Smart city height limit and load limit emergency early warning Internet of Things system, method and medium

Abstract

The invention provides a smart city height limit and load limit emergency early warning Internet of Things system and method, and a medium. Relates to the field of urban road vehicle height and load limit supervision. The method is executed by an emergency supervision and management platform of a smart city height and load limit emergency early warning Internet of Things system, and comprises the steps of obtaining vehicle sensing data of an upstream road section of a target road section; determining a risk vehicle based on the vehicle perception data; and in response to the fact that the estimated arrival time of the risky vehicle arriving at the target road section meets a preset condition, executing signal lamp control, including: predicting the time of the risky vehicle arriving at the target signal lamp; determining a first control parameter based on the time when the risk vehicle arrives at the target signal lamp; sending a first control instruction to the target signal lamp based on the first control parameter; and controlling the target signal lamp to trigger the sub-clock at the starting time based on the first control instruction, and controlling the relay group to conduct the first lamp bead unit so as to drive the first lamp bead unit to emit light.

Description

Technical Field

[0001] This specification relates to the field of urban road vehicle height and load restriction supervision, and in particular to a smart city height and load restriction emergency early warning Internet of Things system, method and medium. Background Technology

[0002] In urban traffic, there are corresponding height and load limits for bridges, viaducts, and roads. Vehicles exceeding these limits can cause impact damage to bridges, viaducts, and roads, increasing road maintenance costs and creating certain safety hazards.

[0003] Therefore, there is an urgent need to provide a smart city height and load restriction emergency early warning IoT system, method, and medium to detect height and load restrictions on vehicles operating in urban traffic, conduct risk assessment based on the detection results, send early warning information to risky vehicles and traffic management departments, and simultaneously control interconnected devices in urban traffic to perform risk avoidance operations based on the risk assessment results. Summary of the Invention

[0004] To prevent oversized or overloaded vehicles from causing impact damage to traffic facilities such as bridges, viaducts, and roads, reduce road maintenance costs, and minimize traffic safety hazards, this manual provides a smart city height and load restriction emergency early warning IoT system, method, and medium.

[0005] The invention includes a smart city height and load restriction emergency early warning Internet of Things system, the system including an emergency monitoring and management platform, the emergency monitoring and management platform being configured to execute a smart city height and load restriction emergency early warning method.

[0006] The invention includes a smart city height and load restriction emergency early warning method, executed by the emergency monitoring and management platform of a smart city height and load restriction emergency early warning IoT system. The method includes: acquiring vehicle perception data from an upstream road segment of a target road segment, wherein the target road segment is a height and load restriction road segment; identifying risk vehicles based on the vehicle perception data; and, in response to the estimated arrival time of the risk vehicle at the target road segment meeting preset conditions, executing traffic light control, including: predicting the arrival time of the risk vehicle at a target traffic light; determining a first control parameter based on the arrival time of the risk vehicle at the target traffic light; the first control parameter including the start time of the target traffic light transitioning to a target state; sending a first control command to the target traffic light based on the first control parameter; and controlling the target traffic light to trigger a sub-clock at the start time based on the first control command, controlling a relay group to activate a first LED unit to drive the first LED unit to emit light.

[0007] The invention includes a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the aforementioned smart city height and load restriction emergency early warning method.

[0008] The beneficial effects of the above invention include, but are not limited to: (1) It achieves proactive, forward-looking, and precise control of risky vehicles. By sensing and identifying risky vehicles in real time on the upstream road section, predicting their arrival time at the target traffic light, and dynamically generating the first control parameter based on this, the traffic light is driven to switch to red at the precise start time. This method moves the risk interception link forward, avoiding vehicle damage and traffic interruption that may be caused by passive collisions with traditional height restriction barriers, and significantly improving the safety and control efficiency of height and load restriction road sections. At the same time, while blocking risky vehicles, it reduces the negative impact on the overall traffic efficiency of the intersection. (2) By deploying sensing devices according to distance, a hierarchical data collection system is constructed, realizing multi-dimensional perception of the operating status of risky vehicles, and providing a rich data foundation for prediction tasks. Furthermore, based on the fusion analysis of the road conversion rate matrix and motion data sequence, the smart city height and load restriction emergency early warning IoT system can simultaneously take into account the micro-level risky vehicle behavior and the macro-level road network statistical laws, making the prediction of the estimated arrival time more scientific and accurate. This layered perception and fusion prediction mechanism not only enhances the early identification capability of the smart city height and load restriction emergency early warning IoT system for potential risks, but also buys valuable time for subsequent emergency response, significantly improving the active protection capability for height and load restriction road sections. (3) By determining the potential driving path based on the road conversion rate matrix and calibrating the real-time motion data in combination with the historical average speed, the computational complexity can be significantly reduced while effectively ensuring the prediction accuracy, thereby meeting the requirements of the smart city height and load restriction emergency early warning IoT system for real-time response performance. (4) By calculating the farthest reachable point and combining the target road section information to determine the traffic light to be controlled, and then accurately controlling the traffic light to switch to green light based on the common cycle and phase difference parameters, so as to accelerate the clearing of safe vehicles in front and form a dynamic safety buffer zone, which not only effectively reduces the risk of rear-end collisions, but also provides sufficient buffer space for risky vehicles behind, reflecting the control concept of combining active guidance and safety protection, realizing closed-loop active protection from state perception, behavior prediction to signal execution, and improving the emergency control capability and overall traffic safety level of height and load restriction road sections. (5) By integrating multi-source data such as vehicle speed, brake lights, steering angle, and lane departure for analysis and judgment, rather than relying on a single indicator, a multi-dimensional and highly reliable vehicle behavior recognition solution is provided, which greatly improves the accuracy and fault tolerance of judging the response behavior of risky vehicles and reduces the misjudgment rate.(6) Once the smart city height and load limit emergency warning IoT system detects that the risky vehicle has been successfully guided or has left, it immediately releases all special signal controls, so that the traffic signal can be restored to normal operation quickly, minimizing the negative impact on the passage efficiency of other normal vehicles. This reflects the humanistic care and efficiency maximization principle of the smart city height and load limit emergency warning IoT system. At the same time, the agility and intelligence level of the smart city height and load limit emergency warning IoT system are improved by monitoring the response behavior of risky vehicles. It realizes a complete closed loop from “start control” to “termination control”, enabling the smart city height and load limit emergency warning IoT system to flexibly respond to dynamically changing traffic scenarios, rather than rigidly executing preset instructions. Attached Figure Description

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0010] Figure 1 This is an exemplary schematic diagram of a smart city height and load restriction emergency early warning Internet of Things system according to some embodiments of this specification; Figure 2 This is an exemplary flowchart of a smart city height and load restriction emergency early warning method according to some embodiments of this specification; Figure 3 This is an exemplary flowchart illustrating the determination of estimated arrival time according to some embodiments of this specification; Figure 4 These are exemplary schematic diagrams illustrating response behavior monitoring according to some embodiments of this specification; Figure 5 This is an exemplary schematic diagram of a road network shown in some embodiments of this specification. Detailed Implementation

[0011] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0012] Figure 1 These are exemplary schematic diagrams of a smart city height and load restriction emergency early warning IoT system, illustrated according to some embodiments of this specification. It should be noted that the following embodiments are for illustrative purposes only and do not constitute a limitation thereof.

[0013] In some embodiments, such as Figure 1 As shown, the smart city height and load restriction emergency early warning IoT system 100 may include an emergency supervision user platform 110, an emergency supervision service platform 120, an emergency supervision management platform 130, an emergency supervision sensor network platform 140, and an emergency supervision object platform 150.

[0014] In some embodiments, one or more platforms in the smart city height and load restriction emergency early warning IoT system 100 can exchange information and / or data via a network. In some embodiments, the network can be any one or more of a wired network or a wireless network.

[0015] The emergency monitoring user platform 110 refers to a platform for monitoring users to obtain monitoring information and deploy monitoring decisions. Monitoring users can be personnel from traffic safety management departments, etc. In some embodiments, the emergency monitoring user platform 110 may include at least one user interaction device, such as a mobile phone or computer.

[0016] Emergency monitoring service platform 120 refers to a platform used for receiving and transmitting data and / or information. In some embodiments, emergency monitoring service platform 120 may be configured as a communication network or gateway, etc. In some embodiments, emergency monitoring service platform 120 can perform bidirectional data interaction with emergency monitoring user platform 110 and emergency monitoring management platform 130.

[0017] The emergency monitoring and management platform 130 is a comprehensive management platform that manages and coordinates the connections and collaboration between multiple platforms. The emergency monitoring and management platform 130 can be configured as a server or a processor. In some embodiments, the emergency monitoring and management platform 130 is communicatively connected to the emergency monitoring object platform 150 through the emergency monitoring sensor network platform 140.

[0018] In some embodiments, the emergency monitoring and management platform 130 is configured to acquire vehicle perception data of the upstream road segment of the target road segment; identify risky vehicles based on the vehicle perception data; and execute traffic light control in response to the estimated arrival time of the risky vehicle at the target road segment meeting preset conditions, including: predicting the time when the risky vehicle arrives at the target traffic light; determining a first control parameter based on the time when the risky vehicle arrives at the target traffic light; sending a first control command to the target traffic light based on the first control parameter; and controlling the target traffic light to trigger a sub-clock at the start time based on the first control command, controlling the relay group to turn on the first LED unit to drive the first LED unit to emit light.

[0019] The emergency monitoring sensor network platform 140 is used for comprehensive management of sensor information and serves as a communication transmission platform for bidirectional data interaction between the emergency monitoring management platform 130 and the emergency monitoring target platform 150. In some embodiments, the emergency monitoring sensor network platform 140 can be configured as a communication network or gateway. The emergency monitoring sensor network platform 140 is responsible for uploading real-time sensor data collected by the emergency monitoring target platform 150 to the emergency monitoring management platform 130, and for issuing control commands generated by the emergency monitoring management platform 130 to the corresponding emergency monitoring target platform 150 for execution.

[0020] The emergency monitoring platform 150 is a platform for generating monitoring information and executing control information. In some embodiments, the emergency monitoring platform 150 may include various monitoring, sensing, and interactive devices deployed on the roadside and at intersection traffic lights in urban traffic systems, such as roadside radar, traffic signs, electronic displays, laser altimeters, road weighing systems, smart cameras, vehicle vision systems, and signal controllers.

[0021] For more information about the above platforms, please refer to [link / reference]. Figures 2-4 And related explanations.

[0022] The Smart City Height and Load Restriction Emergency Early Warning IoT System 100 enables communication between its various functional platforms, forming a closed-loop information operation. Under the unified management of the Emergency Supervision and Management Platform 130, it coordinates and operates regularly, realizing the informatization and intelligentization of vehicle height and load restriction emergency early warning.

[0023] It should be noted that the above description of the smart city height and load limit emergency early warning IoT system 100 is for ease of description only and should not limit this specification to the scope of the embodiments described.

[0024] Figure 2 This is an exemplary flowchart illustrating an emergency early warning method for height and load restrictions in smart cities, based on some embodiments of this specification. Figure 2 As shown, process 200 includes steps 210-230 as described below. In some embodiments, process 200 may be executed by an emergency monitoring and management platform.

[0025] Step 210: Obtain vehicle perception data of the upstream road segment of the target road segment.

[0026] A target road segment refers to a vulnerable section of a highway or urban road that requires protective measures due to its unique structure and load-bearing capacity limitations. Examples include bridges, tunnels, and culverts. In some embodiments, the target road segment is a height- and load-restricted section.

[0027] Height and load-restricted road sections refer to road segments with height and load-related traffic restrictions established to ensure the operational safety of roads, bridges, tunnels, culverts, and other road sections, and to prevent structural damage or safety accidents caused by vehicles exceeding height or load limits. For example, road sections restricting vehicle height to below a height threshold and vehicle weight to below a weight threshold. The height and weight thresholds can be manually set or preset based on actual regulatory needs, road design standards, and historical operational experience. Vehicle weight refers to the total weight including the vehicle's own weight and its load.

[0028] The upstream section of the target road segment refers to the section of road that is adjacent to the entrance of the target road segment in the direction of vehicle travel and that vehicles must pass through before entering the target road segment.

[0029] Vehicle perception data refers to data about a vehicle's physical state, dynamic characteristics, and basic attributes. Examples include vehicle weight, vehicle height, vehicle identification information, and speed. Vehicle identification information is information that uniquely identifies and distinguishes a vehicle. Examples include license plate number and vehicle identification number (VIN).

[0030] In some embodiments, vehicle perception data can be collected by various sensing devices. These devices include dynamic weighing sensors, laser altimeters, structured light scanners, and surveillance cameras. For example, dynamic weighing sensors are deployed on the ground upstream of the road to measure the vehicle's weight as it passes. Vehicle height can be obtained through three-dimensional contour scanning using laser altimeters or structured light scanners deployed along the roadside; vehicle identification can be achieved through surveillance cameras to obtain license plate numbers, etc. For more information on sensing devices, see [link to documentation]. Figure 1 The relevant content of the emergency supervision platform.

[0031] Step 220: Identify risky vehicles based on vehicle perception data.

[0032] Risky vehicles are those that are excessively tall or overloaded.

[0033] In some embodiments, the emergency monitoring and management platform can identify risky vehicles based on vehicle perception data. For example, if the vehicle height exceeds a height threshold, it is determined that the vehicle is overweight; if the vehicle weight exceeds a weight threshold, it is determined that the vehicle is overloaded.

[0034] Step 230: In response to the estimated arrival time of the risky vehicle to the target road segment meeting the preset conditions, traffic light control is executed.

[0035] Estimated arrival time refers to the estimated time it will take for a risky vehicle to reach the target road segment. In some embodiments, the emergency monitoring and management platform can calculate the estimated arrival time based on the risky vehicle's current location, speed, and remaining distance to the target road segment. For more information on determining the estimated arrival time, see [link to relevant documentation]. Figure 3 And its related descriptions.

[0036] Preset conditions refer to the triggering conditions used by the emergency monitoring and management platform to determine whether traffic light control needs to be implemented. In some embodiments, preset conditions may include an estimated arrival time that is lower than a time threshold, which can be set based on the experience of those skilled in the art.

[0037] Traffic light control refers to the operation of an emergency monitoring and management platform to strategically adjust and intervene in the traffic lights of a target road segment and / or its upstream associated intersections when preset conditions are met.

[0038] In some embodiments, traffic light control can be performed periodically based on a preset period. The preset period can be a preset time such as 30 seconds.

[0039] In some embodiments, traffic light control includes sub-steps 231-234. Sub-steps 231-234 can be executed by an emergency monitoring and management platform.

[0040] Step 231: Predict the time when the risky vehicle will arrive at the target traffic light.

[0041] A target traffic light refers to the first traffic light downstream of the risky vehicle's current location in its travel path and direction of travel. In some embodiments, the target traffic light is dynamically updated based on the risky vehicle's real-time location and direction of travel.

[0042] The time of arrival at the target traffic light refers to the predicted time when a risky vehicle is expected to arrive at its current target traffic light.

[0043] In some embodiments, the emergency monitoring and management platform can estimate the time it will take to arrive at the target traffic light based on the current location, speed, and geographical location of the at-risk vehicle.

[0044] Step 232: Determine the first control parameter based on the time when the risky vehicle arrives at the target traffic light.

[0045] The first control parameter refers to the parameter that regulates the display state of the target traffic light. In some embodiments, the first control parameter includes the start time of the target traffic light transitioning to the target state. The target state can be that the target traffic light remains in a red light display.

[0046] In some embodiments, the emergency monitoring and management platform can determine a first control parameter through various methods based on the time when the at-risk vehicle arrives at the target traffic light. In some embodiments, the start time for the target traffic light to switch to the target state, which is the first control parameter, can be set as the sum of the expected arrival time of the at-risk vehicle and a safety margin. The safety margin is used to compensate for potential delays during prediction and communication, ensuring that the target traffic light is red when the at-risk vehicle arrives. The safety margin can be preset by those skilled in the art based on experience. For example, 5 seconds.

[0047] In some embodiments, the first control parameter further includes the duration of the target signal light in the target state.

[0048] In some embodiments, the emergency monitoring and management platform is further configured to: determine the target dwell time of the risky vehicle at the target traffic light; and determine a first control parameter based on the time the risky vehicle arrives at the target traffic light and the target dwell time.

[0049] The target dwell time refers to the duration for which the emergency monitoring and management platform expects a risky vehicle to stop at its corresponding target signal point due to a red light.

[0050] In some embodiments, the duration of the target stay can be set based on the experience of those skilled in the art.

[0051] In some embodiments, the emergency monitoring and management platform is further configured to determine a target time period based on a determined time point of the risk vehicle; and to determine a target dwell time based on the cumulative distance traveled by the risk vehicle along the original route and the speed sequence of the risk vehicle within the target time period.

[0052] The time point at which a risk vehicle is identified refers to the moment when the emergency monitoring and management platform first determines a vehicle as a risk vehicle based on vehicle perception data. In some embodiments, the time point at which a risk vehicle is identified can be obtained by querying log information recorded in the smart city height and load restriction emergency early warning IoT system, which records the risk vehicle identification event and its corresponding timestamp.

[0053] The target time period refers to the length of time from the determined time of the risk vehicle to the current time.

[0054] The cumulative distance traveled by the at-risk vehicle along its original route refers to the total distance traveled by the at-risk vehicle from the time it was identified until the current time, along its original route. The original route refers to the driving path including the target road segment planned by the driver based on their travel intentions. In some embodiments, the original route can be obtained through an in-vehicle navigation system.

[0055] A speed sequence of risky vehicles refers to an ordered set of instantaneous speed values ​​of risky vehicles that are continuously collected and recorded at fixed time intervals within a target time period. In some embodiments, the instantaneous speed values ​​of risky vehicles can be obtained in real time through onboard GPS, roadside speed sensors, or other positioning devices.

[0056] In some embodiments, the emergency monitoring and management platform can determine the target dwell time based on the cumulative distance traveled by the risk vehicle along the original route and the speed sequence of the risk vehicle within the target time period, using a duration determination model.

[0057] A duration determination model is a model used to determine the duration of a target's stay. In some embodiments, the duration determination model is a machine learning model. For example, the duration determination model may include one or more combinations of a Recurrent Neural Network (DNN) model, a Long Short-Term Memory Network (LSTM) model, or other custom models.

[0058] In some embodiments, the input to the duration determination model may be the cumulative distance traveled by the risk vehicle along the original route within the target time period and the speed sequence of the risk vehicle, and the output of the duration determination model may be the target dwell time.

[0059] In some embodiments, the duration determination model can be obtained by training an initial duration determination model using multiple sets of labeled training samples. Training samples may include historical data showing the identification of risky vehicles and the effective removal of these vehicles. Effective removal of risky vehicles refers to preventing them from entering the target road segment through traffic light control (e.g., increasing red light duration). Training samples include the cumulative distance traveled and speed sequence of the original route corresponding to the risky vehicle. Labels may include the actual dwell time of the risky vehicle corresponding to the training sample at the target traffic light.

[0060] In some embodiments, the emergency monitoring and management platform can input multiple labeled training samples into the initial duration determination model, construct a loss function based on the labels and the results of the initial duration determination model, and iteratively update the parameters of the initial duration determination model based on the loss function through gradient descent or other methods. When preset conditions are met, the model training is complete, and a trained duration determination model is obtained. These preset conditions may include loss function convergence, the number of iterations reaching a threshold, etc.

[0061] In some embodiments of this specification, the smart city height and load restriction emergency early warning IoT system dynamically calculates the cumulative travel distance and speed sequence of at-risk vehicles along their original routes within a target time period, adaptively determining the target dwell time and implementing a response escalation mechanism. The higher the degree of resistance to control by the at-risk vehicle, i.e., the longer the cumulative travel distance along the original route, the longer the red light duration is extended to enhance the blocking effect. This mechanism overcomes the deficiency of fixed-duration control methods that may be ineffective for stubborn vehicles, improves the adaptive processing capability of the smart city height and load restriction emergency early warning IoT system for complex road conditions and abnormal behaviors, thereby effectively forcing at-risk vehicles to change their travel routes and ensuring the safety of the target road section.

[0062] In some embodiments, the emergency monitoring and management platform determines a first control parameter based on the time the at-risk vehicle arrives at the target traffic light and the duration of its stay at the target.

[0063] In some embodiments of this specification, the smart city height and load restriction emergency early warning IoT system introduces "target dwell time" as a control parameter, thereby achieving refined control of the signal control strategy. It abandons the crude control method of fixed-duration red lights and instead dynamically calculates and generates precise control commands based on actual obstruction needs, significantly improving the targeting, adaptability, and execution effectiveness of the control.

[0064] Step 233: Based on the first control parameters, send the first control command to the target traffic light.

[0065] The first control command refers to the command used to instruct the target traffic light to start at a specific time (i.e., the start time of the target state), to indicate whether passage is allowed or prohibited in a specific direction, and to control the duration of its maintenance (i.e., the duration of the target state). For example, the control command could be: "Turn on the red light in the northwest direction at 3:40, and the red light will last for 60 seconds."

[0066] In some embodiments, the first control command is a data message conforming to a standard traffic signal control protocol. The standard traffic signal control protocol may be NTCIP, SPaT, etc. As an example only, the first control command may control the first phase of a target traffic light. The first phase controls the target traffic light to trigger a sub-clock at the red light start time (i.e., the start time of the target state), cyclically controlling the relay group to conduct the red light phase. The first control command can be used to obstruct the passage of at-risk vehicles towards the target road segment.

[0067] In some embodiments, the emergency monitoring and management platform can send a first control command to the target traffic light via the network. For more information on networks, see [link to relevant documentation]. Figure 1 And its related descriptions.

[0068] Step 234: Based on the first control command, control the target signal light to trigger the sub-clock at the start time, control the relay group to turn on the first lamp unit, so as to drive the first lamp unit to emit light.

[0069] A sub-clock is a logic unit that generates independent timing for a single signal light group and can control the phase difference by setting a start delay.

[0070] A relay group is a collection of electrical switching components used to safely drive high-power signal lighting via low-power control circuitry. In some embodiments, the relay activates a physical switch by energizing a coil to connect an external high-voltage circuit.

[0071] The first LED unit refers to an independent lighting component in the target signal light that is controlled by a relay group and used to realize traffic indication function. In some embodiments, the first LED unit may be composed of multiple red light-emitting diodes.

[0072] After receiving and executing the first control command, the target traffic light can adjust the phase of the traffic light based on the first control command, so that when the risky vehicle arrives at the target traffic light, the target traffic light is red, thereby preventing it from continuing to drive to the target road section.

[0073] In some embodiments, traffic light control may further include: in response to the estimated arrival time of a risky vehicle to a target road segment meeting preset conditions, sending an instruction to the risky vehicle's navigation system to guide it through a dynamic "virtual lane," displaying a virtual path that the risky vehicle must follow, which points to a preset "buffer zone" (such as an emergency stopping lane, service area entrance, or specific ramp). The path can be obtained using existing path planning algorithms.

[0074] In some embodiments of this specification, the smart city height and load restriction emergency early warning method achieves proactive, forward-looking, and precise control of risky vehicles. By sensing and identifying risky vehicles in real time on upstream road sections, predicting their arrival time at the target traffic light, and dynamically generating first control parameters based on this, the method drives the traffic light to switch to red at a precise start time. This method moves the risk interception step forward, avoiding vehicle damage and traffic disruptions that may be caused by passive collisions with traditional height restriction barriers, significantly improving the safety and management efficiency of height and load restriction sections. Simultaneously, while blocking risky vehicles, it reduces the negative impact on the overall traffic efficiency of intersections.

[0075] Figure 3 This is an exemplary flowchart illustrating the determination of estimated arrival time according to some embodiments of this specification. Figure 3 As shown, process 300 includes steps 310-330 as described below. In some embodiments, process 300 may be executed by an emergency monitoring and management platform.

[0076] Step 310: Obtain motion sensing data from multi-level sensing devices.

[0077] Multi-level sensing devices are a combination of monitoring devices used to collect vehicle perception data in real time. Examples include surveillance cameras, lidar, laser scanning arrays, and geomagnetic sensors. In some embodiments, multi-level sensing devices can be classified into levels based on their distance from the at-risk vehicle. In some embodiments, the closer the multi-level sensing device is to the at-risk vehicle, the lower its level, i.e., the smaller the level value.

[0078] Motion perception data refers to information that reflects the real-time motion status of a vehicle. Examples include the vehicle's position, speed, and heading angle. In some embodiments, motion perception data includes the position and speed of the at-risk vehicle at multiple points in time.

[0079] In some embodiments, motion perception data can be acquired through multi-level sensing devices. For example, precise speed and position information of the vehicle can be obtained through millimeter-wave radar on the upstream roadside, and the vehicle's trajectory and heading angle changes can be continuously tracked through monitoring cameras.

[0080] Step 320: Based on motion perception data, construct a motion data sequence for the at-risk vehicle.

[0081] Motion data sequence refers to the sequence of motion perception data of a vehicle at multiple points in time, arranged in chronological order according to timestamps.

[0082] In some embodiments, the motion data sequence can extract the identification of the risky vehicle and its corresponding position and speed data under the timestamp in real time from multi-level sensing devices; then arrange all data points in ascending order of timestamp to form a continuous trajectory; then clean and interpolate missing or outlier values ​​through filtering algorithms to ensure the sequence is continuous and complete; finally, store the processed data in a structured form to generate an ordered data sequence containing fields such as timestamp, position, and speed.

[0083] Step 330: Determine the estimated arrival time based on the road conversion rate matrix and motion data sequence.

[0084] A road conversion rate matrix is ​​a sparse square matrix describing the probability of a vehicle moving from its current road segment to downstream road segments in a road network. In some embodiments, the rows of the road conversion rate matrix represent the road segment the vehicle is currently on, and the columns represent the road segments the vehicle might head to. The element values ​​of the road conversion rate matrix represent the traffic flow conversion rate between different road segments. For example, road conversion rate... Indicates the first Vehicles on this road section are heading towards the first The number of road sections accounts for the first The ratio of the total number of vehicles on a given road segment.

[0085] In some embodiments, the dimensions of the road conversion rate matrix can be determined by the road network structure and the dimensions of the multi-level sensing devices. The dimensions of the multi-level sensing devices refer to the range of road segment levels that the monitoring devices of interest can cover in the downstream road network in order to track risky vehicles. In some embodiments, the dimensions of the multi-level sensing devices are preset by those skilled in the art based on experience.

[0086] A road network is a traffic network consisting of a series of one-way road segments and intersections. In a road network, vehicles can only travel in the predetermined permitted direction and are prohibited from traveling in the opposite direction. Each road segment has a unique number (such as road segment 1, road segment 2), and its downstream end connects to one or more intersections. Each intersection can then extend into multiple new downstream road segments, thus creating a continuous network structure with clearly defined flow relationships.

[0087] Figure 5 These are exemplary schematic diagrams of road networks shown in some embodiments of this specification. For example... Figure 5 As shown in the figure, the numbers in the figure represent road segment numbers (for example, "1" represents road segment 1), and the arrows represent the preset permitted driving directions between road segments.

[0088] For example, a road network such as Figure 5 As shown, the road network structure is as follows: Downstream of road segment 1 is an intersection leading to road segments 2 and 3; the intersection downstream of road segment 2 connects to road segments 4 and 5, but road segment 4 has the opposite permitted driving direction to road segment 2, so vehicles from road segment 2 cannot travel to road segment 4; therefore, vehicles from road segment 2 can only travel to road segment 5; the intersection downstream of road segment 3 connects to road segments 6 and 7, but road segment 7 has the opposite permitted driving direction to road segment 3, so vehicles from road segment 3 cannot travel to road segment 7; therefore, vehicles from road segment 3 can only travel to road segment 6; both road segments 5 and 6 lead to road segment 9; the relationships between the remaining road segments 10-14 are not detailed here.

[0089] If the at-risk vehicle is initially located on road segment 1 in the road network structure, and the dimension of the multi-level sensing device is set to 3, then monitoring devices for all road segments at three downstream levels from road segment 1 are required. The first-level road segments are {2, 3}, the second-level are {5, 6}, and the third-level are {9}. Therefore, monitoring devices on the road segment set S = {1, 2, 3, 5, 6, 9} are required, resulting in a 6×6 square matrix for the road conversion rate matrix. The element in the first row and second column of the road conversion rate matrix... This represents the ratio of the number of vehicles on road segment 1 traveling to road segment 2 to the total number of vehicles on road segment 1.

[0090] In some embodiments, if two road segments are not interoperable (e.g., between road segment 2 and road segment 3, or between road segment 2 and road segment 6), the element value of the corresponding road conversion rate matrix can be assigned to 0. If two road segments are not physically adjacent but can be connected by a traversable path (e.g., from road segment 2 to road segment 9, a connection can be made via road segment 5), the element value of the corresponding road conversion rate matrix can be assigned to b. In some embodiments, the value of b can be a preset placeholder.

[0091] In some embodiments, the road conversion rate matrix can be determined based on historical data. The road conversion rate matrix can be determined by obtaining the movement trajectories of all vehicles in the road network within a historical time period recorded in the historical data, and statistically analyzing the vehicle transfer frequency between any two adjacent road segments. For example, if 100 vehicles exited from road segment 1 in the past hour, and all of them entered road segment 2, then the road conversion rate from road segment 1 to road segment 2 is 100%; or, for another example, if 100 vehicles exited from road segment 2, and 30 of them entered road segment 5, then the road conversion rate from road segment 2 to road segment 5 is 30%.

[0092] For more information on estimated arrival times, see step 230 and its related description.

[0093] In some embodiments, the emergency monitoring and management platform can determine the estimated arrival time in various ways based on the road conversion rate matrix and motion data sequence.

[0094] In some embodiments, the emergency monitoring and management platform is further configured to determine potential driving paths based on a road conversion rate matrix; determine the historical average speed corresponding to the potential driving paths; and determine the estimated arrival time based on motion data sequences and historical average speeds.

[0095] A potential driving route refers to one or more candidate routes that a risky vehicle could take from its current location to a target road segment. In some embodiments, a potential driving route consists of multiple road segments.

[0096] For example, such as Figure 5 As shown, if the current location of the risky vehicle is road segment 1 and the target road segment is road segment 14, then the potential driving paths include the following four routes: 1→2→5→9→11→14, 1→2→5→9→10→12→14, 1→3→6→9→11→14 and 1→3→6→9→10→12→14.

[0097] In some embodiments, potential driving paths can be determined using path planning algorithms based on road network structure and traffic rules. Path planning algorithms may include, but are not limited to, Dijkstra's algorithm. One or more of the following: algorithms, fast randomized tree search algorithms, and prediction methods based on probabilistic graphical models.

[0098] In some embodiments, the historical average speed corresponding to a potential driving path refers to the statistical average of the driving speeds of all vehicles on each potential driving path in historical data, under a scenario that matches the current time period and weather conditions.

[0099] In some embodiments, the emergency monitoring and management platform can construct a first preset table based on historical time periods, historical weather conditions, and historical average speeds corresponding to potential driving routes from historical data. The first preset table includes the correspondence between historical time periods, historical weather conditions, and historical average speeds corresponding to potential driving routes. The emergency monitoring and management platform can determine the historical average speed corresponding to a potential driving route by querying the first preset table, based on the current time period, current weather conditions, and current potential driving route.

[0100] In some embodiments, the emergency monitoring and management platform can determine the estimated arrival time based on motion data sequences and historical average speeds using a fusion algorithm. In some embodiments, the fusion algorithm may include the following three steps.

[0101] Step 1: Calculate the path calibration speed. For each potential driving path, the calibration speed is obtained by weighting the speed data in the motion data sequence and the average speed of the potential driving path under the same historical conditions (such as time period and weather). The specific calculation is as follows: (1)

[0102] In equation (1), the subscript The index representing the potential driving path, with a value range of 1. ,in The total number of potential driving paths; This represents the weighting factor, used to adjust the proportion of real-time and historical information. Indicates the first The calibration speed of a potential driving path; This represents velocity data in a motion data sequence; This indicates the historical average speed.

[0103] Step 2, calculate the estimated travel time. In some embodiments, the emergency monitoring and management platform can divide the length of a potential travel path by its corresponding calibration speed to obtain the estimated travel time of the vehicle on that potential travel path. The estimated travel time is calculated as shown in equation (2): (2) In equation (2), Indicates the first Estimated travel time for each potential driving route; Indicates the first The length of each potential driving path.

[0104] Step 3, weighted calculation of estimated arrival time. In some embodiments, the emergency monitoring and management platform can obtain the estimated arrival time by weighting and summing all estimated travel times with the road conversion rate corresponding to each potential travel path as the weight. The estimated arrival time is calculated as shown in the following formula (3): (3) In equation (3), Indicates the estimated arrival time; Indicates the first The product of the road conversion rates of any two physically adjacent road segments within a potential driving path. For example, such as... Figure 5 As shown, the potential driving path 1 is 1→2→5→9→11→14, corresponding to .

[0105] In some embodiments of this specification, by determining potential driving paths based on the road conversion rate matrix and calibrating real-time motion data in combination with historical average speed, the computational complexity can be significantly reduced while effectively ensuring prediction accuracy, thereby meeting the real-time response performance requirements of the smart city height and load restriction emergency early warning IoT system.

[0106] In some embodiments of this specification, a hierarchical data acquisition system is constructed by deploying sensing devices according to distance levels, enabling multi-dimensional perception of the operational status of risky vehicles and providing a rich data foundation for prediction tasks. Furthermore, based on the fusion analysis of the road conversion rate matrix and motion data sequences, the smart city height and load restriction emergency early warning IoT system can simultaneously consider both microscopic risky vehicle behavior and macroscopic road network statistical patterns, making the predicted arrival time more scientific and accurate. This hierarchical perception and fusion prediction mechanism not only enhances the early identification capability of the smart city height and load restriction emergency early warning IoT system for potential risks but also buys valuable time for subsequent emergency response, significantly improving the proactive protection capability for height and load restriction road sections.

[0107] In some embodiments, the emergency monitoring and management platform is further configured to: determine the farthest reachable point of a risky vehicle within a preset time period based on motion data sequences; determine the traffic light to be controlled based on the farthest reachable point and the target road segment; generate second control parameters within the preset time period, the second control parameters including the common cycle duration and phase difference corresponding to the traffic light to be controlled; and send a second control command to the traffic light to be controlled based on the second control parameters within the preset time period; and control the traffic light to be controlled to configure a master clock timer based on the common cycle duration, synchronize and delay the trigger sub-clock based on the phase difference, and control the relay group to turn on the second LED unit to drive the second LED unit to emit light.

[0108] The farthest reachable point of a risk vehicle within a preset time period refers to the farthest location that the risk vehicle can reach within the preset time period based on its current movement status.

[0109] A preset time period refers to a pre-defined future time range, such as the next 5 minutes, the next 10 minutes, or other time intervals. In some embodiments, based on the assumption that all safe vehicles can travel from their current location to the target road segment with green lights, the time required for a safe vehicle to reach the target road segment from its current location can be calculated using the vehicle's motion data sequence, and this time can be used as the preset time period. A safe vehicle is the last vehicle identified before a risky vehicle is identified that has not exhibited any overloading or height-related issues.

[0110] In some embodiments, the emergency monitoring and management platform can determine the furthest travel distance of a risk vehicle within a preset time period based on motion data sequences and kinematic calculations. The platform can then determine the furthest reachable point based on the furthest travel distance, road network structure, the current location of the risk vehicle, and its travel direction. For example, the furthest travel distance can be determined using the following formula (4): (4) In equation (4), Indicates the furthest travel distance; This represents velocity data in a motion data sequence; Indicates a preset time period.

[0111] Traffic lights requiring control are those that need intervention to address the approach of risky vehicles. In some embodiments, all traffic lights located between the furthest reachable point and the target road segment can be identified as traffic lights requiring control by querying road network information.

[0112] The second control parameter refers to the parameter used to regulate the display state of the traffic light to be controlled. In some embodiments, the second control parameter includes the common cycle duration and phase difference corresponding to the traffic light to be controlled.

[0113] The cycle duration is the time required for a traffic light to complete one full cycle. A full cycle refers to the process where a traffic light starts from a certain initial phase, sequentially goes through all phases (such as green, yellow, red, etc.), and finally returns to the initial phase. In some embodiments, the common cycle duration of each traffic light can be determined by modeling and solving using linear programming methods based on traffic parameters such as traffic flow, number of lanes, and pedestrian crossing time at each approach of the intersection where the traffic light is located.

[0114] In some embodiments, the common cycle duration can be the maximum value of the time required for all the traffic lights to complete one full cycle.

[0115] Phase difference refers to the difference in the start time of the green light of the traffic lights to be controlled at adjacent intersections. In some embodiments, the phase difference can be determined based on the distance between adjacent intersections and a preset speed. For example, the phase difference can be determined by the following formula (5): (5) In formula (5) Indicates phase difference; Indicates the distance between adjacent intersections; Indicates the preset speed.

[0116] Preset speed refers to the vehicle speed that is preset by humans.

[0117] For example, if the common cycle length of the traffic lights to be controlled is 50s, the distance from adjacent intersection A to intersection B is 600m, and the preset speed is 10m / s, according to equation (5), the theoretical phase difference is 60s. Since this value is greater than the common cycle length, it is converted into an effective phase difference based on the signal cycle characteristics: 60s-50s=10s. That is, when the green light start time of the traffic lights to be controlled at intersection B is 10s later than that of the traffic lights to be controlled at intersection A, vehicles that pass through the intersection at the start time of the green light at intersection A can still pass through the intersection with a green light when they reach intersection B at the preset speed.

[0118] The second control command is a command used to drive the traffic light to be controlled to perform a control operation. For example, the second control command can be: "cycle duration 120s, phase difference 30s". In some embodiments, the second control command is sent to the traffic light to be controlled via wired or wireless communication.

[0119] In some embodiments, after the signal light to be controlled receives the second control command, it sets the master clock timer according to the common cycle duration, and triggers the relay group to turn on the circuit of the second lamp unit according to the phase difference synchronous delay of the sub-clock, and finally drives it to light up.

[0120] The master clock timer is a module in the traffic light to be controlled that generates a reference timing signal. In some embodiments, the master clock timer uses a common period duration as a timing reference to cyclically generate periodic timing signals, providing a unified time reference for the phase transitions of the traffic light to be controlled.

[0121] The second LED unit refers to an independent lighting component in the traffic light to be controlled, which is controlled by a relay group and used to realize traffic indication function. In some embodiments, the second LED unit may be composed of multiple green light-emitting diodes.

[0122] As an example only, the second control command can control the second phase of the traffic light to be controlled. The second phase controls the target traffic light to trigger a sub-clock at the start of the green light, cyclically controlling the relay group to conduct the green light phase. The second control command can be used to facilitate the safe passage of vehicles to the target road section.

[0123] In some embodiments of this specification, the traffic light to be controlled is determined by calculating the farthest reachable point and combining it with the target road segment information. Then, based on the common cycle and phase difference parameters, the traffic light is precisely controlled to switch to green to accelerate the clearing of safe vehicles ahead and form a dynamic safety buffer zone. This not only effectively reduces the risk of rear-end collisions but also provides sufficient buffer space for risky vehicles behind. It embodies the control concept of combining proactive guidance with safety protection, and realizes closed-loop proactive protection from state perception, behavior prediction to signal execution, thereby improving the emergency control capabilities and overall traffic safety level of height and load restricted road sections.

[0124] Figure 4 This is an exemplary schematic diagram illustrating response behavior monitoring according to some embodiments of this specification.

[0125] In some embodiments, the emergency monitoring and management platform can monitor the response behavior 410 of risky vehicles to traffic light control; the response behavior 410 includes at least one of the following: risky vehicle begins to change lanes or decelerate 410-1, risky vehicle does not respond 410-3, risky vehicle has successfully changed lanes or left the original path 410-2; in response to risky vehicle successfully changing lanes or leaving the original path 410-2, a clear command 420 is sent to the signal controller 430 of the target traffic light to restore the target traffic light to the default timing control parameters.

[0126] For more information on high-risk vehicles, traffic light control, and target traffic lights, please refer to [link / reference]. Figure 2 And its related descriptions.

[0127] Response behavior refers to a series of specific driving actions or states exhibited by a risky vehicle after receiving special instructions (such as lane changing or deceleration) issued by the emergency monitoring and management platform through the target traffic lights.

[0128] In some embodiments, the response behavior may include at least one of the following: the risky vehicle begins to change lanes or decelerates; the risky vehicle does not respond (i.e., the risky vehicle maintains its original speed and original path); and the risky vehicle has successfully changed lanes or left its original path.

[0129] In some embodiments, the emergency monitoring and management platform can determine the response behavior of at-risk vehicles based on various methods. For example, the platform can determine the response behavior of at-risk vehicles based on the driving status (vehicle speed, lane, etc.) obtained from roadside radar and smart cameras.

[0130] In some embodiments, the emergency monitoring and management platform can acquire the vehicle speed, brake light data, wheel steering angle data, and lane departure data of the risky vehicle; in response to the wheel steering angle exceeding the steering threshold in the wheel steering angle data or the brake light illuminating in the brake light data, the response behavior is determined to be to start changing lanes or decelerating; in response to the vehicle speed fluctuation of the risky vehicle being less than the fluctuation threshold and the lane departure data meeting the non-departure condition, the response behavior is determined to be no response.

[0131] The speed of a risky vehicle refers to its real-time speed. In some embodiments, the emergency monitoring and management platform can obtain and record the real-time speed of a risky vehicle based on smart cameras, roadside radar, and GPS positioning.

[0132] Brake light data refers to the status of the brake lights of a high-risk vehicle, reflecting its braking behavior. For example, the brake lights may be illuminated or not. In some embodiments, the emergency monitoring and management platform can acquire brake light data from smart cameras to determine the braking behavior of a high-risk vehicle.

[0133] Wheel steering angle data refers to real-time information reflecting the angle and direction of the steering wheels (usually the front wheels) of a vehicle at risk relative to the vehicle's longitudinal axis. In some embodiments, the emergency monitoring and management platform can acquire wheel steering angle data based on smart cameras and roadside radar.

[0134] Lane departure data refers to real-time information that quantifies the relative position of a vehicle's current location to the reference line of its lane. In some embodiments, lane departure data may include lateral displacement deviation.

[0135] Lateral displacement deviation refers to the vertical distance from the center point of the at-risk vehicle to the center line of the lane in which the at-risk vehicle is located.

[0136] In some embodiments, the emergency monitoring and management platform can identify the left and right lane lines of the lane where the at-risk vehicle is located using a smart camera, and calculate the lane center line. In some embodiments, the emergency monitoring and management platform can also locate the specific position of the at-risk vehicle using a smart camera, roadside radar, and onboard vision system, obtain the vehicle center point of the at-risk vehicle, and then calculate the lateral displacement deviation.

[0137] In some embodiments, lateral displacement deviation can be expressed as a signed value, typically in meters (m) or centimeters (cm). For example, if the center point of the at-risk vehicle is 40 cm to the left of the center line of its lane, the lateral displacement deviation is expressed as -40 cm. As another example, if the center point of the at-risk vehicle is 0.5 m to the right of the center line of its lane, the lateral displacement deviation is expressed as 0.5 m. And as yet another example, if the center point of the at-risk vehicle is on the center line of its lane, the lateral displacement deviation is expressed as 0.

[0138] In some embodiments, if the emergency monitoring and management platform detects that the brake lights in the brake light data are illuminated, it determines that the risky vehicle has begun to decelerate. If the angle of the vehicle's steering wheel relative to the vehicle's longitudinal axis in the wheel steering angle data exceeds the steering threshold, it determines that the risky vehicle has begun to change lanes.

[0139] In some embodiments, the emergency monitoring and management platform can determine the turning threshold in a variety of ways. For example, the turning threshold can be preset by technicians based on prior experience.

[0140] In some embodiments, the steering threshold is related to the lane flow and / or lane width of the lane in which the at-risk vehicle is located.

[0141] In some embodiments, the steering threshold may be positively correlated with lane flow and negatively correlated with lane width.

[0142] Lane flow refers to the real-time traffic flow in the lane where the at-risk vehicle is located, which can be obtained by smart cameras or roadside radar.

[0143] Lane width refers to the width of the lane where the at-risk vehicle is located. It can be obtained from smart cameras, roadside radar, and in-vehicle vision systems, or by directly querying historical statistics from relevant websites.

[0144] In some embodiments of this specification, the turning threshold is made relevant to the lane width and lane traffic flow. For example, when the traffic flow is high in a narrow lane, the turning threshold for lane change determination is automatically reduced, which can improve the risk sensitivity of the IoT system for emergency warning of height and load restrictions in smart cities.

[0145] In some embodiments, if the emergency monitoring and management platform identifies that the speed fluctuation of a risky vehicle is less than the fluctuation threshold and the lane deviation data meets the non-deviation condition, it determines that the risky vehicle has not responded.

[0146] The speed fluctuation of a risky vehicle refers to the variance and / or mean of the absolute value of the speed change of the risky vehicle within a preset time period.

[0147] In some embodiments, the emergency monitoring and management platform can determine the fluctuation threshold based on historical data. The fluctuation threshold can be determined by the variance and / or mean of the absolute values ​​of the speed changes of all unresponsive risk vehicles in the road network within a historical time period corresponding to a preset time period recorded in the historical data.

[0148] The "no deviation condition" refers to a distance threshold. If the lateral displacement deviation of the risk vehicle is always less than this distance threshold within a preset time period, then the risk vehicle is judged to meet the "no deviation condition". This distance threshold can be preset by technicians based on prior experience, for example, 0.3m.

[0149] For more information about preset time periods, please refer to [link / reference]. Figure 3 And its related descriptions.

[0150] In some embodiments of this specification, a multi-dimensional and highly reliable vehicle behavior recognition solution is provided by integrating multi-source data such as vehicle speed, brake lights, steering angle, and lane departure, rather than relying on a single indicator. This greatly improves the accuracy and fault tolerance of judging the response behavior of risky vehicles and reduces the false judgment rate.

[0151] In some embodiments, the emergency monitoring and management platform can obtain continuous location data of the risk vehicle based on roadside radar and / or smart cameras. If it is determined from the continuous location data that the risk vehicle has entered an adjacent lane or other side road that does not lead to the target road segment, it is determined that the risk vehicle has successfully changed lanes or left the original path.

[0152] For more information about the target road section, please refer to [link / reference]. Figure 3 And its related descriptions.

[0153] A signal controller is a device that automatically controls the color status (red, yellow, green) and switching sequence of traffic lights according to a preset plan or external instructions.

[0154] The clear command is a high-priority control command that can control the signal controller to stop the currently executing command (such as the first control command, the second control command) and immediately restore the default timing control parameters.

[0155] In some embodiments, in response to a risky vehicle successfully changing lanes or leaving its original path, the emergency monitoring and management platform can also send a clearing command to the signal controller of the traffic light to be controlled, so that the traffic light to be controlled is restored to the default timing control parameters.

[0156] For more information about the traffic lights to be controlled, please refer to [link / reference]. Figure 3 And its related descriptions.

[0157] The default timing control parameters refer to a set of basic time values ​​that are preset and stored inside the signal controller. These values ​​are used to define the basic timing rules for the periodic and fixed-sequence switching of light colors in each phase of traffic lights at an intersection or in a signal control area.

[0158] In some embodiments of this specification, once the smart city height and load restriction emergency warning IoT system detects that a risky vehicle has been successfully guided or has left, it immediately releases all special signal controls, allowing traffic signals to quickly return to normal operation. This minimizes the negative impact on the passage efficiency of other normal vehicles, reflecting the humanistic care and efficiency maximization principles of the smart city height and load restriction emergency warning IoT system. At the same time, by monitoring the response behavior of risky vehicles, the agility and intelligence level of the smart city height and load restriction emergency warning IoT system are improved, realizing a complete closed loop from "start control" to "termination control". This enables the smart city height and load restriction emergency warning IoT system to flexibly respond to dynamically changing traffic scenarios, rather than rigidly executing preset instructions.

[0159] In some embodiments, this specification also includes a computer-readable storage medium, characterized in that the storage medium stores computer instructions, and when the computer reads the computer instructions in the storage medium, the computer executes the above-described smart city height and load restriction emergency early warning method.

[0160] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0161] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A smart city height and load restriction emergency early warning Internet of Things system, characterized in that, The system includes an emergency monitoring and management platform, which is configured as follows: Obtain vehicle perception data of the upstream road segment of the target road segment, wherein the target road segment is a height-restricted and load-restricted road segment; Based on the vehicle perception data, risky vehicles are identified; In response to the estimated arrival time of the at-risk vehicle at the target road segment meeting a preset condition, traffic light control is executed, including: Predict the time it takes for the at-risk vehicle to arrive at the target traffic light; Based on the time when the risky vehicle arrives at the target traffic light, a first control parameter is determined; the first control parameter includes the start time when the target traffic light transitions to the target state; Based on the first control parameters, a first control command is sent to the target traffic light; Based on the first control command, the target signal light is controlled to trigger a sub-clock at the start time, and the relay group is controlled to turn on the first lamp unit to drive the first lamp unit to emit light.

2. The system as described in claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: Acquire motion sensing data from multi-level sensing devices; the levels of the multi-level sensing devices are determined based on the distance between the multi-level sensing devices and the risky vehicle. Based on the motion perception data, a motion data sequence of the risk vehicle is constructed; The estimated arrival time is determined based on the road conversion rate matrix and the motion data sequence.

3. The system as described in claim 2, characterized in that, The emergency monitoring and management platform is further configured as follows: Based on the road conversion rate matrix, potential driving paths are determined; Determine the historical average speed corresponding to the potential driving path; The estimated arrival time is determined based on the motion data sequence and the historical average speed.

4. The system as described in claim 2, characterized in that, The emergency monitoring and management platform is further configured as follows: Based on the motion data sequence, the furthest reachable point of the at-risk vehicle within a preset time period is determined; Based on the farthest reachable point and the target road segment, determine the traffic lights to be controlled; Generate a second control parameter within a preset time period, the second control parameter including the common cycle duration and phase difference corresponding to the traffic light to be controlled; as well as Within a preset time period, a second control command is sent to the traffic light to be controlled based on the second control parameter; Based on the second control command, the signal light to be controlled is configured with a master clock timer based on the common period duration, a synchronous delay triggering sub-clock based on the phase difference, and the relay group is controlled to turn on the second lamp unit to drive the second lamp unit to emit light.

5. The system as described in claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: Monitor the response behavior of the risky vehicle to the traffic light control; the response behavior includes at least one of the following: the risky vehicle begins to change lanes or decelerates, the risky vehicle does not respond, or the risky vehicle has successfully changed lanes or left the original path; In response to the risk vehicle successfully changing lanes or leaving its original path, a clear command is sent to the signal controller of the target traffic light, so that the target traffic light is restored to its default timing control parameters.

6. The system as described in claim 5, characterized in that, The emergency monitoring and management platform is further configured as follows: Acquire the vehicle speed, brake light data, wheel steering angle data, and lane departure data of the at-risk vehicle; In response to the wheel steering angle exceeding a steering threshold in the wheel steering angle data or the brake light illuminating in the brake light data, the response behavior is determined to be initiating a lane change or deceleration. If the speed fluctuation of the risky vehicle is less than the fluctuation threshold and the lane deviation data meets the non-deviation condition, the response behavior is determined to be no response.

7. A smart city height and load restriction emergency early warning method, characterized in that, The method is executed by the emergency monitoring and management platform, and the method includes: Obtain vehicle perception data of the upstream road segment of the target road segment, wherein the target road segment is a height-restricted and load-restricted road segment; Based on the vehicle perception data, risky vehicles are identified; In response to the estimated arrival time of the at-risk vehicle at the target road segment meeting a preset condition, traffic light control is executed, including: Predict the time it takes for the at-risk vehicle to arrive at the target traffic light; Based on the time when the risky vehicle arrives at the target traffic light, a first control parameter is determined; the first control parameter includes the start time when the target traffic light transitions to the target state; Based on the first control parameters, a first control command is sent to the target traffic light; Based on the first control command, the target signal light is controlled to trigger a sub-clock at the start time, and the relay group is controlled to turn on the first lamp unit to drive the first lamp unit to emit light.

8. The method as described in claim 7, characterized in that, The method further includes: Acquire motion sensing data from multi-level sensing devices; the levels of the multi-level sensing devices are determined based on the distance between the multi-level sensing devices and the risky vehicle. Based on the motion perception data, a motion data sequence of the risk vehicle is constructed; The estimated arrival time is determined based on the road conversion rate matrix and the motion data sequence.

9. The method as described in claim 7, characterized in that, The method further includes: Monitor the response behavior of the risky vehicle to the traffic light control; the response behavior includes at least one of the following: the risky vehicle begins to change lanes or decelerates, the risky vehicle does not respond, or the risky vehicle has successfully changed lanes or left the original path; In response to the risk vehicle successfully changing lanes or leaving its original path, a clear command is sent to the signal controller of the target traffic light, so that the target traffic light is restored to its default timing control parameters.

10. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions from the storage medium, the computer executes a smart city height and load restriction emergency early warning method, including: Obtain vehicle perception data of the upstream road segment of the target road segment, wherein the target road segment is a height-restricted and load-restricted road segment; Based on the vehicle perception data, risky vehicles are identified; In response to the estimated arrival time of the at-risk vehicle at the target road segment meeting a preset condition, traffic light control is executed, including: Predict the time it takes for the at-risk vehicle to arrive at the target traffic light; Based on the time when the risky vehicle arrives at the target traffic light, a first control parameter is determined; the first control parameter includes the start time when the target traffic light transitions to the target state; Based on the first control parameters, a first control command is sent to the target traffic light; Based on the first control command, the target signal light is controlled to trigger a sub-clock at the start time, and the relay group is controlled to turn on the first lamp unit to drive the first lamp unit to emit light.

Images