Vehicle passage control method and system based on defect detection

Abstract

This invention discloses a vehicle traffic control method and system based on defect detection. The method includes: acquiring the vehicle identifier of a vehicle intending to pass through a target checkpoint; determining vehicle defect information corresponding to the vehicle based on the vehicle identifier and preset historical vehicle detection data; predicting the traffic scenario corresponding to the vehicle based on the equipment information of the target checkpoint and the vehicle identifier; calculating the traffic risk parameter corresponding to the vehicle based on the vehicle defect information and the traffic scenario using a risk identification algorithm; the traffic risk parameter indicates the degree of risk of allowing the vehicle to pass through the target checkpoint. Therefore, this invention can improve the monitoring efficiency and accuracy of vehicle traffic risks, provide accurate risk estimation references for traffic control, and improve the safety and intelligence of vehicle traffic control.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a vehicle traffic control method and system based on defect detection. Background Technology

[0002] With the development of intelligent recognition algorithms, more and more vehicle manufacturing and repair organizations are adopting more intelligent and automated production control technologies. Among these, vehicle defect detection involves multiple stages, and vehicles need to pass through different areas throughout the process or after completion. Therefore, how to achieve more accurate and safe vehicle passage control has become a significant technical problem. Current technologies for vehicle passage control mostly only consider vehicle identification such as license plate numbers or driver identification such as facial images. When applied to multi-stage vehicle detection scenarios, they do not fully integrate vehicle defect recognition with the passage scenario to achieve passage control, resulting in insufficient accuracy and safety. Clearly, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a vehicle traffic control method and system based on defect detection, which can improve the monitoring efficiency and accuracy of vehicle traffic risks, provide accurate risk estimation reference for traffic control, and improve the safety and intelligence of vehicle traffic control.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a vehicle traffic control method based on defect detection, the method comprising:

[0005] Obtain the vehicle identification of the vehicle intending to pass through the target checkpoint equipment;

[0006] Based on preset vehicle inspection history data, the vehicle defect information corresponding to the passing vehicle is determined according to the vehicle identifier.

[0007] Based on the equipment information of the target checkpoint equipment and the vehicle identification, predict the passage scenario corresponding to the passing vehicle;

[0008] Based on the vehicle defect information and the passage scenario, and using a risk identification algorithm, the passage risk parameters corresponding to the passing vehicle are calculated; the passage risk parameters indicate the degree of risk of allowing the passing vehicle to pass through the target checkpoint equipment.

[0009] As an optional implementation, in the first aspect of the present invention, the vehicle identification includes at least one of vehicle sensor data, vehicle license plate, vehicle inspection number, and facial image of a person in the vehicle; the vehicle sensor data includes at least one of vehicle image data, vehicle sound data, vehicle light reflection three-dimensional model data, and vehicle temperature and humidity data.

[0010] As an optional implementation, in the first aspect of the present invention, determining the vehicle defect information corresponding to the passing vehicle based on the vehicle identifier, according to preset vehicle detection historical data, includes:

[0011] The vehicle identifier is matched against the vehicle detection history database to obtain the matching result.

[0012] When the matching result indicates that a matching record exists, obtain multiple vehicle detection records obtained through the matching process.

[0013] When the matching result is that no matching record exists, at least one similar vehicle is identified from the multiple detected vehicles in the vehicle detection history database based on the vehicle identifier, and the vehicle detection records corresponding to all the similar vehicles are obtained.

[0014] Based on the vehicle inspection records, determine the vehicle defect information corresponding to the passing vehicle.

[0015] As an optional implementation, in a first aspect of the invention, determining at least one similar vehicle based on the vehicle identifier in the vehicle detection history database includes:

[0016] The vehicle sensor data of the passing vehicles is input into a trained detection elapsed time prediction neural network to obtain the detection elapsed time corresponding to the passing vehicles; the detection elapsed time prediction neural network is trained by a training dataset that includes multiple training vehicle sensor data and corresponding time distance labels from the previous detection to the current time.

[0017] Calculate the difference between the current time point and the elapsed detection time to obtain the possible last detection time for the passing vehicle;

[0018] For each vehicle detected in the vehicle detection history database, obtain the vehicle data and the most recent historical detection time point corresponding to the detected vehicle.

[0019] Calculate the first similarity between the vehicle data and the vehicle identifier;

[0020] Calculate the first time difference between the most recent historical detection time and the possible last detection time;

[0021] Calculate the ratio of the first similarity to the first time difference to obtain the similarity parameter corresponding to the detected vehicle;

[0022] The detected vehicles whose similarity parameter is greater than the parameter threshold are identified as similar vehicles.

[0023] As an optional implementation, in the first aspect of the present invention, determining the vehicle defect information corresponding to the passing vehicle based on the vehicle inspection record includes:

[0024] For each vehicle detection record, calculate the detection time corresponding to the vehicle detection record and the second time difference at the current time point;

[0025] Calculate the second similarity between the vehicle information corresponding to the vehicle detection record and the vehicle identifier;

[0026] Calculate the difference between the number of defects detected in the vehicle inspection record and the average number; the average number is the average number of defects detected in all the vehicle inspection records.

[0027] Calculate the product of the second time difference and the quantity difference, and calculate the ratio of the second similarity to the product to obtain the record priority corresponding to the vehicle detection record;

[0028] The defects detected in the vehicle detection record with the highest record priority are identified as the vehicle defect information corresponding to the passing vehicle.

[0029] As an optional implementation, in the first aspect of the present invention, the vehicle defect information includes a defect type corresponding to at least one vehicle part; the vehicle part is a door, front, body, chassis, roof, rear, trunk, interior space or wheel.

[0030] As an optional implementation, in the first aspect of the present invention, predicting the passage scenario corresponding to the passing vehicle based on the device information of the target checkpoint device and the vehicle identifier includes:

[0031] The device information of the target checkpoint device is input into a trained first passage scene prediction neural network to obtain the first scene prediction result corresponding to the target checkpoint device; the first passage scene prediction neural network is trained using a training dataset that includes multiple training device information and corresponding passage scene annotations; the device information includes device location, device model, device hardware parameters and device software parameters;

[0032] The vehicle identifier is input into a trained second traffic scene prediction neural network to obtain a second scene prediction result corresponding to the passing vehicle; the second traffic scene prediction neural network is trained using a training dataset that includes multiple training vehicle identifiers and corresponding traffic scene annotations;

[0033] The intersection of the first scenario prediction result and the second scenario prediction result is calculated to obtain the passage scenario corresponding to the passing vehicle; the passage scenario is the factory entry inspection scenario, the inspection process transfer scenario, the inspection completed and leaving the factory scenario, the faulty leaving the factory scenario, or the leaving the factory to perform a task scenario.

[0034] As an optional implementation, in the first aspect of the present invention, the step of calculating the traffic risk parameters corresponding to the passing vehicle based on the vehicle defect information and the traffic scenario, using a risk identification algorithm, includes:

[0035] Based on the mathematical correspondence between preset scenarios and risk thresholds, a first reference threshold corresponding to the passage scenario is determined;

[0036] Based on the preset mathematical correspondence between defect and risk thresholds, a second reference threshold corresponding to the vehicle defect information is determined;

[0037] Calculate the weighted average of the first reference threshold and the second reference threshold to obtain the risk reference threshold;

[0038] The vehicle defect information and the traffic scenario are input into a trained traffic risk prediction neural network to obtain the output predicted risk value; the traffic risk prediction neural network is trained using a training dataset that includes multiple training vehicle defect information and training traffic scenarios as well as corresponding traffic risk labels.

[0039] The difference between the predicted risk value and the risk reference threshold is calculated to obtain the traffic risk parameters corresponding to the passing vehicle.

[0040] A second aspect of this invention discloses a vehicle traffic control system based on defect detection, the system comprising:

[0041] The acquisition module is used to acquire the vehicle identifier of the vehicle that wants to pass through the target checkpoint device;

[0042] The determination module is used to determine the vehicle defect information corresponding to the passing vehicle based on the vehicle identifier, according to the preset vehicle detection history data.

[0043] The prediction module is used to predict the passage scenario corresponding to the passing vehicle based on the equipment information of the target checkpoint equipment and the vehicle identifier;

[0044] The calculation module is used to calculate the passage risk parameters corresponding to the passing vehicle based on the vehicle defect information and the passage scenario, using a risk identification algorithm; the passage risk parameters indicate the degree of risk of allowing the passing vehicle to pass through the target checkpoint equipment.

[0045] As an optional implementation, in a second aspect of the invention, the vehicle identification includes at least one of vehicle sensor data, vehicle license plate, vehicle inspection number, and facial image of a person in the vehicle; the vehicle sensor data includes at least one of vehicle image data, vehicle sound data, vehicle light reflection three-dimensional model data, and vehicle temperature and humidity data.

[0046] As an optional implementation, in a second aspect of the invention, the determining module determines the specific method by which it determines the vehicle defect information corresponding to the passing vehicle based on preset vehicle inspection history data and the vehicle identifier, including:

[0047] The vehicle identifier is matched against the vehicle detection history database to obtain the matching result.

[0048] When the matching result indicates that a matching record exists, obtain multiple vehicle detection records obtained through the matching process.

[0049] When the matching result is that no matching record exists, at least one similar vehicle is identified from the multiple detected vehicles in the vehicle detection history database based on the vehicle identifier, and the vehicle detection records corresponding to all the similar vehicles are obtained.

[0050] Based on the vehicle inspection records, determine the vehicle defect information corresponding to the passing vehicle.

[0051] As an optional implementation, in a second aspect of the invention, the specific method by which the determining module determines at least one similar vehicle based on the vehicle identifier in the vehicle detection history database includes:

[0052] The vehicle sensor data of the passing vehicles is input into a trained detection elapsed time prediction neural network to obtain the detection elapsed time corresponding to the passing vehicles; the detection elapsed time prediction neural network is trained by a training dataset that includes multiple training vehicle sensor data and corresponding time distance labels from the previous detection to the current time.

[0053] Calculate the difference between the current time point and the elapsed detection time to obtain the possible last detection time for the passing vehicle;

[0054] For each vehicle detected in the vehicle detection history database, obtain the vehicle data and the most recent historical detection time point corresponding to the detected vehicle.

[0055] Calculate the first similarity between the vehicle data and the vehicle identifier;

[0056] Calculate the first time difference between the most recent historical detection time and the possible last detection time;

[0057] Calculate the ratio of the first similarity to the first time difference to obtain the similarity parameter corresponding to the detected vehicle;

[0058] The detected vehicles whose similarity parameter is greater than the parameter threshold are identified as similar vehicles.

[0059] As an optional implementation, in a second aspect of the invention, the specific method by which the determining module determines the vehicle defect information corresponding to the passing vehicle based on the vehicle inspection record includes:

[0060] For each vehicle detection record, calculate the detection time corresponding to the vehicle detection record and the second time difference at the current time point;

[0061] Calculate the second similarity between the vehicle information corresponding to the vehicle detection record and the vehicle identifier;

[0062] Calculate the difference between the number of defects detected in the vehicle inspection record and the average number; the average number is the average number of defects detected in all the vehicle inspection records.

[0063] Calculate the product of the second time difference and the quantity difference, and calculate the ratio of the second similarity to the product to obtain the record priority corresponding to the vehicle detection record;

[0064] The defects detected in the vehicle detection record with the highest record priority are identified as the vehicle defect information corresponding to the passing vehicle.

[0065] As an optional implementation, in a second aspect of the present invention, the vehicle defect information includes a defect type corresponding to at least one vehicle part; the vehicle part is a door, front, body, chassis, roof, rear, trunk, interior space, or wheel.

[0066] As an optional implementation, in a second aspect of the invention, the prediction module predicts the specific method of the passage scenario corresponding to the passing vehicle based on the device information of the target checkpoint device and the vehicle identifier, including:

[0067] The device information of the target checkpoint device is input into a trained first passage scene prediction neural network to obtain the first scene prediction result corresponding to the target checkpoint device; the first passage scene prediction neural network is trained using a training dataset that includes multiple training device information and corresponding passage scene annotations; the device information includes device location, device model, device hardware parameters and device software parameters;

[0068] The vehicle identifier is input into a trained second traffic scene prediction neural network to obtain a second scene prediction result corresponding to the passing vehicle; the second traffic scene prediction neural network is trained using a training dataset that includes multiple training vehicle identifiers and corresponding traffic scene annotations;

[0069] The intersection of the first scenario prediction result and the second scenario prediction result is calculated to obtain the passage scenario corresponding to the passing vehicle; the passage scenario is the factory entry inspection scenario, the inspection process transfer scenario, the inspection completed and leaving the factory scenario, the faulty leaving the factory scenario, or the leaving the factory to perform a task scenario.

[0070] As an optional implementation, in the second aspect of the present invention, the specific method by which the calculation module calculates the traffic risk parameters corresponding to the passing vehicle based on the vehicle defect information and the traffic scenario, using a risk identification algorithm, includes:

[0071] Based on the mathematical correspondence between preset scenarios and risk thresholds, a first reference threshold corresponding to the passage scenario is determined;

[0072] Based on the preset mathematical correspondence between defect and risk thresholds, a second reference threshold corresponding to the vehicle defect information is determined;

[0073] Calculate the weighted average of the first reference threshold and the second reference threshold to obtain the risk reference threshold;

[0074] The vehicle defect information and the traffic scenario are input into a trained traffic risk prediction neural network to obtain the output predicted risk value; the traffic risk prediction neural network is trained using a training dataset that includes multiple training vehicle defect information and training traffic scenarios as well as corresponding traffic risk labels.

[0075] The difference between the predicted risk value and the risk reference threshold is calculated to obtain the traffic risk parameters corresponding to the passing vehicle.

[0076] A third aspect of the present invention discloses another vehicle traffic control system based on defect detection, the system comprising:

[0077] Memory containing executable program code;

[0078] A processor coupled to the memory;

[0079] The processor calls the executable program code stored in the memory to execute some or all of the steps in the vehicle traffic control method based on defect detection disclosed in the first aspect of the present invention.

[0080] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the vehicle traffic control method based on defect detection disclosed in the first aspect of the present invention.

[0081] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0082] This invention can determine the vehicle defect information corresponding to the passing vehicle based on the vehicle identification according to the preset historical vehicle detection data, and then accurately predict the passage scenario based on the equipment information of the target checkpoint equipment and the vehicle identification. Based on the vehicle defect information and the passage scenario, the invention can accurately calculate the vehicle passage risk, thereby improving the monitoring efficiency and accuracy of vehicle passage risk, providing accurate risk estimation reference for passage control, and improving the safety and intelligence of vehicle passage control. Attached Figure Description

[0083] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0084] Figure 1 This is a flowchart illustrating a vehicle traffic control method based on defect detection disclosed in an embodiment of the present invention.

[0085] Figure 2 This is a schematic diagram of a vehicle traffic control system based on defect detection disclosed in an embodiment of the present invention.

[0086] Figure 3 This is a schematic diagram of another vehicle traffic control system based on defect detection disclosed in an embodiment of the present invention. Detailed Implementation

[0087] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0088] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0089] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0090] This invention discloses a vehicle traffic control method and system based on defect detection. It can determine the vehicle defect information corresponding to a passing vehicle based on preset historical vehicle detection data and vehicle identification, and then accurately predict the traffic scenario based on the equipment information of the target checkpoint and the vehicle identification. This allows for accurate calculation of the vehicle's traffic risk based on the vehicle defect information and the traffic scenario, thereby improving the efficiency and accuracy of vehicle traffic risk monitoring, providing accurate risk estimation references for traffic control, and enhancing the safety and intelligence of vehicle traffic control. Detailed descriptions follow.

[0091] Example 1

[0092] Please see Figure 1 , Figure 1 This is a flowchart illustrating a vehicle traffic control method based on defect detection disclosed in an embodiment of the present invention. Wherein, Figure 1 The described defect detection-based vehicle access control method can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 1 As shown, the vehicle access control method based on defect detection may include the following operations:

[0093] 101. Obtain the vehicle identification of the vehicle that intends to pass through the target checkpoint.

[0094] 102. Based on the preset historical vehicle inspection data, determine the vehicle defect information corresponding to the passing vehicle according to the vehicle identification.

[0095] 103. Based on the equipment information and vehicle identification of the target checkpoint equipment, predict the corresponding traffic scenarios for passing vehicles.

[0096] 104. Based on vehicle defect information and traffic scenarios, calculate the traffic risk parameters corresponding to the passing vehicles using a risk identification algorithm.

[0097] Optionally, the passage risk parameter indicates the level of risk at which vehicles are permitted to pass through the target checkpoint equipment.

[0098] As can be seen, the above-described embodiments of the invention can determine the vehicle defect information corresponding to the passing vehicle based on the vehicle identification according to the preset historical vehicle detection data, and then accurately predict the passage scenario based on the equipment information of the target checkpoint equipment and the vehicle identification. Based on the vehicle defect information and the passage scenario, the passage risk of the vehicle can be accurately calculated, thereby improving the monitoring efficiency and accuracy of vehicle passage risk, providing accurate risk estimation reference for passage control, and improving the safety and intelligence of vehicle passage control.

[0099] As an optional embodiment, in the above steps, the vehicle identification includes at least one of vehicle sensor data, vehicle license plate, vehicle inspection number, and facial image of a person in the vehicle; the vehicle sensor data includes at least one of vehicle image data, vehicle sound data, vehicle light reflection three-dimensional model data, and vehicle temperature and humidity data.

[0100] As can be seen, the specific content of the vehicle identification is defined through the above optional embodiments, which can fully characterize the features of passing vehicles. This can then be used to accurately predict vehicle defects and communication scenarios, helping to improve the monitoring efficiency and accuracy of vehicle traffic risks, providing accurate risk estimation references for traffic control, and improving the safety and intelligence of vehicle traffic control.

[0101] As an optional embodiment, the step above, determining the vehicle defect information corresponding to the passing vehicle based on preset vehicle detection history data and vehicle identification, includes:

[0102] The matching results are obtained by matching the vehicle identification in the vehicle detection history database.

[0103] When the matching result indicates that a matching record exists, retrieve the multiple vehicle detection records obtained from the matching;

[0104] When the matching result is that no matching record exists, at least one similar vehicle is identified based on the vehicle identifier in the vehicle detection history database of multiple detected vehicles, and the vehicle detection records corresponding to all similar vehicles are obtained.

[0105] Based on the vehicle inspection records, determine the vehicle defect information corresponding to the vehicles passing through.

[0106] As can be seen, through the above optional embodiments, accurate vehicle detection records can be obtained by matching vehicle identification in the vehicle detection history database or by identifying similar vehicles, so as to accurately determine defects, facilitate subsequent risk assessment, help improve the monitoring efficiency and accuracy of vehicle traffic risks, provide accurate risk estimation reference for traffic control, and improve the safety and intelligence of vehicle traffic control.

[0107] As an optional embodiment, the step described above, identifying at least one similar vehicle based on the vehicle identifier in the vehicle detection history database, includes:

[0108] The vehicle sensor data of passing vehicles is input into the trained detection elapsed time prediction neural network to obtain the detection elapsed time corresponding to the passing vehicles; optionally, the detection elapsed time prediction neural network is trained by a training dataset that includes multiple training vehicle sensor data and the corresponding time distance label of the last detection from the current time.

[0109] Calculate the difference between the current time and the elapsed detection time to obtain the possible last detection time for the passing vehicle;

[0110] For each vehicle detected in the vehicle detection history database, obtain the vehicle data and the most recent historical detection time point corresponding to that vehicle.

[0111] Calculate the first similarity between vehicle data and vehicle identification;

[0112] Calculate the first time difference between the most recent historical detection time and the possible last detection time;

[0113] Calculate the ratio of the first similarity score to the first time difference to obtain the similarity parameter corresponding to the detected vehicle;

[0114] Vehicles whose similarity parameter is greater than the parameter threshold are identified as similar vehicles.

[0115] As can be seen, through the above optional embodiments, similar vehicles can be accurately screened based on the vehicle data of the detected vehicle and the proximity between the detection time point and the passing vehicles, so as to obtain accurate vehicle detection records, accurately determine defects, facilitate subsequent risk assessment, help improve the monitoring efficiency and accuracy of vehicle traffic risk, provide accurate risk estimation reference for traffic control, and improve the safety and intelligence of vehicle traffic control.

[0116] As an optional embodiment, the step above, determining the vehicle defect information corresponding to the passing vehicle based on the vehicle inspection record, includes:

[0117] For each vehicle inspection record, calculate the inspection time corresponding to that vehicle inspection record and the second time difference at the current time point;

[0118] Calculate the second similarity between the vehicle information and vehicle identification corresponding to the vehicle inspection record;

[0119] Calculate the difference between the number of defects detected in the vehicle inspection record and the average number; optionally, the average number is the average number of defects detected in all vehicle inspection records.

[0120] Calculate the product of the second time difference and the quantity difference, and calculate the ratio of the second similarity to the product to obtain the record priority corresponding to the vehicle detection record;

[0121] Defects detected in the highest priority vehicle inspection records are identified as vehicle defect information corresponding to the passing vehicles.

[0122] As can be seen, through the above optional embodiments, accurate vehicle detection records can be obtained based on the calculation of information similarity between vehicle information in each historical vehicle detection record and vehicle information of the vehicle to be detected, and threshold screening. This enables precise defect identification, facilitates subsequent risk assessment, helps improve the monitoring efficiency and accuracy of vehicle traffic risk, provides accurate risk estimation reference for traffic control, and improves the safety and intelligence of vehicle traffic control.

[0123] As an optional embodiment, the vehicle defect information in the above steps includes a defect type corresponding to at least one vehicle part; the vehicle part is the door, front, body, chassis, roof, rear, trunk, interior space, or wheels.

[0124] As can be seen, the above optional embodiments define the details of vehicle defect information, enabling the vehicle defect information to accurately characterize the vehicle's defect status, facilitating subsequent accurate traffic risk calculation, assisting in improving the monitoring efficiency and accuracy of vehicle traffic risk, providing accurate risk estimation reference for traffic control, and improving the safety and intelligence of vehicle traffic control.

[0125] As an optional embodiment, the step above, predicting the passage scenario corresponding to the passing vehicle based on the device information and vehicle identification of the target checkpoint device, includes:

[0126] The device information of the target level device is input into the trained first passage scene prediction neural network to obtain the first scene prediction result corresponding to the target level device; optionally, the first passage scene prediction neural network is trained through a training dataset that includes multiple training device information and corresponding passage scene annotations; the device information includes device location, device model, device hardware parameters and device software parameters;

[0127] The vehicle identifier is input into the trained second traffic scene prediction neural network to obtain the second scene prediction result corresponding to the passing vehicle; optionally, the second traffic scene prediction neural network is trained using a training dataset that includes multiple training vehicle identifiers and corresponding traffic scene annotations.

[0128] The intersection of the prediction results of the first scenario and the prediction results of the second scenario is calculated to obtain the passage scenario corresponding to the passing vehicle; the passage scenario is the factory inspection scenario, the transfer scenario in the inspection process, the factory exit scenario after inspection, the factory exit scenario due to failure, or the factory exit scenario for performing a task.

[0129] As can be seen, through the above optional embodiments, two trained scene prediction neural networks can be used to predict the scene based on the checkpoint equipment information and vehicle information respectively, and the accurate passage scene can be determined based on the intersection calculation. This facilitates the subsequent accurate calculation of passage risk, helps to improve the monitoring efficiency and accuracy of vehicle passage risk, provides accurate risk estimation reference for passage control, and improves the safety and intelligence of vehicle passage control.

[0130] As an optional embodiment, the step described above, calculating the traffic risk parameters corresponding to the passing vehicle based on the vehicle defect information and traffic scenario using a risk identification algorithm, includes:

[0131] Based on the mathematical correspondence between preset scenarios and risk thresholds, determine the first reference threshold corresponding to the traffic scenario;

[0132] Based on the mathematical correspondence between preset defects and risk thresholds, a second reference threshold corresponding to vehicle defect information is determined.

[0133] Calculate the weighted average of the first and second reference thresholds to obtain the risk reference threshold;

[0134] Vehicle defect information and traffic scenarios are input into a trained traffic risk prediction neural network to obtain the output predicted risk value; optionally, the traffic risk prediction neural network is trained using a training dataset that includes multiple training vehicle defect information and training traffic scenarios as well as corresponding traffic risk labels.

[0135] The difference between the predicted risk value and the risk reference threshold is calculated to obtain the traffic risk parameters corresponding to the passing vehicles.

[0136] As can be seen, through the above optional embodiments, the risk thresholds corresponding to vehicle defects and traffic scenarios can be determined based on the preset risk threshold mathematical relationship to accurately calculate the reference threshold. Then, the risk value is predicted based on the neural network, and the accurate traffic risk is determined based on the difference calculation. This ensures that the calculated risk value takes into account the possible risk level when traffic scenarios and vehicle defects exist alone, thereby improving the monitoring efficiency and accuracy of vehicle traffic risk, providing accurate risk estimation reference for traffic control, and improving the safety and intelligence of vehicle traffic control.

[0137] Example 2

[0138] Please see Figure 2 , Figure 2 This is a schematic diagram of a vehicle traffic control system based on defect detection disclosed in an embodiment of the present invention. Figure 2 The described defect-detection-based vehicle access control system can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 2 As shown, the defect detection-based vehicle access control system may include:

[0139] The acquisition module 201 is used to acquire the vehicle identifier of the vehicle that wants to pass through the target checkpoint device.

[0140] The determination module 202 is used to determine the vehicle defect information corresponding to the passing vehicle based on the preset vehicle detection history data and the vehicle identification.

[0141] The prediction module 203 is used to predict the passage scenario corresponding to the passing vehicle based on the equipment information and vehicle identification of the target checkpoint equipment.

[0142] The calculation module 204 is used to calculate the traffic risk parameters corresponding to the passing vehicles based on the vehicle defect information and traffic scenario, using a risk identification algorithm.

[0143] Optionally, the passage risk parameter indicates the level of risk at which vehicles are permitted to pass through the target checkpoint equipment.

[0144] As can be seen, the above-described embodiments of the invention can determine the vehicle defect information corresponding to the passing vehicle based on the vehicle identification according to the preset historical vehicle detection data, and then accurately predict the passage scenario based on the equipment information of the target checkpoint equipment and the vehicle identification. Based on the vehicle defect information and the passage scenario, the passage risk of the vehicle can be accurately calculated, thereby improving the monitoring efficiency and accuracy of vehicle passage risk, providing accurate risk estimation reference for passage control, and improving the safety and intelligence of vehicle passage control.

[0145] As an optional embodiment, the vehicle identification includes at least one of vehicle sensor data, vehicle license plate, vehicle inspection number, and facial image of a person in the vehicle; the vehicle sensor data includes at least one of vehicle image data, vehicle sound data, vehicle light reflection three-dimensional model data, and vehicle temperature and humidity data.

[0146] As can be seen, the specific content of the vehicle identification is defined through the above optional embodiments, which can fully characterize the features of passing vehicles. This can then be used to accurately predict vehicle defects and communication scenarios, helping to improve the monitoring efficiency and accuracy of vehicle traffic risks, providing accurate risk estimation references for traffic control, and improving the safety and intelligence of vehicle traffic control.

[0147] As an optional embodiment, the determining module determines the specific method of vehicle defect information corresponding to the passing vehicle based on preset vehicle inspection history data and vehicle identification, including:

[0148] The matching results are obtained by matching the vehicle identification in the vehicle detection history database.

[0149] When the matching result indicates that a matching record exists, retrieve the multiple vehicle detection records obtained from the matching;

[0150] When the matching result is that no matching record exists, at least one similar vehicle is identified based on the vehicle identifier in the vehicle detection history database of multiple detected vehicles, and the vehicle detection records corresponding to all similar vehicles are obtained.

[0151] Based on the vehicle inspection records, determine the vehicle defect information corresponding to the vehicles passing through.

[0152] As can be seen, through the above optional embodiments, accurate vehicle detection records can be obtained by matching vehicle identification in the vehicle detection history database or by identifying similar vehicles, so as to accurately determine defects, facilitate subsequent risk assessment, help improve the monitoring efficiency and accuracy of vehicle traffic risks, provide accurate risk estimation reference for traffic control, and improve the safety and intelligence of vehicle traffic control.

[0153] As an optional embodiment, the specific method by which the determining module identifies at least one similar vehicle based on vehicle identifiers in a vehicle detection history database includes:

[0154] The vehicle sensor data of passing vehicles is input into the trained detection elapsed time prediction neural network to obtain the detection elapsed time corresponding to the passing vehicles; optionally, the detection elapsed time prediction neural network is trained by a training dataset that includes multiple training vehicle sensor data and the corresponding time distance label of the last detection from the current time.

[0155] Calculate the difference between the current time and the elapsed detection time to obtain the possible last detection time for the passing vehicle;

[0156] For each vehicle detected in the vehicle detection history database, obtain the vehicle data and the most recent historical detection time point corresponding to that vehicle.

[0157] Calculate the first similarity between vehicle data and vehicle identification;

[0158] Calculate the first time difference between the most recent historical detection time and the possible last detection time;

[0159] Calculate the ratio of the first similarity score to the first time difference to obtain the similarity parameter corresponding to the detected vehicle;

[0160] Vehicles whose similarity parameter is greater than the parameter threshold are identified as similar vehicles.

[0161] As can be seen, through the above optional embodiments, similar vehicles can be accurately screened based on the vehicle data of the detected vehicle and the proximity between the detection time point and the passing vehicles, so as to obtain accurate vehicle detection records, accurately determine defects, facilitate subsequent risk assessment, help improve the monitoring efficiency and accuracy of vehicle traffic risk, provide accurate risk estimation reference for traffic control, and improve the safety and intelligence of vehicle traffic control.

[0162] As an optional embodiment, the method by which the determining module determines the specific vehicle defect information corresponding to the passing vehicle based on the vehicle inspection record includes:

[0163] For each vehicle inspection record, calculate the inspection time corresponding to that vehicle inspection record and the second time difference at the current time point;

[0164] Calculate the second similarity between the vehicle information and vehicle identification corresponding to the vehicle inspection record;

[0165] Calculate the difference between the number of defects detected in the vehicle inspection record and the average number; optionally, the average number is the average number of defects detected in all vehicle inspection records.

[0166] Calculate the product of the second time difference and the quantity difference, and calculate the ratio of the second similarity to the product to obtain the record priority corresponding to the vehicle detection record;

[0167] Defects detected in the highest priority vehicle inspection records are identified as vehicle defect information corresponding to the passing vehicles.

[0168] As can be seen, through the above optional embodiments, accurate vehicle detection records can be obtained based on the calculation of information similarity between vehicle information in each historical vehicle detection record and vehicle information of the vehicle to be detected, and threshold screening. This enables precise defect identification, facilitates subsequent risk assessment, helps improve the monitoring efficiency and accuracy of vehicle traffic risk, provides accurate risk estimation reference for traffic control, and improves the safety and intelligence of vehicle traffic control.

[0169] As an optional embodiment, the vehicle defect information includes a defect type corresponding to at least one vehicle part; the vehicle part may be a door, front, body, chassis, roof, rear, trunk, interior space, or wheel.

[0170] As can be seen, the above optional embodiments define the details of vehicle defect information, enabling the vehicle defect information to accurately characterize the vehicle's defect status, facilitating subsequent accurate traffic risk calculation, assisting in improving the monitoring efficiency and accuracy of vehicle traffic risk, providing accurate risk estimation reference for traffic control, and improving the safety and intelligence of vehicle traffic control.

[0171] As an optional embodiment, the prediction module predicts the specific method of the passage scenario corresponding to the passing vehicle based on the device information and vehicle identification of the target checkpoint equipment, including:

[0172] The device information of the target level device is input into the trained first passage scene prediction neural network to obtain the first scene prediction result corresponding to the target level device; optionally, the first passage scene prediction neural network is trained through a training dataset that includes multiple training device information and corresponding passage scene annotations; the device information includes device location, device model, device hardware parameters and device software parameters;

[0173] The vehicle identifier is input into the trained second traffic scene prediction neural network to obtain the second scene prediction result corresponding to the passing vehicle; optionally, the second traffic scene prediction neural network is trained using a training dataset that includes multiple training vehicle identifiers and corresponding traffic scene annotations.

[0174] The intersection of the prediction results of the first scenario and the prediction results of the second scenario is calculated to obtain the passage scenario corresponding to the passing vehicle; the passage scenario is the factory inspection scenario, the transfer scenario in the inspection process, the factory exit scenario after inspection, the factory exit scenario due to failure, or the factory exit scenario for performing a task.

[0175] As can be seen, through the above optional embodiments, two trained scene prediction neural networks can be used to predict the scene based on the checkpoint equipment information and vehicle information respectively, and the accurate passage scene can be determined based on the intersection calculation. This facilitates the subsequent accurate calculation of passage risk, helps to improve the monitoring efficiency and accuracy of vehicle passage risk, provides accurate risk estimation reference for passage control, and improves the safety and intelligence of vehicle passage control.

[0176] As an optional embodiment, the calculation module calculates the traffic risk parameters corresponding to the passing vehicles based on vehicle defect information and traffic scenarios, using a risk identification algorithm, in the following specific ways:

[0177] Based on the mathematical correspondence between preset scenarios and risk thresholds, determine the first reference threshold corresponding to the traffic scenario;

[0178] Based on the mathematical correspondence between preset defects and risk thresholds, a second reference threshold corresponding to vehicle defect information is determined.

[0179] Calculate the weighted average of the first and second reference thresholds to obtain the risk reference threshold;

[0180] Vehicle defect information and traffic scenarios are input into a trained traffic risk prediction neural network to obtain the output predicted risk value; optionally, the traffic risk prediction neural network is trained using a training dataset that includes multiple training vehicle defect information and training traffic scenarios as well as corresponding traffic risk labels.

[0181] The difference between the predicted risk value and the risk reference threshold is calculated to obtain the traffic risk parameters corresponding to the passing vehicles.

[0182] As can be seen, through the above optional embodiments, the risk thresholds corresponding to vehicle defects and traffic scenarios can be determined based on the preset risk threshold mathematical relationship to accurately calculate the reference threshold. Then, the risk value is predicted based on the neural network, and the accurate traffic risk is determined based on the difference calculation. This ensures that the calculated risk value takes into account the possible risk level when traffic scenarios and vehicle defects exist alone, thereby improving the monitoring efficiency and accuracy of vehicle traffic risk, providing accurate risk estimation reference for traffic control, and improving the safety and intelligence of vehicle traffic control.

[0183] Example 3

[0184] Please see Figure 3 , Figure 3 This is another vehicle traffic control system based on defect detection disclosed in the embodiments of the present invention. Figure 3The described defect-detection-based vehicle access control system is applied in a data processing system / data processing equipment / data processing server (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the defect detection-based vehicle access control system may include:

[0185] Memory 301 storing executable program code;

[0186] Processor 302 coupled to memory 301;

[0187] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the vehicle traffic control method based on defect detection described in Embodiment 1.

[0188] Example 4

[0189] This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the vehicle traffic control method based on defect detection described in Embodiment 1.

[0190] Example 5

[0191] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the vehicle traffic control method based on defect detection described in Embodiment 1.

[0192] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0193] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0194] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0195] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0196] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0197] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0198] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0199] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0200] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0201] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0202] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0203] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0204] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0205] Finally, it should be noted that the vehicle traffic control method and system based on defect detection disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle passage control method based on defect detection, characterized by, The method includes: Obtain the vehicle identification of the vehicle intending to pass through the target checkpoint equipment; Based on preset vehicle inspection history data, the vehicle defect information corresponding to the passing vehicle is determined according to the vehicle identifier. Based on the equipment information of the target checkpoint equipment and the vehicle identification, the passage scenario corresponding to the passing vehicle is predicted; the passage scenario is the factory entry inspection scenario, the transfer scenario in the inspection process, the factory exit scenario after inspection, the factory exit scenario due to failure, or the factory exit scenario for performing a task. Based on the vehicle defect information and the passage scenario, and using a risk identification algorithm, the passage risk parameters corresponding to the passing vehicle are calculated; the passage risk parameters indicate the degree of risk of allowing the passing vehicle to pass through the target checkpoint equipment.

2. The vehicle passage control method based on defect detection according to claim 1, characterized by, The vehicle identification includes at least one of vehicle sensor data, vehicle license plate, vehicle inspection number, and facial image of a person in the vehicle; the vehicle sensor data includes at least one of vehicle image data, vehicle sound data, vehicle light reflection three-dimensional model data, and vehicle temperature and humidity data.

3. The vehicle passage control method based on defect detection according to claim 1, characterized by, The method of determining the vehicle defect information corresponding to the passing vehicle based on the vehicle identifier, according to preset historical vehicle detection data, includes: The vehicle identifier is matched against the vehicle detection history database to obtain the matching result. When the matching result indicates that a matching record exists, obtain multiple vehicle detection records obtained through the matching process. When the matching result is that no matching record exists, at least one similar vehicle is identified from the multiple detected vehicles in the vehicle detection history database based on the vehicle identifier, and the vehicle detection records corresponding to all the similar vehicles are obtained. Based on the vehicle inspection records, determine the vehicle defect information corresponding to the passing vehicle.

4. The vehicle traffic control method based on defect detection according to claim 3, characterized in that, The step of identifying at least one similar vehicle from multiple detected vehicles in the vehicle detection history database based on the vehicle identifier includes: The vehicle sensor data of the passing vehicles is input into a trained detection elapsed time prediction neural network to obtain the detection elapsed time corresponding to the passing vehicles; the detection elapsed time prediction neural network is trained by a training dataset that includes multiple training vehicle sensor data and corresponding time distance labels from the previous detection to the current time. Calculate the difference between the current time point and the elapsed detection time to obtain the possible last detection time for the passing vehicle; For each vehicle detected in the vehicle detection history database, obtain the vehicle data and the most recent historical detection time point corresponding to the detected vehicle. Calculate the first similarity between the vehicle data and the vehicle identifier; Calculate the first time difference between the most recent historical detection time and the possible last detection time; Calculate the ratio of the first similarity to the first time difference to obtain the similarity parameter corresponding to the detected vehicle; The detected vehicles whose similarity parameter is greater than the parameter threshold are identified as similar vehicles.

5. The vehicle traffic control method based on defect detection according to claim 3, characterized in that, The step of determining the vehicle defect information corresponding to the passing vehicle based on the vehicle inspection record includes: For each vehicle detection record, calculate the detection time corresponding to the vehicle detection record and the second time difference at the current time point; Calculate the second similarity between the vehicle information corresponding to the vehicle detection record and the vehicle identifier; Calculate the difference between the number of defects detected in the vehicle inspection record and the average number; the average number is the average number of defects detected in all the vehicle inspection records. Calculate the product of the second time difference and the quantity difference, and calculate the ratio of the second similarity to the product to obtain the record priority corresponding to the vehicle detection record; The defects detected in the vehicle detection record with the highest record priority are identified as the vehicle defect information corresponding to the passing vehicle.

6. The vehicle traffic control method based on defect detection according to claim 1, characterized in that, The vehicle defect information includes a defect type corresponding to at least one vehicle part; the vehicle part is the door, front, body, chassis, roof, rear, trunk, interior space, or wheels.

7. The vehicle traffic control method based on defect detection according to claim 6, characterized in that, The step of predicting the passage scenario corresponding to the passing vehicle based on the device information of the target checkpoint equipment and the vehicle identifier includes: The device information of the target checkpoint device is input into a trained first passage scene prediction neural network to obtain the first scene prediction result corresponding to the target checkpoint device; the first passage scene prediction neural network is trained using a training dataset that includes multiple training device information and corresponding passage scene annotations; the device information includes device location, device model, device hardware parameters and device software parameters; The vehicle identifier is input into a trained second traffic scene prediction neural network to obtain a second scene prediction result corresponding to the passing vehicle; the second traffic scene prediction neural network is trained using a training dataset that includes multiple training vehicle identifiers and corresponding traffic scene annotations; The intersection of the first scenario prediction result and the second scenario prediction result is calculated to obtain the traffic scenario corresponding to the passing vehicle.

8. The vehicle traffic control method based on defect detection according to claim 7, characterized in that, The step of calculating the traffic risk parameters corresponding to the passing vehicle based on the vehicle defect information and the traffic scenario, using a risk identification algorithm, includes: Based on the mathematical correspondence between preset scenarios and risk thresholds, a first reference threshold corresponding to the passage scenario is determined; Based on the preset mathematical correspondence between defect and risk thresholds, a second reference threshold corresponding to the vehicle defect information is determined; Calculate the weighted average of the first reference threshold and the second reference threshold to obtain the risk reference threshold; The vehicle defect information and the traffic scenario are input into a trained traffic risk prediction neural network to obtain the output predicted risk value; the traffic risk prediction neural network is trained using a training dataset that includes multiple training vehicle defect information and training traffic scenarios as well as corresponding traffic risk labels. The difference between the predicted risk value and the risk reference threshold is calculated to obtain the traffic risk parameters corresponding to the passing vehicle.

9. A vehicle traffic control system based on defect detection, characterized in that, The system includes: The acquisition module is used to acquire the vehicle identifiers of vehicles that wish to pass through the target checkpoint equipment; The determination module is used to determine the vehicle defect information corresponding to the passing vehicle based on the vehicle identifier, according to the preset vehicle detection history data. The prediction module is used to predict the passage scenario corresponding to the passing vehicle based on the equipment information of the target checkpoint equipment and the vehicle identification; the passage scenario is a factory entry inspection scenario, a transfer scenario during the inspection process, a factory exit scenario after inspection, a factory exit scenario due to a fault, or a factory exit scenario for performing a task. The calculation module is used to calculate the passage risk parameters corresponding to the passing vehicle based on the vehicle defect information and the passage scenario, using a risk identification algorithm; the passage risk parameters indicate the degree of risk of allowing the passing vehicle to pass through the target checkpoint equipment.

10. A vehicle traffic control system based on defect detection, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the vehicle traffic control method based on defect detection as described in any one of claims 1-8.

Images