Traffic transportation illegal behavior intelligent identification system based on big data analysis

Abstract

The invention discloses a traffic transportation illegal behavior intelligent identification system based on big data analysis, and relates to the technical field of intelligent identification, and the system comprises the steps: carrying out the preprocessing of traffic transportation illegal data, and obtaining a plurality of illegal data sets; screening all the illegal data sets, and obtaining illegal recognition areas of a plurality of illegal behaviors; illegal behaviors are recognized based on the illegal recognition area, and the illegal data set is supplemented based on the recognition result; the method is used for solving the problems that in an existing traffic illegal behavior intelligent recognition system, traffic transportation illegal behaviors cannot be comprehensively recognized, the randomness existing in the traffic transportation illegal behaviors cannot be solved, illegal detection cannot be comprehensively and accurately conducted when the traffic transportation illegal behaviors happen, and the traffic transportation illegal behaviors cannot be accurately recognized. And careless omission of illegal recognition is caused.

Description

Technical Field

[0001] The present invention relates to the field of intelligent identification technology, and in particular to an intelligent identification system for traffic violations based on big data analysis. Background Art

[0002] Traffic violations refer to behaviors that endanger traffic safety when a person fails to comply with the laws, regulations and prohibitions and mandatory provisions issued by relevant departments on traffic management during traffic activities; these behaviors are not limited to speeding, driving under the influence of alcohol, running red lights, driving in the wrong direction and failing to give way as required; intelligent identification methods for traffic violations mainly include image recognition technology, deep learning technology, behavior recognition technology and data analysis and processing technology; image recognition technology mainly collects video or image data of the monitored area in real time through cameras installed in areas such as roads or parking lots; deep learning technology can automatically judge traffic violations, and deep learning technology can accurately classify and judge vehicles by identifying detailed features such as the shape, letter and number combinations of the vehicle.

[0003] The existing intelligent identification system for traffic violations usually analyzes the traffic violation data and divides the traffic violation data of each time period to obtain the traffic violation behaviors in each time period, and classifies the traffic violation behaviors in each time period based on historical data, so as to perform intelligent identification and monitoring. Although this improved system can identify the traffic violations in each time period respectively, the occurrence of traffic violations is random. Only dividing and intelligently identifying based on time periods will result in the inability to comprehensively and accurately detect violations when traffic violations occur, resulting in omissions in violation identification. For example, in the patent application with publication number CN119007458A, a traffic violation based on intelligent identification is disclosed. The method and system for monitoring and early warning of traffic violation data, which is to realize the monitoring and early warning of traffic violation data through intelligent identification of traffic violations, set the violation degree value and violation degree change value for each time period, determine the correlation between traffic violations and traffic accidents, and thus realize the monitoring and early warning of traffic violation data. Other intelligent identification systems for transportation violations, usually with improvements in face recognition or anti-fatigue recognition, still have the problem of insufficient comprehensive identification of transportation violations and inability to solve the randomness of the occurrence of transportation violations, resulting in the inability to comprehensively and accurately detect violations when transportation violations occur, causing omissions in violation identification. In view of this, it is necessary to improve the existing intelligent identification systems for traffic violations. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems in the prior art to some extent. By proposing an intelligent identification system for transportation violations based on big data analysis, it is used to solve the problem that in the existing intelligent identification systems for traffic violations, the identification of transportation violations is not comprehensive enough, and the randomness of the occurrence of transportation violations cannot be solved, resulting in the inability to conduct comprehensive and accurate illegal detection when transportation violations occur, and there are omissions in illegal identification.

[0005] To achieve the above object, the present application provides an intelligent identification system for transportation violations based on big data analysis, including an illegal data extraction module, an illegal data screening module, and an illegal intelligent identification module;

[0006] The illegal data extraction module includes an illegal data extraction unit, and the illegal data extraction unit is configured with an illegal data extraction strategy. The illegal data extraction strategy is used to obtain transportation illegal data based on big data, preprocess the transportation illegal data, and obtain multiple illegal data sets based on the preprocessing results;

[0007] The illegal data screening module includes an illegal data screening unit, and the illegal data screening unit is configured with an illegal data screening strategy. The illegal data screening strategy is used to screen all illegal data sets and obtain the illegal identification areas of multiple illegal acts based on the screening results;

[0008] The illegal intelligent identification module includes an illegal intelligent identification unit, and the illegal intelligent identification unit is configured with an illegal intelligent identification strategy. The illegal intelligent identification strategy is used to identify illegal acts based on the illegal identification areas and supplement the illegal data sets based on the identification results.

[0009] Further, the illegal data extraction strategy includes:

[0010] Obtain the road section for identifying illegal acts, denoted as the identification road section; obtain multiple transportation illegal data based on big data, and denote the illegal acts in all transportation illegal data as recognizable acts KX 1 to recognizable act KX c ; establish c data sets, and denote them as the first illegal data set to the cth illegal data set in sequence. Sequentially denote recognizable act KX 1 to recognizable act KX c as the act identifiers of the first illegal data set to the cth illegal data set.

[0011] Further, the illegal data extraction strategy also includes:

[0012] Preprocess all transportation violation data, and the preprocessing is as follows: For any transportation violation data, obtain the illegal acts in the transportation violation data based on big data analysis, and record the illegal data set corresponding to the behavior identifier that is the same as the illegal act in the transportation violation data as the parent set of the transportation violation data. Among them, there can be multiple parent sets for the same transportation illegal act;

[0013] Obtain the parent sets of all transportation violation data, and store all transportation violation data into the corresponding parent sets.

[0014] Furthermore, the illegal data screening strategy includes:

[0015] For any illegal data set α and the behavior identifier β of the illegal data set α, establish a plane rectangular coordinate system, denoted as the parent set analysis coordinate system. Among them, the units of the X-axis and Y-axis of the parent set analysis coordinate system are both meters; Place the top view corresponding to the recognition section in the first quadrant of the parent set analysis coordinate system in equal proportion, denoted as the parent set section.

[0016] Furthermore, the illegal data screening strategy also includes:

[0017] For any transportation violation data in the illegal data set α, obtain the geographical location where the behavior identifier β exists in the traffic violation data based on big data analysis, and mark the geographical location in the parent set section, denoted as the illegal act point.

[0018] Furthermore, the illegal data screening strategy also includes:

[0019] Obtain all the illegal act points corresponding to the transportation violation data in the illegal data set α within the parent set coordinate system; Use the illegal core algorithm to obtain the illegal core point of the illegal data set α. The illegal core algorithm is: Among them, t is the number of illegal act points, Z i is the ordinate of the i-th illegal act point or the abscissa of the i-th illegal act point. When Z i is the ordinate of the i-th illegal act point, F is the ordinate of the illegal core point; When Z i is the abscissa of the i-th illegal act point, F is the abscissa of the illegal core point.

[0020] Furthermore, the illegal data screening strategy also includes: Mark the illegal core point in the parent set coordinate system based on the ordinate of the illegal core point and the abscissa of the illegal core point obtained by the illegal core algorithm.

[0021] Furthermore, the illegal data screening strategy also includes:

[0022] Record the illegal behavior point farthest from the illegal core point as the farthest illegal distance. Draw a circle with the farthest illegal distance as the radius and the illegal core point as the center, and record the area corresponding to the obtained circle in the recognition section as the illegal recognition area of behavior identifier β;

[0023] Obtain the illegal recognition areas of all behavior identifiers.

[0024] Furthermore, the illegal intelligent recognition strategy includes:

[0025] Place c cameras in the recognition section and take pictures of the c illegal recognition areas respectively; for any one camera, record the behavior identifier corresponding to the illegal recognition area captured by the camera as the shooting identifier, and use the camera to recognize the shooting identifier based on AI recognition.

[0026] Furthermore, the illegal intelligent recognition strategy also includes:

[0027] For any one camera, when the camera recognizes the shooting identifier, add the recognition data of the camera to the illegal data set corresponding to the shooting recognition, and update the illegal recognition area corresponding to the shooting identifier. Adjust the shooting orientation of the camera based on the updated illegal recognition area until the camera can completely capture the updated illegal recognition area;

[0028] When the camera recognizes a behavior identifier other than the shooting identifier, add the recognition data of the camera to the illegal data set corresponding to the behavior identifier captured by the camera, and re-obtain all illegal recognition areas; adjust the shooting orientation of the camera based on the re-obtained illegal recognition area until the camera can completely capture the re-obtained illegal recognition area.

[0029] Advantages of the present invention: This application first obtains transportation violation data based on big data, preprocesses the transportation violation data, and obtains multiple illegal data sets based on the preprocessing results; then screens all illegal data sets, and obtains the illegal recognition areas of multiple illegal behaviors based on the screening results; finally, recognizes illegal behaviors based on the illegal recognition areas, and supplements the illegal data sets based on the recognition results. The advantage of this is that by obtaining multiple illegal data sets and getting multiple illegal recognition areas, it is possible to effectively divide the areas for illegal recognition, analyze the areas where each illegal behavior may occur based on the locations where various illegal behaviors occur, which helps to ensure that the recognized areas can fully cover each illegal behavior during subsequent illegal recognition. At the same time, supplementing the illegal data sets based on the recognition results can update the system in this application in real time to ensure the real-time nature of intelligent recognition, so as to more accurately recognize with the illegal data sets that conform to the actual illegal situation, thereby avoiding the problem of recognition omissions. Brief Description of the Drawings

[0030] Figure 1 is the principle block diagram of the system of the present invention;

[0031] Figure 2 is the schematic diagram of the subset analysis coordinate system of the present invention. Specific embodiments

[0032] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0033] Embodiment 1, in the first aspect, please refer to Figure 1 As shown, the present application provides an intelligent identification system for transportation violations based on big data analysis, including an illegal data extraction module, an illegal data screening module, and an illegal intelligent identification module;

[0034] The illegal data extraction module includes an illegal data extraction unit, and the illegal data extraction unit is configured with an illegal data extraction strategy for obtaining transportation illegal data based on big data, preprocessing the transportation illegal data, and obtaining multiple illegal data sets based on the preprocessing results;

[0035] The illegal data extraction strategy includes: obtaining the road section for identifying illegal acts, denoted as the identification road section; obtaining multiple transportation illegal data based on big data, and respectively denoting the illegal acts in all transportation illegal data as recognizable acts KX 1 to recognizable act KX c ; establishing c data sets, and sequentially denoting them as the first illegal data set to the cth illegal data set, and sequentially denoting recognizable acts KX 1 to recognizable act KX c as the act identifiers of the first illegal data set to the cth illegal data set;

[0036] In the specific implementation process, for example, in a data processing, the multiple recognizable acts KX obtained are speeding, fatigue driving, drunk driving, overloading in transportation, and illegal lane change respectively. Then, after obtaining multiple transportation illegal data, the transportation illegal data corresponding to the above 5 recognizable acts KX can be sequentially denoted as the first illegal data to the fifth illegal data, that is, the value of c is 5;

[0037] The illegal data extraction strategy also includes: preprocessing all transportation illegal data. The preprocessing is as follows: for any transportation illegal data, based on big data analysis, obtain the illegal act in the transportation illegal data, and record the illegal data set corresponding to the act identifier identical to the illegal act in the transportation illegal data as the parent set of the transportation illegal data. Among them, there can be multiple parent sets for the same transportation illegal act;

[0038] Obtain the parent sets of all transportation illegal data, and store all transportation illegal data into the corresponding parent sets.

[0039] The illegal data screening module includes an illegal data screening unit, and the illegal data screening unit is configured with an illegal data screening strategy. The illegal data screening strategy is used to screen all illegal data sets, and obtain the illegal recognition areas of multiple illegal acts based on the screening results;

[0040] The illegal data screening strategy includes: for any illegal data set α and the act identifier β of the illegal data set α, establish a plane rectangular coordinate system, denoted as the parent set analysis coordinate system. Among them, the units of the X-axis and Y-axis of the parent set analysis coordinate system are both meters; place the top view corresponding to the recognition section in the first quadrant of the parent set analysis coordinate system in equal proportion, denoted as the parent set section;

[0041] The illegal data screening strategy also includes: for any transportation illegal data in the illegal data set α, based on big data analysis, obtain the geographical location where the act identifier β exists in the traffic illegal data, and mark the geographical location in the parent set section, denoted as the illegal act point;

[0042] In the specific implementation process, for example, in a data processing, the obtained parent set analysis coordinate system is as Figure 2 shown, where the recognition section is an intersection, and the corresponding parent set section is as shown in the first quadrant of the coordinate system in Figure 2 Through data processing, all the illegal act points are the centers of all the ○ in Figure 2 The illegal core point obtained based on the illegal core algorithm is the center of the △ in Figure 2 Then, through image analysis, it can be obtained that Figure 2 the illegal recognition area in is the circle QY;

[0043] The illegal data screening strategy also includes: obtaining all the illegal act points corresponding to the transportation illegal data in the illegal data set α within the parent set coordinate system; using the illegal core algorithm to obtain the illegal core point of the illegal data set α. The illegal core algorithm is: where t is the number of illegal act points, Z i is the ordinate or abscissa of the i-th illegal act point. When Z iWhen it is the ordinate of the i-th illegal behavior point, F is the ordinate of the illegal core point; when Z i is the abscissa of the i-th illegal behavior point, F is the abscissa of the illegal core point;

[0044] In the specific implementation process, for example, during a data processing, the coordinates of the illegal behavior points obtained are (3, 3), (3, 4), (4, 4), and (4, 3). Then, through the illegal core algorithm, the abscissa of the illegal core point is 3.5, and the ordinate of the illegal core point is 3.5; by obtaining the illegal core point, the points where the behavior identifiers are concentrated in the subset road section can be obtained, which helps to identify the monitoring areas where the behavior identifiers will occur;

[0045] The illegal data screening strategy also includes: based on the ordinate of the illegal core point and the abscissa of the illegal core point obtained by the illegal core algorithm, marking the illegal core point in the subset coordinate system;

[0046] The illegal data screening strategy also includes: recording the illegal behavior point farthest from the illegal core point as the farthest illegal distance, drawing a circle with the farthest illegal distance as the radius and the illegal core point as the center, and recording the area corresponding to the obtained circle in the identification road section as the illegal identification area of the behavior identifier β;

[0047] Obtain the illegal identification areas of all behavior identifiers.

[0048] The illegal intelligent identification module includes an illegal intelligent identification unit, and the illegal intelligent identification unit is configured with an illegal intelligent identification strategy. The illegal intelligent identification strategy is used to identify illegal behaviors based on the illegal identification area and supplement the illegal data set based on the identification result;

[0049] The illegal intelligent identification strategy includes: placing c cameras in the identification road section and respectively photographing the c illegal identification areas; for any one camera, recording the behavior identifier corresponding to the illegal identification area photographed by the camera as the photographed identifier, and using the camera to identify the photographed identifier based on AI identification;

[0050] In the specific implementation process, in actual application, when the c cameras cannot completely photograph the c illegal identification areas, the number of cameras can be increased and the angles of the cameras can be optimized to ensure that all illegal identification areas can be monitored in all directions;

[0051] The illegal intelligent identification strategy also includes: for any one camera, when the camera identifies the photographed identifier, adding the identification data of the camera to the illegal data set corresponding to the photographed identification, and updating the illegal identification area corresponding to the photographed identifier, and adjusting the shooting orientation of the camera based on the updated illegal identification area until the camera can completely photograph the updated illegal identification area;

[0052] When the camera recognizes a behavior identifier other than the shooting identifier, add the recognition data of the camera to the illegal data set corresponding to the behavior identifier captured by the camera, and re-obtain all illegal recognition areas; adjust the shooting orientation of the camera based on the re-obtained illegal recognition areas until the camera can completely capture the re-obtained illegal recognition areas.

[0053] In the specific implementation process, by adding the recognition data of the camera to the illegal data set, the system in this application can be updated in real time to ensure the real-time nature of intelligent recognition, so as to more accurately identify with the illegal data set that conforms to the actual illegal situation, thereby avoiding the problem of recognition omissions.

[0054] Working principle: First, obtain transportation illegal data based on big data, preprocess the transportation illegal data, and obtain multiple illegal data sets based on the preprocessing results; then screen all the illegal data sets, and obtain the illegal recognition areas of multiple illegal behaviors based on the screening results; finally, identify the illegal behaviors based on the illegal recognition areas, and supplement the illegal data sets based on the recognition results.

[0055] Embodiment 2, the present application also provides an intelligent recognition method for transportation illegal behaviors based on big data analysis, including the following steps:

[0056] Step S1, obtain transportation illegal data based on big data, preprocess the transportation illegal data, and obtain multiple illegal data sets based on the preprocessing results;

[0057] Step S2, screen all the illegal data sets, and obtain the illegal recognition areas of multiple illegal behaviors based on the screening results;

[0058] Step S3, identify the illegal behaviors based on the illegal recognition areas, and supplement the illegal data sets based on the recognition results.

[0059] Step S1 includes the following sub-steps:

[0060] Step S111, obtain the road section for identifying illegal behaviors, denoted as the recognition road section;

[0061] Step S112, obtain multiple transportation illegal data based on big data, and denote the illegal behaviors in all the transportation illegal data as recognizable behaviors KX 1 to recognizable behavior KX c ;

[0062] Step S113, establish c data sets, and denote them as the first illegal data set to the cth illegal data set in sequence, and sequentially denote the recognizable behaviors KX 1Up to the recognizable behavior KX c Denoted as the behavior identifiers of the first illegal data set to the c-th illegal data set.

[0063] Step S1 further includes:

[0064] Step S121, preprocess all transportation violation data;

[0065] The preprocessing is as follows: For any transportation violation data, based on big data analysis, obtain the illegal behavior in the transportation violation data, and denote the illegal data set corresponding to the behavior identifier that is the same as the illegal behavior in the transportation violation data as the parent set of the transportation violation data. Among them, there can be multiple parent sets for the same transportation illegal behavior;

[0066] Step S122, obtain the parent sets of all transportation violation data, and store all transportation violation data into the corresponding parent sets.

[0067] Step S2 includes the following sub-steps:

[0068] Step S211, for any illegal data set α and the behavior identifier β of the illegal data set α, establish a plane rectangular coordinate system, denoted as the parent set analysis coordinate system. Among them, the units of the X-axis and Y-axis of the parent set analysis coordinate system are both meters;

[0069] Step S212, place the top view corresponding to the recognition section in the first quadrant of the parent set analysis coordinate system in equal proportion, denoted as the parent set section.

[0070] Step S2 further includes:

[0071] Step S221, for any transportation violation data in the illegal data set α, based on big data analysis, obtain the geographical location where the behavior identifier β exists in the traffic violation data, and mark the geographical location in the parent set section, denoted as the illegal behavior point.

[0072] Step S222, obtain the illegal behavior points corresponding to all transportation violation data in the illegal data set α within the parent set coordinate system;

[0073] Step S223, use the illegal core algorithm to obtain the illegal core point of the illegal data set α. The illegal core algorithm is: Among them, t is the number of illegal behavior points, Z i is the ordinate of the i-th illegal behavior point or the abscissa of the i-th illegal behavior point. When Z i is the ordinate of the i-th illegal behavior point, F is the ordinate of the illegal core point; when Z i is the abscissa of the i-th illegal behavior point, F is the abscissa of the illegal core point.

[0074] Step S2 further includes:

[0075] Step S231, based on the ordinate of the illegal core point and the abscissa of the illegal core point obtained by the illegal core algorithm, mark the illegal core point in the subset coordinate system;

[0076] Step S232, record the illegal act point farthest from the illegal core point as the farthest illegal distance, draw a circle with the farthest illegal distance as the radius and the illegal core point as the center, and record the area corresponding to the obtained circle in the recognition section as the illegal recognition area of behavior identifier β;

[0077] Step S233, obtain the illegal recognition areas of all behavior identifiers.

[0078] Step S3 includes:

[0079] Step S311, place c cameras in the recognition section and respectively take pictures of the c illegal recognition areas;

[0080] Step S312, for any one camera, record the behavior identifier corresponding to the illegal recognition area photographed by the camera as the shooting identifier, and use the camera to identify the shooting identifier based on AI recognition.

[0081] Step S3 further includes:

[0082] Step S321, for any one camera, when the camera recognizes the shooting identifier, add the recognition data of the camera to the illegal data set corresponding to the shooting recognition, and update the illegal recognition area corresponding to the shooting identifier;

[0083] Step S322, adjust the shooting orientation of the camera based on the updated illegal recognition area until the camera can completely photograph the updated illegal recognition area;

[0084] Step S323, when the camera recognizes a behavior identifier other than the shooting identifier, add the recognition data of the camera to the illegal data set corresponding to the behavior identifier photographed by the camera, and re-obtain all illegal recognition areas; adjust the shooting orientation of the camera based on the re-obtained illegal recognition area until the camera can completely photograph the re-obtained illegal recognition area.

[0085] Through the description of the above embodiments, the embodiments of the present invention can be provided as a method, a system or a computer program product. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0086] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The above-described embodiments are merely illustrative. For example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some communication interfaces. The indirect coupling or communication connection of systems, modules, and units can be in an electrical, mechanical, or other form.

[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. Intelligent identification system for traffic violations based on big data analysis, characterized by: It includes illegal data extraction module, illegal data screening module and illegal intelligent identification module; The illegal data extraction module includes an illegal data extraction unit, the illegal data extraction unit is configured with an illegal data extraction strategy, the illegal data extraction strategy is used to obtain traffic violation data based on big data, and pre-process the traffic violation data, and obtain multiple illegal data sets based on the pre-processing results; The illegal data screening module includes an illegal data screening unit, which is configured with an illegal data screening strategy, and the illegal data screening strategy is used to screen all illegal data sets and obtain illegal identification areas of multiple illegal behaviors based on the screening results; The illegal intelligent identification module includes an illegal intelligent identification unit, which is configured with an illegal intelligent identification strategy. The illegal intelligent identification strategy is used to identify illegal behaviors based on illegal identification areas and supplement the illegal data set based on the identification results.

2. The intelligent identification system for traffic violations based on big data analysis according to claim 1 is characterized in that: Illegal data extraction tactics include: Obtain the road section used for illegal behavior identification, which is recorded as the identification section; obtain multiple traffic violation data based on big data, and record the illegal behaviors in all traffic violation data as identifiable behaviors KX1 to identifiable behaviors KX c ; Establish c data sets, and record them as the first illegal data set to the cth illegal data set, and record the identifiable behaviors KX1 to the identifiable behaviors KX c Recorded as the behavior identifiers of the first illegal data set to the cth illegal data set.

3. The intelligent identification system for traffic violations based on big data analysis according to claim 2 is characterized in that: Illegal data extraction tactics also include: All traffic violation data are preprocessed. The preprocessing is as follows: for any traffic violation data, the illegal behaviors in the traffic violation data are obtained based on big data analysis, and the violation data set corresponding to the same behavior identifier as the illegal behavior in the traffic violation data is recorded as the parent set of the traffic violation data, where the same traffic violation behavior can exist in multiple parent sets; Obtain a parent set of all traffic violation data, and store all traffic violation data in the corresponding parent set.

4. The intelligent identification system for traffic violations based on big data analysis according to claim 3 is characterized in that: Illegal data screening strategies include: For any violation data set α and the behavior identifier β of the violation data set α, a plane rectangular coordinate system is established, which is recorded as the parent set analysis coordinate system, where the units of the X-axis and the Y-axis of the parent set analysis coordinate system are both meters; the top view corresponding to the identified road section is placed in equal proportion in the first quadrant of the parent set analysis coordinate system, which is recorded as the parent set road section.

5. The intelligent identification system for traffic violations based on big data analysis according to claim 4 is characterized in that: Illegal data screening strategies also include: For any traffic violation data in the violation data set α, the geographical location of the behavior identifier β in the traffic violation data is obtained based on big data analysis, and the geographical location is marked in the parent set section and recorded as the violation point.

6. The intelligent identification system for traffic violations based on big data analysis according to claim 5 is characterized in that: Illegal data screening strategies also include: Obtain the illegal behavior points corresponding to all the traffic violation data in the illegal data set α in the parent set coordinate system; use the illegal core algorithm to obtain the illegal core points of the illegal data set α, and the illegal core algorithm is: Where t is the number of illegal behavior points, Z i is the ordinate of the ith violation point or the abscissa of the ith violation point. i When Z is the ordinate of the i-th illegal behavior point, F is the ordinate of the illegal core point; i When is the horizontal coordinate of the i-th illegal behavior point, F is the horizontal coordinate of the illegal core point.

7. The intelligent identification system for traffic violations based on big data analysis according to claim 6 is characterized in that: The illegal data screening strategy also includes: marking the illegal core points in the parent set coordinate system based on the vertical coordinates of the illegal core points and the horizontal coordinates of the illegal core points obtained by the illegal core algorithm.

8. The intelligent identification system for traffic violations based on big data analysis according to claim 7 is characterized in that: Illegal data screening strategies also include: The illegal behavior point farthest from the illegal core point is recorded as the farthest illegal distance, a circle is drawn with the farthest illegal distance as the radius and the illegal core point as the center, and the area corresponding to the obtained circle in the identified road section is recorded as the illegal identification area of ​​the behavior identifier β; Get the illegal identification area of ​​all behavior logos.

9. The intelligent identification system for traffic violations based on big data analysis according to claim 8 is characterized in that: Illegal intelligent identification strategies include: Place c cameras in the identification section and take photos of c illegal identification areas respectively; for any camera, record the behavior mark corresponding to the illegal identification area photographed by the camera as the shooting mark, and use the camera to identify the shooting mark based on AI recognition.

10. The intelligent identification system for traffic violations based on big data analysis according to claim 9 is characterized in that: The illegal intelligent identification strategy also includes: For any camera, when the camera recognizes the shooting mark, the camera's recognition data is added to the illegal data set corresponding to the shooting recognition, and the illegal recognition area corresponding to the shooting mark is updated. The camera's shooting direction is adjusted based on the updated illegal recognition area until the camera can fully capture the updated illegal recognition area. When the camera recognizes a behavior identifier other than a shooting identifier, the camera's recognition data is added to the illegal data set corresponding to the behavior identifier shot by the camera, and all illegal identification areas are reacquired; based on the reacquired illegal identification area, the camera's shooting direction is adjusted until the camera can completely capture the reacquired illegal identification area.

Images