A method, device, equipment and medium for correcting the position of a bayonet device

Abstract

The present application relates to the field of traffic technology, and in particular to a method, device, equipment and medium for correcting the position of a checkpoint device. The method comprises: obtaining vehicle position information of a plurality of target vehicles corresponding to a target checkpoint device, clustering the vehicle position information of the plurality of target vehicles according to a preset number of clusters, obtaining a plurality of second vehicle position information clusters, determining a target vehicle position information cluster from the plurality of second vehicle position information clusters, and when the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target checkpoint device is greater than a preset second distance, determining the position information corresponding to the center point of the target vehicle position information cluster as the target position information corresponding to the target checkpoint device; the present invention can obtain position information that is closer to the actual position of the target checkpoint device, thereby improving the accuracy of position prediction of the target checkpoint device.

Description

Technical Field

[0001] The present invention relates to the field of traffic technology, and in particular to a method, device, equipment and medium for correcting the position of a bayonet device. Background Art

[0002] Checkpoint equipment refers to a road traffic on-site monitoring equipment that relies on specific places on the road, such as toll booths, traffic or public security checkpoints, to photograph, record and process all motor vehicles passing through the checkpoint. The equipment is used for all-weather real-time detection and recording at key public security areas such as urban roads or highway entrances and exits, toll booths, etc., and can automatically identify the license plate, color and other characteristics of vehicles passing through the intersection. In order to record the location information and movement trajectory of several vehicles passing through the checkpoint, the location information of the checkpoint equipment is usually collected and stored in advance, but there are still some checkpoint equipment where the location is not stored or the location is collected incorrectly, which affects the accurate judgment of the vehicle movement trajectory by the checkpoint equipment. Therefore, the position of the checkpoint equipment needs to be corrected. Summary of the invention

[0003] The object of the present invention is to provide a method, device, equipment and medium for correcting the position of a bayonet device, which can obtain position information closer to the actual position of a target bayonet device, thereby improving the accuracy of position prediction of the target bayonet device.

[0004] According to a first aspect of the present invention, a method for correcting the position of a bayonet device is provided, comprising the following steps:

[0005] Obtain vehicle position information of a number of target vehicles corresponding to the target checkpoint device and each target vehicle within a preset time period.

[0006] When the pre-collected position information of the target checkpoint device is obtained, the vehicle position information of several target vehicles is clustered according to a preset number of clusters to obtain a preset number of second vehicle position information clusters.

[0007] A target vehicle position information cluster is determined from the preset number of second vehicle position information clusters.

[0008] When the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target checkpoint device is greater than a preset second distance, the position information corresponding to the center point of the target vehicle position information cluster is determined as the target position information corresponding to the target checkpoint device to achieve correction of the position information of the target checkpoint device.

[0009] Further, the vehicle position information of the target vehicle is obtained by the following steps:

[0010] The target image of any target vehicle captured by the target checkpoint device and the target capture time point corresponding to the target image are obtained; the target image refers to the image of the vehicle identification of the corresponding target vehicle captured for the last time within a preset time period.

[0011] According to the target capture time point and the GPS device in the target vehicle corresponding to the target image, the vehicle position information of the target vehicle corresponding to the target image is acquired.

[0012] Further, determining a target vehicle location information cluster from the preset number of second vehicle location information clusters comprises the following steps:

[0013] According to a preset first distance, the second vehicle position information in each second vehicle position information cluster is screened to obtain a third vehicle position information cluster corresponding to each second vehicle position information cluster; the third vehicle position information in the third vehicle position information cluster refers to any second vehicle position information whose distance between the corresponding position and the position represented by the center point of the corresponding third vehicle position information cluster is not greater than the first distance.

[0014] The vehicle position information cluster priority corresponding to each third vehicle position information cluster is obtained.

[0015] The third vehicle location information cluster corresponding to the largest vehicle location information cluster priority is determined as the target vehicle location information cluster.

[0016] Furthermore, the method further comprises the following steps:

[0017] A key vehicle is determined from the plurality of target vehicles; the key vehicle refers to any target vehicle whose distance between the position represented by the target position information corresponding to the target checkpoint device is greater than a preset third distance.

[0018] When there is at least one key vehicle, a vehicle image corresponding to the key vehicle is acquired; the vehicle image corresponding to the key vehicle refers to a target image of a target vehicle corresponding to the key vehicle.

[0019] The vehicle information of the key vehicle is acquired from the vehicle image corresponding to the key vehicle.

[0020] When the vehicle information of the key vehicle is inconsistent with the vehicle information of the target vehicle corresponding to the key vehicle, the key vehicle is marked as an abnormal vehicle.

[0021] Furthermore, the vehicle information of the key vehicle refers to information including the model, brand and body color of the key vehicle obtained from the vehicle image corresponding to the key vehicle.

[0022] Furthermore, the method further comprises the following steps:

[0023] When the position information of the target checkpoint device is not acquired, the vehicle position information of the plurality of target vehicles is clustered into a first vehicle position information cluster.

[0024] The first vehicle position information corresponding to the center point of the first vehicle position information cluster is determined as the target position information corresponding to the target checkpoint device.

[0025] According to a second aspect of the present invention, a device for correcting the position of a bayonet device is provided, the device comprising:

[0026] The first acquisition module is used to acquire a plurality of target vehicles corresponding to the target checkpoint device and vehicle position information of each target vehicle within a preset time period.

[0027] The second acquisition module is used to cluster the vehicle position information of several target vehicles according to a preset number of clusters when the pre-collected position information of the target checkpoint device is acquired, and acquire a preset number of second vehicle position information clusters.

[0028] The first determining module is used to determine a target vehicle location information cluster from the preset number of second vehicle location information clusters.

[0029] The second determination module is used to determine the position information corresponding to the center point of the target vehicle position information cluster as the target position information corresponding to the target checkpoint device when the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target checkpoint device is greater than a preset second distance, so as to realize the correction of the position information of the target checkpoint device.

[0030] Furthermore, the first acquisition module includes:

[0031] The third acquisition module is used to obtain the target image of any target vehicle captured by the target checkpoint device and the target capture time point corresponding to the target image; the target image refers to the image of the vehicle identification of the corresponding target vehicle captured for the last time within a preset time period.

[0032] The fourth acquisition module is used to acquire the vehicle position information of the target vehicle corresponding to the target image according to the target capture time point and the GPS device in the target vehicle corresponding to the target image.

[0033] Furthermore, the first determining module includes:

[0034] A screening module is used to screen the second vehicle position information in each second vehicle position information cluster according to a preset first distance, and obtain a third vehicle position information cluster corresponding to each second vehicle position information cluster; the third vehicle position information in the third vehicle position information cluster refers to any second vehicle position information whose distance between the corresponding position and the position represented by the center point of the corresponding third vehicle position information cluster is not greater than the first distance.

[0035] The fifth acquisition module is used to acquire the vehicle location information cluster priority corresponding to each third vehicle location information cluster.

[0036] The third determination module is used to determine the third vehicle location information cluster corresponding to the largest vehicle location information cluster priority as the target vehicle location information cluster.

[0037] Furthermore, the device further includes an abnormality identification module, and the abnormality identification module includes:

[0038] The fourth determination module is used to determine a key vehicle from the plurality of target vehicles; the key vehicle refers to any target vehicle whose distance from the position represented by the target position information corresponding to the target checkpoint device is greater than a preset third distance.

[0039] The sixth acquisition module is used to acquire a vehicle image corresponding to the key vehicle when there is at least one key vehicle; the vehicle image corresponding to the key vehicle refers to a target image of a target vehicle corresponding to the key vehicle.

[0040] The seventh acquisition module is used to acquire the vehicle information of the key vehicle from the vehicle image corresponding to the key vehicle.

[0041] The marking module is used to mark the key vehicle as an abnormal vehicle when the vehicle information of the key vehicle is inconsistent with the vehicle information of the target vehicle corresponding to the key vehicle.

[0042] Furthermore, the vehicle information of the key vehicle refers to information including the model, brand and body color of the key vehicle obtained from the vehicle image corresponding to the key vehicle.

[0043] Furthermore, the device also includes a backup module, and the backup module includes:

[0044] The clustering module is used to cluster the vehicle position information of the plurality of target vehicles into a first vehicle position information cluster when the position information of the target checkpoint device is not obtained.

[0045] The fifth determining module is used to determine the first vehicle position information corresponding to the center point of the first vehicle position information cluster as the target position information corresponding to the target checkpoint device.

[0046] According to a third aspect of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for correcting the position of a bayonet device when executing the computer program.

[0047] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for correcting the position of a bayonet device is implemented.

[0048] Compared with the prior art, the present invention has at least the following beneficial effects:

[0049] The method of the present invention first obtains the vehicle position information of each target vehicle corresponding to the target checkpoint device within a preset time period. When the position information of the target checkpoint device collected in advance is obtained, the vehicle position information of several target vehicles is clustered into multiple clusters through clustering processing, and the target vehicle position information cluster is obtained. Then, according to the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target checkpoint device, the target position information corresponding to the target checkpoint device is determined to correct the original collected position information of the target checkpoint device. It can be seen from the above content that the present invention obtains multiple clustering centers through a clustering model, and can obtain a center point closer to the actual position of the target checkpoint device according to the clustering situation of each cluster, thereby improving the accuracy and rationality of the prediction of the position of the target checkpoint device. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 A flowchart of a method for correcting the position of a bayonet device provided in Embodiment 1 of the present invention;

[0052] Figure 2 A flowchart of step S100 provided in the first embodiment of the present invention;

[0053] Figure 3 A flowchart of step S300 provided in the first embodiment of the present invention;

[0054] Figure 4 Another flow chart of the method for correcting the position of the bayonet device provided in the first embodiment of the present invention;

[0055] Figure 5 A flowchart of the steps of identifying abnormal vehicles provided in the first embodiment of the present invention;

[0056] Figure 6 A schematic diagram of the structure of a bayonet device position correction device provided in Embodiment 2 of the present invention;

[0057] Figure 7 A schematic diagram of the structure of a first acquisition module 100 provided in Embodiment 2 of the present invention;

[0058] Figure 8 A schematic diagram of the structure of the first determination module 300 provided in the second embodiment of the present invention;

[0059] Fig. 9 A schematic diagram of the structure of a spare module in a bayonet device position correction device provided in Embodiment 2 of the present invention;

[0060] Fig.10 This is a schematic diagram of the structure of an abnormality recognition module in the bayonet device position correction device provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0062] Embodiment 1

[0063] like Figure 1 As shown, this embodiment 1 provides a method for correcting the position of a bayonet device, comprising the following steps:

[0064] S100, obtaining a number of target vehicles corresponding to the target checkpoint device within a preset time period and the vehicle position information of each target vehicle; it can be understood that: obtaining a number of target vehicles means obtaining the vehicle identifications of a number of target vehicles, for example, the license plate numbers of the target vehicles.

[0065] Specifically, the target vehicle refers to any vehicle that passes through the target checkpoint device within a preset time period, wherein the preset time period is a pre-set collection time period, and the duration may be 1 hour.

[0066] Specifically, the vehicle position information of the target vehicle refers to the latitude and longitude information of the target vehicle, wherein the latitude and longitude of the target vehicle are obtained through a GPS device in the target vehicle.

[0067] Specifically, Figure 2As shown, in step S100, the vehicle position information of the target vehicle is obtained by specifically performing the following steps:

[0068] S101, obtaining a target image of any target vehicle captured by a target checkpoint device and a target capture time point corresponding to the target image; the target image refers to an image of a vehicle identification of the corresponding target vehicle captured for the last time within a preset time period; it can be understood that: when a target checkpoint device continuously captures multiple images of the same vehicle, the image of the vehicle identification captured for the last time shall prevail, so that the time point corresponding to the image is closer to the time when the target vehicle approaches the target checkpoint device.

[0069] S102, according to the target capture time point and the GPS device in the target vehicle corresponding to the target image, the vehicle position information of the target vehicle corresponding to the target image is obtained; it can be understood as: recognizing the license plate number in the target image through the OCR character recognition model, and obtaining the GPS device in the vehicle corresponding to the license plate number.

[0070] Specifically, the vehicle position information of the target vehicle is the vehicle information obtained after the target image is identified by a target recognition vehicle model, wherein the target recognition vehicle model is an identification vehicle model trained based on a number of collected vehicle samples of different models, brands and body colors. Those skilled in the art are aware of the specific implementation process of training using any neural network model, which will not be repeated here; in addition, manual recognition can also be used to receive feedback results of manual recognition.

[0071] As described above, through the same time node, the target checkpoint device and the GPS device of the target vehicle are associated, and the location information of the target vehicle corresponding to the GPS device at the time when the target checkpoint device captures the picture is obtained, so that the location information of the target vehicle is closer to the location information of the target checkpoint device, so as to supplement or correct the location information of the target checkpoint device.

[0072] Preferably, before S100, the following steps are also included:

[0073] According to the clock correction system, the clock of the target camera device is corrected to make the clock of the target camera device consistent with the clock of the GPS; it can be understood that: the clock correction system receives the time signal from the global positioning system GPS, automatically adjusts the clock of the target camera device, or adopts a clock correction model based on NTP.

[0074] As described above, by keeping the target camera device clock consistent with the GPS clock, the GPS time on the vehicle can be obtained according to the capture time displayed by the target camera device, thereby obtaining accurate target vehicle location information to improve the correction accuracy of the target camera device.

[0075] S200, when the pre-collected position information of the target checkpoint device is obtained, the vehicle position information of several target vehicles is clustered according to a preset number of clusters to obtain a preset number of second vehicle position information clusters.

[0076] Specifically, the location information of the target checkpoint device includes the latitude and longitude information of the target checkpoint device.

[0077] Specifically, the preset number of clusters meets the following conditions:

[0078] K = roundup ((m / 10) 1 / 2 ), where K is the preset number of clusters and roundup() is the round-up function.

[0079] Specifically, the second vehicle location information cluster is a cluster obtained by clustering the vehicle location information of several target vehicles through a clustering model; it can be understood as: clustering the points corresponding to the latitude and longitude coordinates of several target vehicles, and obtaining several second key location information clusters after iteration, wherein the clustering model can adopt a k-means clustering model. Those skilled in the art are aware of the specific implementation process of the k-means clustering model, which will not be repeated here.

[0080] In the above, the number of clusters is determined by the number of captured target vehicles, so that the number of clusters increases with the increase of captured target vehicles. Therefore, based on a large number of target vehicles with different position information, multiple cluster centers are obtained after iterating the clustering model. According to the clustering situation of each cluster, it is easy to obtain a center point that is closer to the actual position of the target checkpoint device, thereby improving the accuracy of position prediction of the target checkpoint device.

[0081] S300: Determine a target vehicle location information cluster from the preset number of second vehicle location information clusters.

[0082] Specifically, Figure 3 As shown, step S300 specifically includes the following steps:

[0083] S301, according to a preset first distance, the second vehicle position information in each second vehicle position information cluster is screened to obtain a third vehicle position information cluster corresponding to each second vehicle position information cluster; the third vehicle position information in the third vehicle position information cluster refers to any second vehicle position information whose distance between the corresponding position and the position represented by the center point of the corresponding third vehicle position information cluster is not greater than the first distance.

[0084] S302: Obtain the vehicle location information cluster priority corresponding to each third vehicle location information cluster.

[0085] Specifically, the vehicle location information cluster priority corresponding to the third vehicle location information cluster meets the following conditions:

[0086] S=0.7×f-0.3×(∑ f x=1 y x ) / f, where S refers to the vehicle location information cluster priority corresponding to the third vehicle location information cluster, f is the number of third vehicle location information in the third vehicle location information cluster corresponding to S, and y x It is the distance between the position represented by the x-th third key position information in the third vehicle position information cluster corresponding to S and the position information represented by the center point of the third vehicle position information cluster corresponding to S.

[0087] S303: Determine the third vehicle location information cluster corresponding to the largest vehicle location information cluster priority as the target vehicle location information cluster.

[0088] As described above, by screening the second vehicle position information in several second vehicle position information clusters, data with large positioning drift errors can be screened out, so that the center point of each cluster after clustering iteration is more reasonable, and when obtaining the priority of each cluster, the number of sample collection in each cluster and the mean distance of the position of each target vehicle from the center point of the cluster are taken into account. The priority obtained in this way is more accurate, so that the center point of the target vehicle position information cluster is more consistent with the actual position of the target checkpoint device, thereby improving the prediction accuracy of the target checkpoint device.

[0089] S400, when the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target checkpoint device is greater than a preset second distance, the position information corresponding to the center point of the target vehicle position information cluster is determined as the target position information corresponding to the target checkpoint device, so as to realize the correction of the position information of the target checkpoint device; a technician in this field sets the second distance according to actual needs, for example, 5 meters; it can be understood that: according to the longitude and latitude coordinates corresponding to the center point of the target key position information cluster and the longitude and latitude coordinates corresponding to the position information of the target checkpoint device, the target distance D is obtained, and when D≤5 meters, it is considered that the position of the target checkpoint device is accurate and no correction is performed.

[0090] As mentioned above, when the distance between the original position of the target checkpoint device and the predicted position of the target checkpoint device is small, the initial position of the target checkpoint device is considered to be accurate, avoiding miscorrection caused by not taking into account that the target checkpoint device has a certain distance from the captured target vehicle when capturing. The position of the target checkpoint device will only be corrected when the distance between the two is large, which can improve the rationality and accuracy of the correction.

[0091] In another case, if Figure 4 As shown, the method further comprises the following steps:

[0092] S01, when the position information of the target checkpoint device is not obtained, clustering the vehicle position information of the plurality of target vehicles into a first vehicle position information cluster.

[0093] Specifically, the first vehicle location information cluster is a cluster obtained by clustering the vehicle location information of several target vehicles through a clustering model; it can be understood as: clustering the points corresponding to the longitude and latitude coordinates of several target vehicles to obtain the center point of the cluster after clustering.

[0094] Specifically, the clustering model may be a k-means clustering model, through which the vehicle location information of several target vehicles is clustered into a cluster. Those skilled in the art are aware of the specific implementation process of the k-means clustering model, which will not be described in detail here.

[0095] S02: Determine the first vehicle position information corresponding to the center point of the first vehicle position information cluster as the target position information corresponding to the target checkpoint device.

[0096] As mentioned above, when the location information of the target checkpoint device is not obtained, the center point of the cluster can be obtained by clustering the location information of several target vehicles captured within a preset time period, and the location information of the center point is used as the predicted location information of the target checkpoint device. The drift data of the GPS device during positioning is filtered out, so that the predicted location information of the target checkpoint device is more accurate.

[0097] like Figure 5 As shown, the method further comprises the following steps:

[0098] S001, determining a key vehicle from the plurality of target vehicles; the key vehicle refers to any target vehicle whose distance from a position represented by the target position information corresponding to the target checkpoint device is greater than a preset third distance.

[0099] S002, when there is at least one key vehicle, obtaining a vehicle image corresponding to the key vehicle; the vehicle image corresponding to the key vehicle refers to a target image of a target vehicle corresponding to the key vehicle.

[0100] S003: Acquire vehicle information of the key vehicle from the vehicle image corresponding to the key vehicle.

[0101] Specifically, the vehicle information of the key vehicle refers to information including the model, brand and body color of the key vehicle obtained from the vehicle image corresponding to the key vehicle.

[0102] S004, when the vehicle information of the key vehicle is inconsistent with the vehicle information of the target vehicle corresponding to the key vehicle, the key vehicle is marked as an abnormal vehicle; it can also be understood that: when the vehicle information of the key vehicle is consistent with the vehicle information of the target vehicle corresponding to the key vehicle, the recognition result of the vehicle information of the key vehicle is considered to be correct.

[0103] As mentioned above, when the intermediate distance between the vehicle position information of the target vehicle and the target position information corresponding to the target checkpoint device is large, it may be due to an error in the recognition of the license plate number of the target vehicle, resulting in the acquisition of the position information of the real vehicle corresponding to the license plate number. By comparing the target vehicle information identified in the target image with the vehicle type information corresponding to the identified license plate number, it can be known whether the license plate number is recognized incorrectly. When the information of the two is consistent, it indicates that the license plate number is recognized correctly, and it is because the position of the target vehicle has undergone a positioning offset. When the information of the two is inconsistent, it indicates that the license plate number is recognized incorrectly, thereby determining the abnormally identified vehicle, so as to correct the collected target vehicle trajectory information, and to perform subsequent purposes such as re-prediction of the checkpoint position.

[0104] This embodiment first obtains the vehicle position information of each target vehicle corresponding to the target checkpoint device within a preset time period. When the position information of the target checkpoint device collected in advance is obtained, the vehicle position information of several target vehicles is clustered into multiple clusters through clustering processing, and the target vehicle position information cluster is obtained. Then, according to the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target checkpoint device, the target position information corresponding to the target checkpoint device is determined to correct the original collected position information of the target checkpoint device. It can be seen from the above content that the present invention obtains multiple clustering centers through a clustering model, and can obtain a center point closer to the actual position of the target checkpoint device according to the clustering situation of each cluster, thereby improving the accuracy and rationality of the prediction of the position of the target checkpoint device.

[0105] In addition, in another specific embodiment, the method further comprises the following steps:

[0106] S1, obtaining a number of key vehicles corresponding to key checkpoint equipment within a preset historical time period.

[0107] The specific steps are: obtain the key vehicle identification list L={L1, L2, ..., L r , ..., L s}, where L r is the identification of the rth key vehicle passing through the key checkpoint device within the preset historical time period, r=1, 2, ..., s, s is the number of key vehicle identifications.

[0108] Specifically, the key card slot device refers to any card slot device that needs to be calibrated for clock.

[0109] Specifically, the key vehicle identification refers to a unique identification corresponding to the key vehicle, which can be understood as: the identification of the key vehicle is the license plate number of the key vehicle.

[0110] Specifically, the key vehicle refers to any vehicle that passes through a key checkpoint device within a preset historical time period.

[0111] Specifically, obtain L through the following steps r :

[0112] S11, obtaining the key image of the rth vehicle captured by the key checkpoint device within a preset historical time period; the key image refers to the image of the logo of the rth vehicle captured for the last time; it can be understood that: when the key checkpoint device continuously captures multiple images of the same vehicle, the image of the vehicle logo captured for the last time shall prevail.

[0113] S12, according to the OCR character recognition model, obtain L from the key image of the rth vehicle r .

[0114] As mentioned above, for a checkpoint device, based on its capture results, it can collect multiple vehicle identifications passing through the checkpoint device, and then obtain the number of vehicles passing through the checkpoint device in a preset historical time period and the capture time corresponding to each vehicle, so as to compare the capture time with the time of the vehicle passing through the checkpoint device obtained subsequently, providing a basis for the clock correction of the checkpoint device.

[0115] S2, obtaining several key shooting time points corresponding to the key checkpoint equipment according to the obtained several key vehicles.

[0116] The specific steps are as follows: According to L, obtain the key shooting time point list T={T1, T2, ..., T r , ..., T s}, where T r Shooting L for key bayonet equipment r time point.

[0117] S3, according to the given position information of the key checkpoint device, obtain the first passing time point corresponding to each key vehicle, wherein the first passing time point refers to the time point when the key vehicle travels to the position corresponding to the position information of the key checkpoint device.

[0118] The specific steps are: according to the location information of the key checkpoint equipment, obtain the first pass time point list T corresponding to L 0 ={T 0 1. T0 2, ..., T 0 r , ..., T 0 s}, where T 0 r It is the time point when the rth key vehicle drives to the position corresponding to the position information of the key checkpoint device.

[0119] As mentioned above, since each key vehicle must pass through the location of the key checkpoint device, and the time when the key vehicle travels to the corresponding position of the key checkpoint device should be consistent with the time when the key checkpoint device captures the key vehicle, the time when each key vehicle travels to the location can be obtained from the GPS in the vehicle based on the location information of the key checkpoint device, thereby improving the accuracy of collecting the passing time of the key vehicles.

[0120] S4, obtaining a plurality of initial time differences according to a plurality of key shooting time points corresponding to the key checkpoint devices and a first passing time point corresponding to each key vehicle.

[0121] The specific steps are as follows: According to T and T 0 , get the initial time difference list △T={△T1,△T2,……,△T r , ..., △T s}, where △T r =T 0 r -T r .

[0122] S5, obtaining a target time difference ε according to a number of initial time differences and a preset time threshold η.

[0123] In a specific embodiment, S5 includes the following steps:

[0124] S51, according to a preset time threshold η, traverse a number of initial time difference values, and screen out a number of intermediate time difference values; the intermediate time difference value refers to any initial time difference value that is not greater than the time threshold η.

[0125] Specifically, the intermediate time difference list composed of the plurality of intermediate time differences is W={W1, W2, ..., W α , ..., W β}, where W α is the αth intermediate time difference, α=1, 2,…, β, β is the number of intermediate time differences.

[0126] S52: Obtain a target time difference ε according to the plurality of intermediate time differences.

[0127] Specifically, ε meets the following conditions:

[0128] ε = (∑ β α=1 W α ) / β.

[0129] As mentioned above, by filtering out the initial time difference values ​​that are greater than the time threshold, the large error between the collected passage time and the actual passage time to the key equipment checkpoint when the vehicle positioning drifts can be reduced. Finally, by taking the average of the remaining initial time difference values, the accuracy of the difference between the obtained passage time and the capture time can be improved, thereby making the correction of the clock of the key checkpoint equipment more accurate.

[0130] S6, according to the target time difference ε, the clock of the key checkpoint device is corrected so that the position verification of the key checkpoint device is realized on the basis of the corrected clock of the key checkpoint device; it can be understood as: when the target time difference ε is 3s, 3s is added to the clock of the key checkpoint device. For example, if the clock of the key checkpoint device is 10:00, it is corrected to 10:03.

[0131] As mentioned above, on the basis of determining the target time difference, the clock of the key checkpoint device is calibrated so that it can be directly mapped to the time when the vehicle passes through the checkpoint device according to the capture time. There is no need to gradually obtain the time to pass through the checkpoint device according to the vehicle trajectory position, which saves the process and improves the accuracy of the checkpoint device's judgment on the vehicle's movement trajectory.

[0132] Embodiment 2

[0133] like Figure 6 As shown, this second embodiment provides a bayonet device position correction device, including:

[0134] The first acquisition module 100 is used to acquire several target vehicles corresponding to the target checkpoint device within a preset time period and the vehicle position information of each target vehicle; it can be understood that: acquiring several target vehicles means acquiring the vehicle identifications of several target vehicles, for example, the license plate number of the target vehicle.

[0135] Specifically, the target vehicle refers to any vehicle that passes through the target checkpoint device within a preset time period, wherein the preset time period is a pre-set collection time period, and the duration may be 1 hour.

[0136] Specifically, the vehicle position information of the target vehicle refers to the latitude and longitude information of the target vehicle, wherein the latitude and longitude of the target vehicle are obtained through a GPS device in the target vehicle.

[0137] Specifically, Figure 7 As shown, the first acquisition module 100 includes:

[0138] The third acquisition module 101 is used to obtain the target image of any target vehicle captured by the target checkpoint device and the target capture time point corresponding to the target image; the target image refers to the image of the vehicle identification of the corresponding target vehicle captured for the last time within a preset time period; it can be understood that: when the target checkpoint device continuously captures multiple images of the same vehicle, the image of the vehicle identification captured for the last time shall prevail, so that the time point corresponding to the image is closer to the time when the target vehicle approaches the target checkpoint device.

[0139] The fourth acquisition module 102 is used to obtain the vehicle position information of the target vehicle corresponding to the target image according to the target capture time point and the GPS device in the target vehicle corresponding to the target image; it can be understood as: identifying the license plate number in the target image through the OCR character recognition model, and obtaining the GPS device in the vehicle corresponding to the license plate number.

[0140] Specifically, the vehicle position information of the target vehicle is the vehicle information obtained after the target image is identified by a target recognition vehicle model, wherein the target recognition vehicle model is an identification vehicle model trained based on a number of collected vehicle samples of different models, brands and body colors. Those skilled in the art are aware of the specific implementation process of training using any neural network model, which will not be repeated here; in addition, manual recognition can also be used to receive feedback results of manual recognition.

[0141] As described above, through the same time node, the target checkpoint device and the GPS device of the target vehicle are associated, and the location information of the target vehicle corresponding to the GPS device at the time when the target checkpoint device captures the picture is obtained, so that the location information of the target vehicle is closer to the location information of the target checkpoint device, so as to supplement or correct the location information of the target checkpoint device.

[0142] Preferably, the device is also used for:

[0143] According to the clock correction system, the clock of the target camera device is corrected to make the clock of the target camera device consistent with the clock of the GPS; it can be understood that: the clock correction system receives the time signal from the global positioning system GPS, automatically adjusts the clock of the target camera device, or adopts a clock correction model based on NTP.

[0144] As described above, by keeping the target camera device clock consistent with the GPS clock, the GPS time on the vehicle can be obtained according to the capture time displayed by the target camera device, thereby obtaining accurate target vehicle location information to improve the correction accuracy of the target camera device.

[0145] The second acquisition module 200 is used to cluster the vehicle position information of several target vehicles according to a preset number of clusters when the pre-collected position information of the target checkpoint device is acquired, and acquire a preset number of second vehicle position information clusters.

[0146] Specifically, the location information of the target checkpoint device includes the latitude and longitude information of the target checkpoint device.

[0147] Specifically, the preset number of clusters meets the following conditions:

[0148] K = roundup ((m / 10) 1 / 2 ), where K is the preset number of clusters and roundup() is the round-up function.

[0149] Specifically, the second vehicle location information cluster is a cluster obtained by clustering the vehicle location information of several target vehicles through a clustering model; it can be understood as: clustering the points corresponding to the latitude and longitude coordinates of several target vehicles, and obtaining several second key location information clusters after iteration, wherein the clustering model can adopt a k-means clustering model. Those skilled in the art are aware of the specific implementation process of the k-means clustering model, which will not be repeated here.

[0150] In the above, the number of clusters is determined by the number of captured target vehicles, so that the number of clusters increases with the increase of captured target vehicles. Therefore, based on a large number of target vehicles with different position information, multiple cluster centers are obtained after iterating the clustering model. According to the clustering situation of each cluster, it is easy to obtain a center point that is closer to the actual position of the target checkpoint device, thereby improving the accuracy of position prediction of the target checkpoint device.

[0151] The first determination module 300 is used to determine a target vehicle location information cluster from the preset number of second vehicle location information clusters.

[0152] Specifically, Figure 8 As shown, the first determination module 300 includes:

[0153] The screening module 301 is used to screen the second vehicle position information in each second vehicle position information cluster according to a preset first distance, and obtain a third vehicle position information cluster corresponding to each second vehicle position information cluster; the third vehicle position information in the third vehicle position information cluster refers to any second vehicle position information whose distance between the corresponding position and the position represented by the center point of the corresponding third vehicle position information cluster is not greater than the first distance.

[0154] The fifth acquisition module 302 is used to acquire the vehicle location information cluster priority corresponding to each third vehicle location information cluster.

[0155] Specifically, the vehicle location information cluster priority corresponding to the third vehicle location information cluster meets the following conditions:

[0156] S=0.7×f-0.3×(∑ f x=1 y x ) / f, where S refers to the vehicle location information cluster priority corresponding to the third vehicle location information cluster, f is the number of third vehicle location information in the third vehicle location information cluster corresponding to S, and y x It is the distance between the position represented by the x-th third key position information in the third vehicle position information cluster corresponding to S and the position information represented by the center point of the third vehicle position information cluster corresponding to S.

[0157] The third determination module 303 is used to determine the third vehicle location information cluster corresponding to the largest vehicle location information cluster priority as the target vehicle location information cluster.

[0158] As described above, by screening the second vehicle position information in several second vehicle position information clusters, data with large positioning drift errors can be screened out, so that the center point of each cluster after clustering iteration is more reasonable, and when obtaining the priority of each cluster, the number of sample collection in each cluster and the mean distance of the position of each target vehicle from the center point of the cluster are taken into account. The priority obtained in this way is more accurate, so that the center point of the target vehicle position information cluster is more consistent with the actual position of the target checkpoint device, thereby improving the prediction accuracy of the target checkpoint device.

[0159] The second determination module 400 is used to determine the position information corresponding to the center point of the target vehicle position information cluster as the target position information corresponding to the target checkpoint device when the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target checkpoint device is greater than a preset second distance, so as to realize the correction of the position information of the target checkpoint device; the technical personnel in this field set the second distance according to actual needs, for example, 5 meters; it can be understood that: according to the longitude and latitude coordinates corresponding to the center point of the target key position information cluster and the longitude and latitude coordinates corresponding to the position information of the target checkpoint device, the target distance D is obtained, and when D≤5 meters, it is considered that the position of the target checkpoint device is accurate and no correction is performed.

[0160] As mentioned above, when the distance between the original position of the target checkpoint device and the predicted position of the target checkpoint device is small, the initial position of the target checkpoint device is considered to be accurate, avoiding miscorrection caused by not taking into account that the target checkpoint device has a certain distance from the captured target vehicle when capturing. The position of the target checkpoint device will only be corrected when the distance between the two is large, which can improve the rationality and accuracy of the correction.

[0161] The device also includes a backup module, such as Fig. 9 As shown, the standby module includes:

[0162] The clustering module 01 is used to cluster the vehicle position information of the plurality of target vehicles into a first vehicle position information cluster when the position information of the target checkpoint device is not obtained.

[0163] Specifically, the first vehicle location information cluster is a cluster obtained by clustering the vehicle location information of several target vehicles through a clustering model; it can be understood as: clustering the points corresponding to the longitude and latitude coordinates of several target vehicles to obtain the center point of the cluster after clustering.

[0164] Specifically, the clustering model may be a k-means clustering model, through which the vehicle location information of several target vehicles is clustered into a cluster. Those skilled in the art are aware of the specific implementation process of the k-means clustering model, which will not be described in detail here.

[0165] The fifth determining module 02 is used to determine the first vehicle position information corresponding to the center point of the first vehicle position information cluster as the target position information corresponding to the target checkpoint device.

[0166] As mentioned above, when the location information of the target checkpoint device is not obtained, the center point of the cluster can be obtained by clustering the location information of several target vehicles captured within a preset time period, and the location information of the center point is used as the predicted location information of the target checkpoint device. The drift data of the GPS device during positioning is filtered out, so that the predicted location information of the target checkpoint device is more accurate.

[0167] The device also includes an abnormality identification module, such as Fig.10 As shown, the abnormality identification module includes:

[0168] The fourth determination module 001 is used to determine a key vehicle from the plurality of target vehicles; the key vehicle refers to any target vehicle whose distance from the position represented by the target position information corresponding to the target checkpoint device is greater than a preset third distance.

[0169] The sixth acquisition module 002 is used to acquire a vehicle image corresponding to the key vehicle when there is at least one key vehicle; the vehicle image corresponding to the key vehicle refers to a target image of a target vehicle corresponding to the key vehicle.

[0170] The seventh acquisition module 003 is used to acquire the vehicle information of the key vehicle from the vehicle image corresponding to the key vehicle.

[0171] The marking module 004 is used to mark the key vehicle as an abnormal vehicle when the vehicle information of the key vehicle is inconsistent with the vehicle information of the target vehicle corresponding to the key vehicle; it can also be understood that: when the vehicle information of the key vehicle is consistent with the vehicle information of the target vehicle corresponding to the key vehicle, the recognition result of the vehicle information of the key vehicle is considered to be correct.

[0172] As mentioned above, when the intermediate distance between the vehicle position information of the target vehicle and the target position information corresponding to the target checkpoint device is large, it may be due to an error in the recognition of the license plate number of the target vehicle, resulting in the acquisition of the position information of the real vehicle corresponding to the license plate number. By comparing the target vehicle information identified in the target image with the vehicle type information corresponding to the identified license plate number, it can be known whether the license plate number is recognized incorrectly. When the information of the two is consistent, it indicates that the license plate number is recognized correctly, and it is because the position of the target vehicle has undergone a positioning offset. When the information of the two is inconsistent, it indicates that the license plate number is recognized incorrectly, thereby determining the abnormally identified vehicle, so as to correct the collected target vehicle trajectory information, and to perform subsequent purposes such as re-prediction of the checkpoint position.

[0173] This embodiment first obtains the vehicle position information of each target vehicle corresponding to the target checkpoint device within a preset time period. When the position information of the target checkpoint device collected in advance is obtained, the vehicle position information of several target vehicles is clustered into multiple clusters through clustering processing, and the target vehicle position information cluster is obtained. Then, according to the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target checkpoint device, the target position information corresponding to the target checkpoint device is determined to correct the original collected position information of the target checkpoint device. It can be seen from the above content that the present invention obtains multiple clustering centers through a clustering model, and can obtain a center point closer to the actual position of the target checkpoint device according to the clustering situation of each cluster, thereby improving the accuracy and rationality of the prediction of the position of the target checkpoint device.

[0174] In addition, in another specific embodiment, the device is also used to: obtain a number of key vehicles corresponding to key checkpoint equipment within a preset historical time period.

[0175] The specific steps are: obtain the key vehicle identification list L={L1, L2, ..., L r , ..., L s}, where L r is the identification of the rth key vehicle passing through the key checkpoint device within the preset historical time period, r=1, 2, ..., s, s is the number of key vehicle identifications.

[0176] Specifically, the key card slot device refers to any card slot device that needs to be calibrated for clock.

[0177] Specifically, the key vehicle identification refers to a unique identification corresponding to the key vehicle, which can be understood as: the identification of the key vehicle is the license plate number of the key vehicle.

[0178] Specifically, the key vehicle refers to any vehicle that passes through a key checkpoint device within a preset historical time period.

[0179] Specifically, obtain L through the following steps r :

[0180] Obtain a key image of the r-th vehicle captured by the key checkpoint device within a preset historical time period; the key image refers to the image of the logo of the r-th vehicle captured for the last time; it can be understood that: when the key checkpoint device continuously captures multiple images of the same vehicle, the image of the vehicle logo captured for the last time shall prevail.

[0181] According to the OCR character recognition model, L is obtained from the key image of the rth vehicle. r .

[0182] As mentioned above, for a checkpoint device, based on its capture results, it can collect multiple vehicle identifications passing through the checkpoint device, and then obtain the number of vehicles passing through the checkpoint device within a preset historical time period and the capture time corresponding to each vehicle, so as to compare the capture time with the time of the vehicle passing through the checkpoint device obtained subsequently, providing a basis for the clock correction of the checkpoint device.

[0183] The device is also used to obtain a number of key shooting time points corresponding to key checkpoint equipment according to the obtained number of key vehicles.

[0184] The specific steps are as follows: According to L, obtain the key shooting time point list T={T1, T2, ..., T r , ..., T s}, where T r Shooting L for key bayonet equipment r time point.

[0185] The device is also used to: obtain the first passing time point corresponding to each key vehicle based on the given position information of the key checkpoint device, wherein the first passing time point refers to the time point when the key vehicle travels to the position corresponding to the position information of the key checkpoint device.

[0186] The specific steps are: according to the location information of the key checkpoint equipment, obtain the first pass time point list T corresponding to L 0 ={T 0 1. T 0 2, ..., T 0r , ..., T 0 s}, where T 0 r It is the time point when the rth key vehicle drives to the position corresponding to the position information of the key checkpoint device.

[0187] As mentioned above, since each key vehicle must pass through the location of the key checkpoint device, and the time when the key vehicle travels to the corresponding position of the key checkpoint device should be consistent with the time when the key checkpoint device captures the key vehicle, the time when each key vehicle travels to the location can be obtained from the GPS in the vehicle based on the location information of the key checkpoint device, thereby improving the accuracy of collecting the passing time of the key vehicles.

[0188] The device is also used to obtain a plurality of initial time difference values ​​according to a plurality of key shooting time points corresponding to the key checkpoint equipment and a first passing time point corresponding to each key vehicle.

[0189] The specific steps are as follows: According to T and T 0 , get the initial time difference list △T={△T1,△T2,……,△T r , ..., △T s}, where △T r =T 0 r -T r .

[0190] The device is also used to obtain a target time difference ε according to a plurality of initial time differences and a preset time threshold η.

[0191] In a specific embodiment, the target time difference ε is obtained by the following steps:

[0192] According to the preset time threshold η, several initial time difference values ​​are traversed and several intermediate time difference values ​​are screened; the intermediate time difference value refers to any initial time difference value that is not greater than the time threshold η.

[0193] Specifically, the intermediate time difference list composed of the plurality of intermediate time differences is W={W1, W2, ..., W α , ..., W β}, where W α is the αth intermediate time difference, α=1, 2,…, β, β is the number of intermediate time differences.

[0194] According to the several intermediate time differences, a target time difference ε is obtained.

[0195] Specifically, ε meets the following conditions:

[0196] ε = (∑ β α=1 W α ) / β.

[0197] As mentioned above, by filtering out the initial time difference values ​​that are greater than the time threshold, the large error between the collected passage time and the actual passage time to the key equipment checkpoint when the vehicle positioning drifts can be reduced. Finally, by taking the average of the remaining initial time difference values, the accuracy of the difference between the obtained passage time and the capture time can be improved, thereby making the correction of the clock of the key checkpoint equipment more accurate.

[0198] The device is also used to: correct the clock of the key checkpoint device according to the target time difference ε, so that the position verification of the key checkpoint device can be achieved based on the corrected clock of the key checkpoint device; it can be understood that: when the target time difference ε is 3s, 3s is added to the clock of the key checkpoint device. For example, if the clock of the key checkpoint device is 10:00, it is corrected to 10:03.

[0199] As mentioned above, on the basis of determining the target time difference, the clock of the key checkpoint device is calibrated so that it can be directly mapped to the time when the vehicle passes through the checkpoint device according to the capture time. There is no need to gradually obtain the time to pass through the checkpoint device according to the vehicle trajectory position, which saves the process and improves the accuracy of the checkpoint device's judgment on the vehicle's movement trajectory.

[0200] Embodiment 3

[0201] This embodiment 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 following steps are implemented:

[0202] Obtain vehicle position information of a number of target vehicles corresponding to the target checkpoint device and each target vehicle within a preset time period.

[0203] When the pre-collected position information of the target checkpoint device is obtained, the vehicle position information of several target vehicles is clustered according to a preset number of clusters to obtain a preset number of second vehicle position information clusters.

[0204] A target vehicle position information cluster is determined from the preset number of second vehicle position information clusters.

[0205] When the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target checkpoint device is greater than a preset second distance, the position information corresponding to the center point of the target vehicle position information cluster is determined as the target position information corresponding to the target checkpoint device to achieve correction of the position information of the target checkpoint device.

[0206] Embodiment 4

[0207] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0208] Obtain vehicle position information of a number of target vehicles corresponding to the target checkpoint device and each target vehicle within a preset time period.

[0209] When the pre-collected position information of the target checkpoint device is obtained, the vehicle position information of several target vehicles is clustered according to a preset number of clusters to obtain a preset number of second vehicle position information clusters.

[0210] A target vehicle position information cluster is determined from the preset number of second vehicle position information clusters.

[0211] When the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target checkpoint device is greater than a preset second distance, the position information corresponding to the center point of the target vehicle position information cluster is determined as the target position information corresponding to the target checkpoint device to achieve correction of the position information of the target checkpoint device.

[0212] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0213] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, 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.

[0214] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A method for correcting the position of a bayonet device, characterized in that: The following steps are involved: Obtaining a number of target vehicles corresponding to the target checkpoint device and vehicle position information of each target vehicle within a preset time period; When the pre-collected position information of the target checkpoint device is obtained, the vehicle position information of the plurality of target vehicles is clustered according to a preset number of clusters to obtain a preset number of second vehicle position information clusters; Determine a target vehicle position information cluster from the preset number of second vehicle position information clusters; When the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target checkpoint device is greater than a preset second distance, the position information corresponding to the center point of the target vehicle position information cluster is determined as the target position information corresponding to the target checkpoint device, so as to realize the correction of the position information of the target checkpoint device; Wherein, determining the target vehicle location information cluster from the preset number of second vehicle location information clusters comprises the following steps: According to a preset first distance, the second vehicle position information in each second vehicle position information cluster is screened to obtain a third vehicle position information cluster corresponding to each second vehicle position information cluster; the third vehicle position information in the third vehicle position information cluster refers to any second vehicle position information whose distance between the corresponding position and the position represented by the center point of the corresponding third vehicle position information cluster is not greater than the first distance; Obtain the vehicle location information cluster priority corresponding to each third vehicle location information cluster; wherein the vehicle location information cluster priority corresponding to the third vehicle location information cluster meets the following conditions: S=0.7×f-0.3×(∑ f x=1 y x ) / f, S refers to the vehicle position information cluster priority corresponding to the third vehicle position information cluster, f is the number of third vehicle position information in the third vehicle position information cluster corresponding to S, y x is the distance between the position represented by the x-th third key position information in the third vehicle position information cluster corresponding to S and the position information represented by the center point of the third vehicle position information cluster corresponding to S; The third vehicle location information cluster corresponding to the largest vehicle location information cluster priority is determined as the target vehicle location information cluster.

2. The method for correcting the position of the bayonet device according to claim 1, characterized in that: The vehicle position information of the target vehicle is obtained by the following steps: Obtain a target image of any target vehicle captured by the target camera device and a target capture time point corresponding to the target image; the target image refers to an image of the vehicle identification of the corresponding target vehicle captured for the last time within a preset time period; According to the target capture time point and the GPS device in the target vehicle corresponding to the target image, the vehicle position information of the target vehicle corresponding to the target image is acquired.

3. The method for correcting the position of the bayonet device according to claim 2, characterized in that: The method further comprises the following steps: Determine a key vehicle from the plurality of target vehicles; the key vehicle refers to any target vehicle whose distance from the position represented by the target position information corresponding to the target checkpoint device is greater than a preset third distance; When there is at least one key vehicle, a vehicle image corresponding to the key vehicle is acquired; the vehicle image corresponding to the key vehicle refers to a target image of a target vehicle corresponding to the key vehicle; Acquiring vehicle information of the key vehicle from a vehicle image corresponding to the key vehicle; When the vehicle information of the key vehicle is inconsistent with the vehicle information of the target vehicle corresponding to the key vehicle, the key vehicle is marked as an abnormal vehicle.

4. The method for correcting the position of the bayonet device according to claim 3, characterized in that: The vehicle information of the key vehicle refers to information obtained from the vehicle image corresponding to the key vehicle, including the model, brand and body color of the key vehicle.

5. The method for correcting the position of the bayonet device according to claim 1, characterized in that: The method further comprises the following steps: When the location information of the target checkpoint device is not obtained, clustering the vehicle location information of the plurality of target vehicles into a first vehicle location information cluster; The first vehicle position information corresponding to the center point of the first vehicle position information cluster is determined as the target position information corresponding to the target checkpoint device.

6. A bayonet device position correction device, characterized in that: The device comprises: A first acquisition module is used to acquire a number of target vehicles corresponding to the target checkpoint device and vehicle position information of each target vehicle within a preset time period; A second acquisition module is used to cluster the vehicle position information of several target vehicles according to a preset number of clusters when the position information of the target checkpoint device collected in advance is acquired, and acquire a preset number of second vehicle position information clusters; A first determination module, used to determine a target vehicle position information cluster from the preset number of second vehicle position information clusters; A second determination module is used to determine the position information corresponding to the center point of the target vehicle position information cluster as the target position information corresponding to the target bayonet device when the distance between the position represented by the center point of the target vehicle position information cluster and the position represented by the position information of the target bayonet device is greater than a preset second distance, so as to realize the correction of the position information of the target bayonet device; Wherein, the first determining module includes: A screening module, for screening the second vehicle position information in each second vehicle position information cluster according to a preset first distance, and obtaining a third vehicle position information cluster corresponding to each second vehicle position information cluster; the third vehicle position information in the third vehicle position information cluster refers to any second vehicle position information whose distance between the corresponding position and the position represented by the center point of the corresponding third vehicle position information cluster is not greater than the first distance; The fifth acquisition module is used to obtain the vehicle location information cluster priority corresponding to each third vehicle location information cluster; wherein the vehicle location information cluster priority corresponding to the third vehicle location information cluster meets the following conditions: S=0.7×f-0.3×(∑ f x=1 y x ) / f, S refers to the vehicle position information cluster priority corresponding to the third vehicle position information cluster, f is the number of third vehicle position information in the third vehicle position information cluster corresponding to S, y x is the distance between the position represented by the x-th third key position information in the third vehicle position information cluster corresponding to S and the position information represented by the center point of the third vehicle position information cluster corresponding to S; The third determination module is used to determine the third vehicle location information cluster corresponding to the largest vehicle location information cluster priority as the target vehicle location information cluster.

7. The bayonet device position correction device according to claim 6, characterized in that: The first acquisition module includes: The third acquisition module is used to acquire a target image of any target vehicle captured by the target checkpoint device and a target capture time point corresponding to the target image; the target image refers to an image of the vehicle identification of the corresponding target vehicle captured for the last time within a preset time period; The fourth acquisition module is used to acquire the vehicle position information of the target vehicle corresponding to the target image according to the target capture time point and the GPS device in the target vehicle corresponding to the target image.

8. The bayonet device position correction device according to claim 7, characterized in that: The device also includes an abnormality identification module, and the abnormality identification module includes: A fourth determination module is used to determine a key vehicle from the plurality of target vehicles; the key vehicle refers to any target vehicle whose distance from the position represented by the target position information corresponding to the target checkpoint device is greater than a preset third distance; A sixth acquisition module is used to acquire a vehicle image corresponding to the key vehicle when there is at least one key vehicle; the vehicle image corresponding to the key vehicle refers to a target image of a target vehicle corresponding to the key vehicle; a seventh acquisition module, configured to acquire vehicle information of the key vehicle from a vehicle image corresponding to the key vehicle; The marking module is used to mark the key vehicle as an abnormal vehicle when the vehicle information of the key vehicle is inconsistent with the vehicle information of the target vehicle corresponding to the key vehicle.

9. The bayonet device position correction device according to claim 8, characterized in that: The vehicle information of the key vehicle refers to information obtained from the vehicle image corresponding to the key vehicle, including the model, brand and body color of the key vehicle.

10. The bayonet device position correction device according to claim 6, characterized in that: The device also includes a backup module, which includes: A clustering module, for clustering the vehicle position information of the plurality of target vehicles into a first vehicle position information cluster when the position information of the target checkpoint device is not obtained; The fifth determining module is used to determine the first vehicle position information corresponding to the center point of the first vehicle position information cluster as the target position information corresponding to the target checkpoint device.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for correcting the position of the bayonet device according to any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for correcting the position of a bayonet device according to any one of claims 1 to 5 is implemented.

Images