Safety monitoring method and system for traffic deployment and control

Abstract

The invention relates to the technical field of traffic safety monitoring, and discloses a safety monitoring method and system for traffic deployment and control, and the method comprises the steps: obtaining multi-perception data of a traffic road section, generating a data transmission safety strategy, transmitting the multi-perception data to a cloud platform, and guaranteeing the transmission safety of the multi-perception data; traffic congestion road sections are identified and classified by means of a target classification strategy based on multi-perception data, and emphasized monitoring of accident-prone road sections is helped; the abnormal traffic behavior in the traffic congestion road section is judged through the abnormality judgment rule, and the abnormal traffic behavior is early warned, so that intelligent early warning in the traffic congestion road section can be realized; according to early warning of abnormal traffic behaviors, real-time deployment and control decision making is carried out on a traffic congestion road section, and traffic congestion is relieved; and monitoring and optimizing the deployment and control decision, improving the efficiency of traffic deployment and control, and effectively relieving traffic congestion.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic safety monitoring, and in particular to a traffic control safety monitoring method and system. Background Art

[0002] Traditional traffic monitoring methods mainly rely on manual patrols and fixed-point monitoring, which are inefficient and prone to blind spots. At present, intelligent monitoring cameras are used in combination with artificial intelligence and big data technologies to achieve real-time monitoring and data analysis of traffic sections, which can timely monitor traffic conditions and safety conditions, provide real-time warnings and emergency responses, and improve traffic efficiency and safety by optimizing traffic flow and reducing accidents. However, the problem of how to identify and classify traffic congestion sections by collecting multi-sensory data of traffic sections, judge abnormal traffic behaviors in traffic congestion sections and issue warnings, so as to make real-time control decisions and optimization has not been solved.

[0003] For example, a Chinese patent with the authorization announcement number CN117576916B discloses a traffic safety monitoring system based on the Internet of Things. Through the cooperation between multiple modules, the system can implement the following steps: obtain the area of ​​each target road section intersecting with the intersection to be monitored, and the vehicle flow and average vehicle speed corresponding to all vehicles traveling in the forward and reverse directions of each target road section at the preset time within the traffic light cycle to which the current moment belongs; determine the vehicle congestion degree of each target road section at each preset time within the traffic light cycle to which the current moment belongs, and the overall congestion degree; determine the congestion impact of the intersection to be monitored on each target road section; determine the importance of traffic regulation; generate traffic safety monitoring information corresponding to the intersection to be monitored. Traffic safety monitoring is realized, the accuracy of judging the congestion situation at the intersection is improved, and thus traffic safety is improved.

[0004] For example, a Chinese patent with authorization announcement number CN116153092B discloses a smart tunnel traffic safety monitoring method and system, which includes: step S1: using multiple video acquisition devices installed at the entrance, interior and exit of the tunnel to respectively collect video data in the corresponding monitoring area; step S2: performing target detection on the video frame image; step S3: performing license plate detection and recognition on the vehicles at the entrance and exit of the tunnel; step S4: using the obtained vehicle license plate information to perform multi-target tracking across cameras; step S5: performing vehicle license plate re-recognition on the obtained vehicle images at the entrance, interior and exit of the tunnel; step S6: performing brightness anomaly detection on the video frame images of each camera in the tunnel; step S7: performing fire and smoke detection on the video frame images of multiple cameras in the tunnel; step S8: performing multi-target tracking within a single camera for the vehicles detected by each camera in the tunnel to obtain continuous trajectories of all vehicles; step S9: performing continuous trajectories of all vehicles obtained in each camera in the tunnel.

[0005] The above patents have the problem raised by this background technology: they do not solve the problem of how to identify and classify traffic congested sections by collecting multi-sensory data of traffic sections, judge abnormal traffic behaviors in traffic congested sections and issue warnings, so as to make real-time control decisions and adjustments.

[0006] To solve this problem, the present invention proposes a safety monitoring method and system for traffic control. Summary of the invention

[0007] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0008] In view of the problems existing in the above-mentioned existing safety monitoring method and system for traffic control, the present invention is proposed.

[0009] Therefore, the object of the present invention is to provide a safety monitoring method and system for traffic control.

[0010] In order to solve the above technical problems, the present invention provides a safety monitoring method for traffic control: acquiring multi-sensory data of traffic sections, generating a data transmission security strategy and transmitting the multi-sensory data to a cloud platform;

[0011] Based on multi-sensory data, traffic congestion sections are identified and classified with the help of target classification strategy;

[0012] Determine abnormal traffic behavior in congested sections through abnormal judgment rules and warn of abnormal traffic behavior;

[0013] Based on the early warning of abnormal traffic behavior, real-time control decisions are made on traffic congestion sections;

[0014] Monitor and fine-tune deployment decisions.

[0015] As a preferred solution of the safety monitoring method for traffic control described in the present invention, the multi-sensory data includes video data, image data and sound data;

[0016] The data transmission security policy for multi-sensory data is as follows:

[0017] The sensor encrypts the multi-sensory data to generate the sensed encrypted data, generates a verification code for the sensed encrypted data, and generates the sensed data proof, and transmits the sensed encrypted data, the verification code and the sensed data proof to the cloud platform. The cloud platform verifies the validity of the sensed data proof and the consistency of the verification code. If the verification of the sensed data proof and the verification code are passed, the cloud platform decrypts the sensed encrypted data and records it in the cloud platform database in the form of blocks.

[0018] If the verification of the perception data certificate fails or the verification of the verification code fails, the cloud platform does not allow the decryption of the perception encrypted data and returns an instruction to the sensor to retransmit the perception encrypted data, the verification code and the perception data certificate.

[0019] As a preferred solution of the traffic control safety monitoring method described in the present invention, the generation strategy of the verification code is as follows:

[0020] Obtain video data, image data and sound data of the same time period, obtain traffic participants of the video data, image data and sound data, and simultaneously obtain motion information of traffic participants in the video data, road information of the image data and collision information of the sound data, and generate a verification code by combining the traffic participants, motion information, road information and collision information;

[0021] The rules for generating verification codes are as follows:

[0022] First, the traffic participants of the video data, image data and sound data are obtained. If the traffic participant is a car, it is recorded as 0; if the traffic participant is a person, it is recorded as 1; if the traffic participant is a car and a person, it is recorded as 2;

[0023] Secondly, the motion information of the traffic participants in the video data is obtained. If the traffic participant is accelerating, it is recorded as 0; if the traffic participant is moving at a constant speed, it is recorded as 1; if the traffic participant is decelerating, it is recorded as 2;

[0024] Then, the road information of the image data is obtained. If the road condition is smooth, it is recorded as 0; if the road condition is not smooth, it is recorded as 1;

[0025] Then, the collision information of the sound data is obtained. If a collision occurs in the current time period, it is recorded as 0; if no collision occurs in the current time period, it is recorded as 1;

[0026] Finally, generate a verification code.

[0027] As a preferred solution of the safety monitoring method for traffic control described in the present invention, wherein: traffic characteristics are extracted from the acquired traffic participants, movement information, road information and collision information, and the traffic characteristics include traffic flow, speed, road conditions, travel time and accident rate;

[0028] The target classification strategy is as follows:

[0029] First, traffic characteristics are recorded according to different traffic sections, including traffic flow, speed, road conditions, travel time and accident rate of the traffic section; then the traffic congestion index of the traffic section is calculated, and the congestion threshold is set; finally, the traffic congestion index of all traffic sections is sorted in descending order, and the traffic section with a high traffic congestion index is selected as the traffic congested section;

[0030] The calculation formula of the traffic congestion index of a traffic section is as follows:

[0031] j=(f / f m )(2-v1 / v m -v2 / v m )×r×p / t;

[0032] In the formula, j represents the traffic congestion index of the traffic section, f represents the traffic flow of the traffic section, and f m represents the maximum traffic capacity of the traffic section, v1 represents the average speed of the vehicle on the traffic section, and v m represents the maximum speed limit of the traffic section, v2 represents the average walking speed of people in the traffic section, r represents the road conditions of the traffic section, p represents the accident rate of the traffic section, and t represents the average travel time of the traffic section.

[0033] As a preferred solution of the safety monitoring method for traffic control described in the present invention, the traffic characteristics also include direction change and dwell time;

[0034] The warning strategy for abnormal traffic behavior is as follows:

[0035] First, the speed, direction change and stay time of vehicles and people in the traffic congestion section are recorded; then the abnormal traffic behavior is judged according to the abnormal judgment rules; finally, an early warning is issued for the abnormal traffic behavior;

[0036] The exception determination rules are as follows:

[0037] The speed and direction change of the vehicle and the person in the traffic congestion section are compared with the speed threshold and the direction change threshold respectively. If the speed of the vehicle and the person in the traffic congestion section is greater than the speed threshold and the direction change of the vehicle and the person in the traffic congestion section is greater than the direction change threshold, then the abnormality index is calculated;

[0038] The function expression of the anomaly index is as follows:

[0039] i=|vv m |×(1+d) / (t r +1);

[0040] Where i represents the abnormal index of vehicles and people in the traffic congestion section, v represents the average speed of vehicles and people in the traffic congestion section, and v m represents the maximum speed limit of the traffic section, d represents the direction change of vehicles and people in the traffic congestion section, t r Indicates the time that cars and people stay in traffic congestion sections;

[0041] If the abnormality index is greater than the set abnormality threshold, it is determined that the traffic participant has abnormal traffic behavior.

[0042] As a preferred solution of the safety monitoring method for traffic control described in the present invention, the real-time control decision is as follows:

[0043] When there is abnormal traffic behavior in the warning traffic congestion section, if the stay time of vehicles and people in the traffic congestion section is greater than the stay time threshold, the traffic lights are adjusted;

[0044] If the direction change of vehicles and people in the traffic congestion section is greater than the direction change threshold and the stay time of vehicles and people in the traffic congestion section is greater than the stay time threshold, route adjustment is recommended and traffic police are dispatched to divert traffic.

[0045] As a preferred solution of the safety monitoring method for traffic control described in the present invention, wherein: the abnormal index of the traffic congestion section after the control decision is made is monitored, and if the abnormal index of the traffic congestion section is less than or equal to the set abnormal threshold, it means that the effect of the control decision is good;

[0046] If the abnormal index of the traffic congestion section is greater than the set abnormal threshold, it means that the effect of the control decision is not good and the control decision needs to be adjusted;

[0047] The deployment decision tuning strategy is as follows:

[0048] First, adjust the traffic lights. If there is no abnormal traffic behavior in the congested section within a week after the traffic lights are adjusted, it means that the traffic lights are not adjusted properly.

[0049] If there are abnormal traffic behaviors on the congested road within one week after the traffic lights are adjusted, the recommended routes will be optimized and the dispatch of traffic police will be increased. If there are no abnormal traffic behaviors on the congested road within one week after the recommended routes are optimized and the dispatch of traffic police is increased, it means that the dispatch of recommended routes and traffic police is improper.

[0050] If abnormal traffic behavior occurs in congested sections within a week after optimizing the recommended routes and increasing traffic police force, it will be necessary to simultaneously adjust traffic lights, optimize the recommended routes, and increase traffic police force until there is no abnormal traffic behavior in congested sections within a week.

[0051] A traffic control safety monitoring system, comprising: a data acquisition module, a detection and identification module, an abnormality warning module, a control decision module and a monitoring and tuning module;

[0052] The data collection module is used to obtain multi-sensory data of traffic sections, generate data transmission security strategies, and transmit multi-sensory data to the cloud platform;

[0053] The detection and recognition module is used to identify and classify traffic congested sections based on multi-sensory data with the help of target classification strategies;

[0054] The abnormal warning module is used to judge abnormal traffic behavior in traffic congestion sections through abnormal judgment rules and warn of abnormal traffic behavior;

[0055] The control decision module is used to make real-time control decisions on traffic congestion sections based on warnings of abnormal traffic behavior;

[0056] The monitoring and tuning module is used to monitor and optimize deployment decisions.

[0057] A computer device includes a memory for storing instructions and a processor for executing the instructions, so that the device implements a safety monitoring method for traffic control.

[0058] A computer-readable storage medium stores a computer program, which, when executed, implements a safety monitoring method for traffic control.

[0059] The beneficial effects of the present invention are as follows: the present invention obtains multi-sensory data of traffic sections, generates a data transmission security strategy, and transmits the multi-sensory data to a cloud platform, thereby ensuring the transmission security of the multi-sensory data; identifies and classifies traffic congested sections with the help of a target classification strategy based on the multi-sensory data, thereby helping to focus on monitoring accident-prone sections; judges abnormal traffic behaviors in traffic congested sections through abnormal judgment rules, and warns of abnormal traffic behaviors, thereby realizing intelligent early warning in traffic congested sections; makes real-time control decisions for traffic congested sections based on the early warning of abnormal traffic behaviors, thereby alleviating traffic congestion; monitors and optimizes control decisions, thereby improving the efficiency of traffic control, and effectively alleviating traffic congestion. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0061] Figure 1 A method flow chart of a safety monitoring method for traffic control of the present invention;

[0062] Figure 2 A data transmission security strategy flow chart of a traffic control security monitoring method of the present invention;

[0063] Figure 3 A flow chart of an abnormal traffic behavior early warning strategy of a safety monitoring method for traffic control of the present invention;

[0064] Figure 4 The system structure diagram of a traffic control safety monitoring system of the present invention. DETAILED DESCRIPTION

[0065] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0066] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0067] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0068] Example 1

[0069] In this embodiment, a method flow chart of a traffic control safety monitoring method is provided, such as Figure 1 As shown, a safety monitoring method for traffic control includes:

[0070] S1. Obtain multi-sensory data of traffic sections, generate data transmission security strategies and transmit multi-sensory data to the cloud platform.

[0071] Multi-sensory data includes video data, image data, and sound data;

[0072] The data transmission security policy for multi-sensory data is as follows:

[0073] The sensor encrypts the multi-sensory data to generate the sensed encrypted data, generates a verification code for the sensed encrypted data, and generates the sensed data proof, and transmits the sensed encrypted data, the verification code and the sensed data proof to the cloud platform instead of directly transmitting the multi-sensory data itself to the cloud platform. The cloud platform then verifies the validity of the sensed data proof and the consistency of the verification code. If the verification of the sensed data proof passes and the verification code passes, the cloud platform decrypts the sensed encrypted data and records it in the cloud platform database in the form of a block. If the verification of the sensed data proof fails or the verification code fails, the cloud platform does not allow the decryption of the sensed encrypted data and returns instructions to the sensor to transmit the sensed encrypted data, the verification code and the sensed data proof again.

[0074] The verification code generation strategy is as follows:

[0075] Take the video data, image data and sound data of the same time period, obtain the traffic participants in the video data, image data and sound data, and simultaneously obtain the motion information of the traffic participants in the video data, the road information of the image data and the collision information of the sound data, and generate a verification code by combining the traffic participants, motion information, road information and collision information.

[0076] The rules for generating verification codes are as follows:

[0077] First, the traffic participants of the video data, image data and sound data are obtained. If the traffic participant is a car, it is recorded as 0; if the traffic participant is a person, it is recorded as 1; if the traffic participant is a car and a person, it is recorded as 2;

[0078] Secondly, the motion information of the traffic participants in the video data is obtained. If the traffic participant is accelerating, it is recorded as 0; if the traffic participant is moving at a constant speed, it is recorded as 1; if the traffic participant is decelerating, it is recorded as 2;

[0079] Then, the road information of the image data is obtained. If the road condition is smooth, it is recorded as 0; if the road condition is not smooth, it is recorded as 1;

[0080] Then, the collision information of the sound data is obtained. If a collision occurs in the current time period, it is recorded as 0; if no collision occurs in the current time period, it is recorded as 1;

[0081] Finally, generate a verification code.

[0082] It needs to be explained that the perception data proof is to prove whether the multi-sensory data is authentic and valid, and the verification code is to prove whether the multi-sensory data is complete and consistent. The perception data proof does not need to disclose the actual content of the multi-sensory data.

[0083] In specific applications, sensors are used to collect video data, image data and sound data of traffic sections in real time, and the collected video data, image data and sound data are preprocessed, including denoising, segmentation, video compression, image enhancement and sound filtering, to reduce noise and interference, reduce the transmission efficiency of the video, make the image clearer and brighter, and remove noise and frequency interference in the sound, improve the accuracy and clarity of the sound, use data transmission security strategies to ensure the security of multi-sensory data during transmission, and protect the privacy of traffic participants. The data transmission security strategy of multi-sensory data is as follows: Figure 2 As shown, the sensor encrypts the multi-sensory data collected from the traffic section to generate the encrypted data, ensuring the security and privacy protection of the multi-sensory data during transmission. While generating the encrypted data, the sensor will also generate a verification code. According to the generation strategy of the verification code, a verification code can be generated. For example, during the time period, a car accelerates in a section with poor road conditions and hits a roadside stone pillar. The generated verification code is: E0mOb1c0, where the numbers refer to the above-mentioned rules for generating verification codes, and the letter E represents the overall traffic participants, the letter m represents the movement information of the traffic participants in the video data, the letter b represents the road information of the image data, and the letter c represents the collision information of the sound data, which is used to verify the integrity and consistency of the multi-sensory data and generate the perception data proof. The perception data proof includes the timestamp, sensor identifier and encryption algorithm version of the multi-sensory data, which is used to prove the source, authenticity and validity of the multi-sensory data. Then the perception encrypted data, verification code and perception data proof are transmitted to the cloud platform. After receiving the perception data proof, the cloud platform first verifies the perception data proof. , which involves checking the timestamp and sensor identifier in the perception data proof to confirm the source, authenticity and validity of the multi-sensory data, and then verifying the verification code to ensure that the verification code received by the cloud platform is consistent with the verification code generated by the sensor. When the verification of the perception data proof and the verification code are passed, the cloud platform will decrypt the perception encrypted data. Decryption requires reference to the encryption algorithm version of the perception data proof. The decrypted multi-sensory data is recorded in the cloud platform database in the form of blocks. Each block includes a group of multi-sensory data. A group of multi-sensory data includes video data, image data and sound data within ten minutes, ensuring the traceability of multi-sensory data for subsequent intelligent analysis. When the verification of the perception data proof fails or the verification code fails, the cloud platform does not allow the decryption of the perception encrypted data and returns the instructions to the sensor to retransmit the perception encrypted data, verification code and perception data proof. The above data transmission security strategy for multi-sensory data can ensure that the received multi-sensory data comes from a legitimate sensor and has not been tampered with during the transmission process, thereby ensuring the security of the data.

[0084] S2. Identify and classify traffic congested sections based on multi-sensory data with the help of target classification strategy.

[0085] Traffic characteristics are extracted from the acquired traffic participants, movement information, road information and collision information. The traffic characteristics include traffic flow, speed, road conditions, travel time and accident rate.

[0086] The target classification strategy is as follows:

[0087] First, traffic characteristics are recorded according to different traffic sections, including traffic flow, speed, road conditions, travel time and accident rate of the traffic section; then the traffic congestion index of the traffic section is calculated, and the congestion threshold is set; finally, the traffic congestion index of all traffic sections is sorted in descending order, and the traffic sections with high traffic congestion index are selected as traffic congested sections.

[0088] The calculation formula of the traffic congestion index of a traffic section is as follows:

[0089] j=(f / f m )(2-v1 / v m -v2 / v m )×r×p / t;

[0090] In the formula, j represents the traffic congestion index of the traffic section, f represents the traffic flow of the traffic section, and f m represents the maximum traffic capacity of the traffic section, v1 represents the average speed of the vehicle on the traffic section, and v m represents the maximum speed limit of the traffic section, v2 represents the average walking speed of people in the traffic section, r represents the road conditions of the traffic section, p represents the accident rate of the traffic section, and t represents the average travel time of the traffic section.

[0091] It needs to be explained that the traffic flow of a traffic section refers to the number of vehicles and people passing through the traffic section within a certain period of time; the maximum capacity of a traffic section refers to the maximum number of vehicles and people that the traffic section can accommodate under ideal conditions; the road condition of a traffic section refers to an index generated based on the road facility conditions, which is used to reflect the smoothness and safety of the traffic section; the accident rate of a traffic section refers to the probability of an accident occurring within a certain historical period of time.

[0092] In a specific application, there are three traffic sections. One is an urban road with a length of 5 kilometers and good hardware facilities. The traffic flow is 100 and the maximum capacity is 120 / hour. The average driving speed of the car on this urban road is 25 kilometers / hour, the average walking speed of people on this urban road is 5 kilometers / hour, and the maximum speed limit of this urban road is 30 kilometers / hour. The index of the road condition of the urban road generated by the good hardware facilities is 0.8, the accident rate of the urban road is 0.7, the average travel time of the car is 12 minutes, and the average travel time of people is 1 hour. The average travel time of the urban road is 36 minutes. According to the above formula, the traffic congestion index of the urban road is about 0.78; the second is a rural road with a length of 10 kilometers and general hardware facilities. The traffic flow is 50 and the maximum capacity is 80 / hour. The average driving speed of the car on this rural road is 40 kilometers / hour, and the average walking speed of people on this rural road is 4 kilometers / hour. The maximum speed limit of this rural road is 60 kilometers / hour. The road conditions of the rural road are The index generated by the first section based on better hardware facilities is 0.6, the accident rate of rural roads is 0.3, the average travel time of cars is 15 minutes, the average travel time of people is 2.5 hours, and the average travel time of rural roads is 82.5 minutes. According to the above formula, the traffic congestion index of the rural road is about 0.1; the third section is an urban road with a road length of 3 kilometers, general hardware facilities, a traffic flow of 80, a maximum capacity of 100 / hour, an average speed of cars on the urban road of 30 kilometers / hour, an average walking speed of people on the urban road of 6 kilometers / hour, and a maximum speed limit of 40 kilometers / hour. The road conditions of the urban road are based on better hardware facilities. The index generated is 0.8, the accident rate of urban roads is 0.5, the average travel time of cars is 6 minutes, and the average travel time of people is 30 minutes. The average travel time of urban roads is 18 minutes. According to the above formula, the traffic congestion index of the urban road is about 1.17; From the calculated traffic congestion index, it can be seen that the third traffic section needs to be monitored.

[0093] Here, three traffic sections are given as examples. If the total volume of the traffic section is large, the first 10% to 20% of the total volume of the traffic section is generally selected as the traffic congestion section.

[0094] S3. Determine abnormal traffic behavior in the traffic congestion section through abnormal judgment rules and warn of abnormal traffic behavior.

[0095] Traffic characteristics also include direction changes and dwell times;

[0096] Warning strategies for abnormal traffic behavior Figure 3 As shown, the details are as follows:

[0097] First, the speed, direction change and stay time of vehicles and people in traffic congestion sections are recorded; then abnormal traffic behavior is judged according to the abnormal judgment rules; finally, an early warning is issued for abnormal traffic behavior.

[0098] The exception determination rules are as follows:

[0099] The speed and direction change of the vehicle and the person in the traffic congestion section are compared with the speed threshold and the direction change threshold respectively. If the speed of the vehicle and the person in the traffic congestion section is greater than the speed threshold and the direction change of the vehicle and the person in the traffic congestion section is greater than the direction change threshold, the abnormality index is calculated.

[0100] The function expression of the anomaly index is as follows:

[0101] i=|vv m |×(1+d) / (t r +1);

[0102] Where i represents the abnormal index of vehicles and people in the traffic congestion section, v represents the average speed of vehicles and people in the traffic congestion section, and v m represents the maximum speed limit of the traffic section, d represents the direction change of vehicles and people in the traffic congestion section, t r Indicates the time that cars and people stay in traffic congestion sections;

[0103] If the abnormality index is greater than the set abnormality threshold, it means that the traffic participant has abnormal traffic behavior. The abnormality threshold is determined by technical personnel in this field based on experience and actual needs.

[0104] In a specific application, on a city road, the maximum speed limit is 50km / h, the speed threshold of the car is set to 45km / h, the speed threshold of the person is set to 5m / s, the direction change threshold of the car is 30 degrees, the direction change threshold of the person is 60 degrees, the stop time threshold of the car is 120s, and the stop time threshold of the person is 180s. According to the above abnormal index function, the abnormal index of the car and the person are respectively obtained. If the obtained abnormal index is greater than the set abnormal threshold of 5, it is judged that the car or the person has abnormal traffic behavior.

[0105] S4. Based on the warning of abnormal traffic behavior, make real-time control decisions on traffic congestion sections to ensure traffic safety and smooth flow.

[0106] The real-time deployment decision strategy is as follows:

[0107] When there is abnormal traffic behavior in the warning traffic congestion section, if the time that vehicles and people stay in the traffic congestion section is greater than the stay time threshold, the traffic light is adjusted. The stay time threshold is determined by those skilled in the art based on experience and actual needs;

[0108] If the direction change of vehicles and people in the traffic congestion section is greater than the direction change threshold and the stay time of vehicles and people in the traffic congestion section is greater than the stay time threshold, route adjustment is recommended and traffic police are dispatched to divert traffic.

[0109] In specific applications, when there are abnormal traffic behaviors in congested sections, real-time control decisions need to be made. If cars and people stay in this section for a long time, it means that the cycle of the traffic lights is unreasonable, and it is necessary to adjust the cycle of the traffic lights, increase the main road light time, and reduce the side road green light time to optimize traffic flow; if the direction changes of cars and people in this section exceed the threshold and the stay time is long, it means that traffic jams, traffic accidents, etc. may occur. It is necessary to provide real-time route adjustments to the drivers behind to avoid traffic congested sections, and dispatch traffic police to traffic congested sections to divert traffic or direct people to alleviate traffic congestion.

[0110] S5. Monitor and optimize traffic control decisions to improve the efficiency of traffic control.

[0111] Monitor the abnormal index of the traffic congestion section after the control decision is made. If the abnormal index of the traffic congestion section is less than or equal to the set abnormal threshold, it means that the control decision is effective.

[0112] If the abnormal index of the traffic congestion section is greater than the set abnormal threshold, it means that the control decision is not effective and needs to be optimized.

[0113] The deployment decision tuning strategy is as follows:

[0114] First, adjust the traffic lights. If there is no abnormal traffic behavior in the congested section within a week after the traffic lights are adjusted, it means that the traffic lights are not adjusted properly.

[0115] If there are abnormal traffic behaviors on the congested road within one week after the traffic lights are adjusted, the recommended routes will be optimized and the dispatch of traffic police will be increased. If there are no abnormal traffic behaviors on the congested road within one week after the recommended routes are optimized and the dispatch of traffic police is increased, it means that the dispatch of recommended routes and traffic police is improper.

[0116] If abnormal traffic behavior occurs in congested sections within a week after optimizing the recommended routes and increasing traffic police force, it will be necessary to simultaneously adjust traffic lights, optimize the recommended routes, and increase traffic police force until there is no abnormal traffic behavior in congested sections within a week.

[0117] Example 2

[0118] In this embodiment, a system structure diagram of a traffic control safety monitoring system is provided, such as Figure 4As shown, a traffic control safety monitoring system includes a data acquisition module, a detection and identification module, an abnormal warning module, a control decision module and a monitoring and tuning module.

[0119] The data collection module is used to obtain multi-sensory data of traffic sections, generate data transmission security strategies, and transmit multi-sensory data to the cloud platform;

[0120] The detection and recognition module is used to identify and classify traffic congested sections based on multi-sensory data with the help of target classification strategies;

[0121] The abnormal warning module is used to judge abnormal traffic behavior in traffic congestion sections through abnormal judgment rules and warn of abnormal traffic behavior;

[0122] The control decision module is used to make real-time control decisions on traffic congestion sections based on warnings of abnormal traffic behavior;

[0123] The monitoring and tuning module is used to monitor and optimize deployment and control decisions;

[0124] The specific operation of a safety monitoring system for traffic control can be found in a safety monitoring method for traffic control, which will not be described in detail here.

[0125] Example 3

[0126] In this embodiment, a computer device is provided, including a memory and a processor, the memory is used to store instructions, and the processor is used to execute the instructions, so that the computer device executes the steps of implementing the above-mentioned traffic control safety monitoring method.

[0127] Example 4

[0128] In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed, the steps of the above-mentioned traffic control safety monitoring method are implemented.

[0129] The computer-readable storage medium includes: a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and other media for storing program codes.

[0130] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A safety monitoring method for traffic control, characterized in that: include, Acquire multi-sensory data of traffic sections, generate data transmission security strategies and transmit multi-sensory data to the cloud platform; Based on multi-sensory data, traffic congestion sections are identified and classified with the help of target classification strategy; Determine abnormal traffic behavior in congested sections through abnormal judgment rules and warn of abnormal traffic behavior; Based on the early warning of abnormal traffic behavior, real-time control decisions are made on traffic congestion sections; Monitor and fine-tune deployment decisions.

2. A traffic control safety monitoring method as claimed in claim 1, characterized in that: Multi-sensory data includes video data, image data, and sound data; The data transmission security policy for multi-sensory data is as follows: The sensor encrypts the multi-sensory data to generate the sensed encrypted data, generates a verification code for the sensed encrypted data, and generates the sensed data proof, and transmits the sensed encrypted data, the verification code and the sensed data proof to the cloud platform. The cloud platform verifies the validity of the sensed data proof and the consistency of the verification code. If the verification of the sensed data proof and the verification code are passed, the cloud platform decrypts the sensed encrypted data and records it in the cloud platform database in the form of blocks. If the verification of the perception data certificate fails or the verification of the verification code fails, the cloud platform does not allow the decryption of the perception encrypted data and returns an instruction to the sensor to retransmit the perception encrypted data, the verification code and the perception data certificate.

3. A traffic control safety monitoring method as claimed in claim 2, characterized in that: The verification code generation strategy is as follows: Obtain video data, image data and sound data of the same time period, obtain traffic participants of the video data, image data and sound data, and simultaneously obtain motion information of traffic participants in the video data, road information of the image data and collision information of the sound data, and generate a verification code by combining the traffic participants, motion information, road information and collision information; The rules for generating verification codes are as follows: First, the traffic participants of the video data, image data and sound data are obtained. If the traffic participant is a car, it is recorded as 0; if the traffic participant is a person, it is recorded as 1; if the traffic participant is a car and a person, it is recorded as 2; Secondly, the motion information of the traffic participants in the video data is obtained. If the traffic participant is accelerating, it is recorded as 0; if the traffic participant is moving at a constant speed, it is recorded as 1; if the traffic participant is decelerating, it is recorded as 2; Then, the road information of the image data is obtained. If the road condition is smooth, it is recorded as 0; if the road condition is not smooth, it is recorded as 1; Then, the collision information of the sound data is obtained. If a collision occurs in the current time period, it is recorded as 0; if no collision occurs in the current time period, it is recorded as 1; Finally, generate a verification code.

4. A traffic control safety monitoring method as claimed in claim 3, characterized in that: Extract traffic characteristics from the acquired traffic participants, movement information, road information and collision information. Traffic characteristics include traffic flow, speed, road conditions, travel time and accident rate; The target classification strategy is as follows: First, traffic characteristics are recorded according to different traffic sections, including traffic flow, speed, road conditions, travel time and accident rate of the traffic section; then the traffic congestion index of the traffic section is calculated, and the congestion threshold is set; finally, the traffic congestion index of all traffic sections is sorted in descending order, and the traffic section with a high traffic congestion index is selected as the traffic congested section; The calculation formula of the traffic congestion index of a traffic section is as follows: d=(f / f m )(2-v1 / v m -v2 / v m )×r×p / t; In the formula, j represents the traffic congestion index of the traffic section, f represents the traffic flow of the traffic section, and f m represents the maximum traffic capacity of the traffic section, v1 represents the average speed of the vehicle on the traffic section, and v m represents the maximum speed limit of the traffic section, v2 represents the average walking speed of people in the traffic section, r represents the road conditions of the traffic section, p represents the accident rate of the traffic section, and t represents the average travel time of the traffic section.

5. A traffic control safety monitoring method as claimed in claim 4, characterized in that: Traffic characteristics also include direction changes and dwell times; The early warning strategy for abnormal traffic behavior is as follows: First, the speed, direction change and stay time of vehicles and people in the traffic congestion section are recorded; then the abnormal traffic behavior is judged according to the abnormal judgment rules; finally, an early warning is issued for the abnormal traffic behavior; The exception determination rules are as follows: The speed and direction change of the vehicle and the person in the traffic congestion section are compared with the speed threshold and the direction change threshold respectively. If the speed of the vehicle and the person in the traffic congestion section is greater than the speed threshold and the direction change of the vehicle and the person in the traffic congestion section is greater than the direction change threshold, then the abnormality index is calculated; The function expression of the anomaly index is as follows: i=|v-v m |×(1+d) / (t r +1); Where i represents the abnormal index of vehicles and people in the traffic congestion section, v represents the average speed of vehicles and people in the traffic congestion section, and v m represents the maximum speed limit of the traffic section, d represents the direction change of vehicles and people in the traffic congestion section, t r Indicates the time that cars and people stay in traffic congestion sections; If the abnormality index is greater than the set abnormality threshold, it is determined that the traffic participant has abnormal traffic behavior.

6. A traffic control safety monitoring method as claimed in claim 5, characterized in that: The real-time deployment decisions are as follows: When there is abnormal traffic behavior in the warning traffic congestion section, if the stay time of vehicles and people in the traffic congestion section is greater than the stay time threshold, the traffic lights are adjusted; If the direction change of vehicles and people in the traffic congestion section is greater than the direction change threshold and the stay time of vehicles and people in the traffic congestion section is greater than the stay time threshold, route adjustment is recommended and traffic police are dispatched to divert traffic.

7. A traffic control safety monitoring method as claimed in claim 6, characterized in that: Monitor the abnormal index of the traffic congestion section after the control decision is made. If the abnormal index of the traffic congestion section is less than or equal to the set abnormal threshold, it means that the control decision is effective. If the abnormal index of the traffic congestion section is greater than the set abnormal threshold, it means that the effect of the control decision is not good and the control decision needs to be adjusted; The deployment decision tuning strategy is as follows: First, adjust the traffic lights. If there is no abnormal traffic behavior in the congested section within a week after the traffic lights are adjusted, it means that the traffic lights are not adjusted properly. If there are abnormal traffic behaviors on the congested road within one week after the traffic lights are adjusted, the recommended routes will be optimized and the dispatch of traffic police will be increased. If there are no abnormal traffic behaviors on the congested road within one week after the recommended routes are optimized and the dispatch of traffic police is increased, it means that the dispatch of recommended routes and traffic police is improper. If abnormal traffic behavior occurs in congested sections within a week after optimizing the recommended routes and increasing traffic police force, it will be necessary to simultaneously adjust traffic lights, optimize the recommended routes, and increase traffic police force until there is no abnormal traffic behavior in congested sections within a week.

8. A traffic control safety monitoring system, used to implement a traffic control safety monitoring method according to any one of claims 1 to 7, characterized in that: include, Data collection module, detection and identification module, abnormal warning module, control decision module and monitoring and optimization module; The data collection module is used to obtain multi-sensory data of traffic sections, generate data transmission security strategies, and transmit multi-sensory data to the cloud platform; The detection and recognition module is used to identify and classify traffic congested sections based on multi-sensory data with the help of target classification strategies; The abnormal warning module is used to judge abnormal traffic behavior in traffic congestion sections through abnormal judgment rules and warn of abnormal traffic behavior; The control decision module is used to make real-time control decisions on traffic congestion sections based on warnings of abnormal traffic behavior; The monitoring and tuning module is used to monitor and optimize deployment decisions.

9. A computer device, characterized in that: include, A memory for storing instructions; A processor is used to execute the instruction so that the device implements a traffic control safety monitoring method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, a traffic control safety monitoring method as described in any one of claims 1-7 is implemented.

Images