Method and system for processing and merging vehicle passage data into verified records with determination of their reliability

Abstract

FIELD: information technology; data processing.SUBSTANCE: invention relates in particular to the processing and combining of data on the passage of vehicles obtained from various technical registration devices, with the formation of verified records and determination of the reliability of the data, including for use in toll collection systems for travel on toll roads. The method of processing and combining data on vehicle travel into verified records with the determination of their reliability is implemented using a processor and a data storage device. Receive real-time data on vehicle movements from front photo and video recording systems, DSRC identification equipment, vehicle classification system equipment, vehicle axle photo recording system equipment, and rear photo and video recording system equipment. The obtained data is normalized and supplemented, and previously accumulated data on vehicle movements is also obtained. Normalized and supplemented data are compared by selecting the pairs of data to be compared, obtained from different equipment, identifying the matching and differing data in each pair, and comparing them with previously accumulated data on vehicle travel. Based on the comparison results, the reliability of the data in each pair is determined, the pairs of data with the highest reliability are identified, and verified records of vehicle travel are generated on their basis.EFFECT: reduction in the likelihood of incorrect processing of records of vehicle passages in difficult road conditions and non-standard situations, including when a vehicle changes lanes, changes in speed, difficult weather conditions, and equipment failures, as well as an increase in the accuracy and speed of processing data on vehicle passages and a reduction in the number of records requiring additional processing by the operator.8 cl, 2 dwg, 2 tbl

Description

AREA OF TECHNOLOGY

[0001] This technical solution generally relates to the field of information technology, data processing, and image mining, specifically computer vision and visual search systems. It is designed to process and combine vehicle travel data into verified records, determine their validity, and then use them, including in toll collection systems for toll roads. TECHNOLOGY LEVEL

[0002] Video surveillance systems with automatic image recognition are based on fast algorithms that analyze images from optical-electronic modules (OEMs) in real time. The computing resources required for recognition are limited by the technical specifications of the processing server, which is part of the reading module (RM) located at the observation point, as well as the required processing time. The accuracy and feasibility of the recognition task depend significantly on image quality, which in turn is determined by external conditions such as illumination, visibility, and the specific nature of the objects being observed. Among video surveillance systems, vehicle identification systems (VIS) based on license plate recognition are widely used.Environmental factors affect the degree of contamination of the license plate surface and illumination levels, leading to a loss of image quality (contrast, brightness, clarity) and the appearance of noise in the OEM circuit. This makes additional image processing necessary to maximize distortion compensation and noise suppression. (c) K.L. Tassov, "IMAGE PRE-PROCESSING METHODS IN VEHICLE IDENTIFICATION SYSTEMS."

[0003] A solution is known from the prior art, described in CN116012962B "A fusion method of ETC toll lane transaction and plate recognition based on time sequence queue", published on 21.01.2025, which describes a method for integrating transactions of passage on a toll lane and recognition of license plates based on a time series queue, which is characterized in that it includes the following steps: installing two sets of equipment for recognizing license plates on each toll lane; creating a hash table for storing a buffer of the relationship of the movement of vehicles passing along the current toll lane, etc.; building an empty queue of time series of transactions, a time series queue of recognition of front license plates and a time series queue of recognition of rear license plates; obtaining matching vehicle data; and performing a conformity assessment.

[0004] Also known from the prior art is a solution described in US10885369B2 "Electronic Toll Management and Vehicle Identification," published April 18, 2019, which describes vehicle identification in a toll collection system. This includes accessing image data of a first vehicle and obtaining license plate data from the obtained image data of the first vehicle. A set of records is accessed. Each record contains vehicle license plate data. The license plate data of the first vehicle is compared with the license plate data of the vehicles in the record set. Based on the results of the comparison of license plate data, a set of vehicles is determined from among the vehicles with records in this set.

[0005] The disadvantages of the solutions known from the prior art are the inability to minimize the likelihood of incorrect processing of records of vehicle passages in difficult road conditions, non-standard situations, low and high vehicle speeds. DISCLOSURE OF THE INVENTION

[0006] This technical solution is aimed at eliminating the shortcomings inherent in existing solutions known from the prior art.

[0007] The technical problem solved by this technical solution is the consolidation of vehicle travel data for subsequent processing, for example, for toll collection purposes, in such a way as to minimize the likelihood of incorrect processing of vehicle travel records in difficult road conditions, non-standard situations, low and high vehicle speeds, and to minimize the number of errors.

[0008] The technical result that is achieved by solving the above problem is the ability to minimize the likelihood of incorrect processing of records of vehicle passages in difficult road conditions, non-standard situations, and low and high vehicle speeds.

[0009] An additional technical result is an increase in the accuracy and speed of processing vehicle passage data obtained from various sources; the stability of structuring and selection of vehicle passage data in non-standard situations (e.g., changing lanes under a toll collection system; reverse movement; deceleration and acceleration; difficult weather conditions; equipment failures); a reduction in the number of vehicle passage records transmitted to the operator for analysis when additional manual processing is required.

[0010] The specified technical result is achieved by implementing a method for processing and combining into verified records data on vehicle passages with determination of their reliability, implemented using a processor and a data storage device, including the following steps: receiving in real time data on vehicle passages from equipment of front photo and video recording systems, DSRC identification equipment, vehicle classification system equipment, equipment of a vehicle axle photo recording system, equipment of a rear photo and video recording system; normalizing and supplementing the received data on vehicle passages; receiving previously accumulated data on vehicle passages; comparing the normalized and supplemented data on vehicle passages: selecting pairs of data received from different equipment to be compared;The matching and different data for each of the data pairs are identified; the matching and different data for each of the data pairs are compared with previously accumulated data on the passage of vehicles; based on the comparison of the normalized and supplemented data on the passage of vehicles, their reliability in each of the data pairs is determined; the pairs of data with the highest reliability are identified from the normalized and supplemented data on the passage of vehicles; based on the identified pairs of data with the highest reliability, verified records of the passage of vehicles are compiled.

[0011] In one particular example of the implementation of the method, verified records of vehicle passages are used in toll collection systems for travel on toll roads.

[0012] Another particular example of implementing the method uses integration with external systems for data exchange.

[0013] In a particular embodiment of the method, certain reliabilities in each of the data pairs are used to search for anomalies in the data and allow for marking anomalous data for subsequent correction, clarification, exploitation and analysis.

[0014] Furthermore, the claimed technical result is achieved through the operation of a system for processing and combining into verified records data on vehicle passages with a determination of their reliability, containing at least one data processing device, at least one data storage device, at least one program, where one or more programs are stored on one or more data storage devices and executed on one or more data processing devices, wherein one or more programs ensure the execution of the following steps: receiving in real time data on vehicle passages from equipment of front photo and video recording systems, DSRC identification equipment, equipment of a vehicle classification system, equipment of a vehicle axle photo recording system, equipment of a rear photo and video recording system; normalizing and supplementing the received data on vehicle passages;previously accumulated data on vehicle journeys are obtained; normalized and supplemented data on vehicle journeys are compared: pairs of data to be compared, obtained from different equipment, are identified; matching and different data are identified for each of the data pairs; matching and different data for each of the data pairs are compared with previously accumulated data on vehicle journeys; based on the comparison of normalized and supplemented data on vehicle journeys, their reliability in each of the data pairs is determined; pairs of data with the highest reliability are identified from the normalized and supplemented data on vehicle journeys; verified records of vehicle journeys are compiled based on the identified pairs of data with the highest reliability.

[0015] In one particular example of the system implementation, verified records of vehicle passages are used in toll collection systems for travel on toll roads.

[0016] Another particular example of system implementation uses integration with external systems for data exchange.

[0017] In a particular embodiment of the system, certain reliability values ​​in each of the data pairs are used to search for anomalies in the data and allow the marking of anomalous data for subsequent correction, clarification, exploitation and analysis. BRIEF DESCRIPTION OF DRAWINGS

[0018] The features and advantages of the present technical solution will become apparent from the following detailed description and the accompanying drawings, in which: Fig. 1 illustrates a block diagram of the implementation of the claimed method. Fig. 2 illustrates a system for implementing the claimed method. IMPLEMENTATION OF THE INVENTION

[0019] The terms and concepts required to implement this technical solution will be described below.

[0020] DSRC(Dedicated Short Range Communications) is a dedicated short-range communication technology designed for high-speed communication between vehicles and infrastructure.

[0021] A message broker (also known as an integration broker or interface engine) is an architectural pattern in distributed systems; an application that converts a message from a source application using one protocol into a message using a destination application's protocol, thereby acting as an intermediary between them. In addition to converting messages from one format to another, a message broker's responsibilities also include: checking messages for errors; routing them to specific destinations; splitting messages into smaller messages, then aggregating the destinations' responses and sending the result to the source; storing messages in a database; calling web services; and distributing messages to subscribers if publisher-subscriber patterns are used. Using message brokers helps relieve web services in a distributed system by eliminating the need for resource-intensive operations like routing and searching for destinations when sending messages.In addition, the message broker can implement ordered distribution strategies and prioritization, load balancing, and more to improve efficiency.

[0022] RabbitMQ is a software message broker based on the AMQP standard—a replicable middleware focused on message processing. It consists of a server, HTTP, XMPP, and STOMP protocol support libraries, AMQP client libraries for Java and the .NET Framework, and various plugins (such as plugins for monitoring and management via HTTP or a web interface, or the "Shovel" plugin for passing messages between brokers). Clients for accessing RabbitMQ are available for a variety of programming languages, including Perl, Python, Ruby, and PHP. Horizontal scaling is supported for building cluster solutions.

[0023] The claimed technical solution may be implemented, for example, by a system, a machine-readable medium, a server, etc. In this technical solution, the term “system” means, among other things, a computer system, a computer (electronic computer), a CNC (computer numerical control), a PLC (programmable logic controller), computerized control systems, and any other devices capable of performing a given, clearly defined sequence of operations (actions, instructions).

[0024] A command processing unit is an electronic unit or integrated circuit (microprocessor) that executes machine instructions (programs).

[0025] The command processing unit reads and executes machine instructions (programs) from one or more storage devices, such as random access memory (RAM) and / or read-only memory (ROM). ROM may include, but is not limited to, hard disk drives (HDD), flash memory, solid-state drives (SSD), optical storage media (CD, DVD, BD, MD, etc.), etc.

[0026] A program is a sequence of instructions intended for execution by a computer control unit or command processing device.

[0027] The term "instructions" as used in this application may generally refer to software instructions or software commands that are written in a given programming language to perform a specific function, such as, for example, receiving and processing data, generating a user profile, receiving and transmitting signals, analyzing received data, identifying a user, etc. The instructions may be implemented in a variety of ways, including, for example, object-oriented methods. For example, the instructions may be implemented using the C++ programming language, Java, Python, various libraries (e.g., Microsoft Foundation Classes), etc. The instructions that perform the processes described in this solution may be transmitted via both wired and wireless data transmission channels, such as Wi-Fi, Bluetooth, USB, WLAN, LAN, etc.

[0028] The presented method for processing and combining into verified records data on vehicle passages with determination of their reliability (Fig. 1 shows a block diagram of the method - 100) solves the problems of ensuring the possibility of minimizing the probability of incorrect processing of records on vehicle passages in difficult road conditions, non-standard situations, low and high speeds of vehicles, as well as increasing the accuracy and speed of processing data on vehicle passages received from various sources; ensuring the stability of structuring and selection of data on vehicle passages in non-standard situations (for example: changing lanes of a vehicle under a toll collection system; reverse movement; deceleration and acceleration; difficult weather conditions; equipment failures);reducing the number of vehicle passage records transmitted to the operator for analysis when additional manual processing is required - by sequentially performing the following steps:• receive real-time vehicle passage data from front photo and video recording system equipment, DSRC identification equipment, vehicle classification system equipment, vehicle axle photo recording system equipment, and rear photo and video recording system equipment; (101 in Fig. 1)• normalize and supplement the received vehicle passage data; (102 in Fig. 1)• receive previously accumulated vehicle passage data (103 in Fig. 1);• compare normalized and supplemented vehicle passage data (104 in Fig. 1):• select the pairs of data to be compared, received from different equipment;• select matching and different data for each of the data pairs;• compare matching and different data for each of the data pairs with previously accumulated data on vehicle journeys; • based on the comparison of normalized and supplemented data on vehicle journeys, determine their reliability in each of the data pairs (105 in Fig. 1); • select from the normalized and supplemented data on vehicle journeys the data pairs with the highest reliability (106 in Fig. 1); • based on the selected data pairs with the highest reliability, compile verified records on vehicle journeys (107 in Fig. 1).;

[0029] In one embodiment, the described technical solution is an automated information system for processing and combining data on vehicle travel into verified records with a determination of their reliability, implemented through a message broker (for example, RabbitMQ) and relational databases.

[0030] The system receives real-time data on vehicle movements from frontal photo and video recording systems, DSRC identification equipment, vehicle classification systems, vehicle axle photo recording systems, and rear photo and video recording systems. The above equipment is installed on barrier-free toll collection systems. To travel on a toll road, drivers do not need to stop at barriers or waste time at toll booths. Vehicles pass without slowing down under the barrier-free toll collection systems, which are equipped with various cameras and sensors.

[0031] Next, incoming data is normalized and supplemented: any other data from other sources can be supplemented and normalized in the event of the addition of new equipment or changes to the location of the barrier-free toll collection system frame and equipment. Example of supplementation: initially, the equipment sends a lane change indicator, but this is not always accurate, so supplementation is performed according to the criteria below: Original meaning Transformed value The distance of the vehicle position from the center of the lane is less than 1.5 m There is no rebuilding The distance of the vehicle position from the center of the lane is more than 1.5 m There is a restructuring The distance of the vehicle position from the center of the lane is more than 2 m The data is incorrect Example of data normalization: • speed is received in km / h - the data is ordered and systematized in m / h; • date is received in ISO 8601 standard format - - the data is ordered and systematized in Unix time format.

[0032] After this, previously accumulated data on vehicle passages is obtained and a comparison is made between previously normalized and supplemented data on vehicle passages.

[0033] They select data based on vehicle travel data from equipment of front photo and video recording systems, DSRC identification equipment, vehicle classification system equipment, vehicle axle photo recording system equipment, and rear photo and video recording system equipment.

[0034] The data received from the equipment includes: lane detection of lane change or movement between lanes, speed and time, a set of points with a fixed distance from the frame of barrier-free toll collection systems on roads and a recorded time in motion, each point, historical data of travel and traffic situations (traffic jams, weather conditions).

[0035] The pairs of data obtained from different equipment are identified and compared; the matching and differing data for each pair of data are identified; the matching and differing data for each pair of data are compared with previously accumulated data on the passage of vehicles (hereinafter referred to as TS).

[0036] The following attributes are used in the data pair selection process: Attribute Data source Description prob A system for processing and combining data on vehicle movements into verified records with determination of their reliability An attribute whose value will be used to determine the best data pair. The value of this attribute will change throughout the matching process, until the data is written to the database. k1, k2, k3, k4 A system for processing and combining data on vehicle movements into verified records with determination of their reliability Coefficients, the values ​​of which are selected for each frame of the barrier-free toll collection system on roads based on historical data and road characteristics. t A system for processing and combining data on vehicle movements into verified records with determination of their reliability The calculated value of "photo fixation time - classification system time" photo_k A system for processing and combining data on vehicle movements into verified records with determination of their reliability The final coefficient of the pair "Vehicle classification system - Photo and video recording system" Golden Print A system for processing and combining data on vehicle movements into verified records with determination of their reliability An attribute that is selected for a vehicle based on historical data and its license plate number. This attribute contains all data on vehicle trips with a given license plate number over the past month, across all frames. Parallel passage A system for processing and combining data on vehicle movements into verified records with determination of their reliability A mark for improving the selection of the DSRC identification system data packet. This means that almost simultaneously with the vehicle being dismantled, another 1 or more vehicles passed. Speed ​​(speed_km) Vehicle classification system Vehicle speed reported by the classification system Travel time Vehicle classification system The time at which a vehicle's passage was recorded at a specific point. This point is defined so that each piece of equipment records passage at exactly this point. Length Vehicle classification system The length of the vehicle, determined based on the speed of the vehicle and its fixation at different points on the Track Length reliability Vehicle classification system The accuracy of the attribute "Length" as defined by the classification system Stripe Vehicle classification system Vehicle traffic lane defined by the classification system Sign of restructuring Vehicle classification system A sign determined by the classification system that a vehicle is changing lanes under the equipment detection zone Sign of reverse motion Vehicle classification system A sign determined by the classification system that a vehicle is moving in the opposite direction under the equipment detection zone ECTN class Vehicle classification system ECTN Classification System Classification ECTN Class Reliability Vehicle classification system The accuracy of the ECTN Class attribute as defined by the classification system Estimated number of axles Vehicle classification system The number of axles of a vehicle determined by the classification system Offset of the vehicle center relative to the lane Vehicle classification system The displacement of the vehicle center relative to its lane, as determined by the classification system Track: Time\position Vehicle classification system A set of data read in the detection zone. The data includes a large number of readings. Each reading determines the vehicle's position relative to the equipment and the time of the reading. Based on this, the vehicle's length, length reliability, and other attributes are determined. Speed Front photo and video recording system Speed ​​determined by the front photo and video recording system Travel time Front photo and video recording system The time at which a vehicle's passage was recorded at a specific point. This point is defined so that each piece of equipment records passage at exactly this point. Stripe Front photo and video recording system The vehicle's lane of travel determined by the front photo and video recording system license plate Front photo and video recording system State registration plate (Vehicle registration number) determined by the front photo and video recording system Travel time DSRC identification equipment The time at which a vehicle's passage was recorded at a specific point. This point is defined so that each piece of equipment records passage at exactly this point. Antenna Location DSRC identification equipment Each antenna is assigned a value between 0.5 and 12 based on its location. For example, a value of 1 means the antenna is located in the middle of band 1. A value of 2.5 means the antenna is located between bands 2 and 3. This value is important because signal strength depends on antenna placement, and these factors must be taken into account. Time and position Y DSRC identification equipment An auxiliary value. Used to determine which band to assign the antenna signal to if the antenna position is intermediate (e.g., 2.5). If the value is <45, it means the antenna position is 3.0. If >150, it means 2.0. Speed Rear photo and video recording system Speed ​​determined by the rear photo and video recording system Travel time Rear photo and video recording system The time at which a vehicle's passage was recorded at a specific point. This point is defined so that each piece of equipment records passage at exactly this point. Stripe Rear photo and video recording system Vehicle lane determined by the rear photo and video recording system license plate Rear photo and video recording system State registration plate (Vehicle registration number) determined by the rear photo and video recording system Time Axle photo-fixation system The time at which a vehicle's passage was recorded at a specific point. This point is defined so that each piece of equipment records passage at exactly this point. Stripe Axle photo-fixation system Vehicle traffic lane determined by the axle photo-recording system

[0037] At the beginning of the process, each potential data pair is assigned a "prob" parameter. This parameter will subsequently serve as the primary criterion for selecting data for the verified record. At each step of the process, a numerical value will be added or subtracted from the "prob" parameter, depending on the comparison of data between the two systems.

[0038] For the data pair "Classification system - Front photo and video recording system", the following data matching process is given as an example (a similar process is given for the data pair: "Classification system - Rear photo and video recording system"): 1) Match data packets within 5 seconds before and after the time of the vehicle classification system. 2) Compare the lane of the classification system and the photo and video recording system. If the lane is equal, 0.3 is added to the prob attribute. If it is determined that the vehicle is changing lanes, 0.2 is added to the prob attribute. In all other cases, 0.05 is added to the attribute. 3) Determine the vehicle length for the further formula based on the ECTN values ​​​​and the measured vehicle length. If the vehicle's ECTN is <300 and its length is >10 m, the length value is assumed to be 6 m. Otherwise, the actual measured length is used. 4) Determining the speed_km attribute based on the measured speed or the average speed calculated for the last 10 passes through the median strip.5) Calculate the reference value using the formula k1 * speed_km + k2 * length * speed_km + k3 * length + k4 - t, where k1, k2, k3, and k4 are individually selected values ​​for each barrier-free toll collection system frame based on the equipment location and road surface characteristics. If speed_km < 45, the formula result is multiplied by 5.034. If there is a traffic jam on the road, the result of the formula is multiplied by 3.117. Based on the result of the formula values, values ​​are added to the prob attribute. • if the result is <200, then 0.3 is added to the prob attribute. • if the result is <200, but <400, then 0.2 is added to the prob attribute. • if the result is <400, but <600, then 0.1 is added to the prob attribute. • in all other cases, 0.1 is subtracted from the prob attribute. 6) If the difference in speed from the classification system and the speed from the photo recording system is less than 5 km / h, then 0.2 is added to the prob attribute.7) If the photographic material contains a note that the vehicle is recognized in the photo, then 0.1 is added to the prob attribute. 8) Calculate the time delta based on the Trigger zone, Speed ​​track and the time of the photographic material. 9) Based on this delta, assign values: • if the result <=5, then 0.3 is added to the prob attribute. • if the result <=100, then 0.25 is added to the prob attribute. • if the result <=400, then 0.05 is added to the prob attribute. • if the result <600, then - 0.1 is subtracted from the prob attribute. • if the result <1000, then - 0.3 is subtracted from the prob attribute. 10) If the time value from the classification system is less than the time value of the photo, then - 0.3 is subtracted from the prob attribute. 11) Calculate the prob value and generate the photo_k parameter. 12) Attach a photo to the verified record with the largest parameter photo_k NOT <=0.

[0039] For the "Classification System - DSRC Identification System" data pair, the following data selection process is provided as an example: 1) Select data packets within 5 seconds before and after the classification system time. 2) Select the data with the strongest signal level from the selected data packets. 3) Check for parallel passage. If the golden print value matches another vehicle, this data packet from the DSRC antenna is not considered for this vehicle. 4) If the scanner has a photo attached with an unrecognized license plate and there is a photo with a recognized license plate within 5 seconds, then -0.2 is subtracted from the prob attribute. 5) Check for parallel passage. If the golden print value from the system database matches another vehicle, then this data packet from the DSRC antenna is not considered for this vehicle. 6) The selected golden print has information in the system databases: • if it is for the current day, then 0.4 is added to the prob attribute. • if it is more than once, then 0.3 is added to the prob attribute.• if the information is present, then 0.15 is added to the prob attribute. 7) If the scanner and DSRC lanes are the same or adjacent and the difference in the classification system time and DSRC is more than 700 m / s, then the final verified record is marked as “Parallel passage” 8) If: • the lane of the pre-selected photo and the classification system matches, but the DSRC is from an adjacent lane, then 0.05 is added to the prob attribute. • the lane of the pre-selected photo and the classification system does not match, but the DSRC is from an adjacent lane, then 0.1 is added to the prob attribute. 9) If the classification system front trigger time: • is less than the DSRC time, then - 0.5 is subtracted from the prob attribute. • is greater than the DSRC time and the speed from the scanner is more than 45 km / h, then 0.2 is added to the prob attribute. • is greater than the DSRC time and the speed from the scanner is less than 45 km / h, then 0.1 is added to the prob attribute. 0.1.13) Calculate the reference value of the camera-to-DSRC ratio using the formula (k1 * speed_km + k2 * length * speed_km + k3 * length + k4 - t) * speed_mod_k, where k1, k2, k3, and k4 are individually selected values ​​for each frame of the barrier-free toll collection system on the roads, based on the equipment location and road surface characteristics. If speed_km < 45, the result of the formula is multiplied by 5.254. If there is a traffic jam on the road, the result of the formula is multiplied by 3.713.14) Based on the result of the formula values, values ​​are added to the prob attribute. • if the result <=100, then 0.2 is added to the prob attribute. • if the result is 100<, but <=200, then 0.1 is added to the prob attribute. • if the result is 200<, but <=400, then 0.05 is added to the prob attribute. • in all other cases, 0.2 is subtracted from the prob attribute.15) Calculate the reference value of the classification system's ratio to DSRC using the formula (k1 * speed_km + k2 * length * speed_km + k3 * length + k4 - t) * speed_mod_k, where k1, k2, k3, and k4 are individually selected values ​​for each frame of the barrier-free toll collection system on roads, based on the location of the equipment and the characteristics of the road surface. If speed_km < 45, the result of the formula is multiplied by 5.101. If there is a traffic jam on the road, the result of the formula is multiplied by 3.211.16) Based on the result of the formula values, values ​​are added to the prob attribute.• if the result <=100, then 0.3 is added to the prob attribute.• if the result is 100<, but <=200, then 0.2 is added to the prob attribute.• if the result is 200<, but <=400, then 0.1 is added to the prob attribute.• if the result is 400<, but <=1000, then 0 is added to the prob attribute.• in all other cases, 0.1 is subtracted from the prob attribute.10) If there is a traffic jam on the road and the value of the DSRC\camera formula> 400, then this data packet from the DSRC antenna is not considered for this vehicle. 11) If there is a traffic jam on the road and the DSRC band does not match the band from the classification system, then this data packet from the DSRC antenna is not considered for this vehicle. 17) If the DSRC band belongs to a data packet from the classification system and is obtained from the antenna ID: • the DSRC band is not obtained from the antenna ID, but matches the data from the classification system, then 0.3 is added to the prob attribute. • the DSRC band belongs to a data packet from the classification system and is obtained from the antenna ID, but the difference between them is> 0.5 AND <= 1, then 0.075 is added to the prob attribute. • the DSRC band belongs to a data packet from the classification system and is obtained from the antenna ID, but the difference between them is> =0.5, then 0.075 is added to the prob attribute. 0.15.18) If the DSRC lane is not equal to the lane from the classification system and there is a “Parallel Passage” mark, then 0 is subtracted from the prob attribute.319) If the DSRC bandwidth is not equal to the bandwidth from the classification system and:• the bandwidth difference> =1 and there is no parallel passage, then 0.1 is subtracted from the prob attribute.• the bandwidth difference> =1 and there is a parallel passage, then 0.4 is subtracted from the prob attribute.• the bandwidth difference> =2 and there is a parallel passage, then 1 is subtracted from the prob attribute.20) If, during selection, in the range of checked data packets from the classification system there are those with the ECTN value> =300 and the DSCR bandwidth coincides with the bandwidth of an alternative data packet from the classification system and the time difference <700 m / s, then this cycle is terminated and is no longer considered in the selection.21) If 2 DSRCs arrived from different bandwidths and the bandwidth difference <=0.5, then 0.05 is added to the prob attribute.22) If the position of the car on the bandwidth <=0.8 m from the center of the bandwidth + DSRC from antennas 1.5, 2.5, 3.5, 4.5 bands, then 0 is added to the prob attribute.0223) If the license plate from the camera is in the golden print database of the barrier-free toll collection system frames on roads and matches the DSRC under consideration: • occurs 1 time, then 0.1 is added to the prob attribute. • occurs more than 1 time, then 0.2 is added to the prob attribute. 24) If: • the prob value for the golden print <0.1 and the total prob <0.2, then this cycle is completed and is no longer considered in the selection. • the prob value for the golden print <0, according to the DSRC photo the prob value <0 and Speed ​​<45 km\h, then this cycle is completed and is no longer considered in the selection. 25) Calculate the prob value and assign it to this DSRC. If there is no data from the classification system, then all the same steps are performed, excluding the missing data.In this way, pairs of data with the highest reliability are selected from the normalized and supplemented data on the passage of vehicles, and then, based on the selected pairs of data with the highest reliability, verified records of the passage of vehicles are compiled: • photographic material from axle cameras is selected for the selected data based on the closest photo in time; • data from alternative cameras are selected for data from the classification system and previously selected main photos based on the closest photo in time; • data from rear photo and video recording are selected for data from the classification system and previously selected main photos based on the lane, license plate matches and the time of comparison of the rear photo.

[0040] In general (see Fig. 2), the system for processing and combining data on vehicle passages into verified records with determination of their reliability (200) contains one or more processors (201) connected by a common information exchange bus, memory means such as RAM (202) and ROM (203), and input / output interfaces (204).

[0041] The processor (201) (or several processors, a multi-core processor, etc.) can be selected from a range of devices that are widely used at present, for example, from manufacturers such as: Intel™, AMD™, Apple™, Samsung Exynos™, MediaTEK™, Qualcomm Snapdragon™, etc. Under the processor or one of the processors used in the system (200), it is also necessary to take into account a graphic processor, for example, an NVIDIA GPU with a software model compatible with CUDA, or Graphcore, the type of which is also suitable for the full or partial implementation of the method, and can also be used for training and applying machine learning models in various information systems.

[0042] RAM (202) is random access memory (RAM) and is designed to store machine-readable instructions executed by the processor (201) to perform the necessary logical data processing operations. RAM (202) typically contains executable instructions of the operating system and corresponding software components (applications, software modules, etc.). The available memory of a graphics card or graphics processor may also serve as RAM (202).

[0043] ROM (203) is one or more permanent storage devices, such as hard disk drive (HDD), solid state drive (SSD), flash memory (EEPROM, NAND, etc.), optical storage media (CD-R / RW, DVD-R / RW, BlueRay Disc, MD), etc.

[0044] Various types of I / O interfaces (204) are used to organize the operation of the device components (200) and organize the operation of external connected devices. The choice of the appropriate interfaces depends on the specific design of the computing device, which may include, but are not limited to: PCI, AGP, PS / 2, IrDa, FireWire, LPT, COM, SATA, IDE, Lightning, USB (2.0, 3.0, 3.1, micro, mini, type C), TRS / Audio jack (2.5, 3.5, 6.35), HDMI, DVI, VGA, Display Port, RJ45, RS232, etc.

[0045] To ensure user interaction with the device (200), various I / O information means (205) are used, for example, a keyboard, a display (monitor), a touch display, a touchpad, a joystick, a mouse, a light pen, a stylus, a touch panel, a trackball, speakers, a microphone, augmented reality means, optical sensors, a tablet, light indicators, a projector, a camera, biometric identification means (a retina scanner, a fingerprint scanner, a voice recognition module), etc.

[0046] The network communication means (206) provides data transmission via an internal or external computer network, such as an Intranet, Internet, LAN, etc. One or more means (406) may be, but are not limited to: an Ethernet card, a GSM modem, a GPRS modem, an LTE modem, a 5G modem, a satellite communication module, an NFC module, a Bluetooth and / or BLE module, a Wi-Fi module, etc.

[0047] The specific selection of device elements (200) for implementing various hardware and software architectural solutions may vary while maintaining the required functionality. In particular, such an implementation can be accomplished using electronic components used to create digital integrated circuits. These may include, but are not limited to, microcircuits whose operating logic is determined during manufacture, or programmable logic integrated circuits (FPGAs), whose operating logic is specified through programming. Programmers and debugging environments are used for programming, allowing the desired digital device structure to be defined in the form of a circuit diagram or a program in specialized hardware description languages: Verilog, VHDL, AHDL, etc.Alternatives to FPGAs include programmable logic controllers (PLCs), basic matrix chips (BMCs), which require a factory production process for programming; and ASICs (specialized custom large-scale integrated circuits), which are significantly more expensive for small-scale and single-unit production.

[0048] Thus, the implementation can be achieved by standard means based on the classical principles of implementing the basics of computing technology.

[0049] The submitted application materials disclose preferred examples of the implementation of the technical solution and should not be interpreted as limiting other, particular examples of its implementation that do not go beyond the scope of the requested legal protection, which are obvious to specialists in the relevant field of technology.

Claims

1. A method for processing and combining data on vehicle travel into verified records with the determination of their reliability, implemented using a processor and a data storage device, characterized in that: - receive real-time data on vehicle movements from equipment of front photo and video recording systems, DSRC identification equipment, equipment of the vehicle classification system, equipment of the vehicle axle photo recording system, equipment of the rear photo and video recording systems; - normalize and supplement the received data on vehicle movements; - receive previously accumulated data on vehicle movements; - compare normalized and supplemented data on vehicle travel: - identify pairs of data obtained from different equipment that are compared with each other; - identify matching and different data for each pair of data; - compare the matching and differing data for each pair of data with previously accumulated data on vehicle movements; - based on the comparison of normalized and supplemented data on vehicle travel, their reliability is determined in each of the data pairs; - select pairs of data with the highest reliability from normalized and supplemented data on vehicle travel; - based on the selected pairs of data with the highest reliability, verified records of vehicle travel are compiled.

2. A method for processing and combining data on vehicle travel into verified records with determination of their reliability according to paragraph 1, characterized in that the verified records on vehicle travel are used in toll collection systems for travel on toll roads.

3. A method for processing and combining data on vehicle travel into verified records with determination of their reliability according to paragraph 1, characterized by the fact that integration with external systems is used for data exchange.

4. A method for processing and combining data on vehicle travel into verified records with the determination of their reliability according to paragraph 1, characterized in that the determined reliability in each of the data pairs is used to search for anomalies in the data and allows for the marking of anomalous data for subsequent correction, clarification, operation and analysis.

5. A system for processing and combining data on vehicle journeys into verified records with determination of their reliability, containing: at least one data processing device; at least one data storage device; at least one program, where one or more programs are stored on one or more data storage devices and executed on one or more data processing devices, wherein the one or more programs ensure the execution of the following steps: - receive real-time data on vehicle movements from equipment of front photo and video recording systems, DSRC identification equipment, equipment of the vehicle classification system, equipment of the vehicle axle photo recording system, equipment of the rear photo and video recording systems; - normalize and supplement the received data on vehicle movements; - receive previously accumulated data on vehicle movements; - compare normalized and supplemented data on vehicle travel: - identify pairs of data obtained from different equipment that are compared with each other; - identify matching and different data for each pair of data; - compare the matching and differing data for each pair of data with previously accumulated data on vehicle movements; - based on the comparison of normalized and supplemented data on vehicle travel, their reliability is determined in each of the data pairs; - select pairs of data with the highest reliability from normalized and supplemented data on vehicle travel; - based on the selected pairs of data with the highest reliability, verified records of vehicle travel are compiled.

6. A system for processing and combining data on vehicle travel into verified records with determination of their reliability in accordance with paragraph 5, characterized in that the verified records on vehicle travel are used in toll collection systems for travel on toll roads.

7. A system for processing and combining data on vehicle travel into verified records with determination of their reliability in accordance with paragraph 5, characterized by the fact that integration with external systems is used for data exchange.

8. A system for processing and combining data on vehicle travel into verified records with the determination of their reliability according to paragraph 5, characterized in that the determined reliability in each pair of data is used to search for anomalies in the data and allows for the marking of anomalous data for subsequent correction, clarification, operation and analysis.

Images