A method, device, system and storage medium for detecting intentional fare evasion by vehicles

Abstract

The present invention provides a method, device, system and storage medium for detecting intentional fare evasion by vehicles, including: obtaining vehicle information of a target vehicle and a first vehicle, wherein the first vehicle is the preceding vehicle of the target vehicle in the driving direction, and the vehicle information includes at least one of image information, position information and time information; extracting target vehicle features based on the obtained vehicle information of the target vehicle and the first vehicle; inputting the target vehicle features into a pre-trained intentional fare evasion detection machine learning model, and the detection machine learning model determines whether the target vehicle has intentional fare evasion behavior. This method can effectively distinguish between vehicles that do not intend to evade fees and vehicles that do intend to evade fees, and take corresponding measures against vehicles that do intend to evade fees in a timely manner.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent transportation technology, and in particular relates to a method, device, system and storage medium for detecting intentional toll evasion by vehicles. Background Art

[0002] As the number of motor vehicles in my country continues to increase, the traditional manual toll collection model can no longer meet the current requirements for fast passage. More and more car owners choose the Electronic Toll Collection (ETC) lane on the highway to pay for quick passage. In urban traffic, smart parking lots have also launched unattended parking fee collection models in combination with various payment platforms to improve traffic efficiency and save labor costs.

[0003] Whether it is high-speed ETC or smart parking lot, they are all unmanned toll lanes. During operation, there are often vehicles passing through without paying tolls. These vehicles are all toll-evading vehicles. However, among the toll-evading vehicles, some vehicles evade tolls due to system abnormalities or other non-subjective factors; other vehicles deliberately evade tolls by taking advantage of loopholes in the toll collection system.

[0004] However, based on the unpaid fee records, vehicles that evade fees unintentionally and vehicles that evade fees intentionally can only be judged as the same type of evading vehicles, and it is impossible to distinguish between vehicles that evade fees unintentionally and vehicles that evade fees intentionally. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, system and storage medium for detecting intentional toll evasion by vehicles, which can solve the problem of being unable to distinguish between vehicles that intentionally evade tolls and vehicles that do not intend to evade tolls.

[0006] In a first aspect, an embodiment of the present invention provides a method for detecting intentional fare evasion by a vehicle, comprising:

[0007] Obtain vehicle information of a target vehicle and a first vehicle, wherein the first vehicle is the preceding vehicle of the target vehicle along the driving direction; extract target vehicle features based on the acquired vehicle information of the target vehicle and the first vehicle; input the target vehicle features into a pre-trained intentional fare evasion detection machine learning model, and the detection machine learning model determines whether the target vehicle has intentional fare evasion behavior.

[0008] Optionally, the target vehicle features include license plate status features and / or vehicle body status features. Accordingly, extracting the target vehicle features based on the acquired vehicle information of the target vehicle and the first vehicle includes: extracting the license plate status features and / or vehicle body status features of the target vehicle based on the acquired image information of the target vehicle.

[0009] Optionally, the target vehicle features include target vehicle features and driving behavior features. Accordingly, extracting the target vehicle features based on the acquired vehicle information of the target vehicle and the first vehicle includes: calculating the following vehicle distance features between the target vehicle and the first vehicle based on the acquired position information of the target vehicle and the first vehicle, wherein the target vehicle and the first vehicle are adjacent vehicles. Based on the acquired position information of the target vehicle during the process of passing through the lane interception device, extracting the driving behavior features of the target vehicle.

[0010] Optionally, the target vehicle feature includes a driving speed feature. Accordingly, extracting the target vehicle feature based on the acquired vehicle information of the target vehicle and the first vehicle includes: calculating the driving speed of the target vehicle based on the acquired time when the target vehicle arrives at a plurality of preset locations.

[0011] Optionally, the target vehicle characteristics are input into a pre-trained intentional fare evasion detection machine learning model. Before the detection machine learning model determines whether the target vehicle has intentional fare evasion behavior, it also includes: obtaining vehicle information of actual passing vehicles, matching the vehicle information of the actual passing vehicles with the vehicle information of the paid vehicles, and when the match fails, using the actual passing vehicle as the target vehicle.

[0012] In the second aspect, an embodiment of the present invention provides a vehicle intentional fare evasion detection device, including: an acquisition unit, used to acquire vehicle information of a target vehicle and a first vehicle, wherein the first vehicle is the preceding vehicle of the target vehicle along the driving direction; an extraction unit, used to extract target vehicle characteristics based on the acquired vehicle information of the target vehicle and the first vehicle; a judgment unit, used to input the target vehicle characteristics into a pre-trained intentional fare evasion detection machine learning model, and the detection machine learning model judges whether the target vehicle has intentional fare evasion behavior.

[0013] In the third aspect, an embodiment of the present invention provides a vehicle intentional fare evasion detection system, comprising: a vehicle position detection device, a license plate recognition device, an interception device and a data processing module, wherein the vehicle position detection device, the license plate recognition device and the interception device are respectively connected to the data processing module, wherein the vehicle position detection device is used to detect the positions of a first vehicle and a target vehicle and the driving behavior of the target vehicle in the process of passing through the interception device, and transmit the positions and driving behaviors of the first vehicle and the target vehicle to the data processing module; the license plate recognition device is used to detect the license plate status of the target vehicle, and transmit the license plate status to the data processing module; the data processing module is used to input the positions, driving behaviors and license plate status of the first vehicle and the target vehicle into a pre-trained intentional fare evasion detection machine learning model, and the detection machine learning model determines whether the target vehicle has intentional fare evasion behavior.

[0014] Optionally, it also includes: a charging module connected to the data processing module, wherein the vehicle position detection device is also used to obtain the vehicle information of the actual passing vehicles, and transmit the vehicle information of the actual passing vehicles to the data processing module; the charging module is used to transmit the paid vehicle information to the data processing module; the data processing module is used to receive the actual passing vehicle and the paid vehicle information, and match and analyze the vehicle information of the actual passing vehicle with the paid vehicle information.

[0015] Optionally, it also includes a bracket, on which a vehicle position detection device and a communication antenna module for communicating with a target vehicle are arranged, and the communication antenna module is connected to the charging module.

[0016] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium. When the computer-readable storage medium is run on a terminal device, the terminal device executes any one of the vehicle intentional fare evasion detection methods in the first aspect.

[0017] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0018] The embodiment of the present invention calculates the following distance between the target vehicle and the first vehicle by acquiring the position of the target vehicle and the position of the first vehicle; calculates the driving speed of the target vehicle based on the time when the target vehicle arrives at multiple preset positions; acquires the license plate status of the target vehicle, and the specific license plate status may be a normal license plate, an unhung license plate, or an obscured license plate; acquires the driving behavior of the target vehicle during the process of passing through a lane interception device, and the specific driving behavior includes normal, parking, or reversing behavior; and inputs the above-mentioned information acquired into a pre-trained intentional fare evasion detection machine learning model, and determines whether the target vehicle has intentional fare evasion behavior by detecting the machine learning model, and then determines whether the target vehicle is an intentional fare evasion vehicle, and takes corresponding measures against the intentional fare evasion vehicle in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0020] Figure 1 This is one of the structural schematic diagrams of a vehicle intentional fare evasion detection system provided by an embodiment of the present invention;

[0021] Figure 2This is the second structural diagram of the vehicle intentional fare evasion detection system provided by one embodiment of the present invention;

[0022] Figure 3 It is a flow chart of a method for detecting intentional fare evasion by a vehicle provided by an embodiment of the present invention;

[0023] Figure 4 It is a schematic diagram of the structure of a vehicle intentional fare evasion detection device provided by an embodiment of the present invention;

[0024] Figure 5 It is a schematic diagram of the structure of a vehicle intentional toll evasion detection device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0026] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0027] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0028] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.

[0029] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0030] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0031] In the process of studying intentional and unintentional evasion of tolls, the inventors found that the most common means of intentional evasion of tolls are the following: first, the drop bar coil in the toll lane has a certain width, and the target vehicle follows the adjacent normal vehicle in front, causing the system to mistakenly judge that the two vehicles are the same vehicle; second, the anti-smashing function of the interception device is triggered to force the interception device to be lifted, thereby achieving the purpose of evading tolls.

[0032] In response to the two methods of evasion mentioned above, corresponding measures have been taken. One is to use gratings instead of coils, and the other is to use high-speed interception devices to increase the difficulty of evasion. However, the above measures cannot completely eliminate the behavior of deliberate evasion. Another method is to use other vehicle evasion detection equipment to compare the charging record flow, locate the unpaid vehicles, and then collect the fees later. However, this method cannot distinguish between unintentional evasion and deliberate evasion.

[0033] Vehicles that evade fees unintentionally are considered to have done so unintentionally, and the owner only needs to be notified and the fee paid. However, vehicles that evade fees intentionally are considered to have done so maliciously, and may be subject to certain penalties if necessary. For vehicles that evade fees intentionally, there are usually a large number of evasion records, and their driving patterns can be analyzed through the records to identify vehicles that evade fees intentionally.

[0034] The vehicle intentional evasion detection system provided by the embodiment of the present invention includes: a vehicle position detection device, a license plate recognition device, an interception device and a data processing module, wherein the vehicle position detection device, the license plate recognition device and the interception device are respectively connected to the data processing module, wherein the vehicle position detection device can be used to detect the position of the first vehicle and the target vehicle and the driving behavior of the target vehicle in the process of passing through the interception device, and transmit the position and driving behavior of the first vehicle and the target vehicle to the data processing module; the specific vehicle position detection device can be set to detect the position by a laser sensor, an ultrasonic sensor, a video detector, etc. The license plate recognition device can extract and recognize the license plate state of the moving target vehicle from a complex background, can be used to detect the license plate state of the target vehicle, and transmit the license plate state to the data processing module; the data processing module can be used to input the position, driving behavior and license plate state of the first vehicle and the target vehicle into a pre-trained intentional evasion detection machine learning model, and determine whether the target vehicle has intentional evasion behavior by detecting the machine learning model.

[0035] In the embodiment of the present invention, the vehicle position detection device detects the position and driving behavior of the destination vehicle and the first vehicle, the license plate recognition device detects the license plate status, and the above information is input into the pre-trained intentional evasion detection machine learning model through the data processing module, so as to determine whether the evading vehicle is unintentional evasion or intentional evasion.

[0036] The front in the context of the present invention refers to the opposite direction of the target vehicle's driving direction, and the rear refers to the target vehicle's driving direction.

[0037] In some possible embodiments, see Figure 1 , Figure 1 A schematic structural diagram of a vehicle intentional evasion detection system in an ETC lane is shown, including a bracket 8, an interception device 7, a vehicle position detection device 1, a license plate recognition device 2, a charging module 4 such as an ETC charging system, a communication antenna module 3 such as an ETC antenna and a data processing module 5. The vehicle position detection device 1, the license plate recognition device 2, the charging module 4 and the interception device 7 are respectively connected to the data processing module 5.

[0038] In this embodiment, the vehicle position detection device 1 can specifically detect the position through a laser sensor, an ultrasonic sensor, a video detector, etc. For example, when a laser sensor is set to detect the position, multiple laser transmitters and multiple laser receivers can be set. When the target vehicle is detected, the laser irradiation is blocked, and the time when the target vehicle passes the laser transmitter can be collected. In addition, in this embodiment, by setting a laser sensor, the passing vehicles can also be counted. By comparing the number of payment records transmitted by the charging module 4 with the actual detected passing data, the vehicles that have passed without paying the fee can be obtained, and then the data of the unpaid passing vehicles are input into the trained intentional evasion detection machine learning model to determine whether the target vehicle intentionally evades the fee.

[0039] The license plate recognition device 2 can be a license plate identifier, which is used to identify the license plate number of the vehicle and detect the actual hanging state of the license plate. Of course, the license plate recognition device 2 can also be set as a shooting device, which is used to take pictures of the license plate state and detect the actual hanging state of the license plate; and can cooperate with a low-power roadside unit to obtain the unique MAC code of the vehicle's on-board unit or the electronic license plate, or other devices that can obtain the vehicle's identification information, such as RFID, and can also be used to identify the vehicle's electronic license plate. The detection of the electronic license plate can be used as a basis for subsequent recovery.

[0040] The interception device 7 can be a barrier machine, a pull rod machine, a gate machine, an electric telescopic door, etc., or other devices that can be used to intercept the passage of vehicles, which is not limited in this embodiment.

[0041] Specifically, in this embodiment, the vehicle position detection device 1 and the communication antenna module 3 are arranged on the top of the bracket 8, which can increase the detection range; the scanning direction of the vehicle position detection device 1 can be to scan along the driving direction of the target vehicle 9, so as to detect the positions of the target vehicle 9 and the first vehicle 10. The interception device 7 can be arranged at the rear position of the bracket 8, and a certain distance such as 3m can be set between the interception device 7 and the bracket 8. The bracket 8 and the charging module 4 can be arranged on one side of the lane, and the license plate recognition device 2 can be arranged on the other side of the lane. In order to protect the charging module 4 and the data processing module 5, the two can be arranged in the booth 6.

[0042] In some other possible embodiments, see Figure 2 , Figure 2A schematic structural diagram of a vehicle intentional evasion detection system in an intelligent parking lot is shown, comprising a vehicle position detection device 1, a license plate recognition device 2, an interception device 3, a charging module 4 and a data processing module 5. The vehicle position detection device 1, the license plate recognition device 2, the charging module 4 and the interception device 3 are respectively connected to the data processing module 5, and the connection method can be a communication connection, and the communication connection method can be a wired communication connection, such as HDMI, USB, RS485 or RS232, etc., or a wireless communication connection, such as Bluetooth or WiFi and other wireless communications; for example, the vehicle position detection device 1, the license plate recognition device 2, the data processing module 5 and the charging module 4 can all be connected to the same switch through a network port.

[0043] Specifically, the vehicle position detection device 1 and the license plate recognition device 2 can be installed on the same side of the lane; the interception device 3 can be installed about 1 meter behind the vehicle position detection device 1, and the license plate recognition device 2 can be installed about 3 meters behind the interception device 3. To protect the charging module 4 and the data processing module 5, the two can be set in the guard booth 6.

[0044] Figure 3 A schematic flow chart of a method for detecting intentional toll evasion by a vehicle provided by an embodiment of the present invention is shown, specifically:

[0045] S100, obtaining vehicle information of a target vehicle and a first vehicle, wherein the first vehicle is a preceding vehicle of the target vehicle along a driving direction, and the vehicle information includes at least one of image information, position information and time information.

[0046] It is understandable that the positions of the target vehicle and the first vehicle can be detected by a vehicle position detection device, and the vehicle position detection device sends the detected position information to a data processing module for analysis and processing. Specifically, the position can be detected by a laser sensor, an ultrasonic sensor, a video detector, etc. And the time when the vehicle position detection device detects the position can be recorded. For example, when a laser sensor is set to detect the position, multiple laser transmitters and multiple laser receivers can be set. When the target vehicle or the first vehicle passes by, the laser irradiation is blocked, and the time when the target vehicle passes this laser transmitter can be collected. In this embodiment, image information of the vehicle can be collected by an image acquisition device, such as a photo-taking device, a video camera, etc.

[0047] S200: Extracting target vehicle features based on the acquired vehicle information of the target vehicle and the first vehicle.

[0048] In some embodiments, target vehicle features may be extracted based on the acquired location information.

[0049] The target vehicle characteristics include following distance characteristics and driving behavior characteristics. Accordingly, step S200 may include:

[0050] S210, calculating a following distance feature between the target vehicle and the first vehicle based on the acquired position information of the target vehicle and the position information of the first vehicle, wherein the target vehicle and the first vehicle are adjacent vehicles.

[0051] As an example, the position of the target vehicle can be the front position of the target vehicle, and the position of the first vehicle can be the rear position of the first vehicle. The distance between the front position of the target vehicle and the rear position of the first vehicle is used as the following distance, and the following distance is input into the machine learning model as a following distance feature. In this case, the distance between the target vehicle and the first vehicle is relatively smaller, which is more in line with the scanning range of the laser sensor.

[0052] In a possible implementation, step S210 specifically includes:

[0053] S211, obtaining a first position of the target vehicle and a third position of the first vehicle corresponding to the first position, and calculating a first sub-following distance between the target vehicle and the first vehicle;

[0054] S212, acquiring a second position of the target vehicle and a fourth position of the first vehicle corresponding to the second position, and calculating a second sub-following distance between the target vehicle and the first vehicle.

[0055] When the target vehicle is located at different positions, the distance between the target vehicle and the first vehicle, i.e., the first sub-following distance and the second sub-following distance, is calculated, and the first sub-following distance and the second sub-following distance are used as input data of a pre-trained intentional evasion detection machine learning model.

[0056] Of course, more than two positions of the target vehicle may be obtained, and more than two positions corresponding to the first vehicle may be obtained to calculate more than two following vehicle distances.

[0057] As an example but not a limitation, the position of the intercepting device is selected as the origin, and the front Y1 and the front Y2 of the intercepting device are set as the measurement points. Y1 and Y2 are measurement points at different positions. For example, Y1 is 5m, Y2 is 2m, and the scanning range of the laser sensor is -10m to 10m. For another example, Y1 is 4m, Y2 is 1m, and the scanning range of the laser sensor is -5m to 5m. When the laser sensor detects that the front of the target vehicle has reached position Y1, the position Y3 of the rear of the first vehicle, i.e., the adjacent preceding vehicle, is detected at the same time. When the laser sensor detects that the front of the target vehicle has reached position Y2, the position Y4 of the rear of the first vehicle, i.e., the adjacent preceding vehicle, is detected at the same time. When the front of the target vehicle is calculated to be at Y1 and Y2 respectively, the following distances with the preceding vehicle are D1=Y1-Y3 and D2=Y2-Y4 respectively. It can be understood that when the front of the target vehicle reaches position Y1 or Y2, the distance between the target vehicle and the first vehicle may be far. When the laser sensor detects that the front of the target vehicle reaches position Y1 or Y2, for example, the first vehicle is not in the scanning range set by the laser sensor, such as -10m to 10m. At this time, the position of the rear of the first vehicle can be taken as -10m; for another example, the first vehicle is not in the scanning range set by the laser sensor, such as -5m to 5m. At this time, the position of the rear of the first vehicle can be taken as -5m, and the distance between the front of the target vehicle and the rear of the first vehicle is calculated.

[0058] S220, based on the acquired position information of the target vehicle in the process of passing through the lane interception device, extract the driving behavior characteristics of the target vehicle. The driving behavior includes normal, parking or reversing behavior, and O can be used to represent the driving behavior. The driving behavior is input into the machine learning model as the driving behavior characteristics.

[0059] The time period from when the front of the target vehicle reaches the interception device position to when the rear of the target vehicle completely passes the interception device position is taken as the target vehicle passing through the lane interception device; the vehicle position detection device detects the driving behavior of the target vehicle during this time period.

[0060] In other embodiments, the target vehicle features may be extracted based on the acquired time information.

[0061] The target vehicle characteristics include driving speed characteristics. Accordingly, step S200 may include:

[0062] S230, calculating the travel speed of the target vehicle based on the acquired time when the target vehicle arrives at the plurality of preset positions.

[0063] A vehicle position detection device can be used to detect the time when the target vehicle arrives at a preset position, and send the time to a data processing module; then the driving speed is input into the machine learning model as a driving speed feature.

[0064] Specifically, the driving speed may include a first sub-driving speed and a second sub-driving speed. Accordingly, step S230 includes:

[0065] S231, calculating a first sub-travel speed of the target vehicle based on the acquired time when the target vehicle arrives at the first preset position and the second preset position in sequence;

[0066] S232, based on the acquired time when the target vehicle arrives at the third preset position and the fourth preset position in sequence, calculate the second sub-driving speed of the target vehicle; wherein the first preset position, the second preset position, the third preset position and the fourth preset position are multiple preset positions set along the driving direction.

[0067] When the target vehicle is located in different position segments, the driving speed of the target vehicle, namely the first sub-driving speed and the second sub-driving speed, is calculated, and the first sub-driving speed and the second sub-driving speed are used as input data of the pre-trained intentional evasion detection machine learning model.

[0068] As an example but not a limitation, the position of the interception device is selected as the origin, and X1, X2, X3, and X4 in front of the interception device are the test points at four different positions, for example, X1 is 6m, X2 is 5m, X3 is 2m, and X4 is 1m. For another example, X1 is 5m, X2 is 4m, X3 is 1.5m, and X4 is 0.5m. When the vehicle position detection device detects that the front of the target vehicle reaches the above four positions, the time at that time is recorded, which are T1, T2, T3, and T4, respectively. The driving speed of the target vehicle between Y1 and Y2 is calculated as V1 = (X1-X2) / (T2-T1), and the driving speed between Y3 and Y4 is V2 = (X3-X4) / (T4-T3).

[0069] In still other embodiments, target vehicle features may be extracted based on the acquired image information.

[0070] As an example, the target vehicle characteristics may include a license plate state characteristic and / or a vehicle body state characteristic, and a driving speed characteristic. Accordingly, step S200 may include:

[0071] S240, extracting a license plate state feature and / or a vehicle body state feature of the target vehicle based on the acquired image information of the target vehicle;

[0072] As an example, the license plate status features include normal license plates, unhung license plates, and blocked license plates, and the license plate status can be represented by S. For example, a position M in front of the license plate recognition device, such as 5m or 3m, is selected as a capture point. When the vehicle position detection device detects that the front of the target vehicle has arrived at the capture point, the position information of the target vehicle is sent to the data processing module, and the data processing module triggers the license plate recognition device to detect the license plate status of the target vehicle.

[0073] The body state features include the body shapes of cars, buses, and trucks. Different types of cars have different probabilities of evading tolls. Trucks have a higher probability of evading tolls due to their higher tolls. Therefore, by obtaining the body state and using it as an input feature, the accuracy of judgment can be improved.

[0074] S300, input the target vehicle characteristics into the pre-trained intentional fare evasion detection machine learning model, and detect the machine learning model to determine whether the target vehicle has intentional fare evasion behavior. It can effectively distinguish between vehicles that do not intend to evade fees and vehicles that do intend to evade fees.

[0075] In some feasible embodiments, the trigger status information of the anti-smashing function of the barrier can be obtained and input into the training model to improve the accuracy of the judgment result.

[0076] In other feasible embodiments, the onboard unit (OBU) status information of the target vehicle can also be detected. The OBU status information may include disassembly status, card-free status, no entry status, etc., and input into the training model to improve the accuracy of the judgment result.

[0077] It should be noted that the pre-trained intentional fare evasion detection machine learning model is trained through the following steps:

[0078] S410, extracting vehicle features of the toll evasion data sample and constructing a feature vector;

[0079] It can be understood that the feature vector can be constructed according to the first sub-following distance D1 and the second sub-following distance D2, the first sub-traveling speed V1 and the second sub-traveling following distance V2, the license plate state S, and the driving behavior O of the target vehicle;

[0080] S420, training the fare evasion data samples to obtain a pre-trained machine learning model for detecting intentional fare evasion.

[0081] A classification algorithm based on a combination of neural networks and decision trees can be used to train the fare evasion data samples. Of course, other algorithms can also be used for training, such as regression algorithms, Bayesian methods, etc. Among them, the distinction between unintentional fare evasion and intentional fare evasion in the fare evasion sample data is mainly based on manual review. For example, a single vehicle often appears in the fare evasion data, or a vehicle with obvious intentional fare evasion behavior in the manual observation of the vehicle passing video can be used as an intentional fare evasion sample; the fare evasion samples that appear when the ETC system fails can be used as unintentional fare evasion samples; samples that cannot be manually judged as intentional fare evasion can be temporarily removed and not included in the training samples to improve the accuracy of the final training model.

[0082] The embodiment of the present invention obtains the target vehicle characteristics of the target vehicle and inputs the above-obtained information into a pre-trained intentional fare evasion detection machine learning model. It can determine whether the target vehicle has intentional fare evasion behavior by detecting the machine learning model, and then determine whether the target vehicle is an intentional fare evasion vehicle, and take corresponding measures against the intentional fare evasion vehicle in a timely manner to reduce economic losses.

[0083] In a possible implementation, before step S300, the method further includes:

[0084] S500, obtaining vehicle information of the actual passing vehicle, matching the vehicle information of the actual passing vehicle with the vehicle information of the paid vehicle, and when the matching fails, taking the actual passing vehicle as the target vehicle.

[0085] When the match fails, it means that the actual passing vehicle has not paid the fee, and is an unintentional fee evasion vehicle or a deliberate fee evasion vehicle. This vehicle is used as the target vehicle, and the vehicle information of the target vehicle is input into the pre-trained deliberate fee evasion detection machine learning model. The machine learning model is used to determine whether the target vehicle has deliberate fee evasion behavior, and it can be determined whether the vehicle is unintentional fee evasion or deliberate fee evasion. When the match succeeds, it means that the actual passing vehicle has paid the fee and is a normal passing vehicle. Among them, vehicle information includes following distance, driving speed, license plate status and driving behavior.

[0086] As an example, a laser sensor can be used to count the actual number of vehicles passing through. The number of payment records recorded by the ETC toll collection system or the parking lot toll collection system can be compared with the actual detected passage data to obtain vehicles that have passed without paying. The vehicle information of the target vehicle that has passed without paying can then be input into a pre-trained intentional evasion detection machine learning model to determine whether the target vehicle has intentionally evaded fees.

[0087] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0088] Corresponding to the vehicle intentional evasion detection method of the above embodiment, Figure 4 A structural block diagram of a vehicle intentional toll evasion detection device provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown.

[0089] See also Figure 4 , the device comprises:

[0090] An acquisition unit 41 is used to acquire vehicle information of a target vehicle and a first vehicle, wherein the first vehicle is a preceding vehicle of the target vehicle along a driving direction;

[0091] An extraction unit 42, configured to extract a target vehicle feature based on the acquired vehicle information of the target vehicle and the first vehicle;

[0092] The first judgment unit 43 is used to input the target vehicle characteristics into a pre-trained intentional fare evasion detection machine learning model, and detect the machine learning model to determine whether the target vehicle has intentional fare evasion behavior.

[0093] In some feasible embodiments, the extraction unit 42 of the device further includes:

[0094] The following distance calculation unit is used to calculate the following distance characteristics of the target vehicle and the first vehicle based on the acquired position information of the target vehicle and the position information of the first vehicle, wherein the target vehicle and the first vehicle are adjacent vehicles.

[0095] As an example, the following distance calculation unit of the device further includes:

[0096] A first following distance calculation subunit, used to obtain a first position of the target vehicle and a third position of the first vehicle corresponding to the first position, and calculate a first sub-following distance between the target vehicle and the first vehicle;

[0097] The second following distance calculation subunit is used to obtain the second position of the target vehicle and the fourth position of the first vehicle corresponding to the second position, and calculate the second sub-following distance between the target vehicle and the first vehicle.

[0098] In some other feasible embodiments, the extraction unit 42 of the device further includes:

[0099] The speed calculation unit is used to calculate the travel speed of the target vehicle based on the acquired time when the target vehicle arrives at multiple preset positions.

[0100] As an example, the speed calculation unit of the device further includes:

[0101] A first speed calculation subunit, used to calculate a first sub-travel speed of the target vehicle based on the acquired time when the target vehicle arrives at the first preset position and the second preset position in sequence;

[0102] The second speed calculation subunit is used to calculate the second sub-driving speed of the target vehicle based on the time when the target vehicle arrives at the third preset position and the fourth preset position in sequence; wherein the first preset position, the second preset position, the third preset position and the fourth preset position are multiple preset positions set along the driving direction.

[0103] In some further feasible embodiments, the extraction unit 42 of the device further includes:

[0104] The license plate acquisition unit is used to acquire the license plate status of the target vehicle, and the license plate status can be a normal license plate, an unsuspended license plate, or a blocked license plate.

[0105] In some further feasible embodiments, the extraction unit 42 of the device further includes:

[0106] The driving behavior detection unit is used to extract the driving behavior characteristics of the target vehicle based on a plurality of image information obtained when the target vehicle passes through the lane interception device.

[0107] In some feasible embodiments, the device further comprises:

[0108] The second judgment unit is used to obtain the vehicle information of the actual passing vehicle, match the vehicle information of the actual passing vehicle with the vehicle information that has paid the fee, and when the matching fails, use the actual passing vehicle as the target vehicle.

[0109] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0110] 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 for illustration. In actual applications, the above-mentioned function allocation can be 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. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0111] Figure 5 This is a schematic diagram of the structure of a vehicle intentional evasion detection device provided by an embodiment of the present invention. Figure 5 As shown, the vehicle intentional evasion detection device of this embodiment includes: at least one processor 50 ( Figure 5 Only one is shown in the figure) a processor, a memory 51, and a computer program 52 stored in the memory 51 and executable on at least one processor 50. When the processor 50 executes the computer program 52, the steps in any of the above-mentioned embodiments of the method for detecting intentional fare evasion by a vehicle are implemented.

[0112] The vehicle intentional evasion detection device 5 can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The vehicle intentional evasion detection device can include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will understand that Figure 5 It is merely an example of the vehicle intentional fare evasion detection device 5 and does not constitute a limitation of the vehicle intentional fare evasion detection device 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0113] The processor 50 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0114] In some embodiments, the memory 51 may be an internal storage unit of the vehicle intentional fare evasion detection device 5, such as a hard disk or memory of the vehicle intentional fare evasion detection device 5. In other embodiments, the memory 51 may also be an external storage device of the vehicle intentional fare evasion detection device 5, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the vehicle intentional fare evasion detection device 5. Further, the memory 51 may also include both the internal storage unit and the external storage device of the vehicle intentional fare evasion detection device 5. The memory 51 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as program codes of computer programs, etc. The memory 51 may also be used to temporarily store data that has been output or is to be output.

[0115] An embodiment of the present invention also provides a vehicle intentional fare evasion detection device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on at least one processor, and when the processor executes the computer program, it implements the steps in any of the above-mentioned method embodiments.

[0116] An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0117] An embodiment of the present invention provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0118] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0119] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0120] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0121] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for detecting intentional toll evasion by a vehicle, characterized in that: The vehicle intentional toll evasion detection method is used for an unmanned toll lane, and the vehicle intentional toll evasion detection method comprises: Acquire vehicle information of a target vehicle and a first vehicle, wherein the first vehicle is a preceding vehicle of the target vehicle along a travel direction, and the vehicle information includes at least one of image information, position information, and time information; Extracting target vehicle features based on the acquired vehicle information of the target vehicle and the first vehicle; Inputting the target vehicle characteristics into a pre-trained intentional fare evasion detection machine learning model, the detection machine learning model determines whether the target vehicle has intentional fare evasion behavior; The target vehicle characteristics include following distance characteristics and driving behavior characteristics. Accordingly, The step of extracting target vehicle features based on the acquired vehicle information of the target vehicle and the first vehicle includes: Based on the acquired position information of the target vehicle and the position information of the first vehicle, calculating the following distance characteristics of the target vehicle and the first vehicle, wherein the target vehicle and the first vehicle are adjacent vehicles; Extracting driving behavior characteristics of the target vehicle based on the acquired position information of the target vehicle in the process of passing through the lane interception device; The time period from when the front of the target vehicle reaches the interception device position to when the rear of the target vehicle completely passes the interception device position is taken as the time period of the target vehicle passing through the lane interception device; the vehicle position detection device detects the driving behavior of the target vehicle within the time period.

2. The vehicle intentional fare evasion detection method according to claim 1, characterized in that: The target vehicle features include license plate state features and / or vehicle body state features. Accordingly, The step of extracting target vehicle features based on the acquired vehicle information of the target vehicle and the first vehicle includes: Based on the acquired image information of the target vehicle, the license plate state characteristics and / or vehicle body state characteristics of the target vehicle are extracted.

3. The vehicle intentional fare evasion detection method according to claim 1, characterized in that: The target vehicle characteristics include driving speed characteristics, and accordingly, The step of extracting target vehicle features based on the acquired vehicle information of the target vehicle and the first vehicle includes: The travel speed of the target vehicle is calculated based on the acquired time when the target vehicle arrives at a plurality of preset positions.

4. The method for detecting intentional toll evasion by a vehicle according to claim 1, characterized in that: The inputting of the target vehicle characteristics into the pre-trained intentional fare evasion detection machine learning model, and the detection machine learning model determining whether the target vehicle has intentional fare evasion behavior, further comprises: The vehicle information of the actual passing vehicle is obtained, and the vehicle information of the actual passing vehicle is matched with the vehicle information of the paid vehicle. When the matching fails, the actual passing vehicle is used as the target vehicle.

5. A vehicle intentional fare evasion detection device, using the vehicle intentional fare evasion detection method as claimed in claim 1, characterized in that: include: An acquisition unit, used to acquire vehicle information of a target vehicle and a first vehicle, wherein the first vehicle is a preceding vehicle of the target vehicle along a traveling direction; an extraction unit, configured to extract a target vehicle feature based on the acquired vehicle information of the target vehicle and the first vehicle; A judgment unit is used to input the target vehicle characteristics into a pre-trained intentional fare evasion detection machine learning model, and the detection machine learning model determines whether the target vehicle has intentional fare evasion behavior.

6. A vehicle intentional evasion detection system, characterized in that: The vehicle intentional evasion detection system is used for unmanned toll lanes, and the vehicle intentional evasion detection system comprises: a vehicle position detection device, a license plate recognition device, an interception device and a data processing module, wherein the vehicle position detection device, the license plate recognition device and the interception device are respectively connected to the data processing module, wherein: The vehicle position detection device is used to detect the positions of the first vehicle and the target vehicle and the driving behavior of the target vehicle in the process of passing through the interception device, and transmit the positions of the first vehicle and the target vehicle and the driving behavior to the data processing module; The license plate recognition device is used to detect the license plate status of the target vehicle and transmit the license plate status to the data processing module; The data processing module is used to input the positions of the first vehicle and the target vehicle, the driving behavior and the license plate status into a pre-trained intentional evasion detection machine learning model, and the detection machine learning model determines whether the target vehicle has intentional evasion behavior; The time period from when the front of the target vehicle reaches the position of the interception device to when the rear of the target vehicle completely passes the position of the interception device is taken as the time period of the target vehicle passing through the interception device; the vehicle position detection device detects the driving behavior of the target vehicle within the time period.

7. The vehicle intentional fare evasion detection system according to claim 6, characterized in that: Also includes: A charging module connected to the data processing module, wherein: The vehicle position detection device is further used to obtain vehicle information of actual passing vehicles and transmit the vehicle information of actual passing vehicles to the data processing module; The charging module is used to transmit the paid vehicle information to the data processing module; The data processing module is used to receive the information of the actual passing vehicles and the paid vehicles, and match and analyze the vehicle information of the actual passing vehicles with the paid vehicle information.

8. The vehicle intentional fare evasion detection system according to claim 7, characterized in that: It also includes a bracket, on which the vehicle position detection device and a communication antenna module for communicating with the target vehicle are arranged, and the communication antenna module is connected to the charging module.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images