includes sub-data of a plurality of measurement points, and the sub-data includes at least two dimensions of point position and echo intensity. The wave line is obtained by performing straight line detection on a clustering set obtained by clustering a plurality of measurement points based on a clustering threshold related to the point position. The setting method of the clustering threshold and the specific process of wave detection can be referred to the following disclosed embodiments, which will not be described here.

[0040] It should be noted that the radar can include but is not limited to a millimeter wave radar, etc., and the type of radar is not limited here. In addition, in actual application, the radar can be scanned at a preset period (such as 10 Hz, 20 Hz, etc.), so that each scan can obtain a frame of measurement data, and the number of measurement points contained in each frame of measurement data can be the same or can not be the same, which is not limited here. For the specific meaning of the measurement point, please refer to the working principle of the radar, which will not be repeated here. In addition, wave detection can be performed on each frame of measurement data each time, and after the wave detection of the frame of measurement data is completed, the wave detection of the next frame of measurement data can be continued. Exemplarily, wave detection can be performed on each frame of measurement data scanned by the radar in turn to detect a wave line for each frame; or, according to actual application needs, a frame of measurement data can be selected every preset number of frames (such as 1 frame, 2 frames, etc.) to perform wave detection, which is not limited here.

[0041] In one implementation scenario, the point position represents the position of the measurement point in the detection range of the radar. Exemplarily, a two-dimensional coordinate system can be established with the radar position as the origin, so that the point position of the measurement point can be represented by two-dimensional coordinates (x, y). It should be noted that, in order to facilitate subsequent calculation, the unit of coordinate value can be meters. Of course, a polar coordinate system can also be established with the radar position as the polar point, so that the point position of the measurement point can be represented by polar coordinates. It should be noted that the polar coordinates can include the straight-line distance from the measurement point to the radar and the angle with the polar coordinate axis. Of course, in order to facilitate subsequent calculation, the polar coordinates can also be converted into two-dimensional coordinates, which can be referred to the conversion formula between two-dimensional coordinates and polar coordinates, which will not be repeated here.

[0042] In one implementation scenario, the sub-data can also include a radial speed (Radial Speed) representing the velocity component of the measurement point in the direction along the line connecting the measurement point and the radar. It should be noted that when the measurement point moves close to the radar, its radial speed can be represented as a negative value, and vice versa, when the measurement point moves away from the radar, its radial speed can be represented as a positive value. In addition, in order to facilitate subsequent calculation, the unit of radial speed can be meters per second (i.e. m / s).

[0043] In one implementation scenario, please refer to Figure 2 , Figure 2 is a schematic diagram of an embodiment of measurement data. As Figure 2 shown, three frames of measurement data are shown, and the first row of each frame of measurement data respectively includes: frame number (Time), the number of measurement points (Num) contained in the frame of measurement data, and the measurement time of the frame of measurement data. As Figure 2For example, the first frame of measurement data has a frame sequence number (Time) of 4501, contains 6 measurement points (Num), i.e., measurement points numbered 0-5, and has a measurement time of 2022-03-31 11:24:48. Figure 2 The other two frames of measurement data can be similarly processed, and will not be described here. In addition, the rows of each frame of measurement data after the first row are the sub-data of each measurement point, where: the first column of each frame of measurement data is the identifier (ID) of the measurement point, and the identifiers of different measurement points in each frame of measurement data are different; the second and third columns of each frame of measurement data are the coordinates of the point position, where the second column is the coordinate value of the x-axis direction, and the third column is the coordinate value of the y-axis direction; the fourth column of each frame of measurement data is the echo intensity; and the fifth column of each frame of measurement data is the radial velocity. It should be noted that, Figure 2 The table shown is only one possible form of expression of the measurement data in the actual application process, and does not limit the specific form of expression of the measurement data.

[0044] In one implementation scenario, in order to intuitively reflect each measurement point in the measurement data, the data of each measurement point can also be visualized. Specifically, different colors, different styles, etc. can be used to represent measurement points with different motion directions. For example, red can be used to represent measurement points close to the radar (with negative radial velocity), green can be used to represent measurement points far from the radar (with positive radial velocity), and black can be used to represent stationary measurement points.

[0045] Step S13: sequentially detecting whether a wavy line in each frame of measurement data crosses the detection line, taking the wavy line that crosses the detection line as the target line, and taking the cluster set of the target line obtained by straight line detection as the target set.

[0046] In the embodiments of the present disclosure, the detection line is parallel to the end line of the wave, and is away from the radar relative to the end line. For example, a preset distance can be pushed away from the end line in a direction away from the radar to obtain the end line. The preset distance can be set to 20 meters, 30 meters, 40 meters, etc., which is not limited here. It should be noted that the end line represents the disappearance position of the wavy line in the radar detection range. In addition, the detection line can be automatically generated based on the end line, or can also be manually drawn by the user, which is not limited here.

[0047] In one embodiment, to determine the end line, the disappearance position of the wave line within the radar detection range can be determined first, and then a straight line passing through the disappearance position and perpendicular to the running direction of the wave can be determined as the end line. Specifically, a plurality of frames of measurement data obtained by scanning the wave with the radar can be obtained in advance. On this basis, for each frame of measurement data, the position of the wave line closest to the radar can be obtained, and median filtering can be performed based on the obtained positions to obtain the disappearance position of the wave. Then, a straight line passing through the disappearance position and perpendicular to the running direction of the wave can be determined as the end line.

[0048] In one embodiment, the measurement points formed by the wave are consistent in a statistical sense. Therefore, the running direction of the wave can be obtained by statistically analyzing the running directions of the measurement points in a period of time. It should be noted that the running direction is different from the target direction described above. The running direction has a more accurate angle of movement, while the target direction is only a rough direction relative to the radar.

[0049] In one embodiment, please refer to Figure 3 , Figure 3 is a schematic diagram of an embodiment of the end line. As shown in Figure 3 , the lowermost horizontal thick line represents the end line, and the three horizontal thick lines above the end line represent wave lines. The specific detection process can be referred to the following disclosed embodiments, which will not be described here. Please continue to refer to Figure 4 , Figure 4 is a schematic diagram of an embodiment of the detection line. As shown in Figure 4 , the cross line represents the detection line.

[0050] In one embodiment, N detection lines can be set according to the needs during the wave intensity detection process. For example, according to the actual application needs, only wave intensity detection is needed at a distance of 20 meters from the disappearance position of the wave, so only one detection line can be set. Alternatively, according to the actual application needs, wave detection is needed at a distance of 20 meters and 40 meters from the disappearance position of the wave, respectively, so two detection lines can be set. Other cases can be similarly deduced, which will not be described one by one here.

[0051] It should be noted that, taking the selection of the direction of arrival as the target direction as an example, as the radar continuously scans the waves to obtain new measurement data, the wave line of the target direction starting from the starting line will gradually move towards the radar. When the wave line crosses the detection line in the ith frame of measurement data, the wave line that crosses the line in the ith frame of measurement data can be recorded as the target line, and the cluster set of the target line obtained through straight line detection can be recorded as the target set. According to the numerical mapping relationship and the cluster set, the wave intensity of the target line is determined. In this way, the foregoing wave detection, crossing detection and other steps are performed on each frame of measurement data, respectively, so that the wave line that crosses each time and the corresponding cluster set can be obtained. Of course, in actual application, in order to detect the wave intensity, the direction of arrival can also be selected as the target direction, which is not limited herein.

[0052] Step S14: Mapping the echo intensity of each measurement point in the target set based on the numerical mapping relationship to obtain the wave intensity when the target line crosses the line.

[0053] In one implementation scenario, the echo intensity of each measurement point in the target set can be mapped based on the numerical mapping relationship to obtain the wave intensity at the measurement point. On this basis, numerical statistics can be performed based on the wave intensity at each measurement point in the target set to obtain the wave intensity when the target line crosses the line. Taking the target set containing M measurement points as an example, the echo intensity of the M measurement points can be mapped respectively by using the numerical mapping relationship to obtain the wave intensity at the M measurement points. On this basis, the wave intensity at the M measurement points can be statistically processed by using numerical statistical methods such as taking the average, taking the median, taking the maximum, taking the minimum, etc. to obtain the wave intensity when the target line crosses the line. The foregoing method can map the echo intensity of each measurement point in the target set based on the numerical mapping relationship to obtain the wave intensity at the measurement point, and perform numerical statistics based on the wave intensity at each measurement point in the target set to obtain the wave intensity when the target line crosses the line, which can quickly and conveniently determine the wave intensity when the target line crosses the line.

[0054] In one implementation scenario, in addition to the foregoing implementation, the measurement points in the target set can be sorted in ascending order of echo intensity, and the measurement points within a target range in the sorted target set can be removed, and the target range includes at least one of the following: within a first proportion (e.g., 10%, 20%, etc.) at the front, within a second proportion (e.g., 10%, 20%, etc.) at the back, so that the echo intensity of the remaining measurement points in the target set can be mapped based on the numerical mapping relationship to obtain the wave intensity at the remaining measurement points, and then the wave intensity at the remaining measurement points in the target set is statistically analyzed to obtain the wave intensity when the target line crosses the line. Still taking an example that the target set contains M measurement points, the M measurement points can be sorted in ascending order of echo intensity, and then the first 20% of the measurement points and the last 20% of the measurement points can be removed, and the remaining 60% of the measurement points in the middle part can be mapped using the numerical mapping relationship to obtain the wave intensity at the remaining 60% of the measurement points. On this basis, the wave intensity at the remaining 60% of the measurement points can be statistically analyzed in a manner such as taking the average, taking the median, taking the maximum, taking the minimum, etc. to obtain the wave intensity when the target line crosses the line. The above method sorts the measurement points in the target set in ascending order of echo intensity, and removes the measurement points within a target range in the sorted target set, and the target range includes at least one of the following: within a first proportion at the front, within a second proportion at the back, so that the echo intensity of the remaining measurement points in the target set is mapped based on the numerical mapping relationship to obtain the wave intensity at the remaining measurement points, and then the wave intensity at the remaining measurement points in the target set is statistically analyzed to obtain the wave intensity when the target line crosses the line, which can remove as much interference as possible to improve the accuracy of wave intensity detection.

[0055] In one implementation scenario, after obtaining the wave intensity when the target line crosses the line, the wave intensity trend in a preset period can be further obtained based on the wave intensity when the target line crosses the line in each of the preset period. For example, the wave intensity trend in a day can be obtained based on the wave intensity when the target line crosses the line in each of the day, or the wave intensity trend in a week can be obtained based on the wave intensity when the target line crosses the line in each of the week. According to actual application needs, the preset period can also be set to one month, one quarter, one year, etc., which is not limited herein.

[0056] The scheme pre-fits the numerical mapping relationship between the wave intensity and the echo intensity of the radar, and on this basis, based on the measurement data of the radar scanning of the wave, the wave line is detected, and the measurement data includes sub-data of a plurality of measurement points, and the sub-data includes at least two dimensions of point position and echo intensity. The wave line is obtained by performing straight line detection on the clustering set obtained by clustering a plurality of measurement points based on the clustering threshold related to the point position, and then detecting whether each frame of measurement data occurs wave line crossing detection line in turn, and the wave line crossing the detection line is taken as the target line, and the clustering set of the target line obtained by straight line detection is taken as the target set, and the detection line is parallel to the end point line of the wave, and is away from the radar relative to the end point line. Therefore, based on the numerical mapping relationship, the echo intensity of each measurement point in the target set is mapped to obtain the wave intensity when the target line crosses the detection line. On the one hand, since the wave intensity detection does not need to rely on visual shooting, but only needs to scan by the radar, the influence of natural factors such as light and weather can be reduced as much as possible. On the other hand, the clustering threshold is set according to the point position, so that the variable threshold can be used according to the actual situation of the target point to cluster the target point. Compared with using a constant threshold for clustering, it is helpful to further improve the accuracy of wave detection. On the other hand, by pre-fitting the numerical mapping relationship between the wave intensity and the echo intensity, and then using the pre-fitted numerical mapping relationship to map the echo intensity of each measurement point involved in the wave line crossing the detection line in the intensity detection process, the wave intensity when crossing the detection line can be obtained. The wave intensity obtained by mapping is as close as possible to the real intensity. Therefore, the accuracy, stability and scene adaptability of the wave intensity detection can be improved.

[0057] Please refer to Figure 5 , Figure 5 is Figure 1 a flowchart of an embodiment of step S12 in

[0058] Step S51: Based on the radial velocity of each measurement point in the measurement data, the measurement points matched with the target direction are selected as target points.

[0059] In the embodiments of the present disclosure, the target direction is any one of the directions of approach and departure. It should be noted that the direction of approach refers to the movement close to the radar, and the direction of departure refers to the movement away from the radar. In actual application, since the measurement points of the two directions have a certain possibility of appearing in the same frame of measurement data, in order to reduce the interference of wave detection as much as possible, the measurement points of the two directions can be decoupled. For example, only the direction of approach can be selected as the target direction to detect the wave line in the direction of approach through the step in the embodiments of the present disclosure; or only the direction of departure can be selected as the target direction to detect the wave line in the direction of departure through the step in the embodiments of the present disclosure; or the direction of approach and the direction of departure can be selected as the target direction respectively to detect the wave line in the direction of approach and the wave line in the direction of departure respectively through the step in the embodiments of the present disclosure, which is not limited herein.

[0060] In a specific implementation scenario, when the direction of departure is selected as the target direction, the measurement point with a positive radial velocity can be regarded as a measurement point matched with the target direction and as a target point. Please refer to FIG. 6. Figure 6 Figure 6 FIG. 6 is a distribution diagram of target points when the direction of departure is selected as the target direction.

[0061] In a specific implementation scenario, when the direction of approach is selected as the target direction, the measurement point with a negative radial velocity can be regarded as a measurement point matched with the target direction and as a target point. Please refer to FIG. 7. Figure 7 Figure 7 FIG. 7 is a distribution diagram of target points when the direction of approach is selected as the target direction.

[0062] In a specific implementation scenario, in order to further improve the accuracy of wave detection, the measurement point with an absolute value of radial velocity lower than a speed threshold value can be removed before the target point is screened. The speed threshold value can be set according to actual application, for example, can be set to 0.2 m / s, 0.3 m / s, etc., which is not limited herein.

[0063] Step S52: determining whether the first target point belongs to the cluster set in which the second target point is located based on the cluster threshold value and the data difference between the sub-data of the first target point and the sub-data of the second target point.

[0064] ​​In the embodiments of the present disclosure, the first target point is an unclustered target point, and the second target point is a clustered target point. It should be noted that at the beginning of the clustering operation, a plurality of clustering sets can be initialized, and a target point is selected as the second target point for each initialized clustering set and is attributed to the clustering set, and the selected target points for each initialized clustering set are different, that is, the target points cannot be repeatedly selected at the initialization stage, and the remaining unselected target points can be used as the first target point. The initialized clustering set can be 2, 3, 4, 5, etc., which is not limited herein. For the initialization at the beginning of clustering, the technical details of the clustering algorithm such as K-Means can be referred to, which is not described herein.

[0065] It should be noted that in the embodiments of the present disclosure, the clustering threshold is related to the point position, and the clustering threshold can be determined according to the point position of any one of the first target point and the second target point, which can be referred to in the subsequent related description, and is not described herein. In the clustering, the first target point can be determined to belong to the clustering set of the second target point based on the clustering threshold and the size relationship between the data difference values. More specifically, it can be determined whether the data difference value is not greater than the clustering threshold, if yes, it can be determined that the first target point belongs to the clustering set of the second target point, otherwise, it can be determined that the first target point does not belong to the clustering set of the second target point, and a new second target point is selected to re-cluster the first target point.

[0066] In one implementation scenario, as described above, the sub-data can further include the echo intensity in addition to the point position and the radial velocity. In the clustering, at least one dimension can be referred to. That is, the data difference value can include a sub-difference value corresponding to the selected dimension, and in this case, the clustering threshold can include a sub-threshold value corresponding to the selected dimension. On this basis, when performing the clustering operation, the sub-difference value and the sub-threshold value of the same dimension can be compared to determine whether the first target point belongs to the clustering set of the second target point. That is, the data difference value can include a sub-difference value of at least one dimension of the point position, the radial velocity, and the echo intensity, and correspondingly, the clustering threshold can include a sub-threshold value of at least one dimension of the point position, the radial velocity, and the echo intensity.

[0067] In one specific implementation scenario, in the dimension of the point position, the sub-threshold value is positively correlated with the first distance from the point position of the first target point to the radar position, that is, the greater the first distance (i.e., the farther the first target point is from the radar), the greater the sub-threshold value in the dimension of the point position, and vice versa, the smaller the first distance (i.e., the closer the first target point is to the radar), the smaller the sub-threshold value in the dimension of the point position. It should be noted that the specific numerical mapping relationship between the sub-threshold value and the first distance in the dimension of the point position can be obtained by pre-acquiring a large amount of sample measurement data, and by manually labeling the measurement points belonging to the same clustering set, and then statistically analyzing the sub-differences of the measurement points belonging to the same clustering set in the dimension of the point position, and the sub-differences of the measurement points belonging to different clustering sets in the dimension of the point position, and fitting the specific numerical mapping relationship between the sub-threshold value and the first distance in the dimension of the point position based on the above sub-differences. The specific process of data fitting can refer to polynomial fitting, universal model fitting, etc. In order to distinguish the "numerical mapping relationship" in the foregoing disclosed embodiments and the present embodiment, the numerical mapping relationship between the echo intensity and the wave intensity in the foregoing disclosed embodiments can be referred to as the first mapping relationship, and the numerical mapping relationship in the present embodiment can be referred to as the second mapping relationship.

[0068] In one specific implementation scenario, in the dimension of the radial velocity, the sub-threshold value is positively correlated with the second distance from the point position of the second target point to the radar position, that is, the greater the second distance (i.e., the farther the second target point is from the radar), the greater the sub-threshold value in the dimension of the radial velocity, and vice versa, the smaller the second distance (i.e., the closer the second target point is to the radar), the smaller the sub-threshold value in the dimension of the radial velocity. It should be noted that the specific numerical mapping relationship between the sub-threshold value and the second distance in the dimension of the radial velocity can refer to the specific numerical mapping relationship between the sub-threshold value and the first distance in the dimension of the point position, and the specific principle thereof will not be repeated here.

[0069] In one specific implementation scenario, in the dimension of the echo intensity, the sub-threshold value is negatively correlated with the second distance from the point position of the second target point to the radar position, that is, the greater the second distance (i.e., the farther the second target point is from the radar), the smaller the sub-threshold value in the dimension of the echo intensity, and vice versa, the smaller the second distance (i.e., the closer the second target point is to the radar), the greater the sub-threshold value in the dimension of the echo intensity. It should be noted that the specific numerical mapping relationship between the sub-threshold value and the second distance in the dimension of the echo intensity can refer to the specific numerical mapping relationship between the sub-threshold value and the first distance in the dimension of the point position, and the specific principle thereof will not be repeated here.

[0070] It should be noted that the above numerical mapping relationship is only a few possible embodiments, in actual application process, in order to improve the clustering accuracy, in order to further improve the accuracy of wave detection, a large number of sample measurement data can be obtained in the water area where wave detection is needed, and then the numerical mapping relationship is fitted.

[0071] In one implementation scenario, in actual application process, one dimension of point position, radial velocity and echo intensity can be selected as target dimension, then in this case, the data difference can specifically include the sub-difference of the target dimension between the first target point and the second target point, and the clustering threshold can specifically include the sub-threshold of the target dimension, then it can be detected whether the sub-difference of the target dimension satisfies the preset condition, and the preset condition can include that the sub-difference of the target dimension is not greater than the sub-threshold of the target dimension. On this basis, in response to the sub-difference of the target dimension satisfying the preset condition, it can be determined that the first target point belongs to the clustering set of the second target point, otherwise, in response to the sub-difference of the target dimension not satisfying the preset condition, a new second target point can be selected, and the step of detecting whether the sub-difference of the target dimension satisfies the preset condition is re-executed until the clustering set of the first target point is determined.

[0072] In one specific implementation scenario, in the case of selecting point position as target dimension, the first weight in x-axis direction and the second weight in y-axis direction can be obtained based on the first distance from the point position of the first target point to the radar position, and the first weight is greater than the second weight, and the first weight and the second weight are positively correlated with the first distance. For the convenience of description, the first weight can be denoted as a x , and the second weight can be denoted as a y . On this basis, the first difference in x-axis direction of the point position of the first target point and the second target point can be obtained, and the second difference in y-axis direction of the point position of the first target point and the second target point can be obtained, and the corresponding sub-difference in the dimension of the point position can be obtained based on the ratio of the first difference and the first weight, and the ratio of the second difference and the second weight. Specifically, the absolute value of the difference in x-axis direction of the point position of the first target point and the second target point can be taken as the first difference, and the absolute value of the difference in y-axis direction of the point position of the first target point and the second target point can be taken as the second difference, and the square root of the sum of the square of the ratio of the first difference and the first weight and the square of the ratio of the second difference and the second weight can be taken as the corresponding sub-difference in the dimension of the point position. For the convenience of description, the corresponding sub-difference in the dimension of the point position dis(e i ,e j ) can be represented as:

[0073]

[0074] In the above formula (1), ei Indicates the first target point, e j Let x represent the second target point. i This represents the x-coordinate of the first target point along the x-axis, and y-coordinate... i This represents the y-coordinate of the first target point. j k This represents the coordinates of the second target point along the x-axis, and y-axis... j k This represents the y-axis coordinate of the second target point, with the superscript k indicating that the second target point is a target point in cluster set k. In this method, the data difference includes the sub-difference between the first and second target points regarding their positions. Based on the first distance from the first target point's position to the radar position, a first weight in the x-axis direction and a second weight in the y-axis direction are obtained, with the first weight being greater than the second weight. Both the first and second weights are positively correlated with the first distance. The first difference between the first and second target points in the x-axis direction and the second difference in the y-axis direction are also obtained. Based on these, the sub-difference of the position is obtained using the ratio of the first difference to the first weight and the ratio of the second difference to the second weight. Therefore, in the process of obtaining the sub-difference in the position dimension, weighted distances are calculated in the x-axis and y-axis directions, which helps to balance the coordinate differences in the x-axis and y-axis directions, thereby improving the accuracy of the sub-difference in the position dimension.

[0075] In a specific implementation scenario, when radial velocity is chosen as the target dimension, the absolute value of the difference between the radial velocities of the first target point and the second target point can be used as the sub-difference value in the radial velocity dimension. For ease of description, the sub-difference value dv(e) in the radial velocity dimension can be... i ,e j ) is represented as:

[0076] dv(e i ,e j )=|v i -v j |……(2)

[0077] In the above formula (2), v i The radial velocity v represents the first target point. j This represents the radial velocity of the second target point.

[0078] In one specific implementation scenario, in the case of selecting echo intensity as the target dimension, the absolute value of the difference between the echo intensity of the first target point and the echo intensity of the second target point can be taken as the sub-difference value in the echo intensity dimension. For ease of description, the sub-difference value drcs(e i ,e j ) in the echo intensity dimension can be represented as:

[0079] drcs(e i ,e j ) = |rcs i -rcs j | … (3)

[0080] In the above formula (3), rcs i represents the echo intensity of the first target point, and rcs j represents the echo intensity of the second target point.

[0081] In another implementation scenario, different from the foregoing implementation of selecting only one dimension for clustering, in order to further improve the clustering accuracy, any two dimensions among the point position, the radial velocity, and the echo intensity can be selected as the target dimensions, on the basis of which, it can be detected whether the sub-difference values of the target dimensions all satisfy the preset condition, and the preset condition can specifically include that the sub-difference value of the target dimension is not greater than the sub-threshold value of the same target dimension. In response to the sub-difference values of the target dimensions all satisfying the preset condition, it can be determined that the first target point belongs to the clustering set in which the second target point is located, and in response to the sub-difference value of at least one dimension not satisfying the preset condition, a new second target point can be selected, and the foregoing step of detecting whether the sub-difference values of the target dimensions all satisfy the preset condition can be re-executed until the clustering set of the first target point is determined.

[0082] In another implementation scenario, unlike the aforementioned implementations that select only one dimension for clustering or select any two dimensions for clustering, to maximize clustering accuracy, point location, radial velocity, and echo intensity can all be used as target dimensions. That is, the data difference includes the sub-differences between the first and second target points in each dimension, and the clustering threshold includes the sub-thresholds for each dimension. This allows us to obtain the magnitude relationship between the sub-differences of each dimension and the sub-thresholds of the same dimension. Based on whether the magnitude relationships corresponding to each dimension satisfy preset conditions, we can determine whether the first target point belongs to the cluster set containing the second target point. Specifically, we can check whether the sub-differences of each dimension satisfy preset conditions, where the preset conditions include: the sub-difference of a dimension is not greater than the sub-threshold of the same dimension. If the sub-differences of each dimension satisfy the preset conditions, it can be determined that the first target point belongs to the cluster set containing the second target point. If the sub-differences of at least one dimension do not satisfy the preset conditions, a new second target point can be selected, and the steps of checking whether the sub-differences of each dimension satisfy the preset conditions are repeated until the cluster set of the first target point is determined. In other words, if in cluster set C k In the middle, there exists a second target point e. j And it is related to the first target point e i The first target point e can be determined if the sub-differences in the three dimensions of point location, radial velocity, and echo intensity are all no greater than the corresponding sub-thresholds. i Belongs to the second target point e j The cluster set C it belongs to k For ease of description, the above statement can be expressed as:

[0083]

[0084] In the above formula (4), The sub-threshold corresponding to the dimension of the point location. The sub-threshold representing the dimension corresponding to the radial velocity. This represents the sub-threshold corresponding to the dimension of echo intensity. It should be noted that the calculation method for sub-differences and the setting method for sub-thresholds can be found in the aforementioned descriptions, and will not be repeated here. The above method checks whether the sub-differences of each dimension meet preset conditions, including that the sub-differences of a dimension are not greater than the sub-threshold of the same dimension. If the sub-differences of each dimension meet the preset conditions, it is determined that the first target point belongs to the cluster set of the second target point. If the sub-differences of at least one dimension do not meet the preset conditions, a new second target point is selected, and the steps of checking whether the sub-differences of each dimension meet the preset conditions are repeated until the cluster set of the first target point is determined. This allows reference to each dimension during the clustering process, which helps improve the accuracy of the clustering operation.

[0085] In one implementation scenario, in the clustering process of the first target point, if the sub-difference value of at least one dimension does not satisfy the preset condition, a new second target point is selected, and the new second target point is not in the same cluster set as any second target point that has been compared. In this case, in response to the absence of a second target point that satisfies the preset condition with the first target point, the first target point is assigned to a new cluster set. That is, in the absence of a second target point that satisfies the preset condition with the first target point, the first target point can be considered not to belong to any existing cluster set, so a new cluster set can be created and the first target point can be assigned to the new cluster set. The above-mentioned manner, in response to the absence of a second target point that satisfies the preset condition with the first target point, assigns the first target point to a new cluster set, which helps to improve the robustness of the clustering operation.

[0086] In one implementation scenario, in order to further improve the accuracy of the clustering operation, after it is determined that the first target point belongs to the cluster set in which the second target point is located, a second target point can be selected from a cluster set that has not been selected, and the above-mentioned clustering operation can be repeated to determine whether the first target point belongs to the cluster set that has not been selected, so as to determine which cluster sets the first target point belongs to. In this case, in response to the fact that the second target points from multiple cluster sets respectively satisfy the preset condition with the first target point, the multiple cluster sets can be merged into a new cluster set, and the first target point can be assigned to the new cluster set. The above-mentioned manner, in response to the fact that the second target points from multiple cluster sets respectively satisfy the preset condition with the first target point, merges the multiple cluster sets into a new cluster set, and assigns the first target point to the new cluster set, which can improve the accuracy of the clustering operation.

[0087] Step S53: Based on the cluster set, a straight line detection is performed to obtain a wavy line of the target direction.

[0088] In one implementation scenario, after the clustering operation is performed on all the first target points, straight line detection can be performed on each of the clustering sets to obtain a wavy line corresponding to each of the clustering sets. It should be noted that, since the radial velocity of the target points matches the target direction, the straight line detection also obtains a wavy line of the target direction. For example, if the destination direction is selected as the target direction, the straight line detection can obtain a wavy line of the destination direction; or, if the arrival direction is selected as the target direction, the straight line detection can obtain a wavy line of the arrival direction; or, if the arrival direction and the destination direction are selected as the target directions respectively, the straight line detection can obtain a wavy line of the arrival direction and a wavy line of the destination direction respectively. In addition, the straight line detection can include, but is not limited to, Hough transform, LSD detection (i.e., Line Segment Detector), FLD detection, LSWMS detection, etc., which are not limited herein. The specific process of the straight line detection can refer to the technical details of the above-mentioned straight line detection algorithm, which will not be described here.

[0089] In another implementation scenario, in order to further exclude interference and improve the accuracy of the wave detection, the number threshold of the clustering set can be determined based on the point position of the target points in the clustering set before the straight line detection, and the clustering set can be selected to be retained or filtered based on whether the total number of the target points in the clustering set is greater than the number threshold of the clustering set. Specifically, in the case that the total number of the target points in the clustering set is greater than the number threshold of the clustering set, the clustering set can be selected to be retained, otherwise, in the case that the total number of the target points in the clustering set is not greater than the number threshold of the clustering set, the clustering set can be selected to be filtered. In addition, as a possible implementation, the distance between the point position of the target points in the clustering set and the radar position can be positively correlated with the number threshold of the clustering set. Of course, in order to improve the accuracy of the number threshold, the sample measurement data can be obtained on site at the place where the wave detection is needed, and the numerical mapping relationship between the above-mentioned distance and the number threshold can be fitted based on the sample measurement data. The above-mentioned method, after the clustering operation is completed and before the straight line detection, first determines the number threshold of the clustering set based on the point position of the target points in the clustering set, and then selects to retain or filter the clustering set based on whether the total number of the target points in the clustering set is greater than the number threshold of the clustering set, which can exclude the interference factors in the wave detection as much as possible and help to improve the accuracy of the wave detection.

[0090] In one implementation scenario, taking line detection using the Hough transform as an example, the Hough transform can be performed on each cluster set to obtain candidate lines. That is, each cluster set, after undergoing the Hough transform, yields a corresponding candidate line. Based on this, candidate lines can be further filtered using at least one of the following: the angle between the normal direction of the candidate line and the direction of wave motion, and the length of the candidate line, to obtain wavy lines. This method, after obtaining candidate lines by performing the Hough transform on the cluster sets, further filters candidate lines based on at least one of the following: the angle between the normal direction of the candidate line and the direction of wave motion, and the length of the candidate line, to obtain wavy lines. This further minimizes interference factors in wave detection, contributing to improved accuracy.

[0091] In a specific implementation scenario, in order to facilitate the Hough transform of each cluster set, the sub-data (e.g., location) of each target point in the cluster set can be discretized before performing the Hough transform.

[0092] In a specific implementation scenario, the measurement points formed by the waves are statistically consistent. Therefore, the direction of wave movement can be obtained by statistically analyzing the movement directions of the measurement points over a period of time. It should be noted that the direction of movement is a different concept from the aforementioned target direction. The direction of movement has a more precise angle of motion relative to the target direction, while the target direction is only a rough direction relative to the radar.

[0093] In a specific implementation scenario, if the included angle is greater than an angle threshold, candidate lines can be filtered out; if the length is less than a length threshold, candidate lines can be filtered out. It should be noted that in practical applications, at least one of the included angle and length can be used to filter candidate lines. For example, only the included angle can be selected for filtering, or only the length can be selected for filtering, or both the included angle and length can be selected simultaneously. When both the included angle and length are selected for filtering, if the included angle is not greater than an angle threshold and the length is not less than a length threshold, candidate lines can be retained; otherwise, candidate lines can be filtered out. Please refer to the relevant documentation. Figure 7 and Figure 8 , Figure 8 This is a schematic diagram of one embodiment of the wavy line. After examining... Figure 7 The target points shown can be obtained by performing the aforementioned clustering operations and line detection steps. Figure 8 The wavy line in bold black indicates the case. Other cases can be deduced similarly, and will not be listed here.

[0094] The scheme filters the measurement points matching the target direction of the wave as target points based on the radial velocities of the measurement points in the measurement data, determines whether the first target point belongs to the cluster threshold in which the second target point is located based on the cluster threshold and the data difference between the sub-data of the first target point and the sub-data of the second target point, the cluster threshold is related to the position of the point, the first target point is an unclustered target point, and the second target point is a clustered target point, and then performs straight line detection based on the cluster set to obtain the wave line in the target direction. On the one hand, the wave detection is performed by the radar, which can reduce the influence of natural factors such as light and weather as much as possible, and helps to improve the stability and scene adaptability of the wave detection. On the other hand, the measurement points matching the target direction are filtered based on the radial velocities, so that the wave detection can be performed in different directions, and then the interference of other directions can be excluded as much as possible when detecting the wave in the target direction, which helps to improve the accuracy of the wave detection. In addition, the cluster threshold is set according to the position of the point, so that the variable threshold can be used to cluster the target points according to the actual situation of the target points, which helps to further improve the accuracy of the wave detection. Therefore, the accuracy, stability and scene adaptability of the wave detection can be improved.

[0095] Please refer to Figure 9 , Figure 9 is a flowchart of another embodiment of the wave intensity detection method of the present application. Specifically, it can include the following steps:

[0096] Step S901: Detect whether a numerical mapping relationship has been constructed. If not, perform step S902, and if yes, perform step S905.

[0097] Specifically, the numerical mapping relationship represents the functional relationship between the echo intensity and the wave intensity, which can be obtained by data fitting according to the sample data labeled offline. In addition, offline labeling means labeling the true wave intensity value of the echo intensity value in the sample data collected in the field. For details, please refer to the related description in the foregoing disclosed embodiments, which will not be repeated here.

[0098] Step S902: Collect radar and wave data simultaneously.

[0099] Specifically, in the case where the numerical mapping relationship has not been constructed, radar and wave data can be collected simultaneously. That is, the target tracking data and the wave intensity data of the wave detected by the radar are collected simultaneously. For details, please refer to the related description in the foregoing disclosed embodiments, which will not be repeated here.

[0100] Step S903: Obtain sample data by offline labeling based on the radar and wave data.

[0101] Specifically, the meaning of offline labeling can be referred to the related description above, which will not be repeated here.

[0102] Step S904: based on the sample data, a numerical mapping relationship between the echo intensity and the wave intensity is constructed.

[0103] For details, please refer to the relevant description in the foregoing disclosed embodiments, which will not be repeated here.

[0104] Step S905: initialization.

[0105] Specifically, the contents of the initialization mainly include but are not limited to: a velocity threshold for filtering out measurement points, a clustering threshold, related parameters for straight line detection, related parameters for filtering out candidate lines, and the number of frames for smoothing wave periods. For details, please refer to the relevant description in the foregoing disclosed embodiments, which will not be repeated here.

[0106] Step S906: obtaining measurement data of the wave by the radar.

[0107] Specifically, the radar (such as a millimeter wave radar) can track and detect the wave through a target detection tracking algorithm, and output measurement data in real time. In addition, for the specific meaning of the measurement data, please refer to the relevant description in the foregoing disclosed embodiments, which will not be repeated here.

[0108] Step S907: filtering out stationary measurement points.

[0109] Specifically, the measurement points with an absolute value of radial velocity lower than a velocity threshold (such as 0.2 m / s, etc.) can be regarded as stationary measurement points, and these measurement points can be filtered out to avoid affecting the wave detection.

[0110] Step S908: screening measurement points matching the target direction of the wave as target points.

[0111] For details, please refer to the relevant description in the foregoing disclosed embodiments, which will not be repeated here.

[0112] Step S909: target point clustering.

[0113] For details, please refer to the relevant description in the foregoing disclosed embodiments, which will not be repeated here.

[0114] Step S910: data discretization is performed on each target point in the clustering set.

[0115] For details, please refer to the relevant description in the foregoing disclosed embodiments, which will not be repeated here.

[0116] Step S911: straight line detection is performed on the clustering set to obtain candidate lines.

[0117] For details, please refer to the relevant description in the foregoing disclosed embodiments, which will not be repeated here.

[0118] Step S912: Obtain the movement direction of the wave.

[0119] For details, refer to the related description in the foregoing disclosed embodiments, which will not be repeated here.

[0120] Step S913: Filter out the candidate line with interference.

[0121] Specifically, if the included angle between the normal direction of the candidate line and the movement direction of the wave is greater than an angle threshold (e.g., 30 degrees, 40 degrees, etc.), the candidate line can be filtered out. In addition, if the length of the candidate line is less than a length threshold, the candidate line can also be filtered out.

[0122] Step S914: Determine whether the detection line has been determined. If not, step S915 is executed, and if yes, step S918 is executed.

[0123] Specifically, the specific meaning of the detection line can refer to the related description in the foregoing disclosed embodiments, which will not be repeated here.

[0124] Step S915: Determine the end point of the wave.

[0125] Specifically, the disappearing position of the wave can be marked as the end point.

[0126] Step S916: End point line correction.

[0127] Specifically, the movement direction of the wave can be statistically obtained in large quantities, and the end point line perpendicular to the movement direction can be drawn at the end point.

[0128] Step S917: Generate the detection line.

[0129] Specifically, the detection line can be generated by translating a preset distance (e.g., 20 meters, 40 meters, etc.) away from the radar starting from the end point line.

[0130] Step S918: Real-time detect whether the wave line crosses the detection line. If yes, step S919 is executed, and if not, step S906 is executed.

[0131] For details, refer to the related description in the foregoing disclosed embodiments, which will not be repeated here.

[0132] Step S919: Take the wave line crossing the detection line as the target line, and take the clustering set of the target line obtained by straight line detection as the target set.

[0133] For details, refer to the related description in the foregoing disclosed embodiments, which will not be repeated here.

[0134] Step S920: Map the echo intensity of each measurement point in the target set based on the numerical mapping relationship respectively, to obtain the wave intensity when the target line crosses the line.

[0135] The body can refer to the relevant description in the foregoing disclosed embodiments, which will not be repeated here.

[0136] Step S921: smoothing the wave intensity.

[0137] Specifically, the average intensity of the wave in a period of time (e.g., 30 minutes) can be counted.

[0138] Step S922: drawing the intensity change trend of the wave in the preset period.

[0139] Specifically, the foregoing disclosed embodiments can be referred to for relevant description, which will not be repeated here.

[0140] The above scheme does not rely on visual technology, but only uses radar to realize wave detection and wave intensity detection, which can improve the accuracy, stability and scene adaptability of wave intensity detection.

[0141] Please refer to Figure 10 , Figure 10 is a frame diagram of an embodiment of the wave intensity detection device 100. The wave intensity detection device 100 includes a relationship fitting module 101, a wave detection module 102, a crossing line detection module 103, and an intensity mapping module 104. The relationship fitting module 101 is configured to pre-fit a numerical mapping relationship between wave intensity and radar echo intensity. The wave detection module 102 is configured to detect a wave line based on measurement data of wave scanning by the radar. The measurement data includes sub-data of a plurality of measurement points, and the sub-data includes at least two dimensions of point position and echo intensity. The wave line is obtained by performing straight line detection on a clustering set obtained by clustering a plurality of measurement points based on a clustering threshold related to the point position. The crossing line detection module 103 is configured to detect whether each frame of measurement data crosses a detection line, and to take the wave line that crosses the detection line as a target line, and to take the clustering set of the target line obtained by straight line detection as a target set. The detection line is parallel to the end point line of the wave, and is away from the radar relative to the end point line. The intensity mapping module 104 is configured to map the echo intensity of each measurement point in the target set based on the numerical mapping relationship, to obtain the wave intensity when the target line crosses the detection line.

[0142] The scheme can reduce the influence of natural factors such as light and weather as much as possible, because the wave intensity detection does not need to rely on visual shooting but only needs to be scanned by radar. The scheme can cluster the target points according to the actual situation of the target points by using a variable threshold, which is helpful to further improve the accuracy of wave detection compared with using a constant threshold. The scheme can make the mapped wave intensity as close as possible to the real intensity by pre-fitting the numerical mapping relationship between the wave intensity and the echo intensity and mapping the echo intensity of each measurement point involved in the wave line crossing the detection line in the intensity detection process. Therefore, the scheme can improve the accuracy, stability and scene adaptability of wave intensity detection.

[0143] In some disclosed embodiments, the relationship fitting module 101 includes a sample acquisition submodule for acquiring sample data collected in the field of the wave; wherein the sample data includes echo intensity values and wave intensity values of the wave at a plurality of sample points when the wave is scanned by the radar; the relationship fitting module 101 includes a function fitting submodule for performing function fitting based on the sample data to obtain the numerical mapping relationship.

[0144] In some disclosed embodiments, the intensity mapping module 104 includes a first mapping submodule for mapping the echo intensity of each measurement point in the target set based on the numerical mapping relationship to obtain the wave intensity at the measurement point; the intensity mapping module 104 includes a first statistical submodule for performing numerical statistics based on the wave intensity at each measurement point in the target set to obtain the wave intensity when the target line crosses the line.

[0145] In some disclosed embodiments, the intensity mapping module 104 includes a point position sorting submodule for sorting the measurement points in the target set in the order of the echo intensity from small to large; the intensity mapping module 104 includes a point position screening submodule for eliminating the measurement points in the target range in the sorted target set; wherein the target range includes at least one of the following: located in the front first proportion, located in the rear second proportion; the intensity mapping module 104 includes a second mapping submodule for mapping the echo intensity of each remaining measurement point in the target set based on the numerical mapping relationship to obtain the wave intensity at the remaining measurement point; the intensity mapping module 104 includes a second statistical submodule for performing numerical statistics based on the wave intensity at each remaining measurement point in the target set to obtain the wave intensity when the target line crosses the line.

[0146] In some disclosed embodiments, the wave intensity detection device 100 further includes a trend analysis module for obtaining the intensity change trend in the preset period based on the wave intensity when the line is crossed each time in the preset period.

[0147] In some disclosed embodiments, the wave intensity detection apparatus 100 further comprises a position determination module configured to obtain, for a plurality of frame measurement data, a position of a wave line closest to the radar, and perform median filtering based on the obtained positions to obtain a disappearance position of the wave; the wave intensity detection apparatus 100 further comprises a straight line determination module configured to determine a straight line perpendicular to a movement direction of the wave and passing through the disappearance position as an end line.

[0148] In some disclosed embodiments, the sub-data further comprises a radial velocity of the measurement point, the wave detection module 102 comprises a screening sub-module configured to screen, based on the radial velocity of each measurement point in the measurement data, a measurement point matching a target direction as a target point; wherein the target direction is any one of a going direction or a coming direction; the wave detection module 102 comprises a clustering sub-module configured to determine, based on a clustering threshold and a data difference value between the sub-data of a first target point and the sub-data of a second target point, whether the first target point belongs to a clustering set in which the second target point is located; wherein the first target point is an un-clustered target point, and the second target point is a clustered target point; the wave detection module 102 comprises a detection sub-module configured to perform straight line detection based on the clustering set to obtain a wave line of the target direction.

[0149] In some disclosed embodiments, the clustering threshold comprises a sub-threshold of at least one dimension of the point position, the radial velocity, or the echo intensity; wherein in the dimension of the point position, the sub-threshold is positively correlated with a first distance from the point position of the first target point to the radar position, in the dimension of the radial velocity, the sub-threshold is positively correlated with a second distance from the point position of the second target point to the radar position, and in the dimension of the echo intensity, the sub-threshold is negatively correlated with the second distance.

[0150] In some disclosed embodiments, the data difference value comprises a sub-difference value of each dimension of the first target point and the second target point, the clustering threshold comprises a sub-threshold of each dimension, the clustering sub-module comprises a condition detection unit configured to detect whether the sub-difference value of each dimension satisfies a preset condition; wherein the preset condition comprises that the sub-difference value of the dimension is not greater than the sub-threshold of the same dimension; the clustering sub-module comprises a clustering determination unit configured to determine that the first target point belongs to the clustering set in which the second target point is located in response to the sub-difference value of each dimension satisfying the preset condition; the clustering sub-module comprises a re-clustering unit configured to select a new second target point and re-perform the step of detecting whether the sub-difference value of each dimension satisfies the preset condition until the clustering set of the first target point is determined in response to the sub-difference value of at least one dimension not satisfying the preset condition.

[0151] In some disclosed embodiments, the data difference value comprises a sub-difference value of the first target point and the second target point with respect to the point position, the clustering sub-module comprises a weight measurement unit configured to obtain a first weight in the x-axis direction and a second weight in the y-axis direction based on a first distance from the point position of the first target point to the radar position; wherein the first weight is greater than the second weight, and the first weight and the second weight are positively correlated with the first distance; the clustering sub-module comprises a difference measurement unit configured to obtain a first difference in the x-axis direction of the point position of the first target point and the second target point, and obtain a second difference in the y-axis direction of the point position of the first target point and the second target point; and the clustering sub-module comprises a difference value determination unit configured to obtain the sub-difference value of the point position based on a ratio of the first difference and the first weight, and a ratio of the second difference and the second weight.

[0152] In some disclosed embodiments, the wave detection module 102 comprises a threshold determination sub-module configured to determine a quantity threshold of the cluster set based on the point positions of the target points in the cluster set; and the wave detection module 102 comprises a cluster screening sub-module configured to select to retain or filter out the cluster set based on whether the total number of the target points in the cluster set is greater than the quantity threshold of the cluster set.

[0153] In some disclosed embodiments, the detection sub-module comprises a candidate line obtaining unit configured to perform Hough transform on each cluster set respectively to obtain a candidate line; and the detection sub-module comprises a candidate line screening unit configured to screen the candidate line based on at least one of an included angle between a normal direction of the candidate line and a movement direction of the wave, and a length of the candidate line, to obtain the wave line.

[0154] Please refer to Figure 11 , Figure 11 is a schematic diagram of the framework of an embodiment of the electronic device 110. The electronic device 110 comprises a memory 111 and a processor 112 coupled with each other, the memory 111 stores program instructions, and the processor 112 is configured to execute the program instructions to implement the steps in any of the wave intensity detection method embodiments described above. In addition, the electronic device 110 can further comprise a radar (not shown) configured to scan the wave to obtain measurement data, and the radar can comprise but is not limited to a millimeter wave radar, etc., which is not limited herein. For details, please refer to the related description in the foregoing disclosed embodiments, which will not be repeated here.

[0155] Specifically, the processor 112 is configured to control itself and the memory 111 to implement the steps in any of the above wave intensity detection method embodiments. The processor 112 can also be referred to as a CPU (Central Processing Unit). The processor 112 can be an integrated circuit chip having a processing capability of signals. The processor 112 can also be a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like. In addition, the processor 112 can be implemented by multiple integrated circuit chips together.

[0156] The above scheme, since the electronic device 110 can implement the steps in any of the above wave intensity detection method embodiments, on the one hand, the electronic device 110 can reduce the influence of natural factors such as light and weather as much as possible when detecting the wave intensity, because it does not need to rely on visual shooting, but only needs to scan by radar. On the other hand, the clustering threshold is set according to the position of the point, so that the variable threshold can be used to cluster the target points according to the actual situation of the target points, which is helpful to further improve the accuracy of wave detection compared with using constant threshold for clustering. On the other hand, by pre-fitting the numerical mapping relationship between the wave intensity and the echo intensity, and then mapping the echo intensity of each measurement point involved in the wave line crossing the detection line in the intensity detection process using the pre-fitted numerical mapping relationship, the wave intensity when crossing the detection line can be obtained, which can make the wave intensity obtained by mapping as close as possible to the true intensity. Therefore, the accuracy, stability and scene adaptability of wave intensity detection can be improved.

[0157] Please refer to Figure 12 , Figure 12 is a framework schematic diagram of an embodiment of the computer readable storage medium 120 of the present application. The computer readable storage medium 120 stores program instructions 121 capable of being executed by the processor, and the program instructions 121 are used to implement the steps in any of the above wave intensity detection method embodiments.

[0158] According to the scheme, since the computer readable storage medium 120 implements the steps in any of the wave intensity detection method embodiments, on the one hand, the computer readable storage medium 120 can reduce the influence of natural factors such as light and weather as much as possible since it does not need to rely on visual shooting when detecting wave intensity, but only needs to be scanned by radar, on the other hand, the clustering threshold is set according to the point position, so that the variable threshold can be used to cluster the target point according to the actual situation of the target point, compared with using a constant threshold to cluster, which helps to further improve the accuracy of wave detection, and on the other hand, the numerical mapping relationship between wave intensity and echo intensity is fitted in advance, and the numerical mapping relationship fitted in advance is used to map the echo intensity of each measurement point involved in the wave line crossing the detection line in the intensity detection process to obtain the wave intensity when crossing the detection line, which can make the wave intensity obtained by mapping as close to the real intensity as possible. Therefore, the accuracy, stability and scene adaptability of wave intensity detection can be improved.

[0159] In several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only illustrative, for example, the division of modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0160] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment scheme.

[0161] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0162] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in part, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the methods in the embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and various other media that can store program codes.

[0163] If the technical solutions of the present application involve personal information, the product applying the technical solutions of the present application has been informed of the personal information processing rules before processing the personal information, and has obtained the personal independent consent. If the technical solutions of the present application involve sensitive personal information, the product applying the technical solutions of the present application has obtained the personal independent consent before processing the sensitive personal information, and at the same time meets the requirement of "explicit consent". For example, at the personal information collection device such as camera, a clear and prominent mark is set to inform that the personal information collection range has been entered, and the personal information will be collected. If the individual voluntarily enters the collection range, it is regarded as agreeing to collect the personal information. Or, on the device for processing personal information, the personal information processing rules are informed by using obvious marks / information, and the personal authorization is obtained by means of pop-up information or asking the individual to upload the personal information. The personal information processing rules can include personal information processor, personal information processing purpose, processing method, and personal information type, etc.

Claims

1. A wave intensity detection method characterized by, The method comprises the following steps: pre-fitting a numerical mapping relationship between wave intensity and radar echo intensity; detecting a wave line based on measurement data of radar scanning of the wave; wherein the measurement data comprises sub-data of a plurality of measurement points, the sub-data comprises at least two dimensions of point position and echo intensity, and the wave line is obtained by performing straight line detection on a clustering set obtained by clustering the plurality of measurement points based on a clustering threshold related to the point position; sequentially detecting whether the wave line of each frame of the measurement data crosses a detection line, taking the wave line crossing the detection line as a target line, and taking a clustering set of the target line obtained by the straight line detection as a target set; wherein the detection line is parallel to an end line of the wave and is away from the radar relative to the end line; mapping the echo intensity of each measurement point in the target set based on the numerical mapping relationship to obtain the wave intensity when the target line crosses the detection line.

2. The method of claim 1, wherein, The method for pre-fitting the numerical mapping relationship between the wave intensity and the radar echo intensity comprises the following steps: obtaining sample data collected in the field for the wave; wherein the sample data comprises echo intensity values and wave intensity values of the wave at a plurality of sample points when the radar scans the wave; performing function fitting based on the sample data to obtain the numerical mapping relationship.

3. The method of claim 1, wherein, The method for mapping the echo intensity of each measurement point in the target set based on the numerical mapping relationship to obtain the wave intensity when the target line crosses the detection line comprises the following steps: mapping the echo intensity of each measurement point in the target set based on the numerical mapping relationship to obtain the wave intensity at the measurement point; performing numerical statistics on the wave intensity at each measurement point in the target set to obtain the wave intensity when the target line crosses the detection line.

4. The method of claim 1, wherein, The method for mapping the echo intensity of each measurement point in the target set based on the numerical mapping relationship to obtain the wave intensity when the target line crosses the detection line comprises the following steps: sorting the measurement points in the target set in the order of the echo intensity from small to large; removing the measurement points in the target range in the sorted target set; wherein the target range comprises at least one of the following: located in the front first proportion, located in the rear second proportion; mapping the echo intensity of the remaining measurement points in the target set based on the numerical mapping relationship to obtain the wave intensity at the remaining measurement points; performing numerical statistics on the wave intensity at the remaining measurement points in the target set to obtain the wave intensity when the target line crosses the detection line.

5. The method of claim 1, wherein, After the step of mapping the echo intensity of each measurement point in the target set based on the numerical mapping relationship to obtain the wave intensity when the target line crosses the detection line, the method further comprises the following steps: obtaining a trend of intensity change in a preset period based on the wave intensity when the target line crosses the detection line in each of the preset period.

6. The method of claim 1, wherein, The step of obtaining the end line comprises the following steps: for a plurality of frames of the measurement data, obtaining the position of the wave line closest to the radar, and performing median filtering based on the obtained positions to obtain the disappearance position of the wave; A straight line perpendicular to the direction of the wave motion and passing through the vanishing position is taken as the end point line.

7. The method of claim 1, wherein, The sub-data further comprises radial velocities of the measuring points, and the wave line is detected based on the measuring data of the radar scanning. The radial velocities of the measuring points in the measuring data are used to screen the measuring points matching the target direction as target points, wherein the target direction is any one of the going direction or the coming direction. The clustering threshold and the data difference between the sub-data of the first target point and the sub-data of the second target point are used to determine whether the first target point belongs to the clustering set in which the second target point is located, wherein the first target point is an un-clustered target point, and the second target point is a clustered target point. The clustering set is used for straight line detection to obtain the wave line of the target direction.

8. The method of claim 7, wherein, The clustering threshold comprises sub-thresholds in at least one dimension of the point position, the radial velocity or the echo intensity. In the dimension of the point position, the sub-threshold is positively correlated with a first distance from the point position of the first target point to the radar position, in the dimension of the radial velocity, the sub-threshold is positively correlated with a second distance from the point position of the second target point to the radar position, and in the dimension of the echo intensity, the sub-threshold is negatively correlated with the second distance.

9. The method according to claim 7 or 8, characterized in that, The data difference comprises sub-differences of the first target point and the second target point in each dimension, the clustering threshold comprises sub-thresholds in each dimension, and the determination of whether the first target point belongs to the clustering set in which the second target point is located based on the clustering threshold and the data difference between the sub-data of the first target point and the sub-data of the second target point comprises: Each of the sub-differences in each dimension is detected to determine whether the sub-difference satisfies a preset condition, wherein the preset condition comprises that the sub-difference in the dimension is not greater than the sub-threshold in the same dimension. In response to the sub-difference in each dimension satisfying the preset condition, it is determined that the first target point belongs to the clustering set in which the second target point is located. In response to the sub-difference in at least one dimension not satisfying the preset condition, a new second target point is selected, and the step of detecting whether the sub-difference in each dimension satisfies the preset condition is re-executed until the clustering set of the first target point is determined.

10. The method according to claim 7 or 8, characterized in that, The data difference comprises a sub-difference of the first target point and the second target point with respect to the point position, and the step of obtaining the sub-difference of the point position comprises: Based on a first distance from the point position of the first target point to the radar position, a first weight in the x-axis direction and a second weight in the y-axis direction are obtained, wherein the first weight is greater than the second weight, and the first weight and the second weight are positively correlated with the first distance. A first difference in the x-axis direction of the point positions of the first target point and the second target point is obtained, and a second difference in the y-axis direction of the point positions of the first target point and the second target point is obtained. A sub-difference value of the point position is obtained based on a ratio of the first difference and the first weight, and a ratio of the second difference and the second weight.

11. The method of claim 7, wherein, After determining whether the first target point belongs to the cluster set in which the second target point is located based on the cluster threshold and a data difference between sub-data of the first target point and sub-data of the second target point, and before performing straight line detection on the cluster set to obtain the wave line of the target direction, the method further comprises: Determining a quantity threshold of the cluster set based on the point positions of the target points in the cluster set; Based on whether the total number of the target points in the cluster set is greater than the quantity threshold of the cluster set, the cluster set is selected to be retained or filtered out.

12. The method of claim 7, wherein, The straight line detection on the cluster set to obtain the wave line of the target direction comprises: Performing Hough transform on each of the cluster sets to obtain a candidate line; Based on at least one of an included angle between a normal direction of the candidate line and a movement direction of the wave, and a length of the candidate line, the candidate line is screened to obtain the wave line.

13. A wave intensity detection apparatus characterized by comprising: Comprise: A relationship fitting module is configured to pre-fit a numerical mapping relationship between wave intensity and echo intensity of a radar; A wave detection module is configured to detect a wave line based on measurement data of a wave scanned by the radar; wherein the measurement data comprises sub-data of a plurality of measurement points, the sub-data comprises at least two dimensions of point position and echo intensity, and the wave line is obtained by performing straight line detection on a cluster set obtained by clustering the plurality of measurement points based on a cluster threshold related to the point position; A crossing line detection module is configured to sequentially detect whether each frame of the measurement data crosses a detection line, and to take a wave line crossing the detection line as a target line, and to take a cluster set of the target line obtained by the straight line detection as a target set; wherein the detection line is parallel to a terminal line of the wave, and is away from the radar relative to the terminal line; An intensity mapping module is configured to map the echo intensity of each of the measurement points in the target set based on the numerical mapping relationship, to obtain wave intensity when the target line crosses the detection line.

14. An electronic device, comprising: A memory and a processor are coupled to each other, the memory stores program instructions, and the processor is configured to execute the program instructions to implement the wave intensity detection method of any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that, The program instructions stored in the memory can be run by the processor, and the program instructions are used to implement the wave intensity detection method of any one of claims 1 to 12.

Images