Electronic snapshot illegal parking method and system based on big data vehicle track

Abstract

The invention belongs to the technical field of vehicle illegal parking snapshot. The invention discloses an electronic snapshot illegal parking method based on a big data vehicle track. The method comprises the following steps: acquiring a first group of illegal images of a vehicle driving into a parking forbidding road section according to a preset first interval time; performing feature extraction on the first group of violation images to obtain a first group of feature information; comparing the first group of feature information with violation image information stored in a database, if the comparison is not successful, generating information of persuading to leave and prohibiting parking road sections, sending the information to a vehicle owner of the vehicle, and storing the first group of feature information in the database to obtain first violation image information; after a preset second interval time, obtaining four images of the vehicle on the parking forbidding road section again to obtain a second group of violation images; performing feature extraction on the second group of violation images to obtain a second group of feature information; and comparing the second group of feature information with violation image information stored in the database to generate violation information. The method has the advantages of high real-time performance and more accurate illegal judgment.

Description

Technical Field

[0001] The present application belongs to the technical field of capturing illegal parking of vehicles, and in particular, relates to a method and system for electronically capturing illegal parking based on big data vehicle trajectories. Background Art

[0002] With the acceleration of urbanization and the sharp increase in the number of vehicles, urban road traffic management faces unprecedented challenges, especially the problem of illegal parking. The traditional manual patrol method is difficult to adapt to the current management needs due to its low efficiency and limited coverage.

[0003] In addition, the existing parking capture system has obvious deficiencies in processing large amounts of vehicle data. They are often unable to analyze and process data in a timely and effective manner, resulting in the failure to monitor and manage illegal parking behaviors in a timely manner. More seriously, the existing system also has the problem of repeated penalties, which not only increases the burden on car owners, but also reduces the fairness and efficiency of traffic management.

[0004] Therefore, modern urban traffic management urgently needs a new technical solution to improve the efficiency of illegal parking supervision, reduce manual intervention, and achieve rapid identification and processing of violations while avoiding repeated penalties to meet the growing needs of traffic management. Summary of the invention

[0005] Based on this, it is necessary to provide an electronic capture method and system for illegal parking based on big data vehicle trajectories to solve the above technical problems.

[0006] In a first aspect, the present application provides a method for electronically capturing illegal parking based on big data vehicle trajectories, the method comprising: According to a preset first interval time, a first group of violation images of a vehicle entering a no-parking section is acquired, wherein the first group of violation images includes four images taken sequentially at the first interval time; Extracting features from the first group of traffic violation images to obtain a first group of feature information; Comparing the first set of feature information with the traffic violation image information stored in a database, and if the comparison is unsuccessful, generating information of persuading the vehicle to leave the prohibited parking section, sending the information to the owner of the vehicle, and storing the first set of feature information in the database, to obtain the first traffic violation image information; After a preset second interval time, four images of the vehicle in the no-parking section are acquired again to obtain a second set of violation images, wherein the second set of violation images includes four images taken sequentially at the first interval time; Extracting features from the second group of traffic violation images to obtain a second group of feature information; The second set of feature information is compared with the traffic violation image information stored in the database, and when the second set of feature information is successfully compared with the first traffic violation image information, violation information is generated.

[0007] In some practicable manners, the step of acquiring the first violation stamp image of the vehicle entering the no-parking section according to the preset first interval time includes: Obtain the illegal parking duration regulations for areas where parking is prohibited; According to the provision, determining the first preset interval time; Acquire a first violation image taken when the vehicle enters a no-parking section, and a second violation image, a third violation image, and a fourth violation image taken in sequence at a first interval; The first group of traffic violation images is obtained by combining the first traffic violation image, the second traffic violation image, the third traffic violation image and the fourth traffic violation image.

[0008] In some practicable manners, the step of extracting features from the first group of traffic violation images to obtain a first group of feature information includes: Extracting features from the first group of traffic violation images to obtain the license plate number, vehicle logo, vehicle type, vehicle color and shooting time of the vehicle; Acquire the device code information, device coordinate information, road location information, and road code information of the device that photographed the first group of traffic violation images; The vehicle license plate number, vehicle logo, vehicle type, vehicle color and shooting time, as well as the device code information, the device coordinate information, the road location information and the road code information are combined to obtain the first set of feature information.

[0009] In some practicable manners, the step of comparing the first set of feature information with the traffic violation image information stored in a database, and if the comparison is unsuccessful, generating information of persuading the vehicle to leave a prohibited parking section, sending the information to the owner of the vehicle, and storing the first set of feature information in the database, and obtaining the first traffic violation image information includes: Storing the traffic violation image information of the day in the database; Comparing the first set of feature information and the traffic violation image information to obtain a comparison result; If the comparison result is successful, illegal information will be generated; If the comparison result is unsuccessful, information on dissuading the vehicle from a prohibited parking section will be generated and sent to the owner of the vehicle, and the first set of feature information will be stored in the database to obtain the first violation image information.

[0010] In some practicable manners, the step of acquiring four images of the vehicle in the no-parking section again after the preset second interval time to obtain a second set of violation images includes: Establishing the preset second interval time; After the last image of the first group of violation images is formed, timing is performed according to the second interval time. After the second interval time, four images of the vehicle in the prohibited parking section are acquired again in sequence according to the first interval time to obtain a second group of violation images.

[0011] In some practicable manners, the step of extracting features from the second set of violation images to obtain a second set of feature information includes: Extracting features from the second group of traffic violation images to obtain the license plate number, vehicle logo, vehicle type, vehicle color and shooting time of the vehicle; Acquire the device code information, device coordinate information, road location information, and road code information of the device that photographed the second set of traffic violation images; The vehicle license plate number, vehicle logo, vehicle type, vehicle color and shooting time, as well as the device code information, the device coordinate information, the road location information and the road code information are combined to obtain the first set of feature information.

[0012] In some practicable manners, the step of comparing the second set of feature information with the traffic violation image information stored in the database, and generating violation information when the second set of feature information is successfully compared with the first traffic violation image information, includes: Comparing the second set of feature information with the traffic violation image information stored in the database on that day to obtain a comparison result; When the second set of feature information is successfully compared with the first set of traffic violation image information, the first two images in the first set of traffic violation image information and the last two images in the second set of traffic violation images are extracted to obtain four traffic violation images; Generate violation information according to the four violation images; The second group of traffic violation images is stored in the database to obtain the second traffic violation image information.

[0013] In some practicable manners, after the step of storing the second set of traffic violation images in the database to obtain the second traffic violation image information, the following steps are included: After a preset second interval time of obtaining the second set of violation images, four images of the vehicle in the no-parking section are obtained again to obtain a third set of violation images; Extracting features from the third group of traffic violation images to obtain a third group of feature information; The third set of feature information is compared with the traffic violation image information stored in the database. When the third set of feature information is successfully compared with the first traffic violation image information and the second traffic violation image information, the third set of traffic violation images is discarded.

[0014] In a second aspect, the present application provides a system for electronically capturing illegal parking based on big data vehicle trajectories, applying the aforementioned method for electronically capturing illegal parking based on big data vehicle trajectories, the system comprising: The image acquisition module is used to obtain a first group of violation images of a vehicle entering a no-parking section according to a preset first interval time, wherein the first group of violation images includes four images taken sequentially at the first interval time.

[0015] An image recognition module, used for extracting features from the first group of traffic violation images to obtain a first group of feature information; A big data trajectory analysis module is used to compare the first set of feature information with the traffic violation image information stored in a database. If the comparison is unsuccessful, information on persuading the vehicle to leave a prohibited parking section is generated and sent to the owner of the vehicle, and the first set of feature information is stored in the database to obtain the first traffic violation image information; The image acquisition module is also used to obtain four images of the vehicle in the prohibited parking section again after a preset second interval time to obtain a second group of violation images, wherein the second group of violation images includes four images taken sequentially at the first interval time.

[0016] The image recognition module is further used to extract features from the second group of traffic violation images to obtain a second group of feature information; The violation processing program module is used to compare the second set of feature information with the violation image information stored in the database, and generate violation information when the second set of feature information is successfully compared with the first violation image information.

[0017] In a third aspect, the present application provides a computer program, which, when executed by a processor, implements the steps of the aforementioned method for electronically capturing illegal parking based on big data vehicle trajectories.

[0018] Beneficial effects: The present application provides a method for electronically capturing illegal parking based on big data vehicle trajectories, the method comprising: obtaining a first group of illegal images of a vehicle entering a prohibited parking section according to a preset first interval time, wherein the first group of illegal images includes four images taken sequentially at the first interval time. Feature extraction is performed on the first group of illegal images to obtain a first group of feature information; the first group of feature information is compared with the illegal image information stored in the database, if the comparison is not successful, information on persuading the vehicle to leave the prohibited parking section is generated and sent to the owner of the vehicle, and the first group of feature information is stored in the database to obtain the first illegal image information; after the preset second interval time, four images of the vehicle in the prohibited parking section are obtained again to obtain a second group of illegal images, wherein the second group of illegal images includes four images taken sequentially at the first interval time. Feature extraction is performed on the second group of illegal images to obtain a second group of feature information; the second group of feature information is compared with the illegal image information stored in the database, and when the second group of feature information is successfully compared with the first illegal image information, illegal information is generated. Through the above method, the road camera is used to capture the illegal parking data of motor vehicles, and whether there is illegal parking is determined based on the parking time of the motor vehicle. The violation handling program determines whether the vehicle is currently illegally parking for the first time. If it is the first time, a message reminder is generated and sent to the owner of the motor vehicle, thereby promptly preventing the owner from continuing to violate the law and avoiding unnecessary fines for violations. While improving the user experience, it also alleviates the traffic hazards caused by random parking. At the same time, the violation handling program determines whether the vehicle has been parked in the same position within a certain time range based on the road section information where the equipment is located, the vehicle's historical illegal parking data and the vehicle's driving trajectory. If it has been punished, the fine will not be repeated, avoiding unnecessary fines for violations for the user. Compared with the existing methods, the electronic capture illegal parking method and system proposed in this application have low delay rate and strong real-time performance when processing massive traffic violation data, and more accurate violation judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A flowchart of a method for electronically capturing illegal parking based on big data vehicle trajectories in one embodiment; Figure 2 A schematic diagram of the electronic capture illegal parking structure of an electronic capture illegal parking system based on big data vehicle trajectory in one embodiment; Figure 3 The present invention is a schematic diagram of a program for capturing illegal parking in an electronic parking capture system based on big data vehicle trajectories in one embodiment. DETAILED DESCRIPTION

[0021] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used herein includes any and all couplings of one or more related listed items.

[0023] It can be understood that the terms "first", "second", etc. used in the present application can be used in this article to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from another element.

[0024] The following is an explanation of the terms mentioned in this application to facilitate understanding of this solution: Histogram is a commonly used statistical tool in image processing and computer vision, which is used to describe the distribution of pixel values ​​in an image.

[0025] The rapid advancement of urbanization has brought about a surge in population and vehicle numbers, which has posed a severe challenge to urban road traffic management. Among many traffic problems, illegal parking has become a focal issue due to its prevalence and serious impact on the smoothness of urban traffic. Illegal parking not only hinders traffic flow and increases traffic congestion, but may also cause traffic accidents, which has a negative impact on urban order and the quality of life of residents.

[0026] Traditional illegal parking management mainly relies on manual patrols, which have obvious limitations. Patrol officers need to patrol the streets to check whether there are vehicles parked illegally, and then record and punish them. This method not only consumes a lot of manpower and material resources, but is also inefficient and difficult to cover all areas that need supervision. In addition, the randomness and subjectivity of manual patrols may also lead to unfair law enforcement and regulatory loopholes.

[0027] With the development of technology, some cities have begun to adopt electronic capture systems to assist in the management of illegal parking. However, these systems have also exposed many problems in practical applications. First, the existing electronic capture systems are often unable to handle large amounts of vehicle data and are unable to analyze and process data in real time and accurately. This leads to delays in the system's identification of illegal parking behaviors and the inability to punish illegal vehicles in a timely manner, thereby reducing management efficiency. Secondly, the existing systems have defects in data management and analysis, and repeated penalties often occur, causing unnecessary troubles and economic losses to car owners. In addition, these systems often lack the ability to conduct in-depth analysis of historical vehicle violation data and are unable to effectively identify and prevent repeated violations.

[0028] As the number of vehicles increases, illegal parking becomes more complicated. Urban traffic management departments need more intelligent and efficient technical means to meet this challenge. They need systems that can process and analyze massive amounts of data to quickly identify and accurately manage illegal parking behaviors. At the same time, the system also needs to be highly automated and intelligent to reduce manual intervention and improve the fairness and consistency of law enforcement. In short, the field of urban traffic management urgently needs innovative technical solutions to deal with the increasingly serious problem of illegal parking.

[0029] In summary, this application provides a method for electronically capturing illegal parking based on big data vehicle trajectories, which combines advanced technologies such as big data processing, cloud computing, the Internet of Things, machine vision, and image processing. Through image capture, image recognition, violation determination, and real-time analysis of vehicle trajectories, it can automatically capture, identify, and handle illegal parking behaviors. The system can use big data platforms and image processing technologies to quickly process and deeply mine massive amounts of vehicle data, extract key information such as vehicle characteristics, locations, and driving trajectories, and intelligently handle illegal parking behaviors based on this information. At the same time, the system can also upload the captured evidence of violations to the data center in real time, providing timely and accurate law enforcement basis for traffic management departments.

[0030] like Figure 1 As shown, in the first aspect, the present application provides a method for electronically capturing illegal parking based on big data vehicle trajectories, the method comprising: S100, acquiring a first set of violation images of a vehicle entering a no-parking section according to a preset first interval time.

[0031] The first group of traffic violation images includes four images taken sequentially at a first interval.

[0032] Specifically, according to a preset time interval, obtaining a group of violation images of a vehicle entering a no-parking section may include the following steps: S101, obtaining the illegal parking time regulations for the area where the prohibited parking section is located. The system needs to query and obtain the regulations for the specific prohibited parking section to understand the specific time regulations for illegal parking in the area, that is, how long illegal parking exceeds is considered illegal parking. These regulations will determine the length of the preset time interval in the subsequent steps.

[0033] S102, according to the regulations, determine the first preset interval time. According to the illegal parking duration regulations obtained in step S101, the system will determine a preset time interval, i.e., the first time interval. For example, the first time interval is 1 minute. This time interval will be used for subsequent shooting of the violation image group to ensure that the violation of the vehicle in the prohibited parking section can be captured.

[0034] S103, obtaining the first violation image taken when the vehicle enters the no-parking section, and the second violation image, the third violation image, and the fourth violation image taken in sequence at the first interval. When the vehicle enters the no-parking section, the system will start taking the first violation image. Then, the system will take the second, third, and fourth violation images in sequence at the preset first interval. These images will serve as records of the violation.

[0035] S104, combining the first violation image, the second violation image, the third violation image and the fourth violation image to obtain the first group of violation images. Finally, the system combines the four violation images into a complete violation image group, i.e., the first group of violation images, for subsequent analysis and processing of illegal parking behaviors.

[0036] Through the above method, by continuously shooting four images, the system can provide a complete record of the violation, enhancing the integrity and reliability of the evidence. Reduce misjudgment: The shooting of multiple images helps to distinguish between temporary parking and illegal parking, reducing the penalty errors caused by misjudgment. Improve law enforcement efficiency: The automated image acquisition and combination process reduces manual intervention, improving law enforcement efficiency and response speed.

[0037] For example, assuming that the illegal parking time for a no-parking section is set to 3 minutes, the system sets the preset first interval time to 3 minutes.

[0038] S101: The system finds that the illegal parking time limit for this road section is 3 minutes.

[0039] S102: The system determines that the preset first interval time is 3 minutes.

[0040] S103: A car enters a no-parking section at 9:00 am, and the system captures the first image at 9:00 am. Then, the system captures the second, third, and fourth images at 9:01, 9:02, and 9:03, respectively.

[0041] S104: The system combines the four images into a violation image group, which records the illegal parking behavior of the vehicle in the prohibited parking section from 9:00 to 9:03.

[0042] S200: extracting features from the first group of traffic violation images to obtain a first group of feature information.

[0043] Specifically, obtaining the first set of feature information may include the following steps: S201, extracting features from the first group of violation images to obtain the vehicle license plate number, vehicle logo, vehicle type, vehicle color and shooting time. The system uses image recognition technology to extract key vehicle feature information from the four violation images. This includes the license plate number (for vehicle identification and subsequent violation processing), vehicle logo and vehicle type (for further confirmation of vehicle identity), vehicle color (as an additional identification feature of the vehicle), and shooting time (recording the specific moment when the violation occurred).

[0044] S202, obtaining device code information, device coordinate information, road location information, and road code information for photographing the first group of violation images. Further information related to the device photographing the violation images is collected, including device code (uniquely identifying each camera or monitoring device), device coordinates (specific geographic location, such as longitude and latitude), road location (name of the street or road section where the violation occurred), and road code (which may be used for internal identification in a traffic management system).

[0045] S203, the license plate number, vehicle logo, vehicle type, vehicle color and shooting time of the vehicle, as well as the device code information, the device coordinate information, the road location information and the road code information are combined to obtain the first set of feature information. The system integrates all the extracted vehicle feature information and device information to form a complete set of feature information. This set of information will be used for recording, analyzing and processing illegal parking.

[0046] The above method can record the information of vehicles and camera equipment in detail, which can ensure the accuracy and fairness of violation handling. Enhance the traceability of data. The complete feature information makes each violation incident traceable and verifiable, which increases the transparency of data. Optimize traffic management. This information can be used to analyze the patterns and trends of violation behaviors, thereby optimizing traffic management and law enforcement strategies.

[0047] S300, comparing the first set of feature information with the violation image information stored in a database. If the comparison is unsuccessful, generating information to persuade the vehicle to leave the prohibited parking section, sending it to the owner of the vehicle, and storing the first set of feature information in the database to obtain the first violation image information.

[0048] Specifically, obtaining the first traffic violation image information may include the following steps: S301, storing the image information of the traffic violation of the day in the database. The system will store the image information of the traffic violation of the day in a central database. The database contains detailed information of all traffic violation events of the day, including vehicle feature information and specific circumstances of the traffic violation events.

[0049] S302, compare the first set of feature information and the violation image information to obtain a comparison result. The system compares the extracted first set of feature information with the violation image information stored in the database. The comparison process may involve information such as the license plate number, vehicle features, violation time and location, etc., to determine whether the vehicle has a previous violation record.

[0050] If the comparison result is successful, a violation information will be generated. If the comparison result shows that the vehicle has a previous violation record, the system will generate a violation information, which means that the vehicle has violated parking regulations and needs to be punished accordingly.

[0051] If the comparison result is unsuccessful, the system will generate information on the road section that is dissuading the driver from parking prohibited and send it to the owner of the vehicle, and store the first set of feature information in the database to obtain the first violation image information. If the comparison result shows that the vehicle has no previous violation record, the system will generate information on the road section that is dissuading the driver from parking prohibited and send it to the owner of the vehicle. At the same time, the system will store the first set of feature information in the database and mark it as the first violation image information for subsequent comparison.

[0052] Through the above method, the automated comparison and information processing process can reduce manual operations and improve the efficiency of handling violations. Reduce misjudgments. Through accurate feature comparison, the system can reduce misjudgments caused by incorrect information. Timely response. For vehicles that violate the law for the first time, timely sending of persuasion information can prevent further violations, reduce traffic congestion and potential safety hazards. Storing the image information of the violation on the same day complies with the legal provisions that only one penalty can be imposed on the same location every day.

[0053] For example, suppose a car illegally parks in a no-parking section. The system extracts the first set of feature information and performs the following operations: S301: The system stores information of all traffic violations of the day in the database.

[0054] S302: The system compares the extracted first set of feature information with the traffic violation image information in the database and finds that there is no matching record, indicating that this is the first traffic violation of the vehicle.

[0055] Unsuccessful matching: The system generates a dissuasion message, which may read: "Dear car owner, your vehicle is illegally parked in a prohibited parking section of a certain street. Please leave immediately to avoid being punished." This message is sent to the car owner via SMS.

[0056] Storage information: At the same time, the system stores the first set of feature information of this violation in the database as a record of the first violation image information.

[0057] Through this process, the system not only notifies the car owner in a timely manner, but also provides data support for future traffic management.

[0058] S400, after a preset second interval time, four images of the vehicle on the prohibited parking section are acquired again to obtain a second set of violation images.

[0059] The second group of traffic violation images includes four images taken sequentially at the first interval time.

[0060] Specifically, obtaining the second set of traffic violation images may include the following steps: S401, constructing the second preset interval time. The system sets a preset second interval time according to traffic regulations or specific operating procedures. This time interval is used to determine how long to wait after the first illegal image capture to capture the image again to confirm whether the vehicle is still illegally parked.

[0061] S402, after the last image of the first group of violation images is formed, timing is performed according to the second interval time, and after the second interval time, four images of the vehicle in the prohibited parking section are acquired again in sequence at the first interval time to obtain a second group of violation images. After the first group of violation images is captured and the preset second interval time has passed, the system will start the image capture process again. The system will capture four new images in sequence at the first interval time (for example, once per minute), and these images will constitute the second group of violation images for further confirming the violation of the vehicle.

[0062] Through the above method, the accuracy of traffic violation judgment is improved. By taking images at different time points, the system can more accurately determine whether the vehicle continues to park illegally. Reduce misjudgment. If the vehicle has left after the second interval, the system will not mistakenly handle it as a traffic violation. Strengthen law enforcement. For vehicles that continue to violate traffic rules, the second set of violation images provides additional evidence, allowing law enforcement agencies to take stricter measures.

[0063] For example, suppose a car illegally parks in a no-parking section, and the system captures the first set of illegal images from 9:00 to 9:03 a.m., and sends a message to the car owner to persuade him to leave. However, the car owner does not leave within the specified time.

[0064] After 9:03 (the time when the last image of the first set of violation images was taken), the system waited for 10 minutes, from 9:03 to 9:13. At 9:13, the system began to take four images again at a frequency of one per minute, at 9:13, 9:14, 9:15 and 9:16. The second set of violation images was obtained, and the system combined these four newly taken images into the second set of violation images to confirm the vehicle's continued violation in the prohibited parking section. Through this process, the system can ensure the effective monitoring and handling of continued illegal parking behaviors and provide strong evidence support for law enforcement agencies.

[0065] S500: extracting features from the second group of traffic violation images to obtain a second group of feature information.

[0066] Wherein, obtaining the second set of characteristic information may include the following steps: S501, performing feature extraction on the second group of traffic violation images to obtain the license plate number, vehicle logo, vehicle type, vehicle color and shooting time of the vehicle.

[0067] S502, obtaining the device code information, device coordinate information, road location information, and road code information of the device that photographed the second group of traffic violation images.

[0068] S503, combining the vehicle license plate number, vehicle logo, vehicle type, vehicle color and shooting time, as well as the device code information, the device coordinate information, the road location information and the road code information to obtain the first set of feature information.

[0069] It should be noted that the steps of obtaining the second set of traffic violation images are the same as those of obtaining the first set of traffic violation images, and will not be repeated here.

[0070] S600, comparing the second set of feature information with the traffic violation image information stored in the database, and generating violation information when the second set of feature information is successfully compared with the first traffic violation image information.

[0071] Specifically, generating illegal information may include the following steps: S601, compare the second set of feature information with the violation image information stored in the database on the same day to obtain a comparison result. The system compares the feature information of the second set of violation images (such as license plate number, vehicle type, vehicle color, etc.) with the violation image information stored in the database on the same day. This process is intended to verify whether the vehicle has a violation record before the same day and confirm the vehicle identity.

[0072] When the second set of feature information is successfully compared with the first set of traffic violation image information, the first two images in the first set of traffic violation image information and the last two images in the second set of traffic violation images are extracted to obtain four traffic violation images.

[0073] S602, generating violation information based on the four violation images. Once the comparison is successful, the system will extract the first two images from the first violation image information and the last two images from the second set of violation images, for a total of four violation images. These four images will serve as evidence of the illegal parking behavior. The system will generate violation information based on these images, including detailed information such as vehicle characteristics, violation time, and location.

[0074] S603, storing the second set of violation images in the database to obtain the second violation image information. Finally, the system stores the second set of violation images in the database and marks them as the second violation image information. This provides a complete record for future query, analysis and law enforcement.

[0075] It should be noted that the illegal information generated according to the first set of characteristic information in step S302 is the same as step S602 and will not be described in detail.

[0076] It should also be noted that after the step of storing the second set of traffic violation images in the database to obtain the second traffic violation image information, the following steps are included: S604, after the preset second interval time of obtaining the second group of traffic violation images, four images of the vehicle in the no-parking section are obtained again to obtain a third group of traffic violation images.

[0077] S605: extract features from the third group of traffic violation images to obtain a third group of feature information.

[0078] S606, comparing the third set of feature information with the traffic violation image information stored in the database, and when the third set of feature information is successfully compared with the first traffic violation image information and the second traffic violation image information, discarding the third set of traffic violation images.

[0079] It should be noted that after the second group of violation images is acquired and processed, the system will wait for another preset second interval time. After that, the system will acquire four new images again in the prohibited parking section to form a third group of violation images. This step is intended to monitor whether the vehicle continues to park illegally. The third group of violation images is processed in the same way as the second group of violation images, which will not be repeated here. When the third group of violation images is compared with the first group of violation images and the second group of violation images, it means that the vehicle has repeated violations at different time points. According to certain traffic management regulations, multiple violation records may be allowed within a certain period of time, but after exceeding a certain number of times, subsequent violations may be regarded as repeated, so the third group of violation images will be discarded and no further penalties will be imposed, thus avoiding the problem of repeated penalties at the same location.

[0080] For example, assuming that a car illegally parks in a no-parking section, the system captures a first set of violation images from 9:00 to 9:03 in the morning, a second set of violation images from 10:00 to 10:03, and a third set of violation images from 11:00 to 11:03.

[0081] S604: The system acquires a third set of traffic violation images again after a preset time period after the second set of traffic violation images are acquired.

[0082] S605: The system extracts features from the third group of traffic violation images to obtain a third group of feature information.

[0083] S606: The system compares the third set of feature information with the first and second violation image information in the database and finds that the comparison is successful. According to regulations, the third set of violation images is discarded and the vehicle owner is not punished repeatedly.

[0084] In one embodiment, after the second set of violation images are acquired and processed, the system will wait for another preset second interval time. After that, the system will acquire images again at the no-parking section, including the following steps: Acquire the first image after the preset second interval time; Extracting features from the first image, and comparing the extracted features with the second traffic violation image information in the database to obtain a comparison result; If the comparison result is the same vehicle, the setting of generating four images to form a violation image group will be abandoned, and the next second interval time will be waited for to obtain images again.

[0085] If the comparison result is that the vehicles are not the same, three images are taken in sequence at the first interval to form a violation image group consisting of four images.

[0086] Through the above method, before the third group of violation images is formed, the features of the first image can be used to make a judgment in advance. If the features of the first image can be successfully matched with the violation image information in the database, the three images taken in sequence will become meaningless when compared with the first interval time again. Therefore, the subsequent program that requires taking three images again will be discarded. At the same time, the first image will be discarded and does not need to be stored in the database, avoiding adding burden to the computer room.

[0087] In one embodiment, a method for electronically capturing illegal parking based on big data vehicle trajectories further includes the following steps: According to the first set of characteristic information, the license plate of the vehicle is characteristically marked to obtain a first label of the license plate, and stored in a database; Extracting license plate features from the first image in the second group of traffic violation images to obtain a second label for the license plate; Compare the license plate features corresponding to the first tag and the second tag in the database to obtain a comparison result; If the comparison result is the same license plate, the features of other vehicles will not be compared and it will be determined to be the same vehicle.

[0088] Through the above method, the number of feature comparisons can be effectively reduced, and only the license plate is compared. At this time, the second image, the third image, and the fourth image taken according to the first interval time are used as supplementary evidence, and only the license plate recognition is performed. That is to say, after the first image in the second group of violation images is formed, when the vehicle leaves, the first image in the second group of violation images and the first two images in the first group of violation images are used together as violation evidence to generate violation information. It can be understood that when the vehicle is photographed again after the second interval time and the same vehicle information is obtained, it has been shown that the vehicle has a problem of illegal parking. In this way, even if the second image, the third image, and the fourth image in the second group of violation images are missing, it is still determined that the vehicle has a problem of illegal parking.

[0089] It should be noted that the extraction of vehicle license plates includes the following steps: Build the initial large model; The vehicles that have been put on the market are input into the initial large model for training to obtain the target large model. The purpose of training the initial large model is to be able to identify the license plate position in a targeted manner for different models and effectively extract the license plate information. The architecture of the large model is a conventional large model architecture, and this application does not adjust the architecture of the large model.

[0090] Input the first image in the second group of violation images into the target large model to obtain the vehicle license plate information features and form a second label; The second label is compared with the first label formed by the license plate corresponding to the first set of characteristic information to obtain a comparison result.

[0091] Through the above method, the large model is used to specifically identify the license plate information features of the first image in the second group of violation images, and other features are discarded. In this way, the license plate information features corresponding to the second label and the first label can be compared, and only by comparing this feature, it can be determined that they are the same vehicle. Further, the time required for vehicle identification is simplified and waste of resources is avoided.

[0092] In one embodiment, if a vehicle enters a no-parking section and its license plate information is blocked by a following vehicle or a preceding illegal vehicle, the following steps are included: Acquire several frames of images before the first group of violation images; wherein, several frames of images can be acquired at set intervals. For example, the interval between frames can be set to 2 seconds, 4 seconds, 6 seconds, etc., that is, after acquiring one frame of image, the next frame of image is acquired after a set number of seconds.

[0093] Perform feature recognition on several frames of images in time sequence to obtain the vehicle's license plate information features. The time sequence is to deduce backward from the first group of violation images to perform feature recognition. For example, the time when the first image in the first group of violation images was formed is 9:00:00. In this way, a frame of image at 8:59:58 is recognized. If the license plate information feature cannot be recognized, a frame of image formed two seconds earlier at 8:59:56 is recognized. When the license plate information feature is recognized at 8:59:56, the video from 8:59:56 to 9:00:00 is used as an additional feature of the first group of feature information. That is to say, when stored in the database, the first group of violation images and the video from 8:59:56 to 9:00:00 are stored at the same time to ensure the integrity of the violation evidence.

[0094] The vehicle's license plate information features are added to the first set of feature information formed by the first set of violation images. Since the vehicle is blocked by the following vehicle or the previous violation vehicle, the vehicle's license plate information features are lost when the first set of violation images are formed. Therefore, the vehicle's license plate information features need to be supplemented to form complete vehicle violation information.

[0095] The first set of feature information is compared with the traffic violation image information stored in the database.

[0096] The above method ensures that, after a vehicle stops at a prohibited parking section and the license plate is blocked by other vehicles or other objects, the vehicle license plate captured during the vehicle's driving can still be used as a supplementary feature to the first set of feature information and compared with the violation images stored in the database.

[0097] It should be noted that if the vehicle is parked in a prohibited parking section and the license plate of the vehicle is blocked, when obtaining the second set of violation images of the vehicle for the preset second interval, it may still be impossible to obtain the license plate of the vehicle. Therefore, the second set of violation images may include the following steps: Performing grayscale conversion on any image in the first group of violation images to obtain a first grayscale image; Performing a histogram calculation according to the first grayscale image to obtain a first histogram; Performing grayscale conversion on the first image of the second group of violation images to obtain a second grayscale image; Performing a histogram calculation according to the second grayscale image to obtain a second histogram; Comparing the first histogram and the second histogram for similarity to obtain a comparison result; wherein the comparison may be performed using methods such as histogram intersection, chi-square test, and Bhattacharyya distance; If the comparison result is greater than a preset threshold, it is determined that the vehicles in the first histogram and the vehicles in the second histogram are the same vehicle.

[0098] Through the above method, it is possible to effectively identify whether a vehicle is the same vehicle even if the vehicle is parked in a prohibited parking section and the license plate is blocked. Example

[0099] The present application provides a method for electronically capturing illegal parking based on big data vehicle trajectories, the method comprising: S1. When a vehicle enters a road section where parking is prohibited, the road camera automatically captures a group of images and continuously captures the illegal parking data of the motor vehicle at a set time interval.

[0100] The number of images captured by the road camera in a group is 4, the time interval between groups is 10 minutes, and the time interval within a group is 1 minute.

[0101] S2. Input the image data captured in S1 into an image recognition module to extract vehicle feature information of the illegal vehicle.

[0102] S3. Determine whether there is illegal parking according to the parking time of the motor vehicle. If there is, generate four images with specified time intervals, and send the image data and violation data to the violation processing program.

[0103] Among them, violation data includes equipment information and vehicle information. Equipment information mainly includes equipment name, equipment code, equipment coordinates, road location, road code, etc.; vehicle information mainly includes license plate number, vehicle logo, vehicle type, vehicle color, violation time, etc.

[0104] S4. The violation handling program determines the violation of the vehicle based on the road section information where the device is located, the vehicle's historical illegal parking data and the vehicle's trajectory.

[0105] S5. When the vehicle is judged as illegally parked for the first time by the violation handling program, a text message or message reminder is generated and sent to the communication device of the owner bound to the motor vehicle, notifying the owner to leave within 10 minutes.

[0106] S6. When the vehicle is determined by the violation processing program as not the first illegal parking, a violation is generated, and the violation data of the illegally parked vehicle is stored in the Oracle database, and the synthetic image data is stored in the FastDFS file system.

[0107] The composite image is mainly composed of 4 images, of which the first two images are taken from the first group, and the last two images are taken from the second group. The 4 images indicate that a message reminder is sent to the user when the violation occurs for the first time. If the user still does not leave after 10 minutes, the composite image records the user's violation evidence.

[0108] Furthermore, the violation handling procedure in step S4 determines the vehicle violation specifically as follows: S4.1. The violation handling procedure queries the vehicle's illegal parking data for the day in the Oracle database based on the device information and vehicle information. If the license plate number, vehicle type, road name, and road code are the same, but the device name and device code are different, the violation data will be filtered to avoid cross-enforcement and continue to step S4.2.

[0109] Among them, the fields for device information query are device name, device code, road name, and road code; the fields for vehicle information query are license plate number and vehicle type.

[0110] S4.2, the violation handling procedure queries the vehicle's parking violation data for the day in the Oracle database based on the license plate number and vehicle type. If there is no result data within the specified time range, execute step S6, otherwise continue to execute step S4.3; S4.3, the violation handling program queries the result of step S4.2 based on the road location and road code. If there is no data result, step S6 is executed, otherwise, step S4.4 is continued; S4.4, the violation handling procedure uses the license plate number and vehicle type as conditions to query the trajectory information of the illegally parked vehicle on the day in the big data trajectory analysis. If there is vehicle trajectory information within the specified time range, step S6 is executed, otherwise the violation penalty will not be repeated and this violation data will be filtered out.

[0111] Among them, vehicles are only penalized once a day at the same location for violations.

[0112] like Figure 2 and Figure 3 As shown, in the second aspect, the present application provides an electronic capture illegal parking system based on big data vehicle trajectory, which applies the aforementioned electronic capture illegal parking method based on big data vehicle trajectory, and the system includes an image acquisition module, an image recognition module, a violation processing program module, a big data trajectory analysis module, and a data and image storage module.

[0113] The image acquisition module is used to obtain a first set of violation images of a vehicle entering a no-parking section according to a preset first interval time, wherein the first set of violation images includes four images taken sequentially at the first interval time. The image acquisition module is also used to obtain four images of the vehicle in the no-parking section again after a preset second interval time to obtain a second set of violation images, wherein the second set of violation images includes four images taken sequentially at the first interval time. In other words, the illegal parking data of motor vehicles entering the no-parking section are continuously captured at set time intervals.

[0114] The image recognition module is used to extract features from the first group of violation images to obtain a first group of feature information. The image recognition module is also used to extract features from the second group of violation images to obtain a second group of feature information. In other words, the image capture module recognizes vehicle features (such as license plate number, vehicle logo, vehicle type, vehicle color, etc.) of the captured image.

[0115] The violation processing program module is used to compare the second set of feature information with the violation image information stored in the database, and generate violation information when the second set of feature information is successfully compared with the first violation image information. In other words, the violation of the current vehicle is determined based on the road section information where the device is located, the historical illegal parking data of the vehicle and the vehicle trajectory, and the violation information is generated.

[0116] The big data trajectory analysis module is used to compare the first set of feature information with the violation image information stored in the database. If the comparison is unsuccessful, information on persuading the vehicle owner to leave the prohibited parking section is generated and sent to the owner of the vehicle. The first set of feature information is stored in the database to obtain the first violation image information. In other words, based on the license plate number, vehicle type and time as conditions, big data is used to analyze whether the illegally parked vehicle has a driving track and whether it has been parked in the same location.

[0117] The data and image storage module is used to store the illegal image information in the big data trajectory analysis module. That is, the illegal data of illegally parked vehicles is stored in the Oracle database, and the synthetic image data is stored in the FastDFS file system. The historical illegal parking data of vehicles is queried from the Oracle database.

[0118] In a third aspect, the present application provides a computer program, which, when executed by a processor, implements the steps of the aforementioned method for electronically capturing illegal parking based on big data vehicle trajectories.

[0119] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0120] The various embodiments in the present disclosure are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0121] The protection scope of the present disclosure is not limited to the above-mentioned embodiments. Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the scope and spirit of the present disclosure. If these changes and modifications fall within the scope of the claims of the present disclosure and their equivalents, the intention of the present disclosure also includes these changes and modifications.

Claims

1. A method for electronically capturing illegal parking based on big data vehicle trajectories, characterized in that: Methods include: According to a preset first interval time, a first group of violation images of a vehicle entering a no-parking section is acquired, wherein the first group of violation images includes four images taken sequentially at the first interval time; Extracting features from the first group of traffic violation images to obtain a first group of feature information; Comparing the first set of feature information with the traffic violation image information stored in a database, and if the comparison is unsuccessful, generating information of persuading the vehicle to leave the prohibited parking section, sending the information to the owner of the vehicle, and storing the first set of feature information in the database, to obtain the first traffic violation image information; After a preset second interval time, four images of the vehicle in the no-parking section are acquired again to obtain a second set of violation images, wherein the second set of violation images includes four images taken sequentially at the first interval time; Extracting features from the second group of traffic violation images to obtain a second group of feature information; The second set of feature information is compared with the traffic violation image information stored in the database, and when the second set of feature information is successfully compared with the first traffic violation image information, violation information is generated.

2. The electronic capture method for illegal parking based on big data vehicle trajectory according to claim 1 is characterized in that: The step of acquiring the first violation stamp image of the vehicle entering the no-parking section according to the preset first interval time comprises: Obtain the illegal parking duration regulations for areas where parking is prohibited; According to the provision, determining the first preset interval time; Acquire a first violation image taken when the vehicle enters a no-parking section, and a second violation image, a third violation image, and a fourth violation image taken in sequence at a first interval; The first group of traffic violation images is obtained by combining the first traffic violation image, the second traffic violation image, the third traffic violation image and the fourth traffic violation image.

3. The electronic capture method for illegal parking based on big data vehicle trajectory according to claim 2 is characterized in that: The step of extracting features from the first group of traffic violation images to obtain a first group of feature information includes: Extracting features from the first group of traffic violation images to obtain the license plate number, vehicle logo, vehicle type, vehicle color and shooting time of the vehicle; Obtaining device code information, device coordinate information, road location information, and road code information for photographing the first set of traffic violation images; The vehicle license plate number, vehicle logo, vehicle type, vehicle color and shooting time, as well as the device code information, the device coordinate information, the road location information and the road code information are combined to obtain the first set of feature information.

4. The electronic capture method for illegal parking based on big data vehicle trajectory according to claim 1 is characterized in that: The step of comparing the first set of feature information with the traffic violation image information stored in the database, and if the comparison is unsuccessful, generating information of persuading the vehicle to leave the prohibited parking section, sending the information to the owner of the vehicle, and storing the first set of feature information in the database to obtain the first traffic violation image information includes: Storing the traffic violation image information of the day in the database; Compare the first set of feature information and the traffic violation image information to obtain a comparison result; If the comparison result is successful, illegal information will be generated; If the comparison result is unsuccessful, information on dissuading the vehicle from a prohibited parking section will be generated and sent to the owner of the vehicle, and the first set of feature information will be stored in the database to obtain the first violation image information.

5. The electronic capture method for illegal parking based on big data vehicle trajectory according to claim 1 is characterized in that: The step of acquiring four images of the vehicle in the no-parking section again after the preset second interval time to obtain a second set of violation images comprises: Establishing the preset second interval time; After the last image of the first group of violation images is formed, timing is performed according to the second interval time. After the second interval time, four images of the vehicle in the prohibited parking section are acquired again in sequence according to the first interval time to obtain a second group of violation images.

6. The electronic capture method for illegal parking based on big data vehicle trajectory according to claim 1 is characterized in that: The step of extracting features from the second group of traffic violation images to obtain a second group of feature information includes: Extracting features from the second group of traffic violation images to obtain the license plate number, vehicle logo, vehicle type, vehicle color and shooting time of the vehicle; Acquire the device code information, device coordinate information, road location information, and road code information of the device that photographed the second set of traffic violation images; The vehicle license plate number, vehicle logo, vehicle type, vehicle color and shooting time, as well as the device code information, the device coordinate information, the road location information and the road code information are combined to obtain the first set of feature information.

7. The electronic capture method for illegal parking based on big data vehicle trajectory according to claim 1 is characterized in that: The step of comparing the second set of feature information with the traffic violation image information stored in the database, and generating violation information when the second set of feature information is successfully compared with the first traffic violation image information, comprises: Comparing the second set of feature information with the traffic violation image information stored in the database on that day to obtain a comparison result; When the second set of feature information is successfully compared with the first set of traffic violation image information, the first two images in the first set of traffic violation image information and the last two images in the second set of traffic violation images are extracted to obtain four traffic violation images; Generate violation information according to the four violation images; The second group of traffic violation images is stored in the database to obtain the second traffic violation image information.

8. The electronic capture method for illegal parking based on big data vehicle trajectory according to claim 7 is characterized in that: After the step of storing the second set of traffic violation images in the database to obtain the second traffic violation image information, the method further comprises: After a preset second interval time of obtaining the second set of violation images, four images of the vehicle in the no-parking section are obtained again to obtain a third set of violation images; Extracting features from the third group of traffic violation images to obtain a third group of feature information; The third set of feature information is compared with the traffic violation image information stored in the database. When the third set of feature information is successfully compared with the first traffic violation image information and the second traffic violation image information, the third set of traffic violation images is discarded.

9. An electronic capture system for illegal parking based on big data vehicle trajectories, characterized in that: The electronic capture method for illegal parking based on big data vehicle trajectory applied to any one of claims 1-8, the system comprising: An image acquisition module, used for acquiring a first group of violation images of a vehicle entering a no-parking section according to a preset first interval time, wherein the first group of violation images includes four images taken sequentially at the first interval time; An image recognition module, used for extracting features from the first group of traffic violation images to obtain a first group of feature information; A big data trajectory analysis module is used to compare the first set of feature information with the traffic violation image information stored in a database. If the comparison is unsuccessful, information on persuading the vehicle to leave a prohibited parking section is generated and sent to the owner of the vehicle, and the first set of feature information is stored in the database to obtain the first traffic violation image information; The image acquisition module is further used to acquire four images of the vehicle in the prohibited parking section again after a preset second interval time to obtain a second set of violation images, wherein the second set of violation images includes four images taken sequentially at the first interval time; The image recognition module is further used to extract features from the second group of traffic violation images to obtain a second group of feature information; The violation processing program module is used to compare the second set of feature information with the violation image information stored in the database, and generate violation information when the second set of feature information is successfully compared with the first violation image information.

10. A computer program, characterized in that When the computer program is executed by a processor, the steps of the method for electronically capturing illegal parking based on big data vehicle trajectories according to any one of claims 1 to 8 are implemented.

Images