Radar data processing method, program product, electronic device and storage medium

Abstract

The present application provides a radar data processing method, a program product, an electronic device and a storage medium. The method comprises: comparing acquired radar data with a baseline value to obtain a difference value; if the difference value is less than a threshold value, reporting the radar data at a first data reporting frequency; if the difference value is not less than the threshold value, reporting the radar data at a second data reporting frequency; and updating the baseline value on the basis of the baseline value and the threshold value, wherein the second data reporting frequency is higher than the first data reporting frequency. An appropriate reporting frequency is selected on the basis of the comparison result between the difference value and the threshold value, so as to automatically adjust the reporting frequency; for non-abnormal situations, unnecessary data transmissions are reduced, thus saving network bandwidth and storage resources; for abnormal situations, the second data reporting frequency which is a higher frequency is used for data reporting, such that the problem of missing data is ameliorated, thus improving the accuracy of reported data. By means of dynamically adjusting a baseline value, the real state of radar data can be more accurately reflected, reducing false alarms caused by a fixed baseline value.

Description

A radar data processing method, program product, electronic device and storage medium

[0001] Cross-reference to Related Applications

[0002] The present application claims priority from the Chinese patent application No. 2024113121474 entitled "A radar data processing method, program product, electronic device and storage medium" filed on September 19, 2024 with the China Patent Office, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the field of radar, in particular, to a radar data processing method, program product, electronic device and storage medium. BACKGROUND

[0004] Radar is a radio device that uses electromagnetic waves to send and receive signals to detect the position, speed and other characteristics of target objects. Radar has a wide range of applications in aviation, navigation, transportation and other fields and plays an important role. The uploading and processing of a large amount of data will consume more computing resources and time, which may cause the system response speed to slow down and affect the application scenarios with high real-time requirements. The current processing method is to use a periodic transmission method for radar data, which may cause important events to be missed and the safety monitoring system to be unable to accurately assess the safety status. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide a radar data processing method, program product, electronic device and storage medium to improve the problem of being unable to accurately assess the safety status caused by periodic transmission of radar data.

[0006] In a first aspect, the embodiments of the present application provide a radar data processing method, comprising: comparing the collected radar data with a base value to obtain a difference value; if the difference value is less than a threshold value, reporting the radar data according to a first data reporting frequency; if the difference value is not less than the threshold value, reporting the radar data according to a second data reporting frequency; and updating the base value according to the base value and the threshold value, so that the difference value of the subsequently collected radar data is obtained based on the updated base value; the second data reporting frequency is higher than the first data reporting frequency.

[0007] In the implementation process, the radar data collected is compared with the base value to obtain a difference value, a suitable reporting frequency is selected based on a comparison result of the difference value and the threshold value, and the reporting frequency is automatically adjusted. For non-exceptional cases, unnecessary data transmission can be reduced, and network bandwidth and storage resources can be saved. For exceptional cases, data reporting is performed at a second data reporting frequency with a higher frequency, the situation of missing reporting of emergency events is reduced, and the safety and accuracy of detection are improved. Moreover, the base value is dynamically adjusted, the real state of the radar data can be more accurately reflected, and false positives or false negatives caused by a fixed base value can be reduced.

[0008] Optionally, in the embodiments of the present application, the base value is updated according to the base value and the threshold value, including: after the radar data reported at the second data reporting frequency reaches a preset period or a preset number, a preset weight parameter is obtained, the base value and the threshold value are weighted and summed based on the weight parameter, and an updated base value is obtained.

[0009] In the implementation process of the above embodiments: after the radar data reported at the second data reporting frequency reaches a preset period or a preset number, the base value is dynamically updated according to the base value and the threshold value, which can ensure the accuracy of the difference value, reflect the latest state of the monitored object, and reduce false positives caused by a fixed base value. Moreover, the contribution of the base value and / or the threshold value in updating the base value is considered in the process of updating the base value, which improves the accuracy of the base value determination.

[0010] Optionally, in the embodiments of the present application, after the base value is updated, the method further includes: obtaining a proportional relationship between the threshold value and the base value before the update; updating the threshold value based on the proportional relationship and the base value after the update; or; obtaining historical fluctuation data of the historical radar data and current fluctuation data of the radar data; obtaining a fluctuation ratio based on the historical fluctuation data and the current fluctuation data; updating the threshold value according to the fluctuation ratio; wherein the historical fluctuation data is configured to describe the data fluctuation degree of the historical radar data; and the current fluctuation data is configured to describe the data fluctuation degree of the current fluctuation data.

[0011] In the implementation process of the above embodiments: by dynamically adjusting the threshold value, the adjusted threshold value can adapt to the change of the fluctuation of the radar data, more accurately reflect the real state of the radar data, and reduce false positives or false negatives caused by a fixed threshold value.

[0012] Optionally, in the embodiments of the present application, the radar data is obtained by the radar device; after comparing the collected radar data with the base value to obtain the difference value, the method further comprises: obtaining the position information of the point on the scanning surface of the radar device during the collection of the radar data; if the difference value is less than the threshold value, then the camera shoots the point based on the position information of the point at a first shooting frequency; if the difference value is not less than the threshold value, then the camera shoots the point based on the position information of the point at a second shooting frequency; wherein the ratio of the first data reporting frequency to the second data reporting frequency is equal to the ratio of the first shooting frequency to the second shooting frequency.

[0013] In the implementation process of the above embodiments: during the reporting of the radar data, the synchronously photographed photos or videos provide intuitive evidence for the monitoring results, so that the combination of the radar data and the visual images can provide more comprehensive monitoring scene information, and the integrity of the data is ensured. And based on the comparison result of the difference value and the threshold value, a suitable shooting frequency is selected to automatically adjust the shooting frequency and improve the safety and accuracy of the detection.

[0014] Optionally, in the embodiments of the present application, obtaining the point information of the radar device during the collection of the radar data comprises: obtaining the radar position parameters of the radar device in the digital elevation model; the position parameters include at least one of longitude, latitude, elevation and zero point orientation of the radar antenna; mapping the radar data to the digital elevation model to obtain the point position parameters of the point on the scanning surface relative to the digital elevation model; and determining the point information of the point relative to the radar device according to the radar position parameters and the point position parameters.

[0015] In the implementation process of the above embodiments: this process combines the remote monitoring capability of the radar and the image capturing capability of the camera, and through accurate calculation and automatic control, effective monitoring of ground deformation and timely snapping of abnormal areas are realized. And the point information of the point relative to the radar device is determined through the digital elevation model, which improves the accuracy of the point information.

[0016] Optionally, in the embodiment of the present application, the radar position parameter and the point position parameter are converted to obtain point information of the point relative to the radar device, including: if the zero point position orientations of the camera and the radar device are inconsistent, the camera coordinates, the radar coordinates, the camera zero point position orientation and the radar zero point position orientation are obtained respectively; wherein the camera coordinates and the radar coordinates are coordinate information in the same coordinate system; the conversion parameters are obtained by using a calibration algorithm according to the camera coordinates, the radar coordinates, the camera zero point position orientation and the radar zero point position orientation; the conversion parameters are configured to adjust the camera zero point position orientation and the radar zero point position orientation to be consistent; the camera zero point position orientation and the radar zero point position orientation are adjusted to be consistent by using the conversion parameters; and the radar position parameter and the point position parameter are converted to obtain the point information of the point relative to the radar device in the case that the camera zero point position orientation and the radar zero point position orientation are consistent.

[0017] In the implementation process of the above embodiment: the camera zero point position orientation and the radar zero point position orientation are adjusted to be consistent by using the calibration algorithm, the consistency of the radar device and the camera in spatial perception is realized, and a data basis is provided for subsequent point shooting, point information calculation and other tasks. A plurality of camera setting modes are provided, the camera external condition is supported, and the split type work is adopted to improve the shooting flexibility.

[0018] Optionally, in the embodiment of the present application, the method further includes: obtaining a to-be-detected photo and a scene of the to-be-detected photo obtained by shooting; inputting the to-be-detected photo into an abnormality recognition model corresponding to the scene to obtain an abnormality recognition result; and reporting the to-be-detected photo and the corresponding abnormality recognition result.

[0019] In the implementation process of the above embodiment: through the automatic image recognition process, manual intervention can be greatly reduced, and processing efficiency can be improved. According to the scene of the to-be-detected photo, a suitable abnormality recognition model is selected, the professional and targeted nature of the abnormality recognition model is ensured, and the accuracy of the recognition result is improved.

[0020] In a second aspect, the embodiment of the present application further provides a radar data processing device, including: a difference calculation module configured to compare the collected radar data with a base value to obtain a difference; a data reporting module configured to: if the difference is less than a threshold value, report the radar data according to a first data reporting frequency; if the difference is not less than the threshold value, report the radar data according to a second data reporting frequency; and update the base value according to the base value and the threshold value, so that the difference of the subsequently collected radar data is obtained based on the updated base value; and the second data reporting frequency is higher than the first data reporting frequency.

[0021] In a third aspect, the embodiments of the present application further provide a computer program product, comprising computer program instructions, which, when executed by a processor, perform the method provided in the first aspect or any one of the implementation manners of the first aspect.

[0022] In a fourth aspect, the embodiments of the present application further provide an electronic device, comprising a processor and a memory, wherein the memory stores computer program instructions, which, when executed by the processor, perform the method provided in the first aspect or any one of the implementation manners of the first aspect.

[0023] In a fifth aspect, the embodiments of the present application further provide a computer-readable storage medium, which stores computer program instructions, which, when executed by a processor, perform the method provided in the first aspect or any one of the implementation manners of the first aspect.

[0024] By using the radar data processing method, device, electronic device and storage medium provided in the present application, the radar data collected is compared with the base value to obtain a difference value, and a suitable reporting frequency is selected based on the comparison result of the difference value and the threshold value, so as to automatically adjust the reporting frequency. For non-exceptional cases, unnecessary data transmission can be reduced, and network bandwidth and storage resources can be saved. For exceptional cases, data reporting is performed by using a second data reporting frequency with a higher frequency, so as to reduce the situation of missing reporting of emergency events and improve the safety and accuracy of detection. Moreover, by dynamically adjusting the base value, the real state of the radar data can be more accurately reflected, and false positives or false negatives caused by a fixed base value can be reduced. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0026] FIG. 1 is a flow diagram of a radar data processing method provided by an embodiment of the present application;

[0027] FIG. 2 is a structural diagram of a radar data processing device provided by an embodiment of the present application;

[0028] FIG. 3 is a structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0029] The embodiments of the technical solutions of the present application will be described in detail below with reference to the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present application, and therefore only serve as examples, and cannot limit the protection scope of the present application.

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of this application.

[0031] In the description of the embodiments of the present application, the technical terms "first", "second" and the like are only configured to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0032] There is a close relationship between radar data upload frequency and safety monitoring. Safety monitoring often has high requirements for the real-time performance of data. Radar, as an important monitoring tool, can reflect the state and changes of the target in real time. Therefore, the upload frequency of radar data directly affects the real-time performance of safety monitoring. Higher upload frequency can ensure that the safety monitoring system can obtain the latest radar data faster, so as to respond and make decisions more timely.

[0033] The related technology uses fixed frequency and period to report radar data, but if the upload frequency of radar data is too low, important events occurring between two uploads may be missed, affecting the integrity of the data. This may make the safety monitoring system unable to fully and accurately assess the current safety situation, thereby affecting the monitoring effect and the accuracy of decision-making. The selection of radar data upload frequency also needs to consider the stability of the system. Too high upload frequency may increase the burden of the system, causing the system to be unable to process and malfunction or crash.

[0034] The embodiments of the present application provide a radar data processing method, which compares the collected radar data with a base value to obtain a difference value, selects a suitable reporting frequency based on the comparison result of the difference value and a threshold value, and realizes automatic adjustment of the reporting frequency. For non-exceptional cases, unnecessary data transmission can be reduced, and network bandwidth and storage resources can be saved. For exceptional cases, a second data reporting frequency with a higher frequency is used for data reporting, which improves the problem of missing emergency events and improves the safety and accuracy of detection. And by dynamically adjusting the base value, the real state of the radar data can be more accurately reflected, and false positives or false negatives caused by fixed base values can be reduced.

[0035] Please refer to the flowchart of a radar data processing method provided by the embodiment of the present application shown in FIG. 1. The radar data processing method provided by the embodiment of the present application can be applied to an electronic device, which can include a server, a PC, a tablet computer, a smart phone, or other physical devices, or can also be a virtual machine or a container, etc. The electronic device can be a single device, or a combination of multiple devices, or a cluster of a large number of devices. The radar data processing method can include the following steps:

[0036] Step S110: comparing the collected radar data with the base value to obtain a difference value.

[0037] Step S121: if the difference value is less than the threshold value, reporting the radar data according to a first data reporting frequency.

[0038] Step S122: if the difference value is not less than the threshold value, reporting the radar data according to a second data reporting frequency; and updating the base value according to the base value and the threshold value, so that the difference value of the subsequently collected radar data is obtained based on the updated base value; the second data reporting frequency is higher than the first data reporting frequency.

[0039] In step S110, the radar data can include basic detection data, radar image data, point cloud data, etc. The basic detection data includes distance data, angle data, and speed data, etc.; the radar image data is, for example, a deformation cloud image or a scattering cloud image, etc.; the point cloud data is composed of a large number of points, each point contains its three-dimensional coordinates (X, Y, Z) and possibly other attributes (such as intensity, reflectivity, etc.). The above-mentioned radar data can be collected by a radar device or a GNSS (Global Navigation Satellite System).

[0040] The base value can be regarded as a reference point of the radar data, configured to compare the radar data. For the initial base value, the base value can be the initial data collected by the monitoring device within a certain period of time, which is used as the comparison benchmark for subsequent changes. For example, in deformation monitoring, the base value can be the elevation data of the terrain or structure collected for the first time after the device is installed. It can be understood that each type of radar data can have its corresponding base value. For example, if the radar data is angle data, the base value should be an angle base value. For another example, if the radar data is deformation data, the base value can be an elevation base value.

[0041] The collected radar data is compared with the base value to obtain a difference value, for example, the collected radar data can be subtracted from its corresponding base value to obtain a difference value. The difference value is configured to represent the amount of change of the corresponding radar data of the monitoring object since the base value is determined. If the radar data is deformation data, the amount of change represents the amount of deformation of the terrain or structure, and the reason for the deformation can be ground uplift or ground subsidence, etc.

[0042] In step S121, the threshold is configured to represent the fluctuation amount of the radar data, and when the difference between the monitored data and the base value exceeds the threshold, it can be considered that the point has a change or an anomaly that needs attention. The threshold can be set based on historical data or specific safety standards, and normal fluctuations and abnormal fluctuations can be distinguished by the threshold.

[0043] The difference is compared with the threshold, and if the difference is less than the threshold, it means that the change amount of the radar data is within the normal fluctuation range, and the radar data is reported according to the first data reporting frequency.

[0044] In step S122, if the difference is not less than the threshold (i.e., the difference is greater than or equal to the threshold), it means that the change amount of the radar data exceeds the normal fluctuation range, and an abnormality may occur, such as a large deformation, etc., and the radar data is reported according to the second data reporting frequency; the second data reporting frequency is higher than the first data reporting frequency, that is, the frequency of data reporting is accelerated when the difference is not less than the threshold, so as to quickly respond to the actual change of the radar data and timely notify relevant personnel or system to take action.

[0045] Considering that the position information provided by the radar data acquisition device records the relative position change relative to a starting point, if the acquisition device is configured to monitor deformation or other types of displacement, and these displacements occur continuously, the acquired values may gradually increase over time. In this case, if a fixed base value is used, the subsequent difference calculation may not be accurate, and the difference may always be greater than (or equal to) the threshold, causing false alarms, etc.

[0046] Based on this finding, in the embodiments of the present application, after reporting the radar data according to the second data reporting frequency, the base value is updated according to the base value and the threshold. In this way, for subsequent radar data that has not been reported, the difference can be calculated based on the new base value, and the reporting frequency can be determined based on the difference.

[0047] As an implementation, after reporting the radar data according to the second data reporting frequency for a preset period, the base value is updated according to the threshold and the base value, and the updated base value is compared with the new radar data to obtain the difference.

[0048] In the above implementation process, the acquired radar data and the base value are compared to obtain the difference, and based on the comparison result of the difference and the threshold, the appropriate reporting frequency is selected to automatically adjust the reporting frequency. For non-abnormal cases, unnecessary data transmission can be reduced, saving network bandwidth and storage resources. For abnormal cases, the second data reporting frequency with a higher frequency is used for data reporting, which improves the problem of missing emergency events and improves the safety and accuracy of detection. Moreover, by dynamically adjusting the base value, the real state of the radar data can be more accurately reflected, and false positives or false negatives caused by a fixed base value can be reduced.

[0049] Optionally, in the embodiments of the present application, the base value is updated according to the base value and the threshold value, including: after the radar data is reported according to the second data reporting frequency for a preset period or a preset number of times, a preset weight parameter is obtained, the base value and the threshold value are weighted and summed based on the weight parameter, and an updated base value is obtained.

[0050] The preset period or the preset number of times can be preconfigured, for example, the reporting period is preconfigured as 2 hours or the preset number of times is set as 20 groups, the radar data is reported according to the second data reporting frequency, and after the reporting time reaches 2 hours or the reporting number reaches 20 groups, the base value is updated.

[0051] The base value updating manner is: a preset weight parameter is obtained, the weight parameter includes a base value weight and / or a threshold value weight. The weight parameter is configured to determine the contribution degree of the base value and / or the threshold value in the process of updating the base value. For example, if the base value weight and the threshold value weight are both 1, the value obtained by summing the base value and the threshold value is the updated base value.

[0052] In the implementation process of the above embodiments: after the radar data is reported according to the second data reporting frequency for a preset period or a preset number of times, the base value is dynamically updated according to the base value and the threshold value, which can ensure the accuracy of the difference value, reflect the latest state of the monitored object, and reduce false positives caused by a fixed base value. And in the process of updating the base value, the contribution degree of the base value and / or the threshold value in the process of updating the base value is considered, which improves the accuracy of the base value determination.

[0053] Optionally, in the embodiments of the present application, after the base value is updated, the threshold value can also be dynamically adjusted, and the adjustment manner can adopt any one of the following two manners:

[0054] The first manner is to obtain the proportional relationship between the threshold value and the base value before the update; and update the threshold value based on the proportional relationship and the base value after the update. For example, the proportional relationship between the initial threshold value and the initial base value is 1 / 5, and then, in order to ensure that the proportional relationship remains unchanged, the updated threshold value is determined according to the updated base value and the proportional relationship.

[0055] The second manner is to obtain historical fluctuation data of historical radar data and current fluctuation data of the radar data. For example, historical radar data of a historical time period (for example, the past 30 days) is selected, the standard deviation of the historical radar data in this period of time is calculated, and the historical fluctuation data is obtained. The historical fluctuation data is configured to describe the data fluctuation degree of the historical radar data. The formula for calculating the historical fluctuation data can be:

[0056] wherein, σ1 represents historical fluctuation data, N represents the number of historical radar data, i represents the label of historical radar data, X i represents the i-th historical radar data, and μ1 represents the average of historical radar data.

[0057] The current fluctuation data is configured to describe the data fluctuation degree of the current fluctuation data, and the formula for calculating the current fluctuation data of the radar data can be:

[0058] wherein, σ2 represents current fluctuation data, M represents the number of current radar data, j represents the label of current radar data, X j represents the j-th current radar data, and μ2 represents the average of current radar data.

[0059] Based on the historical fluctuation data and the current fluctuation data, the fluctuation ratio is obtained. The fluctuation ratio is the ratio of the current fluctuation data to the historical fluctuation data. This ratio is configured to measure the change degree of the historical fluctuation data relative to the historical fluctuation data.

[0060] According to the fluctuation ratio, the threshold value is updated. For example, the updated threshold value = threshold value * fluctuation ratio. Of course, an adjustment coefficient can also be introduced to correct the updated threshold value.

[0061] In the implementation process of the above embodiment: by dynamically adjusting the threshold value, the adjusted threshold value can adapt to the change of the fluctuation of the radar data, more accurately reflect the real state of the radar data, and reduce the false alarm or omission caused by the fixed threshold value.

[0062] Optionally, in the embodiment of the present application, the radar data is obtained by a radar device, and the radar can be installed on a gimbal. The gimbal is a mechanical platform that can install a camera or other equipment and can rotate and tilt the radar or camera in the horizontal and vertical directions. The pointing angle of these instruments is adjusted by the gimbal so as to observe or collect data in a specific area.

[0063] After comparing the collected radar data with the base value to obtain the difference value, the method further comprises:

[0064] The position information of the point position on the scanning surface of the radar device in the process of collecting the radar data is obtained. The position information refers to the position information of the point position relative to the radar device. This process can be realized by using a digital elevation model, which will be described in detail later.

[0065] If the difference is less than the threshold value, then the camera is used to capture the point based on the position information of the point at a first capture frequency. As an implementation, the capture work can be performed in the interval of the radar data reporting; the capture work and the uploading work can be performed simultaneously. The timestamp of the captured image or video is matched with the timestamp of the radar data, and then the radar data and the image at the same time are packaged and uploaded.

[0066] If the difference is not less than the threshold value, then the camera is used to capture the point based on the position information of the point at a second capture frequency; wherein the ratio of the first data reporting frequency to the second data reporting frequency is equal to the ratio of the first capture frequency to the second capture frequency. The second data reporting frequency is higher than the first data reporting frequency, and thus the second capture frequency is higher than the first capture frequency.

[0067] As an implementation, the first capture frequency can be equal to the first data reporting frequency, and the second capture frequency can be equal to the second data reporting frequency, so that the frequency of data reporting and capturing is equal regardless of whether the difference is greater than the threshold value, and synchronous reporting of radar data and collection of images can be achieved.

[0068] In the implementation process of the above embodiment: in the process of reporting the radar data, the synchronously captured photos or videos provide intuitive evidence for the monitoring result, so that the radar data and the visual image can provide more comprehensive monitoring scene information, and the integrity of the data is ensured. And based on the comparison result of the difference and the threshold value, a suitable capture frequency is selected to automatically adjust the capture frequency and improve the safety and accuracy of detection.

[0069] Optionally, in the embodiment of the present application, the point position information scanned by the radar device in the process of collecting radar data is obtained, including: obtaining the radar position parameters of the radar device in the digital elevation model; the position parameters include at least one of longitude, latitude, elevation and zero point orientation of the radar antenna.

[0070] The radar data is mapped to the digital elevation model to obtain the point position parameters of the point on the scanning surface relative to the digital elevation model. For example, the radar scanning monitoring area is obtained, the surface deformation data is obtained, and the data is projected onto the DEM model. Each point on the scanning surface (i.e. each point in the DEM model, also known as a pixel) obtains its longitude, latitude, elevation and deformation value information. This step is configured to associate the radar data (such as deformation data) with geographic position information, facilitating subsequent analysis and processing.

[0071] The point position information of the point position relative to the radar device is determined according to the radar position parameter and the point position parameter. The point position information includes a rotation angle, a pitch angle, and / or a distance, etc. For example, for the pitch angle, the pitch angle refers to the included angle between the radar beam and the horizontal plane, which can be calculated by the difference between the pixel elevation and the radar elevation and the horizontal distance. For the straight-line distance between the radar and the pixel, the distance formula between two points in a three-dimensional space can be used. After obtaining the point position information of the point position relative to the radar device, accurate angle and focal length adjustment parameters are provided for the camera snapshot.

[0072] As an implementation, the camera can be installed on the same gimbal as the radar device, and then the camera and the radar antenna can adopt a horizontal and vertical coaxial manner, share a two-dimensional gimbal, and the zero point positions of the camera and the radar device are consistent. It can be understood that, since the camera and the radar device are installed on the same gimbal, the point position information of the point position relative to the radar device is also the point position information of the point position relative to the camera. Therefore, after obtaining the point position information, the camera can directly rotate and focus according to the calculated point position information (such as the pitch angle, the rotation angle, and the distance information), and perform a snapshot action. For example, the camera rotates in the horizontal or vertical direction according to the rotation angle in the point position information, and adjusts the focal length of the camera according to the distance information in the point position information to ensure that the captured image is clear.

[0073] In the implementation process of the above embodiment: this process combines the remote monitoring capability of the radar and the image capturing capability of the camera, and through accurate calculation and automatic control, effective monitoring of ground deformation and timely snapshot of abnormal areas are realized. And the point position information of the point position relative to the radar device is determined by the digital elevation model, which improves the accuracy of the point position information.

[0074] Optionally, in another implementation of the present application, when the radar device is installed indoors, if the camera and the radar device are installed on the same gimbal, the work of the camera indoors is affected by the wall and the window, and cannot realize effective monitoring. Therefore, the radar and the camera can be set as a split type. That is, the radar uses a separate two-dimensional gimbal, which can realize horizontal and vertical adjustment. The camera uses an outdoor rainproof dome camera, which can realize separate horizontal and vertical adjustment.

[0075] Since the camera and the radar device are not installed on the same gimbal, the zero point positions of the camera and the radar device may not be consistent. At this time, the zero point position of the camera should be adjusted to be consistent with the zero point position of the radar first, and then the step of calculating the point position information of the point position relative to the radar device is performed. The process of adjusting the zero point position of the camera to be consistent with the zero point position of the radar is described below.

[0076] The radar position parameter and the point position parameter are converted to obtain point information of the point relative to the radar device, including: if the zero position orientations of the camera and the radar device are inconsistent, the camera coordinates, the radar coordinates, the camera zero position orientation, and the radar zero position orientation are respectively obtained; wherein the camera coordinates and the radar coordinates are coordinate information in the same coordinate system.

[0077] The zero position orientation refers to the front direction of the device, a certain specific angle (such as 30 degrees east of north), or a direction relative to a certain known reference. For example, the camera zero position orientation can refer to the direction of the front of the camera, or the direction angle of the camera relative to the north. It should be noted that the standards of the camera zero position orientation and the radar zero position orientation should be consistent, for example, the direction of the front of each is taken as the zero position orientation.

[0078] The installation center points of the camera and the radar device can be accurately measured using RTK or a total station, and the geographic coordinates (longitude, latitude, and elevation) of the camera are recorded as the camera coordinates, and the geographic coordinates (longitude, latitude, and elevation) of the radar device are recorded as the radar coordinates.

[0079] According to the camera coordinates, the radar coordinates, the camera zero position orientation, and the radar zero position orientation, a transformation parameter is obtained by using a calibration algorithm; the transformation parameter is configured to adjust the camera zero position orientation and the radar zero position orientation to be consistent. The calibration algorithm is configured to align the perception spaces of the camera and the radar device to make the camera zero position orientation and the radar zero position orientation consistent. The calibration algorithm can perform steps such as spatial geometric transformation, coordinate conversion, and error correction. The transformation parameter includes a rotation matrix and / or a translation vector and other parameters.

[0080] The camera zero position orientation and the radar zero position orientation are adjusted to be consistent by using the transformation parameter. Here, the adjustment can be physical adjustment or software adjustment. Physical adjustment refers to directly adjusting the attitude of the camera or the radar device physically. Software adjustment refers to logically aligning by using the transformation parameter. For example, data preprocessing can be performed using the transformation parameter before the camera takes a picture, to simulate the state of adjusting the camera zero position orientation and the radar zero position orientation to be consistent.

[0081] In the case where the camera zero position orientation and the radar zero position orientation are consistent, the radar position parameter and the point position parameter are converted to obtain point information of the point relative to the radar device.

[0082] In the implementation process of the above embodiments: the zero point position orientation of the camera and the zero point position orientation of the radar are adjusted to be consistent through a calibration algorithm, realizing the consistency of the radar device and the camera in spatial perception, providing a data basis for subsequent point shooting, point information calculation and other tasks. A variety of camera setting modes are provided, supporting the external camera, and adopting a split type work to improve the shooting flexibility.

[0083] Optionally, in the embodiments of the present application, the method further comprises: obtaining a to-be-detected photo obtained by shooting and a scene of the to-be-detected photo; the scene of the to-be-detected photo is, for example, foreign matter intrusion, scene state identification, etc.

[0084] The to-be-detected photo is input into an abnormality recognition model corresponding to the scene to obtain an abnormality recognition result; the abnormality recognition result includes whether an abnormality occurs, the position of the abnormal event in the graph, or an abnormal scene classification. After obtaining the abnormality recognition result, the to-be-detected photo and the corresponding abnormality recognition result can be reported.

[0085] The abnormality recognition model can be a model trained from data in different scenes, or a model trained from a single audit scene.

[0086] If the abnormality recognition model is a model trained from a single scene, then each scene has a corresponding model, and when identifying the to-be-detected photo, the scene corresponding abnormality recognition model should be input to obtain the abnormality recognition result. The advantage of this is that the structure of the abnormality recognition model of each scene is relatively simple, the amount of data required for training the model and the time spent are relatively small, and the real-time performance and accuracy of the model are relatively high.

[0087] If the abnormality recognition model is a model trained from data in different scenes, then the to-be-detected photos of each scene are detected by the abnormality recognition model. The advantage of this is that the trained abnormality recognition model can learn the image features of different scenes, and when auditing the to-be-detected photo, there is no need to distinguish the scene of the to-be-detected photo, and the operation is more convenient.

[0088] Taking the case where the abnormality recognition model is a model trained from a single scene, sample images in the target scene can be obtained or collected, the sample images include positive samples (images without abnormalities) and negative samples (abnormal images), the samples are labeled, and then the samples and their corresponding labels are input into a pre-set neural network model to adjust the parameters of the neural network model, obtaining the abnormality recognition model in the target scene. The above training process is performed for each scene, and thus the abnormality recognition model corresponding to each scene is obtained. The neural network model can be a YOLO model or a CNN model.

[0089] As an implementation manner, a front-end AI algorithm and a back-end cloud platform recognition can be used in two deployment forms.

[0090] For the pre-AI automatic processing algorithm, the algorithm module is deployed in the host. After the installation of the device is completed, a large amount of image data is collected by the camera module. First, the basic scene recognition and the accumulation of the original observation data are performed, and various objects recognized from the monitoring image are distinguished (such as corner reflection, vertical rod, vegetation profile in the scene, terrain, etc.), and an abnormality recognition model is formed. Then, the image to be detected can be denoised, for example, the influence factors such as light, temperature, shadow, etc. are removed, and then the processed image is input into the model for automatic discrimination, such as vertical rod movement, corner reflection movement, animal touch, etc. Then the abnormality recognition result is sent to the detection system.

[0091] The back-end platform recognition scheme is to deploy the AI automatic processing algorithm service in the cloud platform. After the installation of the device is completed, a large amount of image sample data is collected by the camera module. The image sample data is transmitted to the cloud platform through the communication module, and the model training is performed in the cloud platform. Then the image to be detected is sent to the cloud platform for recognition to obtain the abnormality recognition result, and the abnormality recognition result returned by the cloud platform is also received.

[0092] In the implementation process of the above embodiments: through the automatic image recognition process, manual intervention can be greatly reduced, and the processing efficiency can be improved. According to the scene of the image to be detected, a suitable abnormality recognition model can be selected to ensure the professionalism and pertinence of the abnormality recognition model, thereby improving the accuracy of the recognition result.

[0093] Please refer to the structure schematic diagram of the radar data processing apparatus provided by the embodiment of the present application shown in FIG. 2; the embodiment of the present application provides a radar data processing apparatus 200, which comprises:

[0094] The difference calculation module 210 is configured to compare the collected radar data with the base value to obtain a difference value;

[0095] The data reporting module 220 is configured to: if the difference value is less than a threshold value, report the radar data according to a first data reporting frequency; if the difference value is not less than the threshold value, report the radar data according to a second data reporting frequency; and update the base value according to the base value and the threshold value, so that the difference value of the subsequently collected radar data is obtained based on the updated base value; and the second data reporting frequency is higher than the first data reporting frequency.

[0096] Optionally, in the embodiment of the present application, the radar data processing apparatus 200, the data reporting module 220 further comprises a base value updating unit configured to obtain a pre-set weight parameter after reporting the radar data according to the second data reporting frequency reaches a pre-set period or a pre-set number, and obtain the updated base value by weighted sum of the base value and the threshold value based on the weight parameter.

[0097] Optionally, in the embodiment of the present application, the radar data processing apparatus 200, the data reporting module 220 further comprises a threshold updating unit configured to obtain a proportional relationship between the threshold and the base value before updating; update the threshold based on the proportional relationship and the base value after updating; or obtain historical fluctuation data of historical radar data and current fluctuation data of the radar data; obtain a fluctuation proportion based on the historical fluctuation data and the current fluctuation data; update the threshold according to the fluctuation proportion; wherein the historical fluctuation data is configured to describe the data fluctuation degree of the historical radar data; the current fluctuation data is configured to describe the data fluctuation degree of the current fluctuation data.

[0098] Optionally, in the embodiment of the present application, the radar data processing apparatus 200, the radar data is obtained by radar equipment collection; further comprising a radar vision fusion module configured to obtain position information of a point on a scanning surface of the radar equipment in the process of collecting the radar data; if the difference is less than the threshold value; then the point is photographed by a camera based on the position information of the point according to a first photographing frequency; in the case where the difference is not less than the threshold value, the point is photographed by the camera based on the position information of the point according to a second photographing frequency; wherein the ratio of the first data reporting frequency to the second data reporting frequency is equal to the ratio of the first photographing frequency to the second photographing frequency.

[0099] Optionally, in the embodiment of the present application, the radar data processing apparatus 200, the radar vision fusion module is specifically configured to obtain a radar position parameter of the radar equipment in a digital elevation model; the position parameter comprises at least one of longitude, latitude, elevation and zero point orientation of the radar antenna; map the radar data to the digital elevation model to obtain a point position parameter of the point on the scanning surface relative to the digital elevation model; determine the point information of the point relative to the radar equipment according to the radar position parameter and the point position parameter.

[0100] Optionally, in the embodiment of the present application, the radar data processing apparatus 200, the radar and vision fusion module is further configured to: if the zero point position orientations of the camera and the radar device are inconsistent, respectively acquiring the camera coordinates, the radar coordinates, the camera zero point position orientation and the radar zero point position orientation; wherein the camera coordinates and the radar coordinates are coordinate information in the same coordinate system; obtaining a transformation parameter by using a calibration algorithm according to the camera coordinates, the radar coordinates, the camera zero point position orientation and the radar zero point position orientation; the transformation parameter is configured to adjust the camera zero point position orientation and the radar zero point position orientation to be consistent; adjusting the camera zero point position orientation and the radar zero point position orientation to be consistent by using the transformation parameter; and converting the radar position parameter and the point position parameter to obtain the point position information of the point relative to the radar device in the case that the camera zero point position orientation and the radar zero point position orientation are consistent.

[0101] Optionally, in the embodiment of the present application, the radar data processing apparatus 200 further comprises an image detection module configured to: acquire a to-be-detected photo and a scene of the to-be-detected photo; input the to-be-detected photo into an abnormality recognition model corresponding to the scene to obtain an abnormality recognition result; and report the to-be-detected photo and the corresponding abnormality recognition result.

[0102] It should be understood that the apparatus corresponds to the radar data processing method embodiments described above, and can perform each step involved in the above method embodiments. The specific functions of the apparatus can be referred to the description above, and the detailed description is appropriately omitted here to avoid repetition. The apparatus includes at least one software function module stored in the memory in the form of software or firmware or solidified in the operating system (OS) of the apparatus.

[0103] Please refer to FIG. 3 for a structural schematic diagram of an electronic device provided by an embodiment of the present application. An electronic device 300 provided by an embodiment of the present application includes a processor 310 and a memory 320. The memory 320 stores machine-readable instructions executable by the processor 310. When the machine-readable instructions are executed by the processor 310, the method described above is performed.

[0104] The components shown in FIG. 3 can be realized by hardware, software or a combination thereof. The electronic device 300 can be a physical device such as a server, a PC, etc., or a virtual device such as a virtual machine, a virtualization container, etc. Moreover, the electronic device 300 is not limited to a single device, but can also be a combination of multiple devices or a cluster of a large number of devices.

[0105] The embodiment of the present application further provides a storage medium, which stores a computer program, and the computer program is executed by a processor to perform the method.

[0106] The storage medium can be implemented by any type of volatile or nonvolatile storage devices or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk or a compact disk.

[0107] In several embodiments provided by the present application, it should be understood that the disclosed apparatus and method can also be implemented by other manners. The apparatus embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the drawings show the possible implementation architectures, functions and operations of the apparatus, method and computer program product according to the embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a part of code, which contains one or more executable instructions configured to implement the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can also occur in different order from that noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and the combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0108] In addition, each functional module in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0109] The above description is only optional implementation of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the embodiments of the present application, which should be covered within the protection scope of the embodiments of the present application. Industrial applicability

[0110] The embodiments of the present application compare the collected radar data with the base value, obtain a difference value, select a suitable reporting frequency based on the comparison result of the difference value and the threshold value, and realize automatic adjustment of the reporting frequency. For non-exceptional cases, unnecessary data transmission can be reduced, and network bandwidth and storage resources can be saved. For exceptional cases, a second data reporting frequency with a higher frequency is used for data reporting, reducing the omission of reporting emergency events, and improving the safety and accuracy of detection. Moreover, by dynamically adjusting the base value, the real state of the radar data can be more accurately reflected, reducing false positives or false negatives caused by fixed base values, and the practicality is better.

Claims

1. A method of radar data processing, characterized by, The method comprises: comparing the collected radar data with a base value to obtain a difference value; if the difference value is less than a threshold value, reporting the radar data according to a first data reporting frequency; if the difference value is not less than the threshold value, reporting the radar data according to a second data reporting frequency; and updating the base value according to the base value and the threshold value, so that the difference value of the subsequently collected radar data is obtained based on the updated base value; the second data reporting frequency is higher than the first data reporting frequency.

2. The method of claim 1, wherein, The updating of the base value according to the base value and the threshold value comprises: after the reporting of the radar data according to the second data reporting frequency reaches a preset period or a preset number, a preset weight parameter is obtained, the base value and the threshold value are weighted and summed based on the weight parameter, and the updated base value is obtained.

3. The method according to claim 1 or 2, characterized in that, After the base value is updated, the method further comprises: obtaining the proportional relationship between the threshold value and the base value before the update; updating the threshold value based on the proportional relationship and the base value after the update; or; obtaining historical fluctuation data of historical radar data and current fluctuation data of the radar data; obtaining a fluctuation ratio based on the historical fluctuation data and the current fluctuation data; updating the threshold value according to the fluctuation ratio; wherein the historical fluctuation data is configured to describe the data fluctuation degree of the historical radar data; the current fluctuation data is configured to describe the data fluctuation degree of the current fluctuation data.

4. The method according to any one of claims 1 to 3, characterized in that, The radar data is obtained by a radar device; after the comparison of the collected radar data with the base value to obtain the difference value, the method further comprises: obtaining the position information of the point on the scanning surface of the radar device during the collection of the radar data; if the difference value is less than a threshold value, the point is photographed by a camera based on the position information of the point according to a first photographing frequency; if the difference value is not less than the threshold value, the point is photographed by a camera based on the position information of the point according to a second photographing frequency; wherein the ratio of the first data reporting frequency to the second data reporting frequency is equal to the ratio of the first photographing frequency to the second photographing frequency.

5. The method of claim 4, wherein, The obtaining of the point position information of the radar device during the scanning of the radar data comprises: obtaining a radar position parameter of the radar device in a digital elevation model; the position parameter comprises at least one of longitude, latitude, elevation and zero point orientation of the radar antenna; mapping the radar data to the digital elevation model to obtain the point position parameter of the point on the scanning surface relative to the digital elevation model; determining the point position information of the point relative to the radar device according to the radar position parameter and the point position parameter.

6. The method of claim 5, wherein, The conversion of the radar position parameter and the point position parameter to obtain the point position information of the point relative to the radar device comprises: If the camera and the radar device are not in the same direction, the camera coordinates, the radar coordinates, the camera zero position orientation and the radar zero position orientation are obtained respectively; wherein the camera coordinates and the radar coordinates are coordinate information in the same coordinate system; According to the camera coordinates, the radar coordinates, the camera zero position orientation and the radar zero position orientation, a transformation parameter is obtained by using a calibration algorithm; the transformation parameter is configured to adjust the camera zero position orientation and the radar zero position orientation to be consistent; The transformation parameter is used to adjust the camera zero position orientation and the radar zero position orientation to be consistent; In the case that the camera zero position orientation and the radar zero position orientation are consistent, the radar position parameter and the point position parameter are converted to obtain the point information of the point relative to the radar device.

7. The method according to any one of claims 4 to 6, characterized in that, The method further comprises: obtaining a to-be-detected photo and a scene of the to-be-detected photo; inputting the to-be-detected photo into an abnormality recognition model corresponding to the scene to obtain an abnormality recognition result; reporting the to-be-detected photo and the corresponding abnormality recognition result.

8. A computer program product, characterised in that, comprising computer program instructions, which are executed by a processor to perform the method of any one of claims 1 to 7.

9. An electronic device, comprising: comprising: a processor and a memory, wherein the memory stores computer program instructions, and the computer program instructions are executed by the processor to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, the computer readable storage medium stores computer program instructions, and the computer program instructions are executed by a processor to perform the method of any one of claims 1 to 7.

Images