Abnormal Parking Recognition Method, Device and Electronic Equipment

Abstract

This application is applicable to the field of intelligent transportation technology, and provides an abnormal parking recognition method, device and electronic device. The abnormal parking recognition method includes: processing a first radar frame to determine a first target and a second target in the first radar frame, where the first radar frame is a radar frame obtained by a target radar detecting a target detection section, the target detection section is a detection section covered by the signal of the target radar, the first target is a target with a speed greater than a preset speed threshold, and the second target is a target with a speed not greater than the speed threshold; performing trajectory tracking on the corresponding targets according to the first target and the second target; and determining the target where an abnormal parking event exists according to the result of the trajectory tracking. Through the above method, the accuracy of the judgment result of the obtained abnormal parking event can be improved.

Description

Technical Field

[0001] This application belongs to the technical field of intelligent transportation, and particularly relates to an abnormal parking recognition method, device, electronic device, and computer-readable storage medium. Background Art

[0002] With the development of the economy, there are more and more vehicles on the road. To ensure the smooth flow of the road (such as a highway), certain sections are designated where parking is not allowed randomly.

[0003] In the existing abnormal parking recognition methods, a radar is used to detect a target vehicle to obtain the distance information of the target vehicle, and then it is determined whether an abnormal parking event occurs for the target vehicle based on the distance information. However, since the reliability is difficult to guarantee when making a judgment based on the distance information, the accuracy of the abnormal parking recognition result in the existing methods is difficult to ensure. Summary of the Invention

[0004] Embodiments of this application provide an abnormal parking recognition method, device, and electronic device, which can solve the problem that the accuracy of the abnormal parking recognition result obtained by the existing methods for abnormal parking recognition is relatively low.

[0005] In a first aspect, embodiments of this application provide an abnormal parking recognition method, including:

[0006] Processing a first radar frame to determine a first target and a second target in the first radar frame, where the first radar frame is a radar frame obtained by a target radar detecting a target detection section, the target detection section is a detection section covered by the signal of the target radar, the first target is a target with a speed greater than a preset speed threshold, and the second target is a target with a speed not greater than the speed threshold;

[0007] Performing trajectory tracking on the corresponding targets according to the first target and the second target;

[0008] Determining the targets with abnormal parking events in the target detection section according to the results of the trajectory tracking.

[0009] In a second aspect, embodiments of this application provide an abnormal parking recognition device, including:

[0010] A speed discrimination module, configured to process a first radar frame to determine a first target and a second target in the first radar frame, where the first radar frame is a radar frame obtained by a target radar detecting a target detection section, the target detection section is a detection section covered by the signal of the target radar, the first target is a target with a speed greater than a preset speed threshold, and the second target is a target with a speed not greater than the speed threshold;

[0011] A trajectory tracking module, configured to perform trajectory tracking on corresponding targets according to the first target and the second target;

[0012] An abnormal parking event determination module, configured to determine a target with an abnormal parking event in the target detection section according to the result of trajectory tracking.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in the first aspect is implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, storing a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product, which when running on an electronic device causes the electronic device to execute the method described in the first aspect above.

[0016] The beneficial effects of the embodiments of the present application compared with the prior art are as follows:

[0017] In the embodiments of the present application, since the targets with higher speeds and the targets with lower speeds are distinguished before trajectory tracking, when performing trajectory tracking subsequently, it is possible to avoid missing the trajectory tracking of the targets with lower speeds, thereby improving the accuracy of the obtained trajectory tracking results, and further improving the accuracy of determining whether there is an abnormal parking event according to the trajectory tracking results. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art.

[0019] Figure 1 is a flowchart of an abnormal parking recognition method provided by an embodiment of the present application;

[0020] Figure 2 is a schematic flowchart of how to screen new second targets provided by an embodiment of the present application;

[0021] Figure 3 is a deployment schematic diagram of an RSU and a millimeter-wave radar as a fusion device provided by an embodiment of the present application;

[0022] Figure 4 is a schematic structural diagram of an abnormal parking recognition device provided by an embodiment of the present application;

[0023] Figure 5 It is a schematic structural diagram of an electronic device provided by another embodiment of the present application. Detailed implementation manners

[0024] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system architectures, technologies, etc. are presented in order to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0025] It should be understood that when used in the specification and appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0026] It should also be understood that the term "and / or" used in the specification and appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0027] In addition, in the description of the specification and appended claims of the present application, the terms "first", "second", "third", etc. are only used for differentiating descriptions and cannot be understood as indicating or implying relative importance.

[0028] The reference to "one embodiment" or "some embodiments" etc. described in the specification of the present application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present application. Thus, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways.

[0029] Example 1:

[0030] When determining an abnormal parking event, since there are usually many noise points in the point cloud data obtained by performing one-dimensional fast Fourier transform (FFT) on the radar frames obtained from radar detection, when classifying abnormal parking events according to the features extracted from the point cloud data, the accuracy of the obtained classification results will be relatively low. After performing one-dimensional FFT on the radar frame, the distance information of the vehicle is obtained, that is, when determining an abnormal parking event based on the distance information of the vehicle, the obtained accuracy is relatively low.

[0031] To improve the accuracy of the abnormal parking recognition result, an embodiment of the present application provides an abnormal parking recognition method. In this method, first, targets with relatively high speeds and targets with relatively low speeds are distinguished, then the targets after speed discrimination are tracked, and finally, it is determined whether there is an abnormal parking event for the target according to the result of the trajectory tracking.

[0032] The abnormal parking recognition method provided by the embodiment of the present application will be described below with reference to the accompanying drawings.

[0033] Figure 1 The flowchart of an abnormal parking recognition method provided by an embodiment of the present application is shown. This abnormal parking recognition method can be applied in a radar, or in a Road Side Unit (RSU), or in other devices such as a cloud platform, roadside devices, etc. Hereinafter, taking the abnormal parking recognition method that can be applied to a cloud platform as an example, the details are as follows:

[0034] Step S11: Process the first radar frame to determine the first target and the second target in the first radar frame, where the first radar frame is a radar frame obtained by a target radar detecting a target detection section, the target detection section is a detection section covered by the signal of the target radar, the first target is a target with a speed greater than a preset speed threshold, and the second target is a target with a speed not greater than the speed threshold.

[0035] In this embodiment, multiple detection sections are pre-divided on the road according to the range that the signal of the radar can cover. Each detection section corresponds to a radar, and this radar is used to detect the vehicles on its corresponding detection section to obtain the corresponding radar frame. In some embodiments, the radar in the embodiment of the present application uses a millimeter-wave radar. Since compared with a lidar, the millimeter-wave radar has a larger measurement range, lower cost, and is not easily affected by the weather environment, that is, the weather such as cloudy days, rain, snow, and fog will not affect the detection result of the millimeter-wave radar. Therefore, using a millimeter-wave radar can ensure that the obtained radar frame is more accurate.

[0036] In this embodiment, the cloud platform obtains radar frames from the radar and processes these radar frames. Specifically, the cloud platform obtains radar frames containing discrete Analog-to-Digital Converter (ADC) samples from the radar, and performs one-dimensional FFT, two-dimensional FFT, and Constant False-Alarm Rate (CFAR) processing on the ADC samples in each radar frame. Among them, after one-dimensional FFT processing, the distance to the target can be obtained; after two-dimensional FFT processing, the speed of the target can be obtained; and after CFAR processing, a more accurate speed can be obtained. Of course, three-dimensional FFT processing can also be performed on the ADC samples in each radar frame to obtain the angle of the target. After obtaining the speed of the target, compare the speed of the target with a preset speed threshold. If it is greater than the preset speed threshold, classify the target as a first target; if it is less than or equal to the preset speed threshold, classify the target as a second target.

[0037] In some embodiments, considering that the radar has a certain installation height and installation angle compared to the ground, therefore, in order to obtain the actual horizontal distance between the vehicle and the radar, the installation height and installation angle need to be pre-configured in the radar so as to obtain more accurate radar frames.

[0038] Step S12: Perform trajectory tracking on the corresponding targets according to the above first target and the above second target.

[0039] Among them, a tracking algorithm based on Kalman filtering can be used to track the targets.

[0040] In actual situations, the driving speed of a vehicle may sometimes be fast and sometimes slow, and trajectory tracking is usually only performed on targets with relatively fast speeds. Therefore, in the embodiments of the present application, trajectory tracking is performed on both vehicles with relatively fast driving speeds (i.e., the first targets) and vehicles with relatively slow driving speeds (i.e., the second targets), which can avoid missing the trajectory tracking of some second targets.

[0041] Step S13: Determine the targets with abnormal parking events in the above target detection section according to the results of the trajectory tracking.

[0042] Among them, the results of the trajectory tracking include the Identity document (ID), position, speed, timestamp, number of trajectories, etc. of the target.

[0043] Since when a target has an abnormal parking event, the cloud platform will no longer track the target, that is, no longer obtain the trajectory corresponding to the target, therefore, it can be determined whether there is an abnormal parking event in the target detection section according to the results of the trajectory tracking.

[0044] In the embodiments of the present application, since before performing trajectory tracking, targets with relatively high speeds and targets with relatively low speeds are distinguished first, and it is easy to miss tracking targets with relatively low speeds during trajectory tracking. Therefore, when performing trajectory tracking subsequently, it is possible to avoid missing the trajectory tracking of targets with relatively low speeds, thereby improving the accuracy of the obtained trajectory tracking results, and further improving the accuracy of determining whether there is an abnormal parking event based on the trajectory tracking results.

[0045] In some embodiments, considering that the speed of a target is obtained by processing a single radar frame, and the speed obtained from a single radar frame can only reflect the speed of the target corresponding to the moment when the radar frame is collected. Therefore, in order to obtain the speed of a target over a period of time, step S12 described above includes:

[0046] A1. Determine N data frames that are temporally continuous according to the above-mentioned second target. The above-mentioned N data frames are determined according to N radar frames including the above-mentioned first radar frame, and N is an integer greater than 1.

[0047] Specifically, after performing two-dimensional FFT on the radar frame, a Range-Doppler unit is obtained. The rows in this unit are the distance dimension, and the columns are the speed dimension. Then, columns with an absolute value of speed less than or equal to a preset speed threshold are selected from the speed dimension of the Range-Doppler unit to form a low-speed Range-Doppler matrix M LowSpeed which is LowSpeed the data frame of this embodiment.

[0048] In this embodiment, the first radar frame and the (N - 1) radar frames after the first radar frame can be selected as the above-mentioned N radar frames. It is also possible to select the radar frames before the first radar frame, the first radar frame, and the radar frames after the first radar frame as the above-mentioned N radar frames, which is not limited herein.

[0049] A2. Re-determine the speed corresponding to the above-mentioned second target according to the above-mentioned N data frames.

[0050] Specifically, perform low-speed signal processing on M LowSpeed that is, for N temporally continuous M LowSpeed perform FFT in the time dimension to obtain the speeds of each target in the corresponding time period.

[0051] A3. Determine a new second target according to the re-determined speed.

[0052] Specifically, compare the re-determined speed with a preset speed threshold. If it is still not greater than the preset speed threshold, continue to classify the target as a second target, and subsequent trajectory tracking of the second target is still required. In some embodiments, the new second target can be screened out through the Clutter Map Constant False-Alarm Rate (CM-CFAR) algorithm, that is, only the targets whose energy meets certain conditions are screened out to improve the accuracy of the screening results. The speed of the latest frame in the continuous N frames of the new second target is the re-determined speed. Among them, the process of how to screen the new second target can refer to Figure 2 the schematic diagram shown. In Figure 2 , after performing a two-dimensional FFT on the radar frame, a Range-Doppler unit is obtained. Then, select the columns in the velocity dimension of the Range-Doppler unit whose absolute velocity value is less than or equal to the preset speed threshold (i.e., Figure 2 V0 in LowSpeed ) to form a low-speed Range-Doppler matrix M LowSpeed . After performing an angle dimension FFT on the M

[0053] A4. Perform trajectory tracking on the corresponding target according to the above first target and the above new second target.

[0054] During the tracking process, if the speed of the target becomes 0, for example, if the speed of the target is calculated to be 0 from 5 consecutive radar frames, then the tracking of the target is no longer performed.

[0055] In the embodiments of the present application, since the speed of the low-speed second target is reconfirmed, that is, the target that needs to be tracked is reconfirmed, it is possible to avoid missing the target that needs to be tracked and also avoid tracking the target that does not need to be tracked.

[0056] In some embodiments, in order to be able to trigger the recognition of the abnormal stop event at an appropriate time to effectively save system resources, the abnormal stop recognition method of the embodiments of the present application further includes:

[0057] B1. Determine the first vehicle quantity according to the vehicle information obtained by the first roadside unit, and the signal of the first roadside unit covers at least the entrance section of the target detection section.

[0058] In this embodiment, the signal of the RSU can cover only the near area or a larger range. The key is to cover at least the entrance section of the detection section. In this way, when a vehicle passes through the entrance of the detection section, the RSU can communicate with the on-board unit (OBU) of the vehicle to obtain the vehicle information recorded on the OBU. Among them, the vehicle information includes information such as license plate and model. When the cloud platform obtains multiple vehicle information from the RSU, it counts the number of license plates included in the multiple vehicle information, and then determines the number of vehicles passing through the detection section corresponding to the RSU according to the number of license plates.

[0059] Figure 3 Fig. shows a deployment schematic diagram of an RSU and a millimeter-wave radar as a fusion device. In Figure 3 it, the signal of the RSU covers the entrance section of the detection section, and the signal of the millimeter-wave radar covers the entire detection section.

[0060] B2. Determine the second vehicle number according to the vehicle information obtained by the second roadside unit. The signal of the second roadside unit covers at least the entrance section of the detection section downstream of the target detection section.

[0061] In this embodiment, the method for determining the second vehicle number is the same as that for determining the first vehicle number, which will not be elaborated here.

[0062] B3. Determine the number of vehicles in the target detection section according to the first vehicle number and the second vehicle number.

[0063] In this embodiment, since the first vehicle number is determined according to the vehicle information obtained by the first RSU, and the first RSU covers at least the entrance section of the target detection section, the first vehicle number is the vehicle number corresponding to the vehicle driving into the target detection section. At the same time, since the second vehicle number is determined according to the vehicle information obtained by the second RSU, and the second RSU covers at least the entrance section of the detection section downstream of the target detection section, the second vehicle number is the vehicle number corresponding to the vehicle driving out of the target detection section. That is, it can be determined whether there is a vehicle in the target detection section by judging whether the first vehicle number is greater than the second vehicle number.

[0064] The result of the above trajectory tracking includes the number of trajectories. Correspondingly, step S13 includes:

[0065] C1. Determine the number of vehicles detected by the target radar according to the number of trajectories.

[0066] Specifically, since one trajectory corresponds to one vehicle, after determining the number of trajectories, the number of vehicles detected by the target radar can be determined.

[0067] C2. If the number of vehicles in the above-mentioned target detection section is greater than the number of vehicles detected by the above-mentioned target radar, determine the target of an abnormal parking event in the above-mentioned target detection section.

[0068] When the number of vehicles in the target detection section is greater than the number of vehicles detected by the target radar, it indicates that there are vehicles with a speed of 0 in the target detection section. Therefore, when the above situation is met and then the target of an abnormal parking event is determined, the accuracy of the determined target can be improved.

[0069] In the embodiment of the present application, first count the number of vehicles in the target detection section and the number of vehicles that the radar can detect in the target detection section, then compare the two, and only when the former is greater than the latter, determine which vehicle has an abnormal parking event. Since there will be an abnormal parking event only when the number of vehicles in the target detection section is greater than the number of vehicles that the radar can detect in the target detection section, the above method can avoid wasting resources caused by making judgments when there is no need to judge abnormal parking events. At the same time, since the RSU is not easily affected by the environment, it can obtain the vehicle information carried by the OBU in various environments, thus ensuring the accuracy of the subsequent comparison result of the number of vehicles.

[0070] In some embodiments, if the number of vehicles in the above-mentioned target detection section is less than the number of vehicles detected by the above-mentioned target radar, a warning message for indicating that the above-mentioned target radar has failed is sent. Since the target radar detects the vehicles in the target detection section, the number of vehicles that the target radar can detect will not be more than the number of vehicles in the target detection section. Therefore, when the number of vehicles in the above-mentioned target detection section is less than the number of vehicles detected by the above-mentioned target radar, it indicates that the target radar has failed. At this time, sending a warning message is beneficial for the user to repair the target radar in time.

[0071] Of course, if the number of vehicles in the above-mentioned target detection section is equal to the number of vehicles detected by the above-mentioned target radar, there is no need to identify an abnormal parking event.

[0072] In some embodiments, the above step C2 includes:

[0073] C21. If the number of vehicles in the above-mentioned target detection section is greater than the number of vehicles detected by the above-mentioned target radar, determine the radar frame corresponding to the current moment in the above-mentioned target detection section to obtain a second radar frame.

[0074] C22. Obtain the above-mentioned second radar frame and a preset number of radar frames before the above-mentioned second radar frame as target sequence frames.

[0075] In this embodiment, when it is determined that the number of vehicles in the above-mentioned target detection section is greater than the number of vehicles detected by the above-mentioned target radar, it indicates that there is an abnormal parking event in the target detection section, and the vehicle with the abnormal parking event is no longer being tracked. That is, the second radar frame and the radar frames after the second radar frame usually do not contain the relevant information of the vehicle. Therefore, in order to obtain the relevant information of the vehicle, it is necessary to analyze multiple radar frames before the second radar frame.

[0076] C23. Determine vehicle running information according to the above-mentioned target sequence frames.

[0077] In some embodiments, the vehicle running information includes at least one of the following: the average speed of a single target, the average acceleration of a single target, and the average displacement of a single target (i.e., the average value of the inter-frame displacement). Specifically, if the vehicle running information includes the average speed of a single target, the average acceleration of a single target, and the average displacement of a single target, then by performing FFT processing on each target sequence frame, the speed, acceleration, and position of each target in each target sequence frame are determined. Then, the average speed and average acceleration of each target in the target sequence frame are calculated respectively according to the speed and acceleration of each target in each target sequence frame. And, the average displacement of each target in the target sequence frame is calculated according to the position of each target in each target sequence frame. For example, after determining the position of target 1 in radar frame 1 and determining the position of target 1 in radar frame 2, the displacement of target 1 between radar frame 1 and radar frame 2 can be obtained by subtracting the two positions.

[0078] In some embodiments, the above-mentioned vehicle running information includes at least one of the following item pairs: the first item pair, the second item pair, and the third item pair. Among them, the above-mentioned first item pair is the average speed of a single target and the average speed of all targets, the above-mentioned second item pair is the average acceleration of a single target and the average acceleration of all targets, and the above-mentioned third item pair is the average displacement of a single target and the average displacement of all targets.

[0079] It should be noted that the number of frames of the target sequence frame corresponding to determining the average speed of the target, the number of frames of the target sequence frame corresponding to determining the average acceleration of the target, and the number of frames of the target sequence frame corresponding to determining the average displacement of the target may be the same or different.

[0080] C24. Determine the confidence level of the target having an abnormal parking event according to the above-mentioned vehicle running information.

[0081] Among them, the confidence level of the target having an abnormal parking event is used to indicate the probability of the target having an abnormal parking event. When the confidence level corresponding to the target is higher, it indicates that the probability of the target having an abnormal parking event is higher. Conversely, it indicates that the probability of the target having an abnormal parking event is lower. In this step, the confidence level of the target having an abnormal parking event corresponding to the vehicle operation information is determined according to the vehicle operation information.

[0082] If the vehicle operation information includes at least one of the following item pairs: the first item pair, the second item pair, and the third item pair, the confidence level C of the target having an abnormal parking event can be calculated by the following method i :

[0083]

[0084] Among them, i is the ID of the target, P represents the confidence level of the trajectory corresponding to the target i, λ1, λ2, λ3, λ4 are weight coefficients, a i , v i respectively represent the average acceleration and average speed corresponding to the target i, x i and y i respectively represent the average displacement of the target i in the x direction, and the average displacement of the target i in the y direction. respectively represent the average acceleration and average speed corresponding to all targets, respectively represent the average displacement of all targets in the x direction in the target sequence frames, and the average displacement of all these targets in the y direction.

[0085] Since the vehicle operation information adds the average speed and / or average acceleration and / or average displacement of all targets, and during the vehicle's driving process, the speed (and / or average acceleration and / or average displacement) it adopts is related not only to the driver himself but also to the speed (and / or average acceleration and / or average displacement) of surrounding vehicles. Therefore, when determining the confidence level according to the vehicle operation information including item pairs later, the accuracy of the obtained confidence level can be improved.

[0086] C25. Determine M confidence levels in descending order, and determine the targets corresponding to the above M confidence levels as the targets having an abnormal parking event, where M is equal to the difference between the number of vehicles in the above target detection section and the number of vehicles detected by the above target radar.

[0087] In this embodiment, since M represents the number of vehicles having an abnormal parking event, only M confidence levels need to be determined from multiple confidence levels. And since the higher the confidence level, the higher the probability that the corresponding target has an abnormal parking event, determining the targets corresponding to the M highest confidence levels as the targets having an abnormal parking event can improve the accuracy of the obtained targets.

[0088] In some embodiments, after the above step S13, the method further includes:

[0089] D1. Obtain the vehicle information of the target with an abnormal parking event, where the vehicle information includes the license plate.

[0090] In the embodiments of the present application, after determining the target with an abnormal parking event, the vehicle information corresponding to the target can be searched. Alternatively, after the radar detects the ID of the vehicle and the RSU obtains the vehicle information, the ID of the vehicle can be bound to the vehicle information. In this way, after determining which vehicle has an abnormal parking event, the vehicle information corresponding to the vehicle can be quickly found according to the pre-bound relationship.

[0091] D2. Output an abnormal parking prompt, where the abnormal parking prompt includes the above license plate and information indicating that the vehicle corresponding to the license plate has an abnormal parking.

[0092] In the embodiments of the present application, the abnormal parking prompt can be output to a specified device so that the user can quickly know which vehicles have abnormal parking events.

[0093] In some embodiments, the abnormal parking recognition method provided by the embodiments of the present application further includes:

[0094] Determine the lane information corresponding to the vehicle with an abnormal parking event.

[0095] Correspondingly, the abnormal parking prompt in D2 above further includes the lane information corresponding to the vehicle with an abnormal parking event.

[0096] In this embodiment, the lane information corresponding to each detection section can be pre-stored. After determining the vehicle with an abnormal parking event, the lane information corresponding to the vehicle can be determined according to the position of the vehicle. Of course, if the lane information is not pre-stored, the lane information can be obtained. For example, collect the vehicle information for a period of time, count the number of times (density) of vehicles appearing in each detection section within the coverage range and the vehicle speed distribution during this period, obtain the spatial-density matrix of vehicle appearances in the detection section, then cluster the spatial-density matrix, and obtain the straight line with the highest probability of vehicle appearance in the space, which is the lane center line. Finally, obtain the lane line according to the lane center line, that is, obtain the lane information of the detection section.

[0097] In the embodiments of the present application, since the abnormal parking prompt further includes the lane information corresponding to the vehicle, the user can know the lane where the vehicle is located from the abnormal parking prompt, which is beneficial for the user to select the corresponding strategy subsequently.

[0098] It should be understood that the sequence numbers of the steps in the above embodiments do not indicate the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0099] Example 2:

[0100] Corresponding to the abnormal parking recognition method in the above embodiment, Figure 4 The structural block diagram of the abnormal parking recognition device provided by the embodiment of the present application is shown. For the sake of convenience of description, only the parts related to the embodiment of the present application are shown.

[0101] Referring to Figure 4 , the abnormal parking recognition device 4 includes: a speed discrimination module 41, a trajectory tracking module 42, and an abnormal parking event judgment module 43. Among them:

[0102] The speed discrimination module 41 is configured to process the first radar frame to determine a first target and a second target in the first radar frame. Wherein, the first radar frame is a radar frame obtained by the target radar detecting a target detection section, the target detection section is a detection section covered by the signal of the target radar, the first target is a target with a speed greater than a preset speed threshold, and the second target is a target with a speed not greater than the speed threshold.

[0103] The trajectory tracking module 42 is configured to perform trajectory tracking on the corresponding target according to the first target and the second target.

[0104] The abnormal parking event judgment module 43 is configured to determine the target with an abnormal parking event in the target detection section according to the result of the trajectory tracking.

[0105] In the embodiment of the present application, since the target with a larger speed and the target with a smaller speed are distinguished before the trajectory tracking, and it is easy to miss tracking the target with a smaller speed during the trajectory tracking, therefore, during the subsequent trajectory tracking, it is possible to avoid missing the trajectory tracking of the target with a smaller speed, thereby improving the accuracy of the obtained trajectory tracking result, and further improving the accuracy of judging whether there is an abnormal parking event according to the result of the trajectory tracking.

[0106] In some embodiments, the trajectory tracking module 42 includes:

[0107] The continuous data frame determination unit is configured to determine N data frames that are continuous in time according to the second target, and the N data frames are determined according to N radar frames including the first radar frame, and N is an integer greater than 1.

[0108] The speed re-determination unit is configured to re-determine the speed corresponding to the second target according to the N data frames.

[0109] A new second target determination unit for determining a new second target according to the re-determined speed.

[0110] A trajectory tracking unit for performing trajectory tracking on the corresponding target according to the above first target and the above new second target.

[0111] In some embodiments, the abnormal parking recognition device 4 further includes:

[0112] A first vehicle quantity determination module for determining a first vehicle quantity according to the vehicle information obtained by the first roadside unit, and the signal of the first roadside unit covers at least the entrance section of the target detection section.

[0113] A second vehicle quantity determination module for determining a second vehicle quantity according to the vehicle information obtained by the second roadside unit, and the signal of the second roadside unit covers at least the entrance section of the detection section downstream of the target detection section.

[0114] A vehicle quantity determination module for the target detection section for determining the vehicle quantity in the target detection section according to the above first vehicle quantity and the above second vehicle quantity.

[0115] The result of the above trajectory tracking includes the number of trajectories. Correspondingly, the above abnormal parking event judgment module 43 includes:

[0116] A vehicle quantity determination unit detected by radar for determining the vehicle quantity detected by the target radar according to the above number of trajectories.

[0117] A target determination unit for the abnormal parking event for determining the target of the abnormal parking event in the target detection section if the vehicle quantity in the target detection section is greater than the vehicle quantity detected by the target radar.

[0118] In some embodiments, the above target determination unit for the abnormal parking event includes:

[0119] A second radar frame determination unit for determining the radar frame corresponding to the current moment in the target detection section to obtain a second radar frame if the vehicle quantity in the target detection section is greater than the vehicle quantity detected by the target radar.

[0120] A target sequence frame acquisition unit for acquiring the above second radar frame and a preset number of radar frames before the second radar frame as target sequence frames.

[0121] A vehicle running information determination unit for determining vehicle running information according to the above target sequence frames.

[0122] A confidence determination unit, configured to determine the confidence of the occurrence of an abnormal parking event for a corresponding target according to the above vehicle operation information.

[0123] An abnormal target determination unit, configured to determine M confidences in descending order, and determine the targets corresponding to the M confidences as the targets for which an abnormal parking event has occurred, where M is equal to the difference between the number of vehicles in the above target detection section and the number of vehicles detected by the above target radar.

[0124] In some embodiments, the above vehicle operation information includes at least one of the following: the average speed of a single target, the average acceleration of a single target, and the average displacement of a single target.

[0125] In some embodiments, the above vehicle operation information includes at least one of the following item pairs: the first item pair, the second item pair, and the third item pair, where the first item pair is the average speed of a single target and the average speed of all targets, the second item pair is the average acceleration of a single target and the average acceleration of all targets, and the third item pair is the average displacement of a single target and the average displacement of all targets.

[0126] In some embodiments, the abnormal parking recognition device 4 of the embodiments of the present application further includes:

[0127] A vehicle information acquisition module, configured to acquire vehicle information of a target where an abnormal parking event occurs, and the above vehicle information includes a license plate.

[0128] An abnormal parking prompt output module, configured to output an abnormal parking prompt, and the above abnormal parking prompt includes the above license plate and information indicating that the vehicle corresponding to the license plate has an abnormal parking.

[0129] In some embodiments, the abnormal parking recognition device 4 provided by the embodiments of the present application further includes:

[0130] A lane information determination module, configured to determine lane information corresponding to a vehicle where an abnormal parking event occurs.

[0131] Correspondingly, the above abnormal parking prompt further includes lane information corresponding to the vehicle where an abnormal parking event occurs.

[0132] It should be noted that the information interaction, execution process, etc. between the above devices / units, due to being based on the same concept as the method embodiments of the present application, for their specific functions and the technical effects brought, reference can be specifically made to the method embodiment part, and details are not described herein again.

[0133] Example 3:

[0134] Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. AsFigure 5 As shown, the electronic device 5 of this embodiment includes: at least one processor 50 ( Figure 5 only one processor is shown in the figure), a memory 51, and a computer program 52 stored in the memory 51 and executable on the at least one processor 50. When the processor 50 executes the computer program 52, the steps in any of the above method embodiments are implemented.

[0135] The electronic device 5 may be a computing device such as a radar, RSU, desktop computer, notebook, palm computer, and cloud server. The electronic device may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art can understand that Figure 5 merely examples of the electronic device 5, which do not constitute a limitation on the electronic device 5, may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0136] The so-called processor 50 may be a central processing unit (CPU). The processor 50 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0137] The memory 51 may be an internal storage unit of the electronic device 5 in some embodiments, such as the hard disk or memory of the electronic device 5. The memory 51 may also be an external storage device of the electronic device 5 in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 5. Further, the memory 51 may also include both the internal storage unit and the external storage device of the electronic device 5. The memory 51 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 51 may also be used to temporarily store data that has been output or will be output.

[0138] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0139] An embodiment of this application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. When the processor executes the computer program, the steps in any of the foregoing method embodiments are implemented.

[0140] An embodiment of this application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in each of the foregoing method embodiments can be implemented.

[0141] An embodiment of this application provides a computer program product. When the computer program product runs on an electronic device, the electronic device is caused to implement the steps in each of the foregoing method embodiments when executed.

[0142] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / electronic device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0143] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0144] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0145] In the embodiments provided in this application, it should be understood that the disclosed device / network device and method can be implemented in other ways. For example, the device / network device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical, or other form.

[0146] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0147] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An abnormal parking recognition method, characterized in that, Including: Processing the first radar frame to determine a first target and a second target in the first radar frame, where the first radar frame is a radar frame obtained by a target radar detecting a target detection section, the target detection section is a detection section covered by the signal of the target radar, the first target is a target with a speed greater than a preset speed threshold, and the second target is a target with a speed not greater than the speed threshold; Performing trajectory tracking on the corresponding targets according to the first target and the second target; Determining the targets with abnormal parking events in the target detection section according to the results of the trajectory tracking; The performing trajectory tracking on the corresponding targets according to the first target and the second target includes: Determining N consecutive frame data frames in terms of time according to the second target, where the N frame data frames are determined according to N radar frames including the first radar frame, and N is an integer greater than 1; Performing low-speed signal processing on the N frame data frames to re-determine the speed corresponding to the second target; Determining a new second target according to the re-determined speed greater than 0; Performing trajectory tracking on the corresponding targets according to the first target and the new second target.

2. The abnormal parking recognition method according to claim 1, characterized in that Further including: Determining a first vehicle quantity according to the vehicle information obtained by a first roadside unit, where the signal of the first roadside unit covers at least the entrance section of the target detection section; Determining a second vehicle quantity according to the vehicle information obtained by a second roadside unit, where the signal of the second roadside unit covers at least the entrance section of the detection section downstream of the target detection section; Determining the vehicle quantity in the target detection section according to the first vehicle quantity and the second vehicle quantity; The results of the trajectory tracking include the number of trajectories. Correspondingly, the determining the targets with abnormal parking events in the target detection section according to the results of the trajectory tracking includes: Determining the vehicle quantity detected by the target radar according to the number of trajectories; If the vehicle quantity in the target detection section is greater than the vehicle quantity detected by the target radar, determining the targets with abnormal parking events in the target detection section.

3. The abnormal parking recognition method according to claim 2, wherein, The if the vehicle quantity in the target detection section is greater than the vehicle quantity detected by the target radar, determining the targets with abnormal parking events in the target detection section includes: If the vehicle quantity in the target detection section is greater than the vehicle quantity detected by the target radar, determining the radar frame corresponding to the current moment in the target detection section to obtain a second radar frame; Obtaining the second radar frame and a preset number of radar frames before the second radar frame as target sequence frames; Determining vehicle running information according to the target sequence frames; Determining the confidence level of the target having an abnormal parking event according to the vehicle running information; Determining M confidence levels in descending order and determining the targets corresponding to the M confidence levels as the targets having an abnormal parking event, where M is equal to the difference between the vehicle quantity in the target detection section and the vehicle quantity detected by the target radar.

4. The abnormal parking recognition method according to claim 3, wherein, The vehicle operation information includes at least one of the following: the average speed of a single target, the average acceleration of a single target, and the average displacement of a single target.

5. The abnormal parking recognition method according to claim 3, characterized in that The vehicle operation information includes at least one of the following item pairs: the first item pair, the second item pair, and the third item pair. Among them, the first item pair is the average speed of a single target and the average speed of all targets; the second item pair is the average acceleration of a single target and the average acceleration of all targets; the third item pair is the average displacement of a single target and the average displacement of all targets.

6. The abnormal parking recognition method according to any one of claims 1 to 5, characterized in that, After determining the target with an abnormal parking event in the target detection section according to the result of trajectory tracking, it further includes: Obtaining the vehicle information of the target with an abnormal parking event, where the vehicle information includes the license plate. Outputting an abnormal parking prompt, where the abnormal parking prompt includes the license plate and information indicating that the vehicle corresponding to the license plate has an abnormal parking.

7. An abnormal parking recognition device, characterized in that, Including: A speed discrimination module for processing the first radar frame to determine a first target and a second target in the first radar frame. The first radar frame is a radar frame obtained by the target radar detecting the target detection section, and the target detection section is the detection section covered by the signal of the target radar. The first target is a target with a speed greater than a preset speed threshold, and the second target is a target with a speed not greater than the speed threshold. A trajectory tracking module for performing trajectory tracking on the corresponding targets according to the first target and the second target. An abnormal parking event determination module for determining the target with an abnormal parking event in the target detection section according to the result of trajectory tracking. The trajectory tracking module includes: A continuous data frame determination unit for determining N consecutive data frames in time according to the second target. The N data frames are determined according to N radar frames including the first radar frame, and N is an integer greater than 1. A speed re-determination unit for performing low-speed signal processing on the N data frames to re-determine the speed corresponding to the second target. A new second target determination unit for determining a new second target according to the re-determined speed greater than 0. A trajectory tracking unit for performing trajectory tracking on the corresponding targets according to the first target and the new second target.

8. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method according to any one of claims 1 to 6.

Images