CN112070942B - Intelligent management system for park gate during epidemic situation - Google Patents

Intelligent management system for park gate during epidemic situation Download PDF

Info

Publication number
CN112070942B
CN112070942B CN202010828150.7A CN202010828150A CN112070942B CN 112070942 B CN112070942 B CN 112070942B CN 202010828150 A CN202010828150 A CN 202010828150A CN 112070942 B CN112070942 B CN 112070942B
Authority
CN
China
Prior art keywords
module
detection
mechanical arm
information
personnel
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010828150.7A
Other languages
Chinese (zh)
Other versions
CN112070942A (en
Inventor
朱旭芳
袁成人
周杨威
唐晨琪
唐宇思
黎奥丰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Naval University of Engineering PLA
Original Assignee
Naval University of Engineering PLA
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Naval University of Engineering PLA filed Critical Naval University of Engineering PLA
Priority to CN202010828150.7A priority Critical patent/CN112070942B/en
Publication of CN112070942A publication Critical patent/CN112070942A/en
Application granted granted Critical
Publication of CN112070942B publication Critical patent/CN112070942B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/20—Individual registration on entry or exit involving the use of a pass
    • G07C9/22—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
    • G07C9/25—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
    • E—FIXED CONSTRUCTIONS
    • E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
    • E01F—ADDITIONAL WORK, SUCH AS EQUIPPING ROADS OR THE CONSTRUCTION OF PLATFORMS, HELICOPTER LANDING STAGES, SIGNS, SNOW FENCES, OR THE LIKE
    • E01F13/00—Arrangements for obstructing or restricting traffic, e.g. gates, barricades ; Preventing passage of vehicles of selected category or dimensions
    • E01F13/04—Arrangements for obstructing or restricting traffic, e.g. gates, barricades ; Preventing passage of vehicles of selected category or dimensions movable to allow or prevent passage

Abstract

The invention belongs to the field of epidemic situation monitoring equipment systems, and particularly relates to an intelligent management system for a park gate during an epidemic situation. The device comprises an identification detection component, a motion and control component and an information interconnection component; the identification detection component comprises an image database module, an acquisition module, a detection module and an identification module; the motion and control assembly comprises a mechanical arm module and a steering engine driving module; the intelligent monitoring system and the intelligent monitoring method can realize all-weather non-contact intelligent identification and detection by carrying out regional arrangement in a monitored park. The system is mainly suitable for body temperature detection and face recognition of people in a driving car, realizes real-time monitoring of population mobility, reduces the working strength of detection personnel, reduces the protection cost of the detection personnel, is suitable for being widely popularized and used in colleges and universities and living communities, and has high market value. The system needs fewer workers, has low requirements on the working strength of station workers and medical protection, has short detection time, and can conveniently record passengers.

Description

Intelligent management system for park gate during epidemic situation
Technical Field
The invention belongs to the field of epidemic situation monitoring equipment systems, and particularly relates to an intelligent management system for a park gate during an epidemic situation.
Background
Nowadays, although the domestic epidemic situation is effectively controlled, all departments in various regions begin active repeated work and repeated production and study under the support of policies, the epidemic situation is still severe. With the arrival of summer, the temperature gradually rises, and the medical personnel wearing thick and heavy protective clothing sometimes suffer from heatstroke and faint due to insufficient oxygen supply.
In order to cope with epidemic situations, robots are widely used in various fields such as distribution robots, thermal robots and medical robots, and the basic principle is to use robots instead of simple manual operation so as to reduce the risk of contagious infection and the instability in the face of high-strength workload. However, in intensive places such as highways and closed parks or traffic hub areas, people in vehicles are usually mainly detected by manpower, which brings many adverse effects such as large manpower investment, slow detection efficiency, slow information update, high infection risk and the like, and long queues are arranged in highways, important streets and office parks due to vehicle detection of epidemic situations.
Disclosure of Invention
The invention aims to realize all-weather non-contact intelligent identification and detection by carrying out regional arrangement in a monitored park, is mainly used for body temperature detection and face identification of people in a driving car and realizes real-time monitoring of population mobility.
In order to achieve the purpose, the invention adopts the following technical scheme.
An intelligent management system for a park gate in an epidemic situation period comprises an identification detection component, a motion and control component and an information interconnection component;
the identification detection component comprises an image database module, an acquisition module, a detection module and an identification module;
the database module is used for establishing an inherent database and a temporary database for uploading aiming at inherent crowds and temporary crowds, and is established in the following mode:
01, training a residual error network by using a deep learning model in an open source library dlib and combining human face features on the basis of the existing human face data set to obtain a network model;
02, an inherent personnel data table and a temporary personnel data table are arranged in the system, the database module collects all personnel information entering a park based on the identification module, when all data are detected, the data are packaged and sent to a server according to a fixed data format and stored, and the temporary personnel information is removed at regular time; the data table at least comprises an equipment running state table, a non-inherent personnel information table and an inherent personnel information table;
the acquisition module comprises a camera for image acquisition, preferably adopts an infrared night vision camera, transmits acquired image data to the raspberry pi 3b +, supports two modes of remote login operation and offline operation, and processes the image through a python language program to identify a temperature measurement object;
the identification module is used for completing the following steps:
s1, feature extraction: calculating and counting a gradient direction histogram of a local area of the image to form features; the gradient direction is obtained as follows: converting the detected image into black and white, comparing each pixel in the picture with other surrounding pixels, finding and comparing the depth of the current pixel with the pixel directly surrounding the current pixel, pointing the direction of image darkening by using an arrow, and repeating the process until each pixel is replaced by the arrow; these arrows are gradients, which show the flow process from light to dark on the image;
s2, distance measurement, obtaining a relative position through an API of face recognition, returning the relative position to the communication control board to control the operation of the slide rail, and guiding the next temperature detection:
specifically, while face recognition is carried out, position information of the face after the first recognition is returned for movement of the motion module, the camera is calibrated, and based on the fact that the offset of the face in the image relative to the center of the picture and the actual offset of the face relative to the detection terminal are linear in a fixed xoz plane, a fixed proportionality coefficient a is obtained according to a formula, wherein the fixed proportionality coefficient a is theta/pxThe distance delta x that the slide rail needs to move is obtained through the analysis of the face frame in the API, so that the positions of the detection terminal and the detection personnel in the vehicle are consistent;
Figure GDA0002764827810000021
wherein p isxIs a camera collecting pixels laterally, x0、x1、x2And x3Is the face position coordinate, x is the offset of the face in the image relative to the center of the picture;
the motion and control assembly comprises a mechanical arm module and a steering engine driving module;
the mechanical arm module comprises a five-degree-of-freedom mechanical arm and is used for carrying a detection terminal to realize necessary detection on personnel in the vehicle; the mechanical arm is used as an important motion module to help the detection personnel to adopt necessary information for entering the park; the mechanical arm is transmitted by a communication control board, signals are converted by a steering engine driving board and are driven by each steering engine, when a detection terminal judges the position between the mechanical arm and a vehicle body through a distance sensor, the driving board can calculate the angle of each motor needing to rotate through inverse kinematics, and finally the aim of facilitating the detection of the position of a person in the vehicle is achieved;
the steering engine driving module uses the inverse solution of a kinematic equation to realize the motion control of the mechanical arm, and the basic steps comprise:
establishing a kinematic relationship based on joint space and Cartesian space;
establishing a pose expression at the tail end of the mechanical arm by using a homogeneous transformation matrix, and describing a positive kinematics solution from a joint space to a Cartesian space or an inverse kinematics solution from a Cartesian space to the joint space, specifically; the mechanical arm mathematical model and the coordinate system determining system for expressing the position angle relationship between two pairs of joint connecting rods by using DH parameters obtain the parameters of the joints and the connecting rods according to the structural parameters of the mechanical arm and the motion range of the steering engine, and substitute the parameters into the parameters
Figure GDA0002764827810000022
In a transformation matrix;
according to the formula:
Figure GDA0002764827810000023
calculating each joint in sequence, finally obtaining a positive kinematic formula of the mechanical arm, substituting DH parameters to obtain a rotation matrix of each joint:
Figure GDA0002764827810000031
Figure GDA0002764827810000032
after the rotation matrix of each joint is obtained, the coordinates of the tail end can be obtained according to the following formula:
Figure GDA0002764827810000033
step two, inverse solution of kinematic equation
Guiding the mechanical arm to move by using the coordinates returned by the face recognition so as to realize that the detection terminal can be suitable for the position of a detection person; and based on the homogeneous transformation matrix obtained in the step one
Figure GDA0002764827810000034
Solving the angle theta of each rotary jointi(ii) a The coordinates (x, y) of the end point P of the arm are composed of three parts (x)1+x2+x3,y1+y2+y3) Composition is carried out; wherein theta of the above formula1、θ2And theta3Is the angle of the steering engine to be solved, a is the included angle between the claw and the horizontal plane, and a is theta1+θ2+θ3And, and:
x＝l1cosθ1+l2cos(θ1+θ2)+l3cos(θ1+θ2+θ3)
y＝l1sinθ1+l2sin(θ1+θ2)+l3sin(θ1+θ2+θ3)
m＝l3cosa-x n＝l3sina-y
x and y are given by the user; l1、l2And l3For the inherent property of the mechanical structure of the mechanical arm, m and n are substituted into the existing equation, and then the equation is simplified to obtain: l2＝(l1cosθ1+m)2+(l1sinθ1+n)2
The following can be obtained by calculation:
Figure GDA0002764827810000035
the above formula is a form of a root equation of a quadratic equation of unity, where a ═ m2+n2
Figure GDA0002764827810000036
From this we can find θ1、θ2The angle of (d); and solving the angles of the three steering engines based on the steps, and controlling the steering engines according to the angles to realize the control of the coordinate positions.
The intelligent management system for the park gate in the epidemic situation period is further improved, and the intelligent management system further comprises an information interconnection component; the system comprises a meter communication control board taking STM32F103C8T6 as a core, wherein KEIL programming realizes reading of sensor information and uploading to a 485 bus, stepping motor control and expansion of GPIO peripherals; the system comprises two TTL serial ports for connecting a sensor; a 485 serial port interface connected with the 485 control bus; 5-path GPIO, which comprises general TIMER TIMER3 channels 1 and 2; and 3.3V-5V boosting is carried out by adopting 74LS244, and four-wire stepping motor control is carried out.
The information interconnection assembly is used for programming and controlling the STM32F103 by using KEIL, the UART2 is communicated with an upper computer, the received interrupt is used for verifying and analyzing the issued instruction, and the UARTs 1 and 3 are controlled to carry out communication control on corresponding peripherals. UART1 and its interrupt communicate with the temperature sensor, and UART3 sends coordinate information to the robot arm according to the instructions of the upper computer. An external interrupt is triggered by the falling edge of the PB0 pin, activating the distance sensor.
The intelligent management system for the park gate in the epidemic situation period is further improved, and the identification module comprises an identity identification module and a license plate identification module; the identity identification module adopts a TY-801T embedded module, reads the information of the identity card through the RFID technology, and transmits the read information to the database, and the identity identification module needs to record the identity of personnel who enter or exit from the non-warehouse of the park and upload the information of the identification place to the database in real time; the vehicle license plate recognition module uses Http Post, so that the camera is connected with the Http server through ssl, and when a vehicle exists, the recognition system can automatically recognize and display vehicle information.
The beneficial effects are that:
the intelligent monitoring system and the intelligent monitoring method can realize all-weather non-contact intelligent identification and detection by carrying out regional arrangement in a monitored park. The system is mainly suitable for body temperature detection and face recognition of people in a driving car, and real-time monitoring of population mobility is achieved. In addition, still add license plate, people's face and identification's function, carry out all-weather contactless detection to all business turn over garden personnel to guarantee staff and the inside safety in garden, this system can ensure staff's safety effectively, reduces staff's working strength, reduces staff's protection cost simultaneously, is fit for using widely in a large number in colleges and universities and residential quarter, has higher market value. The system needs fewer workers, has low requirements on the working strength of station workers and medical protection, has less detection time, and can conveniently record passengers.
Drawings
FIG. 1 is a block diagram of an identity module architecture;
FIG. 2 is a schematic diagram illustrating a communication flow between the RF card and the reader/writer;
FIG. 3 is a schematic view of camera calibration;
FIG. 4 is a schematic view of the accuracy of the coverage of the field of view by the object under test;
FIG. 5 is a schematic diagram of experimental data of temperature compensation curves of a thermometer and an infrared temperature sensor.
Detailed Description
The invention is described in detail below with reference to specific embodiments.
The intelligent management system for the garden gate in the epidemic situation period mainly comprises an identification detection component, a management module and a management module, wherein the identification detection component comprises an image database module, an acquisition module, an identification module and a detection module;
the database module establishes an inherent database and a temporary database for uploading aiming at inherent population and temporary population. The database is established in the following way: training a residual error network by using a deep learning model in an open source library dlib and combining human face features on the basis of the existing human face data set to obtain a network model; the system comprises a database module, an identification module, a server and a server, wherein the database module is internally provided with an inherent personnel data table and a temporary personnel data table, acquires all personnel information entering a park based on the identification module, packages the data and sends and stores the data to the server according to a fixed data format when all the data are detected, and regularly clears the temporary personnel information; the data table at least comprises an equipment operation state table, a non-inherent person information table and an inherent person information table, which are shown in tables 1, 2 and 3.
TABLE 1 running state table of equipment
Name (name) Type (B) Length of
Total System number of Equipment varchar 20
Total system location of equipment varchar 20
Raspberry pie CPU temperature varchar 20
Raspberry pie CPU usage varchar 20
Raspberry pie RAM _ total varchar 20
Raspberry pie RAM _ used varchar 20
Raspberry type RAM _ free varchar 20
Hard disk capacity total varchar 20
Hard disk capacity used varchar 20
Hard disk capacity free varchar 20
Temperature sensor status varchar 20
Camera sensor state varchar 20
Identity card sensor status varchar 20
State of the mechanical arm varchar 20
State of slide rail varchar 20
TABLE 2 extrinsic person information Table
Name (name) Type (B) Length of
Temporary second generation ID varchar 20
Body temperature varchar 10
Face feature point data varchar 1600
License plate number varchar 20
Time of day varchar 100
Gate position varchar 20
TABLE 3 inherent person information Table
Name (name) Type (B) Length of
Second generation ID card varchar 20
Name (I) varchar 20
Address varchar 200
Identity card number varchar 20
Body temperature varchar 10
Face feature point data varchar 1600
License plate number varchar 20
Time of day varchar 100
Gate position varchar 20
The acquisition module comprises a camera for image acquisition, preferably adopts an infrared night vision camera, transmits acquired image data to the raspberry pi 3b +, supports two modes of remote login operation and offline operation, processes the image through a python language program to identify a temperature measurement object,
the identification module is configured to perform: feature extraction: calculating and counting a gradient direction histogram of a local area of the image to form features; the gradient direction is obtained as follows: converting the detected image into black and white, comparing each pixel in the picture with other surrounding pixels, finding and comparing the depth of the current pixel with the pixel directly surrounding the current pixel, pointing the direction of image darkening by using an arrow, and repeating the process until each pixel is replaced by the arrow; these arrows are gradients, which show the flow process from light to dark on the image; distance is calculated, and this application obtains relative position through face identification's API to return and give the operation of communication control panel in order to control the slide rail, the temperature detection of effectual guide next step makes things convenient for personnel to carry out body temperature and detects.
Specifically, when face recognition is carried out, position information of the face after the first recognition is returned for movement of the motion module, and meanwhile, a camera needs to be calibratedThe method comprises the following steps: based on the fact that the offset of the face in the image relative to the center of the picture and the actual offset of the face relative to the detection terminal are linear in a fixed xoz plane, a fixed proportionality coefficient a is obtained according to a formulaxThe distance delta x that the slide rail needs to move is obtained through the analysis of the face frame in the API, so that the positions of the detection terminal and the detection personnel in the vehicle are consistent; and is
Figure GDA0002764827810000061
Wherein p isxIs a camera collecting pixels laterally, x0、x1、x2And x3Is the face position coordinates and x is the offset of the face in the image relative to the center of the picture.
The distance measurement and calculation obtains the relative position through the API of face recognition, and returns to the communication control panel to control the operation of slide rail, and the temperature detection of next step is effectively guided, makes things convenient for personnel to carry out body temperature detection.
And returning the position information of the face after the first recognition for the movement of the motion module while recognizing the face. The camera needs to be calibrated, and the method comprises the following steps: it is assumed that the offset of the face in the image with respect to the center of the picture and the actual offset of the face with respect to the detection terminal are linear in the fixed xoz plane. And obtaining a fixed proportionality coefficient a ═ theta/p according to a formulax. Finally, the distance delta x that the slide rail needs to move is obtained through the analysis of the face frame in the API, so that the positions of the detection terminal and the detection personnel in the vehicle are consistent, and the principle is shown in figure 3;
wherein p isxIs a camera collecting pixels laterally, x0、x1、x2And x3Is the face position coordinates and x is the offset of the face in the image relative to the center of the picture.
The identity identification module reads the identity card information through the RFID by adopting a TY-801T embedded module and transmits the read information to a database. The identity recognition module is used for recording the identity of personnel who enter and exit a non-warehouse of a garden and uploading recognized place information to a database in real time, and the overall structure block diagram is shown in figure 1; when the identity card is identified, the reader-writer sends a group of electromagnetic waves with fixed frequency to the radio frequency card, an LC series resonance circuit is arranged in the card, the frequency of the LC series resonance circuit is the same as the frequency transmitted by the reader-writer, under the excitation of the electromagnetic waves, the LC resonance circuit generates resonance, so that electric charges are arranged in a capacitor, an electronic pump which is conducted in a one-way mode is connected to the other end of the capacitor, the electric charges in the capacitor are transmitted into the other capacitor to be stored, when the accumulated electric charges reach 2V, the capacitor can be used as a power supply to provide working voltage for other circuits, and data in the card are transmitted out or data in the reader-writer are received, as shown in figure 2.
The license plate recognition module uses Http Post, so that the camera is connected with the Http server through ssl. When a vehicle exists, the vehicle information is triggered and automatically identified and displayed by the identification system. After the detection of other modules is finished and no abnormal condition exists, the camera outputs through IO, so that the barrier gate is lifted, and the vehicle is controlled to enter and exit.
The recognition module has different data verification modes aiming at the inherent population and the non-inherent population and is used for completing deep learning, image acquisition, face image preprocessing, face image feature extraction, matching and recognition; the face recognition means that face information acquired by the image acquisition module is acquired, a multi-dimensional vector is generated by the face through ResNet, the Euclidean distance between the generated vector and a vector in a database is calculated, and the similarity degree of the face is judged. In the second stage, through the acquisition of video stream, the human face of each picture is detected, the human face is identified, and the identified information is marked on the picture;
the body temperature detection module adopts a non-contact infrared temperature sensor with the model number of MLX90614 ESF-BCC. The sensor can detect the surface temperature of an object according to the infrared radiation energy and the wavelength distribution of the object to be detected. One concept that is important for a non-contact infrared thermometry module is the "field of view (FOV)". The field of view is determined by the 50% radiation signal received by the thermopile and is related to the main axis of the sensor. The measured temperature is a weighted average of the temperature of the measured object within the field of view, so the accuracy is highest when the measured object completely covers the FOV field of view, see fig. 4.
In order to obtain accurate body temperature detection, a high-precision thermometer and an infrared temperature sensor are used for respectively measuring, a temperature compensation curve is drawn by combining a distance sensor, and the detected temperature value obtained through the compensation curve is closer to the actual temperature. The MLX90614ESF-BCC is tested, objects with different distances and constant body temperature of 35.5 ℃ are detected by the MLX90614ESF-BCC, and experimental data are drawn as shown in figure 5
The module samples temperature information through the singlechip, and transmits data through TTL level communication through a serial port conversion IC immediately, and the technical parameters are as follows in table 4:
TABLE 4 data parameters
Name (R) Parameter(s)
Target temperature range -70°～330°
Sensor environment range -40°～125°
Measurement accuracy 0.5 deg.C (0-50 deg.C)
Resolution ratio 0.02℃
Response frequency 2HZ
Operating voltage 3～5V
Operating current 15mA
Size of 21.5mm×23mm
The motion and control assembly comprises a mechanical arm module, a steering engine driving module and a communication control module;
the mechanical arm module comprises a five-degree-of-freedom mechanical arm, and a detection terminal is carried to realize necessary detection on people in the vehicle. The robotic arm serves as an important motion module to help the inspector take the necessary information to enter the campus. The mechanical arm is transmitted by the communication control board, signals are converted by the steering engine driving board and are driven by the steering engines, when the position between the detection terminal and the vehicle body is judged through the distance sensor, the driving board can calculate the angle of each motor needing to rotate through inverse kinematics, and finally the position of a person in the vehicle to be detected is conveniently detected.
The steering engine driving module uses the inverse solution of a kinematic equation to realize the motion control of the mechanical arm, and the basic steps comprise:
step one, establishing a kinematic relationship based on joint space and Cartesian space
Establishing a pose expression at the tail end of the mechanical arm by using a homogeneous transformation matrix, and describing a positive kinematics solution from a joint space to a Cartesian space or an inverse kinematics solution from a Cartesian space to the joint space, specifically; the mechanical arm mathematical model and the coordinate system determining system for expressing the position angle relationship between two pairs of joint connecting rods by using DH parameters obtain the parameters of the joints and the connecting rods according to the structural parameters of the mechanical arm and the motion range of the steering engine, and substitute the parameters into the parameters
Figure GDA0002764827810000081
In a transformation matrix.
According to the formula:
Figure GDA0002764827810000082
calculating each joint in sequence, finally obtaining a positive kinematic formula of the mechanical arm, substituting DH parameters to obtain a rotation matrix of each joint:
Figure GDA0002764827810000083
Figure GDA0002764827810000091
after the rotation matrix of each joint is obtained, the coordinates of the tail end can be obtained according to the following formula:
Figure GDA0002764827810000092
step two, inverse solution of kinematic equation
Guiding the mechanical arm to move by using the coordinates returned by the face recognition so as to realize that the detection terminal can be suitable for the position of a detection person;
and based on the homogeneous transformation matrix obtained in the step one
Figure GDA0002764827810000093
Solving the angle theta of each rotary jointi(ii) a The coordinates (x, y) of the end point P of the arm are composed of three parts (x)1+x2+x3,y1+y2+y3) And (4) forming. Wherein theta of the above formula1、θ2And theta3Is the angle of the steering engine to be solved, a is the included angle between the claw and the horizontal plane, and a is theta1+θ2+θ3And, and:
x＝l1cosθ1+l2cos(θ1+θ2)+l3cos(θ1+θ2+θ3)
y＝l1sinθ1+l2sin(θ1+θ2)+l3sin(θ1+θ2+θ3)
m＝l3cosa-x n＝l3sina-y
x and y are given by the user. l1、l2And l3For the inherent property of the mechanical structure of the mechanical arm, m and n are substituted into the existing equation, and then the equation is simplified to obtain: l2＝(l1cosθ1+m)2+(l1sinθ1+n)2
The following can be obtained by calculation:
Figure GDA0002764827810000094
the above formula is a form of a root equation of a quadratic equation of unity, where a ═ m2+n2
Figure GDA0002764827810000095
From this we can find θ1、θ2The angle of (d); and solving the angles of the three steering engines based on the steps, and controlling the steering engines according to the angles to realize the control of the coordinate positions.
The system also comprises an information interconnection assembly, wherein the information interconnection assembly comprises a meter communication control board based on STM32F103C8T6 as a core, and KEIL programming realizes reading of sensor information and uploading to a 485 bus, stepping motor control and expansion of GPIO peripherals; the system comprises two TTL serial ports for connecting a sensor; a 485 serial port interface connected with the 485 control bus; 5-path GPIO, which comprises general TIMER TIMER3 channels 1 and 2; boosting 3.3V-5V by adopting 74LS244, and controlling a four-wire stepping motor; the UART2 communicates with the upper computer, receives the interrupt pair to send the command for verification and analysis, and controls the UART1, 3 to control the communication of the corresponding peripheral. UART1 and its interrupt communicate with the temperature sensor, and UART3 sends coordinate information to the robot arm according to the instructions of the upper computer. An external interrupt is triggered by the falling edge of the PB0 pin, activating the distance sensor.
The specific implementation mode is as follows:
when a vehicle comes, the ground induction coil triggers the high-definition camera to firstly recognize and process the vehicle type and the license plate, and meanwhile, the control room remotely controls the voice to prompt people in the vehicle to descend the vehicle window. According to the camera feedback vehicle type, firstly, the mechanical arm is moved to a corresponding height, and the sliding rail is positioned. The raspberry group carried by the terminal judges whether a passenger is in a seat or not through face capture, if so, the position deviation of the computing terminal and a person to be tested sends coordinates to a communication control panel of the connecting terminal, the position of a sliding rail is further accurately controlled, the posture of a mechanical arm is adjusted through inverse kinematics calculation, the face characteristics of the person to be tested are compared with a database synchronously in the process, and whether extra certificate swiping registration information is needed or not is judged. After the information to be detected of the passenger is collected and completed by the detection terminal according to the flow identification, the information is gathered through the communication control panel, and the information is uploaded to the upper computer of the control room and is uploaded to the cloud end. Each node can call the information in the database at any time to realize interconnection and intercommunication of park management.
And comparing the three detection modes of the handheld thermometer, the site type thermal imaging detector and the product. Compare 3 different ways of function. According to the general passenger distribution situation in the car, comparing each detection mode consumes time. Through comparative analysis, the work needs fewer workers, the work intensity of the site workers is low, the medical protection requirement is low, the detection time is short, passengers can be conveniently recorded, and the specific parameter comparison is shown in tables 5 and 6.
TABLE 5 comparison of the function of each test mode
Figure GDA0002764827810000101
TABLE 6 comparison of average elapsed time for each assay
Figure GDA0002764827810000102
In the process of repeated production and repeated study, the control of secondary outbreak of new crown epidemic situation is particularly important. Especially in places with dense crowd, such as colleges and universities, living quarters and the like, the prevention and the timely discovery of new coronavirus infectors have extremely important function on epidemic prevention and control. The reason for this is that there is no powerful recognition, detection and monitoring system, the market is a high-risk intensive field, the population density is relatively large, and once a case occurs, a large outbreak of aggregation easily occurs. Along with the rise of the temperature, the temperature measurement mode of the whole-body protection handheld temperature measurement gun is not suitable. The development of artificial intelligence provides a prerequisite for changing the temperature measurement mode and establishing a set of intelligent detection and supervision system.
In order to solve the problems of non-contact temperature measurement detection, intelligent prevention and control and the like under the epidemic situation prevention and control situation, the intelligent epidemic situation prevention and control system is additionally provided with the functions of license plate, human face and identity identification, and all-weather non-contact detection is carried out on all people entering and leaving the garden to ensure the safety of the workers and the inside of the garden. The system can effectively guarantee the safety of detection personnel, reduces the working strength of the detection personnel, reduces the protection cost of the detection personnel, is suitable for being widely popularized and used in colleges and universities and living communities, and has high market value.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (4)

1. An intelligent management system for a park gate in an epidemic situation period is characterized by comprising an identification detection component, a motion and control component and an information interconnection component;
the identification detection component comprises an image database module, an acquisition module, a detection module and an identification module;
the database module is used for establishing an inherent database and a temporary database for uploading aiming at inherent crowds and temporary crowds, and is established in the following mode:
s01, training a residual error network by using a deep learning model in an open source library dlib and combining human face features on the basis of the existing human face data set to obtain a network model;
s02, an inherent personnel data table and a temporary personnel data table are arranged in the system, the database module collects all personnel information entering the garden based on the identification module, when all data are detected, the data are packaged and sent to the server according to a fixed data format and stored, and the temporary personnel information is removed at regular time; the data table at least comprises an equipment running state table, a non-inherent personnel information table and an inherent personnel information table;
the acquisition module comprises a camera for image acquisition, preferably adopts an infrared night vision camera, transmits acquired image data to the raspberry pi 3b +, supports two modes of remote login operation and offline operation, processes the image through a python language program to identify a temperature measurement object,
the identification module is used for completing the following steps:
s1, feature extraction: calculating and counting a gradient direction histogram of a local area of the image to form features; the gradient direction is obtained as follows: converting the detected image into black and white, comparing each pixel in the picture with other surrounding pixels, finding and comparing the depth of the current pixel with the pixel directly surrounding the current pixel, pointing the direction of image darkening by using an arrow, and repeating the process until each pixel is replaced by the arrow; these arrows are gradients, which show the flow process from light to dark on the image;
s2, distance measurement, obtaining a relative position through an API of face recognition, returning the relative position to the communication control board to control the operation of the slide rail, and guiding the next temperature detection:
specifically, while face recognition is carried out, position information of the face after the first recognition is returned for movement of the motion module, the camera is calibrated, and based on the fact that the offset of the face in the image relative to the center of the picture and the actual offset of the face relative to the detection terminal are linear in a fixed xoz plane, a fixed proportionality coefficient alpha is obtained according to a formula, wherein the fixed proportionality coefficient alpha is theta/pxThe distance delta x that the slide rail needs to move is obtained through the analysis of the face frame in the API,so as to achieve the consistency of the positions of the detection terminal and the detection personnel in the vehicle;
Figure FDA0003546511900000011
wherein p isxIs a camera collecting pixels laterally, x0、x1、x2And x3Is the face position coordinate, x is the offset of the face in the image relative to the center of the picture;
the motion and control assembly comprises a mechanical arm module and a steering engine driving module;
the mechanical arm module comprises a five-degree-of-freedom mechanical arm and is used for carrying a detection terminal to realize necessary detection on personnel in the vehicle; the mechanical arm is used as an important motion module to help the detection personnel to adopt necessary information for entering the park; the mechanical arm is transmitted by a communication control board, signals are converted by a steering engine driving board and are driven by each steering engine, when a detection terminal judges the position between the mechanical arm and a vehicle body through a distance sensor, the driving board can calculate the angle of each motor needing to rotate through inverse kinematics, and finally the aim of facilitating the detection of the position of a person in the vehicle is achieved;
the steering engine driving module uses the inverse solution of a kinematic equation to realize the motion control of the mechanical arm, and the basic steps comprise:
step one, establishing a kinematic relationship based on joint space and Cartesian space
Establishing a pose expression at the tail end of the mechanical arm by using a homogeneous transformation matrix, and describing a positive kinematics solution from a joint space to a Cartesian space or an inverse kinematics solution from a Cartesian space to the joint space, specifically; the mechanical arm mathematical model and the coordinate system determining system for expressing the position angle relationship between two pairs of joint connecting rods by using DH parameters obtain the parameters of the joints and the connecting rods according to the structural parameters of the mechanical arm and the motion range of the steering engine, and substitute the parameters into the parameters
Figure FDA0003546511900000021
In a transformation matrix;
according to the formula:
Figure FDA0003546511900000022
calculating each joint in sequence, finally obtaining a positive kinematic formula of the mechanical arm, substituting DH parameters to obtain a rotation matrix of each joint:
Figure FDA0003546511900000023
Figure FDA0003546511900000024
Figure FDA0003546511900000025
Figure FDA0003546511900000031
Figure FDA0003546511900000032
after the rotation matrix of each joint is obtained, the coordinates of the tail end can be obtained according to the following formula:
Figure FDA0003546511900000033
step two, inverse solution of kinematic equation
Guiding the mechanical arm to move by using the coordinates returned by the face recognition so as to realize that the detection terminal can be suitable for the position of a detection person;
and based on the homogeneous transformation matrix obtained in the step one
Figure FDA0003546511900000037
Solving the angle theta of each rotary jointi(ii) a The coordinates (x, y) of the end point P of the arm are composed of three parts (x)1+x2+x3,y1+y2+y3) Composition is carried out; wherein θ of the upper diagram1、θ2And theta3Is the angle of the steering engine to be solved, alpha is the included angle between the claw and the horizontal plane, and alpha is theta1+θ2+θ3And, and:
x＝l1cosθ1+l2cos(θ1+θ2)+l3cos(θ1+θ2+θ3)
y＝l1sinθ1+l2sin(θ1+θ2)+l3sin(θ1+θ2+θ3)
m＝l3cosα-x
n＝l3sinα-y
x and y are given by the user; l1、l2And l3For the inherent property of the mechanical structure of the mechanical arm, m and n are substituted into the existing equation, and then the equation is simplified to obtain:
Figure FDA0003546511900000034
the following can be obtained by calculation:
Figure FDA0003546511900000035
the above formula is a form of a root equation of a quadratic equation of unity, where a ═ m2+n2
Figure FDA0003546511900000036
From this, θ can be obtained1、θ2The angle of (d); and solving the angles of the three steering engines based on the steps, and controlling the steering engines according to the angles to realize the control of the coordinate positions.
2. The intelligent management system for the campus gate during epidemic situations as claimed in claim 1, further comprising an information interconnection component; the system comprises a meter communication control board taking STM32F103C8T6 as a core, wherein KEIL programming realizes reading of sensor information and uploading to a 485 bus, stepping motor control and expansion of GPIO peripherals; the system comprises two TTL serial ports for connecting a sensor; a 485 serial port interface connected with the 485 control bus; 5-path GPIO, which comprises general TIMER TIMER3 channels 1 and 2; and 3.3V-5V boosting is carried out by adopting 74LS244, and four-wire stepping motor control is carried out.
3. The intelligent management system for the campus gate during the epidemic situation as claimed in claim 1, wherein the information interconnection module uses KEIL to program STM32F103, UART2 communicates with the upper computer, receives the interrupt to check and analyze the issued command, and controls UART1 and UART3 to perform communication control on corresponding peripherals; UART1 and its interrupt and temperature sensor communication, UART3 according to the upper computer instructions to the arm issued coordinate information; an external interrupt is triggered by the falling edge of the PB0 pin, activating the distance sensor.
4. The intelligent management system for the park gate during the epidemic situation according to claim 1, wherein the identification module comprises an identity identification module and a license plate identification module; the identity identification module adopts a TY-801T embedded module, reads the information of the identity card through the RFID technology, and transmits the read information to the database, and the identity identification module needs to record the identity of personnel who enter or exit from the non-warehouse of the park and upload the information of the identification place to the database in real time; the vehicle license plate recognition module uses Http Post, so that the camera is connected with the Http server through ssl, and when a vehicle exists, the recognition system can automatically recognize and display vehicle information.
CN202010828150.7A 2020-08-17 2020-08-17 Intelligent management system for park gate during epidemic situation Active CN112070942B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010828150.7A CN112070942B (en) 2020-08-17 2020-08-17 Intelligent management system for park gate during epidemic situation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010828150.7A CN112070942B (en) 2020-08-17 2020-08-17 Intelligent management system for park gate during epidemic situation

Publications (2)

Publication Number Publication Date
CN112070942A CN112070942A (en) 2020-12-11
CN112070942B true CN112070942B (en) 2022-04-22

Family

ID=73661368

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010828150.7A Active CN112070942B (en) 2020-08-17 2020-08-17 Intelligent management system for park gate during epidemic situation

Country Status (1)

Country Link
CN (1) CN112070942B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112695674A (en) * 2020-12-16 2021-04-23 深圳市创智安防设备有限公司 Face identification banister with monitoring function just has temperature measurement function

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102663846A (en) * 2012-05-11 2012-09-12 尤敦朋 Intelligent visitor management system based on android operating platform and control method thereof
JP2015062541A (en) * 2013-09-25 2015-04-09 株式会社東芝 X-ray photographing device
JP2016151734A (en) * 2015-02-19 2016-08-22 株式会社ニコン Imaging device
CN107481359A (en) * 2017-07-14 2017-12-15 昆明理工大学 Intelligent door lock system and its control method based on P300 and Mental imagery
CN109087285A (en) * 2018-07-13 2018-12-25 中国人民解放军海军工程大学 Surgery wound detects debridement robot
CN209690995U (en) * 2019-01-01 2019-11-26 广东顺安万城物联技术有限公司 A kind of visitor's vehicle management linkage access control system
CN111397015A (en) * 2020-03-25 2020-07-10 哈尔滨工业大学 Modularization epidemic prevention device

Also Published As

Publication number Publication date
CN112070942A (en) 2020-12-11

Similar Documents

Publication Publication Date Title
CN110142785A (en) A kind of crusing robot visual servo method based on target detection
CN105373135B (en) A kind of method and system of aircraft docking guidance and plane type recognition based on machine vision
CN105302151B (en) A kind of system and method for aircraft docking guiding and plane type recognition
CN103413313B (en) The binocular vision navigation system of electrically-based robot and method
CN109819208A (en) A kind of dense population security monitoring management method based on artificial intelligence dynamic monitoring
CN109192302A (en) A kind of face's multi-modality images acquisition processing device and method
CN208044361U (en) A kind of multifunctional intellectual building site face identification system
CN104932001A (en) Real-time 3D nuclear radiation environment reconstruction monitoring system
CN103632427B (en) A kind of gate cracking protection method and gate control system
CN105243664A (en) Vision-based wheeled mobile robot fast target tracking method
CN206322194U (en) A kind of anti-fraud face identification system based on 3-D scanning
CN113705376B (en) Personnel positioning method and system based on RFID and camera
CN207268846U (en) Electric inspection process robot
CN112070942B (en) Intelligent management system for park gate during epidemic situation
CN102622615A (en) Knife switch state closing reliability judging method based on distance between knife switch arm feature points
CN107300398A (en) A kind of communicated based on WIFI supports the electric inspection process device of positioning and data transfer simultaneously
Mi et al. A vision-based displacement measurement system for foundation pit
CN116704377A (en) Non-inductive personnel positioning method and system based on digital twin model
CN201975857U (en) Intelligent robot inspection system for security detection of transformer station
CN112785564B (en) Pedestrian detection tracking system and method based on mechanical arm
CN104063689A (en) Face image identification method based on binocular stereoscopic vision
CN106056686B (en) A kind of indoor patrol estimation analysis method based on three-D profile
CN109033999B (en) Subway charge platform based on face recognition
CN110440932A (en) A kind of positioning device of fault point and fault point positioning method of polling transmission line
CN111216763A (en) Rail crawling observation device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant