Factory vehicle identification and violation management method, device, equipment and medium

Abstract

The invention relates to a factory vehicle identification and violation management method, device and equipment and a medium, and belongs to the field of access control management. The method comprises the following steps: outputting a face verification instruction by improving face recognition; outputting a vehicle passing permission instruction through license plate recognition; the access control terminal judges whether vehicles and personnel are allowed to enter and exit and generates records; abnormal behaviors of people in a monitoring range are monitored through an improved abnormal monitoring method; vehicle violation information in the factory is checked, driver identity information is obtained by improving face recognition, the number of times of occurrence of the vehicle violation information is accumulated, and the number of times of occurrence is sent to the driver terminal through the violation recognition terminal. According to the invention, face and vehicle identification can be rapidly and accurately carried out, abnormal behaviors of personnel entering and exiting from the factory are monitored, the safety of the factory is ensured, meanwhile, violation information in the factory is monitored, and factory management is facilitated.

Description

Technical Field

[0001] The present invention belongs to the technical field of access control management, and in particular relates to a method, device, equipment and medium for identifying and managing vehicle violations in a factory area. Background Art

[0002] Many existing factories use fixed facial recognition access control gates at the gates, but during rush hour or when a large number of people and vehicles enter, the channel processing capacity is insufficient, resulting in crowded queues. When the face of a person is not straight, it is more difficult to identify, the required recognition time is increased, and the recognition accuracy is reduced, resulting in reduced factory safety and efficiency. At the same time, when the factory personnel have abnormal behavior, there is no effective monitoring measure to detect and deal with the abnormality in time, which will also threaten the safety of the factory. Summary of the invention

[0003] In order to solve the above problems existing in the prior art, the present invention provides a method, device, equipment and medium for identifying and managing vehicle violations in a factory area.

[0004] The purpose of the present invention can be achieved through the following technical solutions:

[0005] A method for identifying and managing vehicle violations in a factory area, wherein the implementation of the method comprises the following steps:

[0006] Outputting a face verification instruction by improving face recognition, wherein the face verification instruction includes a face verification pass instruction and a face verification fail instruction;

[0007] Outputting a vehicle access permission instruction through license plate recognition, wherein the vehicle access permission instruction includes a pass permission instruction and a pass rejection instruction;

[0008] The access control terminal receives the facial verification pass instruction and the pass permission instruction, opens the factory access gate and generates an entry and exit record; the access control terminal receives the facial verification fail instruction and the pass rejection instruction, closes the factory access gate and generates an access rejection record;

[0009] A monitoring range is preset, abnormal behavior indexes of persons within the monitoring range are monitored by an improved abnormal monitoring method, and an abnormal monitoring model is constructed, and abnormal monitoring information is outputted through the abnormal monitoring model, wherein the abnormal detection information includes normal information of persons and abnormal information of persons;

[0010] Inspect the vehicle violation information within the factory area, obtain the driver's identity information through the improved face recognition and accumulate the number of occurrences of the vehicle violation information, and send it to the driver terminal through the violation recognition terminal.

[0011] Preferably, the outputting of face verification instructions by improving face recognition comprises:

[0012] Upload facial information to an access control terminal, which includes a handheld access control terminal and a fixed access control terminal;

[0013] The improved face recognition is performed through the access control terminal.

[0014] Preferably, the improved face recognition includes:

[0015] Collecting the face image of the person entering the factory and locating the facial feature points, wherein the facial feature points include the outer corner of the left eye, the outer corner of the right eye, the upper lip, and the lower lip;

[0016] A face recognition coordinate system is established with the left vertex of the face image as the origin, the upper edge of the face image to the right as the horizontal axis, the left edge of the face image to the bottom as the vertical axis, and the vertical axis perpendicular to the horizontal and vertical axes as the backward direction.

[0017] Obtaining the facial feature point coordinates of the facial feature points in the face recognition coordinate system and calculating the facial inclination angle, the facial feature point coordinates including the coordinates of the outer corner of the left eye, the outer corner of the right eye, the coordinates of the upper lip, and the coordinates of the lower lip;

[0018] Acquire a rotation matrix according to the facial tilt angle;

[0019] According to the rotation matrix, taking the outer corner of the right eye as the rotation center, the face recognition coordinate system and the factory-entered face image are rotated around the vertical axis to obtain a horizontal factory-entered face image;

[0020] Acquire a facial vector according to the facial feature points, the facial vector comprising a first facial vector and a second facial vector, and calculate a facial profile angle through the facial vector;

[0021] Determine the facial side face angle, when the facial side face angle is greater than or equal to 15, obtain the facial verification result by comparing the horizontal factory-entered facial image and the facial information; when the facial side face angle is less than 15, extract the feature point target screenshot of the horizontal factory-entered facial image, generate a simulated frontal face image according to the feature point target screenshot and the horizontal factory-entered facial image, and obtain the facial verification result by comparing the simulated frontal face image and the facial information.

[0022] Preferably, extracting the target screenshot of feature points of the horizontal factory-entering face image includes:

[0023] The facial region of the horizontal incoming face image is cropped and scaled to 128×128 resolution by a scaling factor to obtain a facial region image. The scaling factor is calculated as follows: Among them, e is the scale factor, y ulip is the ordinate in the upper lip coordinates, yllip is the ordinate in the lower lip coordinates, y leye is the ordinate of the left eye outer corner, κ is the mouth constant, which is 88 / 128, and θ is the eye constant, which is 40 / 128;

[0024] The upper boundary ordinate and the lower boundary ordinate of the facial region image are obtained by the scale factor, and the expression of the upper boundary ordinate is y up =y leye -e×θ, where y up is the ordinate of the upper boundary, y leye is the ordinate of the left eye outer corner, e is the scale factor, θ is the eye constant, which is 40 / 128, and the expression of the lower boundary ordinate is y low =y leye +e×κ, where y low is the lower boundary ordinate, κ is the mouth constant, and its value is 88 / 128;

[0025] Calculate the scaling ratio by using the upper boundary ordinate and the lower boundary ordinate;

[0026] The scaled coordinates of the facial feature points are obtained according to the scaling ratio, and the facial area image is cropped according to the scaled coordinates to obtain the feature point target screenshot, wherein the feature point target screenshot includes a left eye outer corner screenshot, a right eye outer corner screenshot, an upper lip screenshot, and a lower lip screenshot.

[0027] Preferably, the outputting of the vehicle access authority instruction by license plate recognition includes:

[0028] Upload the license plate information to the access control terminal;

[0029] The access control terminal identifies the license plate information of vehicles entering the factory, and the license plate recognition is performed by comparing the license plate information allowed to pass and the license plate information of the vehicle entering the factory. When the license plate information allowed to pass and the license plate information of the vehicle entering the factory are consistent, the instruction to allow passage is output; when the license plate information allowed to pass and the license plate information of the vehicle entering the factory are inconsistent, the instruction to refuse passage is output.

[0030] Preferably, the step of monitoring the abnormal behavior index of the personnel within the monitoring range by improving the abnormal monitoring method and constructing an abnormal monitoring model comprises:

[0031] Obtain normal behavior trajectories of personnel;

[0032] Acquire a first person image through a first industrial camera and obtain a minimum external bounding box for person identification, and calculate a human body aspect ratio through the minimum external bounding box for person identification;

[0033] Acquire a second person image through a second industrial camera and calculate the moving distance of the person;

[0034] Calculate the moving speed of the personnel according to the moving distance of the personnel;

[0035] Obtaining a movement trajectory of a person and obtaining a normal coincidence degree, wherein the normal coincidence degree is a coincidence degree between the movement trajectory of the person and the normal behavior trajectory of the person;

[0036] Calculating the abnormal behavior index according to the personnel moving speed and the normal overlap;

[0037] When the abnormal behavior index takes a value of 1, the abnormal information of the personnel is output to the access control terminal, and the access control terminal sends a patrol instruction and generates a patrol record. When the abnormal behavior index takes a value of 0, the normal information of the personnel is output.

[0038] Preferably, the calculation formula of the abnormal behavior index is: in, is the abnormal behavior index, v is the personnel moving speed, and Q is the normal overlap.

[0039] A plant area vehicle identification and violation management device, used to execute the plant area vehicle identification and violation management method described above, characterized in that it comprises a face recognition module, a vehicle identification module, a door access module, an abnormality monitoring module, and a violation identification module;

[0040] The face recognition module is used to output a face verification instruction by improving face recognition, and the face verification instruction includes a face verification pass instruction and a face verification fail instruction;

[0041] The vehicle identification module is used to output a vehicle access authority instruction through license plate recognition, and the vehicle access authority instruction includes a pass permission instruction and a pass rejection instruction;

[0042] The access control module is used for the access control terminal to receive the face verification pass instruction and the access permission instruction, open the factory access and generate an entry and exit record, and the access control terminal to receive the face verification failure instruction and the access rejection instruction, close the factory access and generate an access rejection record;

[0043] The abnormal monitoring module is used to preset a monitoring range, monitor the abnormal behavior index of personnel within the monitoring range by improving the abnormal monitoring method and construct an abnormal monitoring model, and output abnormal monitoring information through the abnormal monitoring model, wherein the abnormal detection information includes normal personnel information and abnormal personnel information;

[0044] The violation recognition module is used to check the vehicle violation information in the factory area, obtain the driver's identity information through the improved face recognition and accumulate the number of occurrences of the vehicle violation information, and send it to the driver terminal through the violation recognition terminal.

[0045] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned factory vehicle identification and violation management method is implemented.

[0046] A storage medium containing computer executable instructions, which are used to execute the above-mentioned factory vehicle identification and violation management method when executed by a computer processor.

[0047] The beneficial effects of the present invention are:

[0048] (1) By improving the face recognition output face verification instructions, the efficiency and accuracy of face recognition are improved, and the face can still be accurately recognized and the face verification instructions can be output even when the face is not straight or the face is in profile;

[0049] (2) By improving the abnormal monitoring method, the abnormal behavior index of personnel within the monitoring range is monitored and an abnormal monitoring model is constructed to quickly and accurately identify the abnormal behavior of personnel within the factory area and prevent the abnormal behavior of personnel from posing a threat to the safety of the factory area;

[0050] (3) According to the rotation matrix, the face recognition coordinate system and the incoming face image are rotated around the vertical axis with the outer corner of the right eye as the rotation center to obtain a horizontal incoming face image. The outer corner of the right eye as the rotation center can prevent the facial area from rotating beyond the image boundary, causing partial loss and thus affecting subsequent recognition;

[0051] (4) Determine the facial profile angle. When the facial profile angle is less than 15, extract the feature point target screenshot of the horizontal face image, generate a simulated frontal face image based on the feature point target screenshot and the horizontal face image, and obtain the face verification result by comparing the simulated frontal face image with the face information. When the person turns his face and the facial image is deformed, the face is simulated to avoid inaccurate recognition, thereby improving the accuracy of later face recognition;

[0052] (5) The abnormal behavior index of personnel can be comprehensively judged by the personnel's movement speed and normal overlap, which can make the judgment more accurate and reduce misjudgment and missed judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0054] Figure 1 The present invention is a flowchart of the steps of a method for identifying and managing vehicle violations in a factory area. DETAILED DESCRIPTION

[0055] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0056] The working principle and use process of the present invention:

[0057] See also Figure 1 , a method for identifying and managing vehicle violations in a factory area, comprising:

[0058] S1: outputting a face verification instruction by improving face recognition, wherein the face verification instruction includes a face verification pass instruction and a face verification fail instruction;

[0059] S2: Outputting a vehicle access permission instruction through license plate recognition, wherein the vehicle access permission instruction includes a pass permission instruction and a pass rejection instruction;

[0060] S3: The access control terminal receives the facial verification pass instruction and the pass permission instruction, opens the factory entrance and generates an entry and exit record. The access control terminal receives the facial verification fail instruction and the pass denial instruction, closes the factory entrance and generates an access denial record. After registration, the relevant personnel and vehicles can pass as temporary visitors and generate an entry and exit record.

[0061] S4: Preset a monitoring range, the monitoring range includes the factory entrance, monitor the abnormal behavior index of personnel within the monitoring range by improving the abnormal monitoring method and build an abnormal monitoring model, output abnormal monitoring information through the abnormal monitoring model, and the abnormal detection information includes normal personnel information and abnormal personnel information;

[0062] S5: Check the vehicle violation information in the factory area, which includes but is not limited to illegal parking, illegal driving, and speeding. The driver's identity information is obtained through the improved face recognition and the number of occurrences of the vehicle violation information is accumulated, and sent to the driver terminal through the violation recognition terminal.

[0063] In this embodiment, the face verification instruction is output by improving the face recognition, and the face verification instruction includes a face verification pass instruction and a face verification fail instruction, which can be specifically implemented by the following steps:

[0064] S101: Upload facial information to an access control terminal, where the access control terminal includes a handheld access control terminal and a fixed access control terminal;

[0065] S102: Performing the improved face recognition through the access control terminal.

[0066] In this embodiment, the improved face recognition is performed by the access control terminal, which can be implemented by the following steps:

[0067] S102-1: Collecting the face image of the person entering the factory and locating the facial feature points, wherein the facial feature points include the outer corner of the left eye, the outer corner of the right eye, the upper lip, and the lower lip;

[0068] S102-2: Establish a face recognition coordinate system with the left vertex of the face image as the origin, the upper edge of the face image to the right as the horizontal axis, the left edge of the face image to the bottom as the vertical axis, and the vertical axis perpendicular to the horizontal and vertical axes and the backward direction as the vertical axis;

[0069] S102-3: Obtain the facial feature point coordinates of the facial feature points in the face recognition coordinate system and calculate the facial tilt angle, the facial feature point coordinates include the coordinates of the outer corner of the left eye, the outer corner of the right eye, the coordinates of the upper lip, and the coordinates of the lower lip. The facial tilt angle is the angle between the face and the horizontal direction. The calculation formula of the facial tilt angle is: Among them, α is the facial tilt angle, y leye is the ordinate of the left eye outer corner, x leye is the horizontal coordinate of the left eye outer corner coordinate, y reye is the ordinate of the outer corner of the right eye, x reye is the horizontal coordinate of the outer corner of the right eye;

[0070] S102-4: Obtain a rotation matrix according to the facial tilt angle. The expression of the rotation matrix is: Among them, R is the rotation matrix, α is the facial tilt angle, y reye is the ordinate of the outer corner of the right eye, x reye is the horizontal coordinate of the outer corner of the right eye;

[0071] S102-5: According to the rotation matrix, with the outer corner of the right eye as the rotation center, the face recognition coordinate system and the incoming face image are rotated around the vertical axis to obtain a horizontal incoming face image. With the outer corner of the right eye as the rotation center, it is possible to avoid the facial region from rotating beyond the image boundary, causing partial loss and thus affecting subsequent recognition;

[0072] S102-6: Obtain a facial vector according to the facial feature points, the facial vector including a first facial vector and a second facial vector, the first facial vector being a vector from the outer corner of the left eye to the upper lip, the second facial vector being a vector from the outer corner of the right eye to the upper lip, and calculating the facial profile angle using the facial vectors, the calculation formula is: Where β is the facial profile angle, a is the first facial vector, and b is the second facial vector;

[0073] S102-7: Determine the side face angle of the face. When the side face angle of the face is greater than or equal to 15, obtain the face verification result by comparing the horizontal factory-entered face image and the face information. When the matching degree is greater than or equal to 90%, output the face verification pass instruction. When the matching degree is less than 90%, output the face verification fail instruction. When the side face angle of the face is less than 15, extract the feature point target screenshot of the horizontal factory-entered face image, generate a simulated frontal face image according to the feature point target screenshot and the horizontal factory-entered face image, obtain the face verification result by comparing the simulated frontal face image and the face information. When the matching degree is greater than or equal to 85%, output the face verification pass instruction. When the matching degree is less than 85%, output the face verification fail instruction. When the person turns his face and causes the facial image to be deformed, the face is simulated to avoid inaccurate recognition and improve the accuracy of later face recognition.

[0074] The facial region of the horizontal incoming face image is cropped and scaled to 128×128 resolution by a scaling factor to obtain a facial region image. The scaling factor is calculated as follows: Among them, e is the scale factor, y ulip is the ordinate in the upper lip coordinates, y llip is the ordinate in the lower lip coordinates, y leye is the ordinate of the left eye outer corner, κ is the mouth constant, which is 88 / 128, and θ is the eye constant, which is 40 / 128;

[0075] The upper boundary ordinate and the lower boundary ordinate of the facial region image are obtained by the scale factor, and the expression of the upper boundary ordinate is y up =y leye -e×θ, where y up is the ordinate of the upper boundary, y leye is the ordinate of the left eye outer corner, e is the scale factor, θ is the eye constant, which is 40 / 128, and the expression of the lower boundary ordinate is y low =y leye +e×κ, where y low is the lower boundary ordinate, κ is the mouth constant, and its value is 88 / 128;

[0076] The scaling ratio is calculated by the upper boundary ordinate and the lower boundary ordinate, and the calculation formula is: Where ψ is the scaling ratio;

[0077] The scaled coordinates of the facial feature points are obtained according to the scaling ratio, and the facial area image is cropped according to the scaled coordinates to obtain the feature point target screenshot, wherein the feature point target screenshot includes a left eye outer corner screenshot, a right eye outer corner screenshot, an upper lip screenshot, and a lower lip screenshot.

[0078] In this embodiment, a vehicle access permission instruction is outputted through license plate recognition, and the vehicle access permission instruction includes a pass permission instruction and a pass rejection instruction, which can be specifically implemented through the following steps:

[0079] S201: Uploading the license plate information to the access control terminal;

[0080] S202: Identify the license plate information of the vehicle entering the factory through the access control terminal, perform the license plate recognition by comparing the license plate information allowed to pass and the license plate information of the vehicle entering the factory, and when the license plate information allowed to pass and the license plate information of the vehicle entering the factory are consistent, output the instruction to allow passage; when the license plate information allowed to pass and the license plate information of the vehicle entering the factory are inconsistent, output the instruction to deny passage.

[0081] In this embodiment, the abnormal behavior index of the personnel within the monitoring range is monitored by improving the abnormal monitoring method and an abnormal monitoring model is constructed, which can be implemented by the following steps:

[0082] S401: Acquire a normal behavior trajectory of a person, where the normal behavior trajectory of a person is a straight line connecting the factory entrance and the point where the person enters the monitoring range;

[0083] S401: Acquire a first person image through a first industrial camera and obtain a minimum external bounding box for person identification, wherein the minimum external bounding box for person identification is a minimum rectangular box that can frame all body parts of the person, and calculate the body width-to-height ratio through the minimum external bounding box for person identification, and the calculation formula is: Wherein, b is the aspect ratio of the human body, l is the width of the minimum bounding box for person recognition, and h is the height of the minimum bounding box for person recognition;

[0084] S402: Acquire a second person image through a second industrial camera and calculate the moving distance of the person. The calculation formula is d=Db(V 1 -V 2 ), where d is the moving distance of the person, D is the center distance between the first industrial camera and the second industrial camera, b is the aspect ratio of the human body, V 1 is the camera parallax of the first industrial camera, V 2 is the camera parallax of the second industrial camera;

[0085] S403: Calculate the personnel moving speed according to the personnel moving distance, and the calculation formula is: Where v is the speed of the person, d is the distance the person moves, and Δt is the interval between the first person image and the second person image.

[0086] S404: Acquire a movement trajectory of a person and acquire a normal coincidence degree, where the normal coincidence degree is a coincidence degree between the movement trajectory of the person and the normal behavior trajectory of the person;

[0087] S405: Calculate the abnormal behavior index according to the personnel movement speed and the normal overlap, so as to make the judgment more accurate and reduce misjudgment and missed judgment. The calculation formula is: Among them, ζ is the abnormal behavior index, v is the personnel movement speed, and Q is the normal overlap;

[0088] S406: When the abnormal behavior index is 1, the abnormal information of the personnel is output to the access control terminal, and the access control terminal sends a patrol instruction and generates a patrol record, and the security personnel conducts the patrol. When the abnormal behavior index is 0, the normal information of the personnel is output.

[0089] A factory area vehicle identification and violation management device comprises a face recognition module, a vehicle identification module, an access control module, an abnormality monitoring module and a violation identification module.

[0090] The face recognition module is used to output a face verification instruction by improving face recognition, and the face verification instruction includes a face verification pass instruction and a face verification fail instruction;

[0091] The vehicle identification module is used to output a vehicle access authority instruction through license plate recognition, and the vehicle access authority instruction includes a pass permission instruction and a pass rejection instruction;

[0092] The access control module is used for the access control terminal to receive the face verification pass instruction and the access permission instruction, open the factory access and generate an entry and exit record, and the access control terminal to receive the face verification failure instruction and the access rejection instruction, close the factory access and generate an access rejection record;

[0093] The abnormal monitoring module is used to preset a monitoring range, monitor the abnormal behavior index of personnel within the monitoring range by improving the abnormal monitoring method and construct an abnormal monitoring model, and output abnormal monitoring information through the abnormal monitoring model, wherein the abnormal detection information includes normal personnel information and abnormal personnel information;

[0094] The violation recognition module is used to check the vehicle violation information in the factory area, obtain the driver's identity information through the improved face recognition and accumulate the number of occurrences of the vehicle violation information, and send it to the driver terminal through the violation recognition terminal.

[0095] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0096] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0097] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0098] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A method for identifying and managing vehicle violations in a factory area, characterized in that: The implementation of the factory area vehicle identification and violation management method includes the following steps: Outputting a face verification instruction by improving face recognition, wherein the face verification instruction includes a face verification pass instruction and a face verification fail instruction; Outputting a vehicle access permission instruction through license plate recognition, wherein the vehicle access permission instruction includes a pass permission instruction and a pass rejection instruction; The access control terminal receives the facial verification pass instruction and the pass permission instruction, opens the factory access gate and generates an entry and exit record; the access control terminal receives the facial verification fail instruction and the pass rejection instruction, closes the factory access gate and generates an access rejection record; A monitoring range is preset, abnormal behavior indexes of persons within the monitoring range are monitored by an improved abnormal monitoring method, and an abnormal monitoring model is constructed, and abnormal monitoring information is outputted through the abnormal monitoring model, wherein the abnormal detection information includes normal information of persons and abnormal information of persons; Inspect the vehicle violation information within the factory area, obtain the driver's identity information through the improved face recognition and accumulate the number of occurrences of the vehicle violation information, and send it to the driver terminal through the violation recognition terminal.

2. The method for identifying and managing vehicle violations in a factory area according to claim 1, characterized in that: The output of face verification instructions by improving face recognition includes: Upload facial information to an access control terminal, which includes a handheld access control terminal and a fixed access control terminal; The improved face recognition is performed through the access control terminal.

3. The method for identifying and managing vehicle violations in a factory area according to claim 2, characterized in that: The improved face recognition includes: Collecting the face image of the person entering the factory and locating the facial feature points, wherein the facial feature points include the outer corner of the left eye, the outer corner of the right eye, the upper lip, and the lower lip; A face recognition coordinate system is established with the left vertex of the face image as the origin, the upper edge of the face image to the right as the horizontal axis, the left edge of the face image to the bottom as the vertical axis, and the vertical axis perpendicular to the horizontal and vertical axes as the backward direction. Obtaining the facial feature point coordinates of the facial feature points in the face recognition coordinate system and calculating the facial inclination angle, the facial feature point coordinates including the coordinates of the outer corner of the left eye, the outer corner of the right eye, the coordinates of the upper lip, and the coordinates of the lower lip; Acquire a rotation matrix according to the facial tilt angle; According to the rotation matrix, taking the outer corner of the right eye as the rotation center, the face recognition coordinate system and the factory-entered face image are rotated around the vertical axis to obtain a horizontal factory-entered face image; Acquire a facial vector according to the facial feature points, the facial vector comprising a first facial vector and a second facial vector, and calculate a facial profile angle through the facial vector; Determine the facial side face angle, when the facial side face angle is greater than or equal to 15, obtain the facial verification result by comparing the horizontal factory-entered facial image and the facial information; when the facial side face angle is less than 15, extract the feature point target screenshot of the horizontal factory-entered facial image, generate a simulated frontal face image according to the feature point target screenshot and the horizontal factory-entered facial image, and obtain the facial verification result by comparing the simulated frontal face image and the facial information.

4. The method for identifying and managing vehicle violations in a factory area according to claim 3, characterized in that: The step of extracting the target screenshot of feature points of the horizontal factory-entered face image comprises: The facial region of the horizontal incoming face image is cropped and scaled to 128×128 resolution by a scaling factor to obtain a facial region image. The scaling factor is calculated as follows: Among them, e is the scale factor, y ulip is the ordinate in the upper lip coordinates, y llip is the ordinate in the lower lip coordinates, y leye is the ordinate of the left eye outer corner, κ is the mouth constant, which is 88 / 128, and θ is the eye constant, which is 40 / 128; The upper boundary ordinate and the lower boundary ordinate of the facial region image are obtained by the scale factor, and the expression of the upper boundary ordinate is y up =y leye -e×θ, where y up is the ordinate of the upper boundary, y leye is the ordinate of the left eye outer corner, e is the scale factor, θ is the eye constant, which is 40 / 128, and the expression of the lower boundary ordinate is y low =y leye +e×κ, where y low is the lower boundary ordinate, κ is the mouth constant, and its value is 88 / 128; Calculate the scaling ratio by using the upper boundary ordinate and the lower boundary ordinate; The scaled coordinates of the facial feature points are obtained according to the scaling ratio, and the facial area image is cropped according to the scaled coordinates to obtain the feature point target screenshot, wherein the feature point target screenshot includes a left eye outer corner screenshot, a right eye outer corner screenshot, an upper lip screenshot, and a lower lip screenshot.

5. The method for identifying and managing vehicle violations in a factory area according to claim 1, characterized in that: The output of the vehicle access authority instruction by license plate recognition includes: Upload the license plate information to the access control terminal; The access control terminal identifies the license plate information of vehicles entering the factory, and the license plate recognition is performed by comparing the license plate information allowed to pass and the license plate information of the vehicle entering the factory. When the license plate information allowed to pass and the license plate information of the vehicle entering the factory are consistent, the instruction to allow passage is output; when the license plate information allowed to pass and the license plate information of the vehicle entering the factory are inconsistent, the instruction to refuse passage is output.

6. The method for identifying and managing vehicle violations in a factory area according to claim 1, characterized in that: The improving the abnormal monitoring method to monitor the abnormal behavior index of the personnel within the monitoring range and constructing the abnormal monitoring model comprises: Obtain normal behavior trajectories of personnel; Acquire a first person image through a first industrial camera and obtain a minimum external bounding box for person identification, and calculate a human body aspect ratio through the minimum external bounding box for person identification; Acquire a second person image through a second industrial camera and calculate the moving distance of the person; Calculate the moving speed of the personnel according to the moving distance of the personnel; Obtaining a movement trajectory of a person and obtaining a normal coincidence degree, wherein the normal coincidence degree is a coincidence degree between the movement trajectory of the person and the normal behavior trajectory of the person; Calculating the abnormal behavior index according to the personnel moving speed and the normal overlap; When the abnormal behavior index takes a value of 1, the abnormal information of the personnel is output to the access control terminal, and the access control terminal sends a patrol instruction and generates a patrol record. When the abnormal behavior index takes a value of 0, the normal information of the personnel is output.

7. The method for identifying and managing vehicle violations in a factory area according to claim 6, characterized in that: The calculation formula of the abnormal behavior index is: Among them, ζ is the abnormal behavior index, v is the personnel movement speed, and Q is the normal overlap degree.

8. A vehicle identification and violation management device in a factory area, characterized in that: The device is applied to the factory area vehicle identification and violation management method as described in any one of claims 1 to 7, including a face recognition module, a vehicle recognition module, an access control module, an abnormality monitoring module, and a violation recognition module; The face recognition module is used to output a face verification instruction by improving face recognition, and the face verification instruction includes a face verification pass instruction and a face verification fail instruction; The vehicle identification module is used to output a vehicle access authority instruction through license plate recognition, and the vehicle access authority instruction includes a pass permission instruction and a pass rejection instruction; The access control module is used for the access control terminal to receive the face verification pass instruction and the access permission instruction, open the factory access and generate an entry and exit record, and the access control terminal to receive the face verification failure instruction and the access rejection instruction, close the factory access and generate an access rejection record; The abnormal monitoring module is used to preset a monitoring range, monitor the abnormal behavior index of personnel within the monitoring range by improving the abnormal monitoring method and construct an abnormal monitoring model, and output abnormal monitoring information through the abnormal monitoring model, wherein the abnormal detection information includes normal personnel information and abnormal personnel information; The violation recognition module is used to check the vehicle violation information in the factory area, obtain the driver's identity information through the improved face recognition and accumulate the number of occurrences of the vehicle violation information, and send it to the driver terminal through the violation recognition terminal.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the factory vehicle identification and violation management method as described in any one of claims 1-7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the factory vehicle identification and violation management method as described in any one of claims 1-7.

Images