Lane abnormal event identification method and device based on Internet of Things, and storage medium

Abstract

The invention discloses a lane abnormal event identification method and device based on Internet of Things, and a storage medium, relates to the technical field of smart traffic, and solves the problem of delay in lane abnormal event identification at the present stage. The method comprises the following steps: constructing an abnormal recognition area corresponding to a to-be-recognized road according to a historical congestion condition and a historical accident condition of the to-be-recognized road; installing a plurality of sensors in the abnormity identification area, and collecting real-time traffic data of a target vehicle in the abnormity identification area according to the sensors; the driving condition of the target vehicle is judged in combination with the real-time traffic data, then the driving condition is matched with the abnormal event rule base, and lane abnormal events in the corresponding abnormal recognition areas are recognized; and the lane abnormal event corresponding to the abnormal recognition area is taken as the vehicle abnormal event of the road to be recognized to be publicized, and the driving condition of the target vehicle in the abnormal recognition area is collected and analyzed, so that the lane abnormal event can be recognized timely and accurately.

Description

Technical Field

[0001] This invention belongs to the field of intelligent transportation technology, specifically a method, device, and storage medium for identifying lane abnormal events based on the Internet of Things. Background Technology

[0002] The Internet of Things (IoT) is a technological system that connects objects in the physical world to the internet through information sensing devices, enabling data collection, transmission, analysis, and intelligent control. Its core objective is to equip objects with the capabilities of "sensing, communicating, and computing," thereby forming an intelligent network where "things are interconnected and humans interact with each other." Abnormal lane events refer to behaviors or phenomena in the traffic system that deviate from normal operating patterns, such as abnormal traffic accidents, abnormal illegal parking, and abnormal vehicles driving in the wrong direction.

[0003] However, at present, the accuracy of dynamic identification is low when identifying abnormal events in the lane. In order to improve accuracy, it can only be obtained through human submission, but it does not perform intelligent identification based on the abnormal event rule base. This results in a delay in the detection of abnormal lane events and makes it impossible to respond to abnormal lane events in a timely manner. To this end, the present invention proposes a method, device and storage medium for identifying lane abnormal events based on the Internet of Things. Summary of the Invention

[0004] The purpose of this invention is to propose a method, device, and storage medium for identifying lane abnormal events based on the Internet of Things, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: A lane anomaly event identification method based on the Internet of Things, the method includes: Step S1: Construct the anomaly identification area corresponding to the road to be identified based on the historical congestion and accident data of the road to be identified; Step S2: Install multiple sensors within the anomaly identification area and collect real-time traffic data of target vehicles within the anomaly identification area based on the sensors. Step S3: Based on the real-time traffic data of the target vehicle in the anomaly identification area, determine the driving status of the target vehicle, and then match the driving status with the anomaly event rule base to identify the lane anomaly event in the corresponding anomaly identification area. Step S4: Publicize the lane anomaly events corresponding to the anomaly identification area as vehicle anomaly events of the road to be identified.

[0006] Further, step S1 includes the following sub-steps: Step S11: Obtain the road to be identified and divide the road to be identified into multiple regions to be analyzed at the same intervals; Step S12: Take any endpoint of the road to be identified as the origin, take the direction of the endpoint along the road to be identified as the X-axis, and take the direction perpendicular to the X-axis as the Y-axis to construct a road plane coordinate system; Step S13: Identify the coordinates of the first endpoint, the second endpoint, the third endpoint, and the fourth endpoint of any region to be analyzed. The first boundary equation is obtained by calculating the coordinates of the first endpoint and the second endpoint. The second boundary equation is obtained by calculating the coordinates of the second endpoint and the third endpoint. The third boundary equation is obtained by calculating the coordinates of the third endpoint and the fourth endpoint. The fourth boundary equation is obtained by calculating the coordinates of the fourth endpoint and the first endpoint.

[0007] Furthermore, step S1 also includes the following sub-steps: Step S14: Obtain historical traffic accidents that occurred on the road to be identified within the past year, and identify the accident coordinates of the corresponding historical traffic accidents based on the road plane coordinate system; The accident coordinates are compared sequentially with the first boundary equation, the second boundary equation, the third boundary equation, and the fourth boundary equation of the region to be analyzed. If the accident coordinates are simultaneously located to the right of the first boundary equation, above the second boundary equation, to the left of the third boundary equation, and below the fourth boundary equation, the number of traffic accidents in the corresponding region to be analyzed is incremented by one; otherwise, no operation is performed. Step S15: Count the number of traffic accidents in each region to be analyzed, and sort the regions to be analyzed in descending order of the number of traffic accidents to obtain the region selection sequence.

[0008] Furthermore, step S1 also includes the following sub-steps: Step S16: Read the total number of vehicles entering the road to be identified each day within the past year, sum the total number of vehicles each day within the past year, and take the average value to obtain the average number of vehicles per day for the corresponding road to be identified; divide the average number of vehicles per day by the length of the road to be identified to obtain the traffic flow density of the road to be identified. Step S17: Compare the traffic flow density of the road to be identified with the traffic flow density threshold. If the traffic flow density is less than or equal to the first traffic flow density threshold, then record the number of areas selected by the road to be identified, K, as A1. If the traffic flow density is greater than the first traffic flow density threshold but less than or equal to the second traffic flow density threshold, then record the number of areas selected by the road to be identified, K, as A2. If the traffic flow density is greater than the second traffic flow density threshold, then the number of areas selected for the road to be identified, K, is denoted as A3; where the first traffic flow density threshold is less than the second traffic flow density threshold, and A1, A2, and A3 are all constants and A1 < A2 < A3. Step S18: Select the first K regions to be analyzed in the region selection sequence as the anomaly identification regions of the roads to be identified.

[0009] Further, step S2 includes the following sub-steps: Step S21: Install the visual sensor, radar sensor and acoustic sensor in sequence around the anomaly detection area, and install the geomagnetic sensor in the anomaly detection area, so that the monitoring range of the visual sensor, radar sensor, acoustic sensor and geomagnetic sensor covers the entire anomaly detection area. Step S22: Set the visual sensor and geomagnetic sensor to work around the clock. Monitor the abnormal identification area in real time through the visual sensor and geomagnetic sensor until the target vehicle is confirmed to appear in the abnormal identification area, and then activate the acoustic sensor and radar sensor. Step S23: The radar sensor collects the real-time vehicle coordinates and real-time vehicle speed of the target vehicle within the anomaly identification area; the acoustic sensor collects the real-time noise of the target vehicle within the anomaly identification area. Step S24: The real-time vehicle coordinates, real-time vehicle speed, and real-time noise of the target vehicle are summarized into real-time traffic data.

[0010] Furthermore, the specific process for confirming the presence of a target vehicle in the anomaly identification area is as follows: Step S221: The geomagnetic sensor monitors the abnormal identification area in real time. When the signal output by the geomagnetic sensor changes from low level to high level, it is determined that the geomagnetic sensor has detected an unknown vehicle entering the abnormal identification area. The moment when the low level begins to change to high level is recorded as the geomagnetic induction moment. Step S222: The visual sensor collects images within the abnormal identification area in real time and identifies the presence of unknown vehicles in the image through a vehicle detection algorithm. If an unknown vehicle is detected in the image, it is determined that the visual sensor has detected an unknown vehicle entering the abnormal identification area, and the time corresponding to the image is recorded as the visual sensing time. Step S223: Subtract the geomagnetic sensing time from the visual sensing time and take the absolute value to obtain the sensing deviation time. When both the visual sensor and the geomagnetic sensor detect that an unknown vehicle has entered the abnormal identification area, and the sensing deviation time is less than or equal to the preset deviation time threshold, it is determined that a target vehicle has appeared in the abnormal identification area. Otherwise, it is determined that no target vehicle has appeared in the abnormal identification area.

[0011] Further, step S3 includes the following sub-steps: Step S31: Obtain real-time traffic data of the target vehicle, including its real-time vehicle coordinates, real-time vehicle speed, and real-time noise. Step S32: Subtract the real-time vehicle speed of the previous moment from the real-time vehicle speed of the current moment and divide by the time interval between the two moments to obtain the real-time acceleration of the target vehicle at the current moment. Connect the real-time vehicle coordinates of the current moment with the real-time vehicle coordinates of the previous moment. The real-time vehicle coordinates of the previous moment pointing to the real-time vehicle coordinates of the current moment are used as the vehicle's driving direction at the current moment.

[0012] Furthermore, step S3 also includes the following sub-steps: Step S33: Compare the real-time vehicle speed, real-time vehicle coordinates, real-time acceleration, vehicle driving direction, and real-time noise of the target vehicle with the triggering conditions of lane abnormal events in the abnormal event rule base to determine whether the target vehicle is driving normally or abnormally. Step S34: If the target vehicle is within the anomaly identification area, continuously monitor whether the target vehicle is driving abnormally. If it is driving abnormally, record it as a vehicle anomaly event corresponding to the anomaly identification area.

[0013] The Internet of Things-based lane anomaly event identification device includes a region division module, a data acquisition module, a vehicle monitoring module, a data analysis module, or an anomaly identification module. The region division module is used to construct an anomaly identification region corresponding to the road to be identified based on the historical congestion and accident conditions of the road to be identified and send it to the data acquisition module. The data acquisition module is used to collect real-time traffic data of target vehicles within the area division module and send it to the data analysis module and the vehicle monitoring module. The vehicle monitoring module works in conjunction with the data acquisition module. The vehicle monitoring module is used to determine the presence of target vehicles based on the data from the data acquisition module and control the data acquisition module to perform the data collection work. The data analysis module is used to analyze the operating status of target vehicles based on real-time traffic data and send the vehicle driving status to the anomaly identification module. The anomaly identification module is used to identify whether the target vehicle is driving normally or abnormally based on the vehicle driving status.

[0014] A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the above-described method.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention first constructs an anomaly identification area corresponding to the road to be identified based on the historical congestion and accident conditions of the road to be identified; then, multiple sensors are installed in the anomaly identification area, and real-time traffic data of target vehicles in the anomaly identification area are collected by the sensors. The anomaly identification area is constructed by analyzing the historical conditions of the road to be identified, and then real-time traffic data of target vehicles in the anomaly identification area are collected.

[0016] 2. This invention determines the driving status of target vehicles based on real-time traffic data of target vehicles within the anomaly identification area, and then matches the driving status with the anomaly event rule base to identify lane anomaly events in the corresponding anomaly identification area. The lane anomaly events corresponding to the anomaly identification area are publicized as vehicle anomaly events of the road to be identified. By analyzing the driving status of target vehicles within the anomaly identification area, timely and accurate identification of lane anomaly events can be achieved. Attached Figure Description

[0017] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0018] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a schematic diagram of the road plane coordinate system in this invention; Figure 3 This is a schematic diagram of the region to be analyzed in this invention; Figure 4 This is a block diagram of the device structure of the present invention. Figure 5 This is a schematic diagram of the electronic device in this invention. Detailed Implementation

[0019] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Example 1: Please refer to Figures 1-3 As shown, the technical solution provided by this invention is: a lane anomaly event identification method based on the Internet of Things, which constructs an anomaly identification area corresponding to the road to be identified by analyzing the historical congestion and accident situations of the road to be identified; sets up multiple sensors in the anomaly identification process and collects real-time traffic data of the anomaly identification area; analyzes the real-time traffic data and matches it with anomaly event rule base; identifies lane anomaly events in the corresponding anomaly identification area based on the logical judgment conditions in the anomaly event rule base and announces them. It should be noted in advance that in this invention, the lanes that need to be identified for abnormal events are denoted as the roads to be identified, and the subject of subsequent analysis is also the roads to be identified.

[0021] In this embodiment, the lane anomaly event identification method is as follows: Step S1: Construct the anomaly identification area corresponding to the road to be identified based on the historical congestion and accident data of the road to be identified; In this invention, step S1 includes the following sub-steps: Step S11: Obtain the road to be identified and divide it into multiple regions to be analyzed at equal intervals. It should be noted that the segmentation method here assumes that the road to be identified is a straight road, so it is directly divided at equal intervals. If the road to be identified is not a straight road, it is divided into regions with equal areas to ensure that the area occupied by each region to be analyzed is equal. In this embodiment, the road to be identified is assumed to be a straight road, and the analysis is performed based on the premise that the road to be identified is a straight road; Step S12, as follows Figures 2-3 As shown, an arbitrary endpoint of the road to be identified is taken as the origin, the direction along the road to be identified is taken as the X-axis, and the direction perpendicular to the X-axis is taken as the Y-axis, thus constructing a road plane coordinate system; Step S13: Identify the coordinates of the first endpoint (X1, Y1), the second endpoint (X2, Y2), the third endpoint (X3, Y3), and the fourth endpoint (X4, Y4) of any region to be analyzed. The first boundary equation is obtained by calculating the coordinates of the first endpoint and the second endpoint; the second boundary equation is obtained by calculating the coordinates of the second endpoint and the third endpoint; the third boundary equation is obtained by calculating the coordinates of the third endpoint and the fourth endpoint; and the fourth boundary equation is obtained by calculating the coordinates of the fourth endpoint and the first endpoint. Specifically, the first boundary equation is: (Y2-Y1)×y+(X2-X1)×x+X2×Y1-X1×Y2=0; The second boundary equation is: (Y3-Y2)×y+(X3-X2)×x+X3×Y2-X2×Y3=0; The third boundary equation is: (Y4-Y3)×y+(X4-X3)×x+X4×Y3-X3×Y4=0; The fourth boundary equation is: (Y1-Y4)×y+(X1-X4)×x+X1×Y4-X4×Y1=0; where x represents the independent variable, y represents the dependent variable, and the boundary equation represents the change of y with x; Step S14: Obtain historical traffic accidents that occurred on the road to be identified within the past year, and identify the accident coordinates of the corresponding historical traffic accidents based on the road plane coordinate system; The accident coordinates are compared sequentially with the first boundary equation, the second boundary equation, the third boundary equation, and the fourth boundary equation of the region to be analyzed. If the accident coordinates are simultaneously located to the right of the first boundary equation, above the second boundary equation, to the left of the third boundary equation, and below the fourth boundary equation, the number of traffic accidents in the corresponding region to be analyzed is incremented by one; otherwise, no operation is performed. Specifically, it can be determined through the positional relationship between the coordinate point and the line: In practice, the accident coordinates are substituted into the first boundary equation in turn. If the obtained value is greater than or equal to zero, it means that the accident coordinates are located on the right side of the first boundary equation. If the obtained value is less than zero, it means that the accident coordinates are located on the left side of the first boundary equation. The third boundary equation is the same as the first boundary equation. It should be noted that, in the generalized positional relationship between coordinate points and equations, if the obtained value is equal to zero, it means that the corresponding coordinate point is on the line containing the equation. In this implementation, this case is combined with the case where the coordinate point is located to the right of the line containing the equation. This explanation is hereby given. Substitute the accident coordinates into the second boundary equation in sequence. If the obtained value is less than zero, it means that the accident coordinates are below the second boundary equation. If the obtained value is greater than or equal to zero, it means that the accident coordinates are above the second boundary equation. The fourth boundary equation is calculated in the same way as the second boundary equation. It should be explained that the boundary equation is used here to determine whether the accident coordinates are within the region because the region to be analyzed in this invention is not entirely rectangular. Only a rectangular region to be analyzed is used here for demonstration. If the region to be analyzed is of other shapes, the method of determining by boundary equation described in this invention is equally applicable. Step S15: Count the number of traffic accidents in each region to be analyzed, and sort the regions to be analyzed in descending order of the number of traffic accidents to obtain the region selection sequence; Step S16: Read the total number of vehicles entering the road to be identified each day within the past year, sum the total number of vehicles each day within the past year, and take the average value to obtain the average number of vehicles per day for the corresponding road to be identified; divide the average number of vehicles per day by the length of the road to be identified to obtain the traffic flow density of the road to be identified. Step S17: Compare the traffic flow density of the road to be identified with the traffic flow density threshold. If the traffic flow density is less than or equal to the first traffic flow density threshold, then the number of areas selected by the road to be identified, K, is recorded as A1; if the traffic flow density is greater than the first traffic flow density threshold but less than or equal to the second traffic flow density threshold, then the number of areas selected by the road to be identified, K, is recorded as A2; if the traffic flow density is greater than the second traffic flow density threshold, then the number of areas selected by the road to be identified, K, is recorded as A3; wherein, the first traffic flow density threshold is less than the second traffic flow density threshold, and A1, A2, and A3 are all constants and A1 < A2 < A3; Step S18: Select the first K regions to be analyzed in the region selection sequence as the anomaly identification regions of the roads to be identified.

[0022] Step S2: Install multiple sensors within the anomaly identification area and collect real-time traffic data of target vehicles within the anomaly identification area based on the sensors. The sensors include visual sensors, radar sensors, acoustic sensors, and geomagnetic sensors; the real-time traffic data includes the real-time vehicle speed, real-time vehicle coordinates, and real-time noise of target vehicles within the anomaly identification area. In this invention, the method for determining the real-time traffic data is as follows: Step S21: Install the visual sensor, radar sensor and acoustic sensor in sequence around the anomaly detection area, and install the geomagnetic sensor in the anomaly detection area, so that the monitoring range of the visual sensor, radar sensor, acoustic sensor and geomagnetic sensor covers the entire anomaly detection area. Step S22: Set the visual sensor and geomagnetic sensor to work around the clock. Monitor the abnormal identification area in real time through the visual sensor and geomagnetic sensor until the target vehicle is confirmed to appear in the abnormal identification area, and then activate the acoustic sensor and radar sensor. Among them, visual sensors, geomagnetic sensors, acoustic sensors and radar sensors are connected through the Internet of Things, thereby realizing the interconnection and interoperability between different sensors; In this embodiment, the process of confirming the presence of a target vehicle in the anomaly identification area is as follows: Step S221: The geomagnetic sensor monitors the abnormal identification area in real time. When the signal output by the geomagnetic sensor changes from low level to high level, it is determined that the geomagnetic sensor has detected an unknown vehicle entering the abnormal identification area. The moment when the low level begins to change to high level is recorded as the geomagnetic induction moment. It should be noted that the chassis of the unknown vehicle contains a large amount of metal, and the metal causes changes in the surrounding magnetic field. When the unknown vehicle approaches the geomagnetic sensor, the geomagnetic sensor detects the magnetic field disturbance and outputs a high-level signal. When the unknown vehicle moves away from the geomagnetic sensor, the signal output by the electromagnetic sensor changes from high level to low level. Step S222: The visual sensor collects images within the abnormal identification area in real time and identifies the presence of unknown vehicles in the image through a vehicle detection algorithm. If an unknown vehicle is detected in the image, it is determined that the visual sensor has detected an unknown vehicle entering the abnormal identification area, and the time corresponding to the image is recorded as the visual sensing time. Among them, the vehicle detection algorithm can be either the YOLO object detection algorithm or the SSD object detection algorithm; Step S223: Subtract the geomagnetic sensing time from the visual sensing time and take the absolute value to obtain the sensing deviation time; when both the visual sensor and the geomagnetic sensor detect that an unknown vehicle has entered the abnormal identification area, and the sensing deviation time is less than or equal to the preset deviation time threshold, it is determined that a target vehicle has appeared in the abnormal identification area; otherwise, it is determined that no target vehicle has appeared in the abnormal identification area. Step S23: The radar sensor collects the real-time vehicle coordinates and real-time vehicle speed of the target vehicle within the anomaly identification area; the acoustic sensor collects the real-time noise of the target vehicle within the anomaly identification area. Step S24: The real-time vehicle coordinates, real-time vehicle speed, and real-time noise of the target vehicle are summarized into real-time traffic data.

[0023] Step S3: Based on the real-time traffic data of the target vehicle in the anomaly identification area, determine the driving status of the target vehicle, and then match the driving status with the anomaly event rule base to identify the lane anomaly event in the corresponding anomaly identification area. In this invention, step S3 includes the following sub-steps: Step S31: Obtain real-time traffic data of the target vehicle, including its real-time vehicle coordinates, real-time vehicle speed, and real-time noise. Step S32: Subtract the real-time vehicle speed of the previous moment from the real-time vehicle speed of the current moment and divide by the time interval between the two moments to obtain the real-time acceleration of the target vehicle at the current moment. Connect the real-time vehicle coordinates of the current moment with the real-time vehicle coordinates of the previous moment. The real-time vehicle coordinates of the previous moment pointing to the real-time vehicle coordinates of the current moment are used as the vehicle's driving direction at the current moment. It should be noted that if the real-time acceleration is greater than zero, it means that the target vehicle is accelerating; if the real-time acceleration is equal to zero, it means that the target vehicle is moving at a constant speed; and if the real-time acceleration is less than zero, it means that the target vehicle is decelerating. Step S33: Compare the real-time vehicle speed, real-time vehicle coordinates, real-time acceleration, vehicle driving direction, and real-time noise of the target vehicle with the triggering conditions of lane abnormal events in the abnormal event rule base to determine whether the target vehicle is driving normally or abnormally. This embodiment classifies lane anomaly events into: traffic accident anomalies, illegal parking anomalies, and vehicle driving in the wrong direction anomalies; the triggering conditions for different lane anomaly events are set based on the traffic conditions of the corresponding anomaly identification area; For example, the triggering condition for the traffic accident anomaly is: If the instantaneous acceleration of the target vehicle is less than or equal to -5 m / s 2 If the real-time vehicle speed is 0 m / s, the confidence level increases by 40%; otherwise, no action is taken. If the stationary duration is more than 15 seconds, the confidence level increases by 20%; otherwise, no action is taken. If the real-time noise level is greater than 85 dB, the confidence level increases by 20%; otherwise, no action is taken. The confidence level of the target vehicle is obtained by summing all the confidence levels. If the confidence level is greater than or equal to 75%, the target vehicle is considered to have experienced an abnormal traffic accident; otherwise, the target vehicle is considered not to have experienced an abnormal traffic accident. It should be noted that in actual implementation, the above data is modified according to the actual road conditions; this is only an example for illustration. The triggering conditions for the aforementioned illegal parking anomaly are: If the real-time speed of the target vehicle is 0 m / s, the confidence level is increased by 40%; otherwise, no action is taken. If the real-time coordinates of the target vehicle are within the driving lane area, the confidence level is increased by 20%; otherwise, no action is taken. If the target vehicle remains stationary for more than 60 seconds, the confidence level is increased by 40%; otherwise, no action is taken. The confidence level of the target vehicle is obtained by summing all the confidence levels. If the confidence level is 100%, the target vehicle is considered to have committed an illegal parking violation. Otherwise, the target vehicle is considered not to have committed an illegal parking violation. The triggering condition for the vehicle's abnormal reverse driving is: If the angle between the target vehicle's direction of travel and the lane's prescribed direction is greater than or equal to 90 degrees, the confidence level is increased by 60%; otherwise, no action is taken. If the target vehicle continues to travel in the wrong direction for more than 10 seconds, the confidence level is increased by 40%; otherwise, no action is taken. The confidence scores of all vehicles are summed to determine the confidence score of the vehicle driving in the wrong direction. If the confidence score is 100%, the vehicle is considered to have driven in the wrong direction; otherwise, the vehicle is considered not to have driven in the wrong direction. If the target vehicle is involved in any of the following abnormalities: traffic accident, illegal parking, or driving against traffic, the target vehicle is considered to be driving abnormally; if the target vehicle is not involved in any of these abnormalities, the target vehicle is considered to be driving normally. Step S34: If the target vehicle is within the anomaly identification area, continuously monitor whether the target vehicle is driving abnormally. If it is driving abnormally, record it as a vehicle anomaly event corresponding to the anomaly identification area.

[0024] Step S4: Publicize the lane anomaly events corresponding to the anomaly identification area as vehicle anomaly events of the road to be identified.

[0025] Example 2, as a supplementary explanation to Example 1, if the road analyzed in step S1 is a curved road, then the curved road is divided into equal areas and the boundary equation of the curved road is constructed. The specific process of dividing the curved road into equal areas and constructing the boundary equations is as follows: Step S101: The side of the curved road that is concave is marked as the inner arc, and the other side of the curved road is marked as the outer arc. The left endpoints of the inner arc and the outer arc are connected to obtain the first auxiliary line, and the right endpoints of the inner arc and the outer arc are connected to obtain the second auxiliary line. Step S102: Extend the first auxiliary line and the second auxiliary line, and record the intersection of the first auxiliary line and the second auxiliary line as the common center. Record the angle between the first auxiliary line and the second auxiliary line at the common center as the road angle. Step S103: At the common center, draw multiple bisectors to divide the road angle into multiple equal angles. The bisectors, the inner arc, and the outer arc form multiple closed regions, and each closed region is a region to be analyzed. Step S104: Using the common center of the circle as the origin, and any two mutually perpendicular straight lines as the X-axis and Y-axis, establish a road plane coordinate system for any region to be analyzed. Step S105: The coordinates of the left endpoint of the inner arc corresponding to the region to be analyzed are set as the first endpoint coordinates (X1, Y1), and the coordinates of the right endpoint of the inner arc are set as the second endpoint coordinates (X2, Y2). The coordinates of the left endpoint of the outer arc corresponding to the region to be analyzed are set as the first endpoint coordinates (X1, Y1), and the coordinates of the right endpoint of the outer arc are set as the second endpoint coordinates (X2, Y2). Step S106: Denote the distance from the left endpoint of the inner arc to the center of the circle as the inner radius r1. Then, the boundary equation of the inner arc corresponding to the region to be analyzed is obtained as follows: In the formula, θ is the angle corresponding to the region to be analyzed, θ∈[α,β]; α is the lower limit of θ, β is the upper limit of θ; α=atan2(Y1,X1); β=atan2(Y2,X2); Step S107: Based on steps S104-106, obtain the boundary equation of the outer arc corresponding to the region to be analyzed; It should be noted that since the left and right boundaries of the region to be analyzed are straight lines, they can be obtained by solving the straight line equation in Example 1, which will not be explained in detail here. Example 3, please refer to Figure 4 As shown, based on another concept of the same invention, the present invention now proposes an Internet of Things-based lane abnormal event identification device, including a region division module, a data acquisition module, a vehicle monitoring module, a data analysis module or an abnormality identification module; The region division module is used to construct the anomaly identification region corresponding to the road to be identified based on the historical congestion and accident status of the road to be identified and send it to the data acquisition module. The data acquisition module is used to collect real-time traffic data of target vehicles within the area division module and send it to the data analysis module and the vehicle monitoring module; the vehicle monitoring module works in conjunction with the data acquisition module, and the vehicle monitoring module is used to determine the presence of target vehicles based on the data from the data acquisition module and control the data acquisition module to perform the acquisition work. The data analysis module is used to analyze the operating status of the target vehicle based on real-time traffic data, and send the obtained vehicle driving status to the anomaly identification module; the anomaly identification module is used to identify whether the target vehicle is driving normally or abnormally based on the vehicle driving status.

[0026] Example 3: This embodiment of the invention also provides an electronic device for running the aforementioned Internet of Things-based lane anomaly event recognition method; see [link to previous document]. Figure 5 The schematic diagram of an electronic device provided by the embodiment of the present invention shown above includes a memory and a processor. The memory is used to store one or more computer instructions, which are executed by the processor to realize the above-mentioned Internet of Things-based lane abnormality event identification method. Furthermore, Figure 5 The electronic device shown also includes a communication bus and a communication interface, with the processor, communication interface and memory connected via the communication bus; The memory may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The communication bus can be an ISA bus, PCI bus, or EISA bus, etc. The communication bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The symbol is represented by only one double-headed arrow, but this does not mean that there is only one communication bus or one type of communication bus. The processor may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above methods can be completed by integrated logic circuits in the processor's hardware or by software instructions. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0027] Example 4: This embodiment of the invention also provides a computer storage medium storing computer-executable instructions. When these computer-executable instructions are called and executed by a processor, they cause the processor to implement the above-described Internet of Things-based lane anomaly event recognition method. For specific implementation details, please refer to the method embodiment, which will not be repeated here. The computer program product of the Internet of Things-based lane abnormality event recognition method provided in this embodiment of the invention includes a computer storage medium storing program code. The instructions included in the program code can be used to execute the methods in the preceding method embodiments. For specific implementation, please refer to the method embodiments, which will not be repeated here.

[0028] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system or device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0029] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0030] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0031] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A lane abnormal event recognition method based on Internet of Things, characterized in that, The methods include: Step S1: Construct the anomaly identification area corresponding to the road to be identified based on the historical congestion and accident data of the road to be identified; Step S2: Install multiple sensors within the anomaly identification area and collect real-time traffic data of target vehicles within the anomaly identification area based on the sensors. Step S3: Based on the real-time traffic data of the target vehicle in the anomaly identification area, determine the driving status of the target vehicle, and then match the driving status with the anomaly event rule base to identify the lane anomaly event in the corresponding anomaly identification area. Step S4: Publicize the lane anomaly events corresponding to the anomaly identification area as vehicle anomaly events of the road to be identified.

2. The method for identifying lane anomaly events based on the Internet of Things according to claim 1, characterized in that, Step S1 includes the following sub-steps: Step S11: Obtain the road to be identified and divide the road to be identified into multiple regions to be analyzed at the same intervals; Step S12: Take any endpoint of the road to be identified as the origin, take the direction of the endpoint along the road to be identified as the X-axis, and take the direction perpendicular to the X-axis as the Y-axis to construct the road plane coordinate system; Step S13: Identify the coordinates of the first endpoint, the second endpoint, the third endpoint, and the fourth endpoint of any region to be analyzed. The first boundary equation is obtained by calculating the coordinates of the first endpoint and the second endpoint. The second boundary equation is obtained by calculating the coordinates of the second endpoint and the third endpoint. The third boundary equation is obtained by calculating the coordinates of the third endpoint and the fourth endpoint. The fourth boundary equation is obtained by calculating the coordinates of the fourth endpoint and the first endpoint.

3. The method for identifying lane anomaly events based on the Internet of Things according to claim 2, characterized in that, Step S1 further includes the following sub-steps: Step S14: Obtain historical traffic accidents that occurred on the road to be identified within the past year, and identify the accident coordinates of the corresponding historical traffic accidents based on the road plane coordinate system; The accident coordinates are compared sequentially with the first boundary equation, the second boundary equation, the third boundary equation, and the fourth boundary equation of the region to be analyzed. If the accident coordinates are simultaneously located to the right of the first boundary equation, above the second boundary equation, to the left of the third boundary equation, and below the fourth boundary equation, the number of traffic accidents in the corresponding region to be analyzed is incremented by one; otherwise, no operation is performed. Step S15: Count the number of traffic accidents in each region to be analyzed, and sort the regions to be analyzed in descending order of the number of traffic accidents to obtain the region selection sequence.

4. The method for identifying lane anomaly events based on the Internet of Things according to claim 3, characterized in that, Step S1 further includes the following sub-steps: Step S16: Read the total number of vehicles entering the road to be identified each day within the past year, sum the total number of vehicles each day within the past year, and take the average value to obtain the average number of vehicles per day for the corresponding road to be identified; divide the average number of vehicles per day by the length of the road to be identified to obtain the traffic flow density of the road to be identified. Step S17: Compare the traffic flow density of the road to be identified with the traffic flow density threshold. If the traffic flow density is less than or equal to the first traffic flow density threshold, then record the number of areas selected by the road to be identified, K, as A1. If the traffic flow density is greater than the first traffic flow density threshold but less than or equal to the second traffic flow density threshold, then record the number of areas selected by the road to be identified, K, as A2. If the traffic flow density is greater than the second traffic flow density threshold, then the number of areas selected for the road to be identified, K, is denoted as A3; where the first traffic flow density threshold is less than the second traffic flow density threshold, and A1, A2, and A3 are all constants and A1 < A2 < A3. Step S18: Select the first K regions to be analyzed in the region selection sequence as the anomaly identification regions of the roads to be identified.

5. The method for identifying lane anomaly events based on the Internet of Things according to claim 1, characterized in that, Step S2 includes the following sub-steps: Step S21: Install the visual sensor, radar sensor and acoustic sensor in sequence around the anomaly detection area, and install the geomagnetic sensor in the anomaly detection area, so that the monitoring range of the visual sensor, radar sensor, acoustic sensor and geomagnetic sensor covers the entire anomaly detection area. Step S22: Set the visual sensor and geomagnetic sensor to work around the clock. Monitor the abnormal identification area in real time through the visual sensor and geomagnetic sensor until the target vehicle is confirmed to appear in the abnormal identification area, and then activate the acoustic sensor and radar sensor. Step S23: The radar sensor collects the real-time vehicle coordinates and real-time vehicle speed of the target vehicle within the anomaly identification area; the acoustic sensor collects the real-time noise of the target vehicle within the anomaly identification area. Step S24: The real-time vehicle coordinates, real-time vehicle speed, and real-time noise of the target vehicle are summarized into real-time traffic data.

6. The method for identifying lane anomaly events based on the Internet of Things according to claim 5, characterized in that, The specific process of confirming the presence of the target vehicle in the anomaly identification area is as follows: Step S221: The geomagnetic sensor monitors the abnormal identification area in real time. When the signal output by the geomagnetic sensor changes from low level to high level, it is determined that the geomagnetic sensor has detected an unknown vehicle entering the abnormal identification area. The moment when the low level begins to change to high level is recorded as the geomagnetic induction moment. Step S222: The visual sensor collects images within the abnormal identification area in real time and identifies the presence of unknown vehicles in the image through a vehicle detection algorithm. If an unknown vehicle is detected in the image, it is determined that the visual sensor has detected an unknown vehicle entering the abnormal identification area, and the time corresponding to the image is recorded as the visual sensing time. Step S223: Subtract the geomagnetic sensing time from the visual sensing time and take the absolute value to obtain the sensing deviation time. When both the visual sensor and the geomagnetic sensor detect that an unknown vehicle has entered the abnormal identification area, and the sensing deviation time is less than or equal to the preset deviation time threshold, it is determined that a target vehicle has appeared in the abnormal identification area. Otherwise, it is determined that no target vehicle has appeared in the abnormal identification area.

7. The method for identifying lane anomaly events based on the Internet of Things according to claim 1, characterized in that, Step S3 includes the following sub-steps: Step S31: Obtain real-time traffic data of the target vehicle, including its real-time vehicle coordinates, real-time vehicle speed, and real-time noise. Step S32: Subtract the real-time vehicle speed of the previous moment from the real-time vehicle speed of the current moment and divide by the time interval between the two moments to obtain the real-time acceleration of the target vehicle at the current moment. Connect the real-time vehicle coordinates of the current moment with the real-time vehicle coordinates of the previous moment. The real-time vehicle coordinates of the previous moment pointing to the real-time vehicle coordinates of the current moment are used as the vehicle's driving direction at the current moment.

8. The method for identifying lane anomaly events based on the Internet of Things according to claim 7, characterized in that, Step S3 further includes the following sub-steps: Step S33: Compare the real-time vehicle speed, real-time vehicle coordinates, real-time acceleration, vehicle driving direction, and real-time noise of the target vehicle with the triggering conditions of lane abnormal events in the abnormal event rule base to determine whether the target vehicle is driving normally or abnormally. Step S34: If the target vehicle is within the anomaly identification area, continuously monitor whether the target vehicle is driving abnormally. If it is driving abnormally, record it as a vehicle anomaly event corresponding to the anomaly identification area.

9. A lane anomaly event recognition device based on the Internet of Things, characterized in that, The Internet of Things-based lane anomaly event identification method according to any one of claims 1-8 includes a region division module, a data acquisition module, a vehicle monitoring module, a data analysis module, or an anomaly identification module. The region division module is used to construct an anomaly identification region corresponding to the road to be identified based on the historical congestion and historical accident conditions of the road to be identified and send it to the data acquisition module. The data acquisition module is used to collect real-time traffic data of target vehicles within the area division module and send it to the data analysis module and the vehicle monitoring module. The vehicle monitoring module works in conjunction with the data acquisition module. The vehicle monitoring module is used to determine the presence of target vehicles based on the data from the data acquisition module and control the data acquisition module to perform the data collection work. The data analysis module is used to analyze the operating status of target vehicles based on real-time traffic data, obtain the vehicle driving status, and send it to the anomaly identification module. The anomaly identification module is used to identify whether the target vehicle is driving normally or abnormally based on the vehicle driving status.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method of any one of claims 1 to 8.

Images