CN115830882A - Abnormal parking recognition method and device and electronic equipment - Google Patents
Abnormal parking recognition method and device and electronic equipment Download PDFInfo
- Publication number
- CN115830882A CN115830882A CN202211378508.6A CN202211378508A CN115830882A CN 115830882 A CN115830882 A CN 115830882A CN 202211378508 A CN202211378508 A CN 202211378508A CN 115830882 A CN115830882 A CN 115830882A
- Authority
- CN
- China
- Prior art keywords
- target
- radar
- abnormal parking
- determining
- vehicles
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The application is suitable for the technical field of intelligent traffic, and provides an abnormal parking identification method, an abnormal parking identification device and electronic equipment, wherein the abnormal parking identification method comprises the following steps: processing a first radar frame, and determining a first target and a second target in the first radar frame, wherein 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 a 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; tracking the corresponding target according to the first target and the second target; and determining the target with the abnormal parking event according to the track tracking result. By the method, the accuracy of the judgment result of the abnormal parking event can be improved.
Description
Technical Field
The application belongs to the technical field of intelligent traffic, and particularly relates to an abnormal parking identification method and device, electronic equipment and a computer-readable storage medium.
Background
With the development of economy, vehicles on the highway are more and more. In order to ensure the smoothness of a road (such as an expressway), certain road sections can be defined and can not be stopped randomly.
In the conventional abnormal parking recognition method, a target vehicle is detected by a radar to obtain distance information of the target vehicle, and whether an abnormal parking event occurs in the target vehicle is judged according to the distance information. However, when the judgment is performed according to the distance information, the reliability is difficult to guarantee, so that the accuracy of the abnormal parking recognition result is difficult to guarantee by the conventional method.
Disclosure of Invention
The embodiment of the application provides an abnormal parking recognition method, an abnormal parking recognition device and electronic equipment, and can solve the problem that when the existing method is used for recognizing abnormal parking, the accuracy of an obtained abnormal parking recognition result is low.
In a first aspect, an embodiment of the present application provides an abnormal parking identification method, including:
processing a first radar frame, and determining a first target and a second target in the first radar frame, wherein 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 a 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;
tracking a corresponding target according to the first target and the second target;
and determining the target with the abnormal parking event in the target detection road section according to the result of the track tracking.
In a second aspect, an embodiment of the present application provides an abnormal parking recognition apparatus, including:
the speed distinguishing module is used for processing a first radar frame and determining a first target and a second target in the first radar frame, wherein 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 a 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;
the track tracking module is used for tracking the corresponding target according to the first target and the second target;
and the abnormal parking event judgment module is used for determining the target with the abnormal parking event in the target detection road section according to the track tracking result.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method according to the first aspect when executing the computer program.
In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the method according to the first aspect.
In a fifth aspect, embodiments of the present application provide a computer program product, which, when run on an electronic device, causes the electronic device to perform the method of the first aspect.
Compared with the prior art, the embodiment of the application has the advantages that:
in the embodiment of the application, the target with the higher speed and the target with the lower speed are distinguished before track tracking is carried out, so that track tracking on the target with the lower speed can be avoided being omitted during follow-up track tracking, the accuracy of the obtained track tracking result can be improved, and the accuracy of judging whether an abnormal parking event exists according to the track tracking result is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the embodiments or the description of the prior art will be briefly described below.
Fig. 1 is a flowchart of an abnormal parking recognition method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of how to filter a new second object according to an embodiment of the present application;
fig. 3 is a schematic deployment diagram of an RSU and a millimeter wave radar as a fusion device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an abnormal parking recognition device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to another embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Furthermore, in the description of the present application and the appended claims, the terms "first," "second," "third," and the like are used for distinguishing between descriptions and not necessarily for describing or implying relative importance.
Reference throughout this specification to "one embodiment" or "some embodiments," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," or the like, in various places throughout this specification are not necessarily all referring to the same embodiment, but rather "one or more but not all embodiments" unless specifically stated otherwise.
The first embodiment is as follows:
when abnormal parking event is judged, because point cloud data obtained by performing one-dimensional Fast Fourier Transform (FFT) on a radar frame obtained by radar detection generally has many noise points, when abnormal parking event classification is performed according to features extracted from the point cloud data, the accuracy of the obtained classification result is low. The distance information of the vehicle is obtained after the one-dimensional FFT is carried out on the radar frame, namely, when the abnormal parking event is judged according to the distance information of the vehicle, the obtained accuracy is low.
In order to improve the accuracy of an abnormal parking identification result, the embodiment of the application provides an abnormal parking identification method. According to the method, a target with a high speed and a target with a low speed are distinguished, then the track tracking is carried out on the targets with the distinguished speeds, and finally whether an abnormal parking event exists in the targets or not is determined according to the track tracking result.
The following describes an abnormal parking recognition method provided in an embodiment of the present application with reference to the drawings.
Fig. 1 shows a flowchart of an abnormal parking recognition method provided in an embodiment of the present application, where the abnormal parking recognition method may be applied to a radar, a Road Side Unit (RSU), and other devices, such as a cloud platform and a Road Side device, and the following description takes the application of the abnormal parking recognition method to the cloud platform as an example, and details are as follows:
step S11, processing a first radar frame, and determining 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 a signal of the target radar, the first target is a target whose speed is greater than a preset speed threshold, and the second target is a target whose speed is not greater than the speed threshold.
In this embodiment, a plurality of detection sections are divided on a road in advance according to a range that can be covered by a signal of a radar, each detection section corresponds to one radar, and the radar is used for detecting a vehicle on the corresponding detection section to obtain a corresponding radar frame. In some embodiments, the radar of the embodiments of the present application employs a millimeter wave radar. Because compare with laser radar, millimeter wave radar's measuring range is bigger, the cost is lower, and millimeter wave radar is difficult to receive the influence of weather environment, and the weather of cloudy day, sleet fog also can not influence millimeter wave radar's testing result promptly, consequently, adopts the millimeter wave radar can guarantee that its radar frame of acquireing is more accurate.
In this embodiment, the cloud platform acquires a radar frame from the radar and processes the radar frame. Specifically, the cloud platform acquires radar frames including 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. After one-dimensional FFT processing, the distance of the target can be obtained, after two-dimensional FFT processing, the speed of the target can be obtained, and after CFAR processing, more accurate speed can be obtained. Of course, the ADC samples in each radar frame may also be subjected to three-dimensional FFT processing to obtain the angle of the target. After the speed of the target is obtained, the speed of the target is compared with a preset speed threshold, if the speed of the target is greater than the preset speed threshold, the target is classified as a first target, and if the speed of the target is less than or equal to the preset speed threshold, the target is classified as a second target.
In some embodiments, considering that the radar has a certain installation height and installation angle compared with the ground, in order to obtain an actual horizontal distance between the vehicle and the radar, the installation height and installation angle need to be configured in the radar in advance so as to obtain a more accurate radar frame.
And S12, tracking the corresponding target according to the first target and the second target.
Wherein, a tracking algorithm based on Kalman filtering can be adopted to track the target.
In an actual situation, the driving speed of the vehicle may be sometimes fast and sometimes slow, and only the fast target is usually tracked during the track tracking, so in the embodiment of the present application, track tracking is performed on both the fast vehicle (i.e. the first target) and the slow vehicle (i.e. the second target), which can avoid missing track tracking on some second targets.
And S13, determining a target with an abnormal parking event in the target detection road section according to the track tracking result.
The track tracking result includes an Identity (ID) of the target, a position, a speed, a timestamp, a track number, and the like.
When the abnormal parking event exists in the target, the cloud platform does not track the target any more, namely, the track corresponding to the target is not obtained any more, so that whether the abnormal parking event exists in the target detection road section or not can be judged according to the track tracking result.
In the embodiment of the application, the target with high speed and the target with low speed are distinguished firstly before the track tracking is carried out, and the target with low speed is easy to miss during the track tracking, so that the track tracking of the target with low speed can be avoided during the follow-up track tracking, the accuracy of the obtained track tracking result can be improved, and the accuracy of judging whether an abnormal parking event exists according to the track tracking result is improved.
In some embodiments, considering that the speed of the target is obtained by processing a single radar frame, and the speed obtained from the single radar frame can only reflect the speed of the target corresponding to the time when the radar frame is acquired, so that the step S12 includes, in order to obtain the speed of the target in a period of time:
and A1, determining N continuous frame data frames according to the second target, wherein 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.
Specifically, after two-dimensional FFT is carried out on a radar frame, a Range-Doppler unit is obtained, a row distance dimension and a column velocity dimension are arranged in the Range-Doppler unit, and then columns with velocity absolute values smaller than or equal to a preset velocity threshold value are selected from the velocity dimensions of the Range-Doppler unit to form a Range-Doppler matrix M with low velocity LowSpeed The M is LowSpeed Namely, the data frame of the embodiment.
In this embodiment, the first radar frame and (N-1) radar frames following the first radar frame may be selected as the N-frame radar frames. The radar frame before the first radar frame, and the radar frame after the first radar frame may also be selected as the N-frame radar frame, which is not limited herein.
And A2, re-determining the speed corresponding to the second target according to the N frame data frames.
Specifically, for M LowSpeed For low-speed signal processing, i.e. for N frames M which are successive in time LowSpeed And performing FFT in a time dimension to obtain the speed of each target in a corresponding time period.
And A3, determining a new second target according to the redetermined speed.
Specifically, the redetermined speed is compared with a preset speed threshold, if the redetermined speed is still not greater than the preset speed threshold, the target is continuously divided into a second target, and the second target still needs to be tracked subsequently. In some embodiments, a new second target may be screened out through a Clutter Map- (pixel Map Constant False-Alarm Rate, CM-CFAR) algorithm, that is, only targets with energy meeting a certain condition are screened out, so as to improve accuracy of a screening result, where a speed of a latest frame in consecutive N frames of the new second target is a redetermined speed. The flow of how to filter the new second target may refer to the schematic diagram shown in fig. 2. In fig. 2, after performing two-dimensional FFT on a radar frame, a Range-Doppler cell is obtained, and then a column with a velocity absolute value less than or equal to a predetermined velocity threshold (i.e., V0 in fig. 2) is selected from the velocity dimension of the Range-Doppler cell to form a Range-Doppler matrix M with a low velocity LowSpeed To the M LowSpeed And after the angle dimension FFT, selecting data with the angle meeting the requirement to perform the time dimension FFT, and finally screening out a new second target through a CM-CFAR algorithm.
And A4, tracking the corresponding target according to the first target and the new second target.
In the tracking process, if the velocity of the target becomes 0, for example, if the velocity of the target calculated from 5 consecutive radar frames becomes 0, the target is not tracked any more.
In the embodiment of the present application, since the speed of the low-speed second target is reconfirmed, that is, the target that needs to be subjected to trajectory tracking is reconfirmed, it is possible to avoid missing the target that needs to be subjected to trajectory tracking, and it is also possible to avoid performing trajectory tracking on the target that does not need to be subjected to trajectory tracking.
In some embodiments, in order to trigger the identification of the abnormal parking event at a suitable time, so as to effectively save resources of the system, the abnormal parking identification method in an embodiment of the present application further includes:
b1, determining a first vehicle quantity according to vehicle information obtained by a first road side unit, wherein the signal of the first road side unit at least covers the entrance section of the target detection section.
In this embodiment, the RSU signal may cover only the near zone, or may cover a larger range, and the key is to cover at least the entrance section of the detection section. In this way, when the vehicle passes through the entrance of the detection link, the RSU can communicate with an On Board Unit (OBU) of the vehicle, and acquire vehicle information described in the OBU. The vehicle information comprises information such as license plates and models, when the cloud platform acquires a plurality of pieces of vehicle information from the RSU, the number of the license plates included in the plurality of pieces of vehicle information is counted, and then the number of the vehicles passing through the detection road section corresponding to the RSU is determined according to the number of the license plates.
Fig. 3 shows a deployment schematic diagram of an RSU and a millimeter-wave radar as a fusion device, in fig. 3, a signal of the RSU covers an entrance section of a detection road section, and a signal of the millimeter-wave radar covers the entire detection road section.
And B2, determining a second vehicle quantity according to the vehicle information obtained by a second road side unit, wherein the signal of the second road side unit at least covers the entrance section of the detection road section at the downstream of the target detection road section.
In this embodiment, the method for determining the second number of vehicles is the same as the method for determining the first number of vehicles, and details are not repeated here.
And B3, determining the number of vehicles in the target detection section according to the first number of vehicles and the second number of vehicles.
In this embodiment, since the first number of vehicles 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 number of vehicles is the number of vehicles corresponding to the vehicles entering the target detection section. Meanwhile, since the second number of vehicles is determined based on 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 number of vehicles is the number of vehicles corresponding to vehicles that exit from the target detection section. That is, whether any vehicle is in the target detection section may be indicated by determining whether the first number of vehicles is greater than the second number of vehicles.
The result of the trajectory tracking includes the number of trajectories, and correspondingly, the step S13 includes:
and C1, determining the number of vehicles detected by the target radar according to the number of the tracks.
Specifically, since one trajectory corresponds to one vehicle, the number of vehicles detected by the target radar can be determined after the number of trajectories is determined.
And C2, if the number of the vehicles in the target detection section is larger than that of the vehicles detected by the target radar, determining that the target of the abnormal parking event exists in the target detection section.
When the number of vehicles on the target detection road section is larger than that of vehicles detected by the target radar, the vehicles with the speed of 0 exist on the target detection road section, so that the target with the abnormal parking event is determined when the conditions are met, and the accuracy of the determined target can be improved.
In the embodiment of the application, the number of vehicles of the vehicle with the target detection road section and the number of vehicles of the vehicle which can be detected by the radar in the target detection road section are counted firstly, then the two are compared, and when the former is larger than the latter, the abnormal parking event of the vehicle is judged. Because the abnormal parking event only exists when the number of vehicles on the target detection road section is larger than the number of vehicles which can be detected by the radar on the target detection road section, the method can avoid resource waste caused by judgment when the abnormal parking event is not needed. Meanwhile, the RSU is not easily influenced by the environment, so that the RSU can acquire the vehicle information carried by the RSU from the OBU under various environments, and the accuracy of the comparison result of the number of subsequent vehicles is guaranteed.
In some embodiments, if the number of vehicles in the target detection section is less than the number of vehicles detected by the target radar, a warning message indicating that the target radar is faulty is issued. The target radar detects the vehicles on the target detection road section, so that the number of the vehicles which can be detected by the target radar is not more than the number of the vehicles on the target detection road section, when the number of the vehicles on the target detection road section is less than the number of the vehicles detected by the target radar, the target radar is indicated to have a fault, and at the moment, the warning information is sent out, so that a user can maintain the target radar in time.
Of course, if the number of vehicles on the target detection section is equal to the number of vehicles detected by the target radar, the abnormal parking event does not need to be identified.
In some embodiments, the step C2 includes:
and C21, if the number of the vehicles in the target detection road section is larger than that of the vehicles detected by the target radar, determining a radar frame corresponding to the current moment in the target detection road section to obtain a second radar frame.
And C22, acquiring the second radar frame and a preset number of radar frames before the second radar frame as target sequence frames.
In this embodiment, when it is determined that the number of vehicles on the target detection section is greater than the number of vehicles detected by the target radar, it indicates that there is an abnormal parking event on the target detection section, and the vehicles having the abnormal parking event are no longer tracked, that is, the second radar frame and the radar frames after the second radar frame do not generally include the relevant information of the vehicle, so that in order to obtain the relevant information of the vehicle, it is necessary to analyze a plurality of radar frames before the second radar frame.
And C23, determining vehicle running information according to the target sequence frame.
In some embodiments, the vehicle operation information includes at least one of: the average velocity of a single object, the average acceleration of a single object, and the average displacement of a single object (i.e., the average of the displacements between frames). Specifically, if the vehicle operation information includes an average speed of a single target, an average acceleration of a single target, and an average displacement of a single target, the speed, the acceleration, and the position of each target in each target sequence frame are determined by performing FFT processing on each target sequence frame, the average speed and the average acceleration of each target in each target sequence frame are calculated according to the speed and the acceleration of each target in each target sequence frame, and the average displacement of each target in each target sequence frame is calculated according to the position of each target in each target sequence frame, for example, after the position of the target 1 in the radar frame 1 is determined and the position of the target 1 in the radar frame 2 is determined, the displacements of the target 1 in the radar frame 1 and the radar frame 2 can be obtained by subtracting the two positions.
In some embodiments, the vehicle operation information includes at least one of the following pairs: the first term pair is the average speed of a single target and the average speed of all targets, the second term pair is the average acceleration of a single target and the average acceleration of all targets, and the third term pair is the average displacement of a single target and the average displacement of all targets.
It should be noted that the number of frames of the target sequence frame corresponding to the average velocity of the determined target, the number of frames of the target sequence frame corresponding to the average acceleration of the determined target, and the number of frames of the target sequence frame corresponding to the average displacement of the determined target may be the same or different.
And C24, determining the confidence level of the target abnormal parking event according to the vehicle running information.
The confidence degree of the target with the abnormal parking event is used for indicating the probability of the target with the abnormal parking event, when the confidence degree corresponding to the target is higher, the probability of the target with the abnormal parking event is higher, and otherwise, the probability of the target with the abnormal parking event is lower. In this step, the confidence level of the occurrence of the abnormal parking event of the target corresponding to the vehicle operation information is determined according to the vehicle operation information.
If the vehicle operation information includes at least one of the following pairs: the first term pair, the second term pair and the third term pair can calculate the confidence coefficient C of the target abnormal parking event in the following way i ：
Wherein i is the ID of the target, P represents the confidence of the track corresponding to the target i, and lambda 1 、λ 2 、λ 3 、λ 4 As a weight coefficient, a i 、v i Respectively representing the average acceleration and average velocity, x, of the object i i And y i Respectively, the average displacement of the target i in the x direction, and the average displacement of the target i in the y direction.
Respectively representing the average acceleration and the average velocity corresponding to all the objects,
respectively representing all targets in the x direction in the target sequence frameAnd, the average displacement of all targets in the y-direction.
Since the vehicle running information adds the average speed and/or average acceleration and/or average displacement of all the targets, and the speed (and/or average acceleration and/or average displacement) adopted by the vehicle during running is related to the speed (and/or average acceleration and/or average displacement) of the surrounding vehicles in addition to the driver, the accuracy of the obtained confidence level can be improved when the confidence level is determined according to the vehicle running information comprising the term pair.
And C25, determining M confidence degrees according to the sequence from high to low, and determining that the target corresponding to the M confidence degrees is the target with the abnormal parking event, wherein M is equal to the difference between the number of the vehicles on the target detection road section and the number of the vehicles detected by the target radar.
In this embodiment, M represents the number of vehicles having an abnormal parking event, and therefore, M confidence levels may be determined from a plurality of confidence levels. Since the higher the confidence is, the higher the probability that the target corresponding to the target has the abnormal parking event is, the accuracy of the target obtained by determining the target corresponding to the M highest confidences as the target having the abnormal parking event can be improved.
In some embodiments, after step S13, the method further includes:
and D1, acquiring the vehicle information of the target with the abnormal parking event, wherein the vehicle information comprises a license plate.
In the embodiment of the application, after the target with the abnormal parking event is determined, the vehicle information corresponding to the target can be searched. The method can also be used for binding the ID of the vehicle with the vehicle information after the radar detects the ID of the vehicle and the RSU obtains the vehicle information, so that the vehicle information corresponding to the vehicle can be quickly found out directly according to the pre-binding relationship after the vehicle with the abnormal parking event is judged.
And D2, outputting an abnormal parking prompt, wherein the abnormal parking prompt comprises the license plate and information for indicating that the vehicle corresponding to the license plate has abnormal parking.
In the embodiment of the application, the abnormal parking prompt can be output to the specified equipment, so that a user can quickly know which vehicles have the abnormal parking event.
In some embodiments, the method for identifying an abnormal parking provided by the embodiment of the present application further includes:
and determining the lane information corresponding to the vehicle with the abnormal parking event.
Correspondingly, the abnormal parking guidance of D2 further includes lane information corresponding to the vehicle having the abnormal parking event.
In this embodiment, the lane information corresponding to each detected road segment may be stored in advance, and after the vehicle having the abnormal parking event is determined, the lane information corresponding to the vehicle may be determined according to the position of the vehicle. Of course, if the lane information is not stored in advance, the lane information may be duplicated. For example, vehicle information of a period of time is collected, the number of times (density) of vehicles appearing on each detected road section in a coverage range and vehicle speed distribution in the period of time are counted to obtain a space-density matrix where the vehicles appear on the detected road section, the space-density matrix is clustered to obtain a straight line with the highest probability of the vehicles appearing in the space, namely a lane center line, and finally a lane line is obtained according to the lane center line to obtain lane information of the detected road section.
In the embodiment of the application, the abnormal parking prompt further comprises lane information corresponding to the vehicle, so that the user can know the lane where the vehicle is located from the abnormal parking prompt, and the user can select the corresponding strategy subsequently.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Example two:
fig. 4 shows a block diagram of the abnormal parking recognition apparatus according to the embodiment of the present application, and for convenience of explanation, only the parts related to the embodiment of the present application are shown.
Referring to fig. 4, the abnormal parking recognition device 4 includes: a speed distinguishing module 41, a trajectory tracking module 42 and an abnormal parking event judging module 43. Wherein:
a speed distinguishing module 41, configured to process a first radar frame, and 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 a signal of the target radar, the first target is a target whose speed is greater than a preset speed threshold, and the second target is a target whose speed is not greater than the speed threshold.
And a track tracking module 42, configured to track a corresponding target according to the first target and the second target.
And an abnormal parking event determining module 43, configured to determine, according to a result of the trajectory tracking, a target in the target detection road segment where the abnormal parking event exists.
In the embodiment of the application, the target with the higher speed and the target with the lower speed are distinguished firstly before the track tracking is carried out, and the target with the lower speed is easily missed during the track tracking, so that the track tracking of the target with the lower speed can be avoided during the follow-up track tracking, the accuracy of the obtained track tracking result can be improved, and the accuracy of judging whether an abnormal parking event exists according to the track tracking result is improved.
In some embodiments, trajectory tracking module 42 includes:
a continuous data frame determination unit, configured to determine N frame data frames that are continuous in 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.
And a speed re-determining unit, configured to re-determine a speed corresponding to the second target according to the N frame data frames.
A new second target determination unit for determining a new second target based on the re-determined speed.
And the track tracking unit is used for tracking the corresponding target according to the first target and the new second target.
In some embodiments, the abnormal parking recognition device 4 further includes:
and the first vehicle quantity determining module is used for determining the first vehicle quantity according to the vehicle information obtained by the first road side unit, and the signal of the first road side unit at least covers the entrance section of the target detection road section.
And the second vehicle quantity determining module is used for determining a second vehicle quantity according to the vehicle information obtained by a second road side unit, and the signal of the second road side unit at least covers the entrance section of the detection road section at the downstream of the target detection road section.
And the vehicle number determining module of the target detection section is used for determining the number of the vehicles on the target detection section according to the first vehicle number and the second vehicle number.
The track tracking result includes the number of tracks, and correspondingly, the abnormal parking event determining module 43 includes:
and the radar detected vehicle number determining unit is used for determining the number of the vehicles detected by the target radar according to the track number.
And the target determining unit of the abnormal parking event is used for determining the target of the abnormal parking event in the target detection road section if the number of the vehicles in the target detection road section is larger than that of the vehicles detected by the target radar.
In some embodiments, the target determination unit for an abnormal parking event includes:
and the second radar frame determining unit is used for determining a radar frame corresponding to the current moment in the target detection road section to obtain a second radar frame if the number of vehicles in the target detection road section is greater than that of the vehicles detected by the target radar.
And the target sequence frame acquisition unit is used for acquiring the second radar frame and a preset number of radar frames before the second radar frame as target sequence frames.
And the vehicle running information determining unit is used for determining the vehicle running information according to the target sequence frame.
And the confidence coefficient determining unit is used for determining the confidence coefficient of the abnormal parking event of the corresponding target according to the vehicle running information.
And the abnormal target determining unit is used for determining M confidence degrees in a descending order and determining the target corresponding to the M confidence degrees as the target with the abnormal parking event, wherein M is equal to the difference between the number of the vehicles on the target detection section and the number of the vehicles detected by the target radar.
In some embodiments, the vehicle operation information includes at least one of: average velocity of a single object, average acceleration of a single object, and average displacement of a single object.
In some embodiments, the vehicle operation information includes at least one of the following pairs: the first term pair is the average speed of a single target and the average speed of all targets, the second term pair is the average acceleration of a single target and the average acceleration of all targets, and the third term pair is the average displacement of a single target and the average displacement of all targets.
In some embodiments, the abnormal parking recognition device 4 of the embodiment of the present application further includes:
the vehicle information acquisition module is used for acquiring vehicle information of a target with an abnormal parking event, wherein the vehicle information comprises a license plate.
And the abnormal parking prompt output module is used for outputting an abnormal parking prompt, wherein the abnormal parking prompt comprises the license plate and information for indicating that the vehicle corresponding to the license plate has abnormal parking.
In some embodiments, the abnormal parking recognition device 4 provided in the embodiments of the present application further includes:
and the lane information determining module is used for determining the lane information corresponding to the vehicle with the abnormal parking event.
Correspondingly, the abnormal parking prompt also comprises lane information corresponding to the vehicle with the abnormal parking event.
It should be noted that, for the information interaction, execution process, and other contents between the above-mentioned devices/units, the specific functions and technical effects thereof are based on the same concept as those of the embodiment of the method of the present application, and specific reference may be made to the part of the embodiment of the method, which is not described herein again.
Example three:
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 5, the electronic apparatus 5 of this embodiment includes: at least one processor 50 (only one processor is shown in fig. 5), a memory 51, and a computer program 52 stored in the memory 51 and executable on the at least one processor 50, the steps of any of the various method embodiments described above being implemented when the computer program 52 is executed by the processor 50.
The electronic device 5 may be a radar, an RSU, a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The electronic device may include, but is not limited to, a processor 50, a memory 51. Those skilled in the art will appreciate that fig. 5 is merely an example of the electronic device 5, and does not constitute a limitation of the electronic device 5, and may include more or less components than those shown, or combine some of the components, or different components, such as an input-output device, a network access device, etc.
The Processor 50 may be a Central Processing Unit (CPU), and the Processor 50 may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 51 may in some embodiments be an internal storage unit of the electronic device 5, such as a hard disk or a 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 memory Card (Flash Card), and the like, which are provided on the electronic device 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the electronic device 5. The memory 51 is used for storing an operating system, an application program, a BootLoader (BootLoader), data, and other programs, such as program codes of the computer program. The memory 51 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
An embodiment of the present application further provides a network device, where the network device includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, the processor implementing the steps of any of the various method embodiments described above when executing the computer program.
The embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the steps in the above-mentioned method embodiments.
The embodiments of the present application provide a computer program product, which when running on an electronic device, enables the electronic device to implement the steps in the above method embodiments when executed.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium and can implement the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing apparatus/electronic device, a recording medium, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Such as a usb-disk, a removable hard disk, a magnetic or optical disk, etc. In certain jurisdictions, computer-readable media may not be an electrical carrier signal or a telecommunications signal in accordance with legislative and patent practice.
In the above embodiments, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described or recited in any embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/network device and method may be implemented in other ways. For example, the above-described apparatus/network device embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. An abnormal parking recognition method, comprising:
processing a first radar frame, and determining a first target and a second target in the first radar frame, wherein 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 a 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;
tracking a corresponding target according to the first target and the second target;
and determining the target with the abnormal parking event in the target detection road section according to the result of the track tracking.
2. The method for recognizing abnormal parking according to claim 1, wherein the tracking a corresponding target according to the first target and the second target in the first radar frame comprises:
determining N frame data frames which are continuous in time according to the second target, wherein the N frame data frames are determined according to N radar frames including the first radar frame, and N is an integer larger than 1;
re-determining the speed corresponding to the second target according to the N frame data frames;
determining a new second target based on the re-determined speed;
and tracking the corresponding target according to the first target and the new second target.
3. The abnormal parking recognition method of claim 1, further comprising:
determining the number of first vehicles according to vehicle information obtained by a first road side unit, wherein signals of the first road side unit at least cover an entrance section of the target detection road section;
determining a second vehicle quantity according to vehicle information obtained by a second road side unit, wherein the signal of the second road side unit at least covers an entrance section of a detection road section at the downstream of the target detection road section;
determining the number of vehicles on the target detection section according to the first number of vehicles and the second number of vehicles;
correspondingly, the determining the target with the abnormal parking event in the target detection section according to the result of the track tracking includes:
determining the number of vehicles detected by the target radar according to the number of tracks;
and if the number of the vehicles on the target detection road section is greater than that of the vehicles detected by the target radar, determining that the target of the abnormal parking event exists in the target detection road section.
4. The method for identifying abnormal parking according to claim 3, wherein the determining that the target of the abnormal parking event exists in the target detection section if the number of vehicles on the target detection section is greater than the number of vehicles detected by the target radar comprises:
if the number of vehicles in the target detection road section is larger than that of vehicles detected by the target radar, determining a radar frame corresponding to the current moment in the target detection road section to obtain a second radar frame;
acquiring the second radar frame and a preset number of radar frames before the second radar frame as target sequence frames;
determining vehicle operation information according to the target sequence frame;
determining the confidence coefficient of the target abnormal parking event according to the vehicle running information;
and determining M confidence coefficients according to the sequence from high to low, and determining that the target corresponding to the M confidence coefficients is the target with the abnormal parking event, wherein M is equal to the difference between the number of vehicles on the target detection road section and the number of vehicles detected by the target radar.
5. The abnormal parking recognition method according to claim 4, wherein the vehicle operation information includes at least one of: average velocity of a single object, average acceleration of a single object, and average displacement of a single object.
6. The abnormal parking recognition method according to claim 4, wherein the vehicle operation information includes at least one of the following pairs: the system comprises a first term pair, a second term pair and a third term pair, wherein the first term pair is the average speed of a single target and the average speed of all targets, the second term pair is the average acceleration of the single target and the average acceleration of all targets, and the third term pair is the average displacement of the single target and the average displacement of all targets.
7. The abnormal parking recognition method according to any one of claims 1 to 6, further comprising, after determining that the target of the abnormal parking event exists in the target detection section according to the result of the trajectory tracking:
acquiring vehicle information of a target with an abnormal parking event, wherein the vehicle information comprises a license plate;
and outputting an abnormal parking prompt, wherein the abnormal parking prompt comprises the license plate and information for indicating that the vehicle corresponding to the license plate has abnormal parking.
8. An abnormal parking recognition device, comprising:
the speed distinguishing module is used for processing a first radar frame and determining a first target and a second target in the first radar frame, wherein 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 a 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;
the track tracking module is used for tracking the corresponding target according to the first target and the second target;
and the abnormal parking event judgment module is used for determining the target with the abnormal parking event in the target detection road section according to the track tracking result.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211378508.6A CN115830882A (en) | 2022-11-04 | 2022-11-04 | Abnormal parking recognition method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211378508.6A CN115830882A (en) | 2022-11-04 | 2022-11-04 | Abnormal parking recognition method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115830882A true CN115830882A (en) | 2023-03-21 |
Family
ID=85526679
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211378508.6A Pending CN115830882A (en) | 2022-11-04 | 2022-11-04 | Abnormal parking recognition method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115830882A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118311578A (en) * | 2024-04-16 | 2024-07-09 | 河北省交通规划设计研究院有限公司 | All-weather traffic event detection method based on millimeter wave radar |
-
2022
- 2022-11-04 CN CN202211378508.6A patent/CN115830882A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118311578A (en) * | 2024-04-16 | 2024-07-09 | 河北省交通规划设计研究院有限公司 | All-weather traffic event detection method based on millimeter wave radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5530447A (en) | Blind-zone target discrimination method and system for road vehicle radar | |
| CN108859952B (en) | Vehicle lane change early warning method and device and radar | |
| JP7037672B2 (en) | How to recognize static radar targets with automotive radar sensors | |
| CN112233416A (en) | Traffic flow detection method and device | |
| CN109932702A (en) | Banister control method and banister radar | |
| CN113378751A (en) | Traffic target identification method based on DBSCAN algorithm | |
| CN113787997B (en) | Emergency braking control method, electronic device, and storage medium | |
| CN115830882A (en) | Abnormal parking recognition method and device and electronic equipment | |
| EP0699924B1 (en) | Vehicle obstruction discrimination system | |
| CN114694060A (en) | Road shed object detection method, electronic equipment and storage medium | |
| CN118072554A (en) | Visual induction-based zebra crossing pedestrian safety control method and device | |
| CN116935631A (en) | Abnormal traffic situation detection method, device and system based on radar fusion | |
| CN115966084A (en) | Holographic intersection millimeter wave radar data processing method and device and computer equipment | |
| CN115482672B (en) | Method, device, terminal equipment and storage medium for detecting vehicle reverse running | |
| CN114895274A (en) | Guardrail identification method | |
| CN112014822A (en) | Vehicle-mounted radar measurement data identification method and device, medium and electronic device | |
| CN113589288A (en) | Target screening method, device and equipment based on millimeter wave radar and storage medium | |
| CN113687358A (en) | Target object identification method and device, electronic equipment and storage medium | |
| CN113687348B (en) | Pedestrian recognition method and device based on tracking micro Doppler graph | |
| CN115100844B (en) | Emergency lane occupation behavior identification system, method and terminal equipment | |
| CN111880160B (en) | Man-vehicle identification method and system based on radar | |
| CN113050056B (en) | Radar working environment identification method and device and terminal equipment | |
| CN117538842A (en) | Tunnel omnidirectional wide-area millimeter wave radar sensing method and related equipment | |
| CN115909758B (en) | Laser radar-based vehicle detection method, device, equipment and storage medium | |
| CN114940181A (en) | Vehicle lane change prediction method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |