Highway tunnel traffic status monitoring and early warning method based on electromechanical data

Abstract

The present invention relates to the field of risk warning technology, and specifically to a highway tunnel traffic status monitoring and warning method based on electromechanical data, comprising: obtaining traffic flow data and vehicle driving data in a target tunnel area in a highway tunnel; determining the collision risk probability of the target tunnel area using the traffic flow data; determining the collision reaction time of the target vehicle using the vehicle driving data; determining the risk index of the target vehicle using the collision risk probability and the collision reaction time; determining the vehicle driving state stability of the target lane using the risk index sequence of all vehicles in the target lane where the target vehicle is located; and determining a corresponding target warning signal using the vehicle driving state stability. By comprehensively analyzing the traffic flow data and vehicle driving data in the highway tunnel, the present invention can timely carry out risk prevention and warning for possible accidents, significantly reduce the probability of accidents, ensure driving safety, and effectively improve tunnel traffic efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of risk warning, and in particular to a highway tunnel traffic status monitoring and early warning method based on electromechanical data. Background Art

[0002] The electromechanical systems of highway tunnels, including those for monitoring, toll collection, and communications, generate vast amounts of data that needs to be utilized for tunnel monitoring. However, due to the high speeds of vehicles in highway tunnels and the significant changes in field of view and light intensity during entry and exit, drivers experience temporary blind spots, creating a black hole or white hole effect. This makes highway tunnels highly prone to accidents, necessitating the use of electromechanical systems for intelligent monitoring of highway tunnels. Assessing and predicting accident risks are crucial functions of highway tunnel safety management, but current safety management relies primarily on retrospective analysis, by which time tunnel accidents may have already occurred.

[0003] A common risk warning method is to limit vehicle speeds, but speed limits are too absolute and simplistic. In reality, safety hazards are related to multiple factors. Tunnel speed limits only meet the safety assessment of a single vehicle, while actual tunnel accidents are often caused by multiple vehicles. Therefore, current highway tunnel accident management solutions cannot effectively meet the needs of prediction, prevention, and risk monitoring. Summary of the Invention

[0004] To address the technical issues that current highway tunnel traffic accident management solutions are not ideal in terms of accident prediction, prevention, and risk monitoring, the present invention aims to provide a highway tunnel traffic status monitoring and early warning method based on electromechanical data. The technical solutions employed are as follows:

[0005] The present invention provides a highway tunnel traffic status monitoring and early warning method based on electromechanical data, the method comprising:

[0006] Obtain traffic flow data and vehicle driving data within the target tunnel area of ​​a highway tunnel;

[0007] Determining a collision risk probability in a target tunnel area using the traffic flow data;

[0008] Determine the target vehicle's collision reaction time using vehicle driving data;

[0009] Determining a risk index of a target vehicle using the collision risk probability and the collision reaction time;

[0010] The risk index sequence of all vehicles in the target lane where the target vehicle is located is used to determine the stability of the vehicle driving state in the target lane;

[0011] The corresponding target warning signal is determined by utilizing the vehicle driving state stability.

[0012] Furthermore, traffic flow data and vehicle travel data within the target tunnel area of ​​the highway tunnel are obtained, including:

[0013] Divide the highway tunnel into multiple target tunnel areas;

[0014] Collect image information and radar information within the target tunnel area to obtain traffic flow data and vehicle driving data;

[0015] The vehicle driving data includes the driving speed of each vehicle and the distance between the vehicle and the front and rear vehicles.

[0016] Furthermore, the vehicle driving state stability of the target lane is determined, and then the following steps are further included:

[0017] Determine the reference reaction time range for all vehicles in the target lane;

[0018] Within the reference reaction time range, the safety index of the target lane is determined by utilizing the vehicle driving state stability change and driving speed change of the target vehicle.

[0019] Furthermore, the safety index of the target lane is determined by utilizing the change in vehicle driving state stability and driving speed of the target vehicle, including:

[0020] Determining a driving safety characteristic value of the target vehicle by utilizing a change in vehicle driving state stability and a change in driving speed of the target vehicle;

[0021] The driving safety characteristic value is used to determine a safety index of a target vehicle, and the safety index of the target vehicle is used to determine a mean safety index of a target lane.

[0022] Furthermore, the driving safety characteristic value of the target vehicle is determined by utilizing the vehicle driving state stability change and driving speed change of the target vehicle, including:

[0023] Determining a first vehicle driving state stability of the target vehicle at a current moment and a second vehicle driving state stability at an initial moment of a reference reaction time range;

[0024] Determining a first driving speed of the target vehicle at a current moment and a second driving speed at an initial moment of a reference reaction time range;

[0025] A driving safety characteristic value of the target vehicle is determined using the first vehicle driving state stability, the second vehicle driving state stability, the first driving speed, and the second driving speed.

[0026] Furthermore, the collision risk possibility of the target tunnel area is determined using the traffic flow data, including:

[0027] Determine the traffic volume and traffic flow safety threshold in the target tunnel area;

[0028] Determine the standard deviation of traffic flow between the target tunnel area and the adjacent tunnel areas;

[0029] The collision risk probability of the target tunnel area is determined using the traffic volume, traffic flow safety threshold and traffic flow standard deviation.

[0030] Furthermore, the collision reaction time of the target vehicle is determined using the vehicle driving data, including:

[0031] Determine the speed difference and vehicle distance between the target vehicle and the preceding and following vehicles respectively;

[0032] The target vehicle's collision reaction time is determined using the driving speed difference and vehicle distance.

[0033] Furthermore, the collision reaction time of the target vehicle is determined using the speed difference and the vehicle distance, including:

[0034] determining a maximum driving speed difference among the driving speed differences and a corresponding vehicle distance;

[0035] The maximum speed difference and the corresponding vehicle distance are used to determine the collision reaction time of the target vehicle.

[0036] Furthermore, the risk index of the target vehicle is determined by utilizing the collision risk possibility and the collision reaction time, including:

[0037] Determine the current speed of the target vehicle at the current moment and the average speed of all vehicles in the target lane;

[0038] The risk index of the target vehicle is determined by using the current driving speed, the average vehicle speed, the collision risk possibility, and the collision reaction time.

[0039] Furthermore, the risk indicator sequence of all vehicles in the target lane where the target vehicle is located is used to determine the vehicle driving state stability of the target lane, including:

[0040] Using the risk index sequence of all vehicles in the target lane where the target vehicle is located, determine the risk index difference between the target vehicle and the vehicle in front of it, as well as the mean risk index difference of the target lane;

[0041] The vehicle driving state stability in the target lane is calculated using the risk indicator difference, the mean of the risk indicator difference and the collision reaction time.

[0042] The present invention has the following beneficial effects:

[0043] The present invention predicts the possibility of collision risk in each target tunnel area through traffic flow data, predicts the collision reaction time of each vehicle through vehicle driving data, and then combines the collision risk possibility of the target tunnel area and the collision reaction time of each vehicle to comprehensively judge the risk index faced by each vehicle itself, and then comprehensively identifies and analyzes the risk indicators of all vehicles in the same lane, predicts the vehicle driving state stability of the lane, and finally, based on the vehicle driving state stability obtained after the fusion of traffic flow data and vehicle driving data, obtains different risk signals and releases different warning signals, so that the monitoring results and warning means are not just speed limit measures, and the warning and management measures are more comprehensive and targeted, and the risk probability of accident occurrence is predicted more accurately, so that risk prevention and warning can be carried out in a timely manner for possible accidents, greatly reducing the probability of accidents, ensuring driving safety, and effectively improving the efficiency of tunnel passage. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 A flowchart of a method for monitoring and warning traffic conditions in highway tunnels based on electromechanical data according to an embodiment of the present invention;

[0046] Figure 2 This is a flowchart after step S5 of a method for monitoring and warning traffic conditions in a highway tunnel based on electromechanical data provided by one embodiment of the present invention;

[0047] Figure 3 A detailed flow chart of step S2 in a method for monitoring and warning traffic conditions in a highway tunnel based on electromechanical data provided by one embodiment of the present invention;

[0048] Figure 4 A detailed flow chart of step S3 in a method for monitoring and warning traffic conditions in a highway tunnel based on electromechanical data provided by one embodiment of the present invention;

[0049] Figure 5 This is a schematic diagram of the hardware operating environment of an intelligent monitoring and early warning device for traffic conditions in a highway tunnel based on electromechanical data according to an embodiment of the present invention;

[0050] Figure 6Schematic diagram of the framework structure of an intelligent monitoring and early warning system for highway tunnel traffic status based on electromechanical data according to an embodiment of the present invention;

[0051] Figure 7 This is a schematic diagram of segmenting a target tunnel area of ​​a highway tunnel involved in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a method for monitoring and warning traffic conditions in highway tunnels based on electromechanical data. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0053] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0054] The following describes in detail a specific scheme of a highway tunnel traffic status monitoring and early warning method based on electromechanical data provided by the present invention with reference to the accompanying drawings.

[0055] Example 1:

[0056] For the highway tunnel traffic status monitoring and early warning method based on electromechanical data provided by the present invention, please refer to Figure 1 , which shows a flowchart of the steps of a highway tunnel traffic status monitoring and early warning method based on electromechanical data provided by an embodiment of the present invention.

[0057] The method comprises:

[0058] Step S1, obtaining traffic flow data and vehicle travel data in a target tunnel area of ​​a highway tunnel;

[0059] Specifically, step S1 includes:

[0060] Divide the highway tunnel segment into multiple target tunnel areas;

[0061] Collect image information and radar information within the target tunnel area to obtain traffic flow data and vehicle driving data;

[0062] The vehicle driving data includes the driving speed of each vehicle and the distance between the vehicle and the front and rear vehicles.

[0063] Please refer to Figure 7 , Figure 7This is a schematic diagram of segmenting a target tunnel area of ​​a highway tunnel involved in an embodiment of the present invention.

[0064] This embodiment can be applied to highway electromechanical systems.

[0065] In this embodiment, cameras may be installed at regular intervals on the top of the highway tunnel to obtain the movement status of vehicles in the tunnel.

[0066] Highway tunnels are usually long and need to be segmented to obtain multiple target tunnel areas, which can be represented in the image system.

[0067] Specifically, highway tunnel images can be segmented based on camera locations. Tunnel image segmentation is independent of the current vehicle and is solely dependent on the tunnel and the location of the tunnel camera. The relevant data for this process can be acquired in advance, and once the segment locations are determined, they remain unchanged. The camera locations serve as segmentation points for the tunnel image, resulting in multiple tunnel regions.

[0068] By fusing and matching the image information obtained by the cameras at the same moment, a complete image of the entire tunnel at the current moment can be obtained.

[0069] Surveillance video of the target tunnel area can be combined with radar data for data fusion to generate a depth image for modeling. This depth image is then fed into a CNN (Convolutional Neural Network) model to track the vehicle and mark the vehicles in the video. One segmented tunnel area is then analyzed to obtain surveillance video of the marked vehicles in that area. This surveillance video is then fed into a YOLO model to determine the vehicle's speed for each frame and the distance between the vehicle in front and behind it in each lane.

[0070] The data obtained and processed by the electromechanical system above reflects the operating characteristics of the vehicle at the current moment (image frame). The above analysis is performed on each vehicle to obtain the driving characteristics of each vehicle, thereby completing the acquisition of traffic flow data and vehicle driving data.

[0071] Step S2, determining the collision risk possibility of the target tunnel area using the traffic flow data;

[0072] For details, please refer to Figure 3 , step S2, comprising:

[0073] Step S21, determining the traffic volume and traffic volume safety threshold of the target tunnel area;

[0074] Step S22, determining the standard deviation of the traffic flow between the target tunnel area and the front and rear adjacent tunnel areas;

[0075] Step S23 , using the traffic volume, traffic volume safety threshold, and traffic volume standard deviation, determines the collision risk possibility of the target tunnel area.

[0076] Obtain the current traffic flow in the target tunnel area through existing traffic flow detection technology Select the traffic flow of each tunnel area at the current moment. Since the tunnel segments are ordered, the area of ​​the highway tunnel exit can be used as the first element of the sequence and the tunnel entrance as the last element to obtain the corresponding traffic flow sequence:

[0077]

[0078] The air quality in the tunnel can be detected and the traffic flow safety threshold of the target tunnel area can be determined based on the air quality. .

[0079] If the traffic volume in a certain target tunnel area exceeds the traffic volume safety threshold, it means that the accident risk in this tunnel area of ​​the highway is higher. However, if each tunnel area has consistent traffic volume, it means that the abnormal traffic volume in this tunnel area is affected by the abnormal traffic volume in front of this tunnel section, and the possibility of collision accident risk in this tunnel section is actually lower.

[0080] Based on the above analysis, the following factors can be combined to determine the collision risk possibility in the target tunnel area. for:

[0081]

[0082] The probability of collision risk; is the traffic volume in the target tunnel area at the current moment, is the corresponding traffic flow safety threshold; The difference between the traffic volume and the safe traffic volume reflects the accident risk. is the positive correlation normalization function; It represents the standard deviation of traffic flow between the target tunnel area and the adjacent tunnel areas before and after it. A larger traffic flow standard deviation indicates a larger difference in traffic flow between adjacent tunnel areas, and a greater likelihood of a collision risk. Conversely, if the traffic flow before and after the target tunnel area remains roughly the same, vehicles in the highway tunnel remain in normal traffic despite a higher traffic flow, and the likelihood of a collision risk is lower.

[0083] In addition, for the inlet and outlet tunnel areas, since there is no reference tunnel area before or after, the standard deviation of the two tunnel areas is compared as the above formula. .

[0084] Step S3, determining the collision reaction time of the target vehicle using the vehicle driving data;

[0085] For details, please refer to Figure 4 , step S3, comprising:

[0086] Step S31, determining the speed difference and vehicle distance between the target vehicle and the preceding and following vehicles respectively;

[0087] Step S32: Determine the collision reaction time of the target vehicle using the driving speed difference and the vehicle distance.

[0088] More specifically, step S32 includes:

[0089] determining a maximum driving speed difference among the driving speed differences and a corresponding vehicle distance;

[0090] The maximum speed difference and the corresponding vehicle distance are used to determine the collision reaction time of the target vehicle.

[0091] Because vehicles experience varying traffic flow characteristics in different tunnel sections, for example, upon entering a tunnel, there are rapid changes in light intensity. Drivers typically slow down to ensure safety, allowing time for adaptation before accelerating to prevent congestion. Alternatively, certain sections of the tunnel may be less crowded. Consequently, actual tunnel traffic flow exhibits normal variations, making it difficult to maintain high consistency across tunnel sections. This makes it difficult to distinguish between normal traffic fluctuations and traffic that could potentially lead to collisions. To more clearly identify the potential accident risk within each tunnel section, further analysis is required, incorporating vehicle driving characteristics.

[0092] Select a target lane in the target tunnel area, determine all vehicles in the lane, and obtain the vehicle driving data corresponding to these vehicles. The average speed of all vehicles in the lane can be used as the normal speed of the lane, which is recorded as .

[0093] If the target vehicle's current speed is significantly different from the normal speed in the lane, there is a greater probability of a rear-end collision with the vehicle behind (speed too low) or a collision with the vehicle in front (speed too high), resulting in a higher accident risk. Based on this, the following factors are combined to analyze the danger level of the target vehicle at its current speed and the corresponding collision reaction time:

[0094]

[0095]

[0096] Indicates the target vehicle's speed Speed ​​of the vehicle ahead in the same lane and the speed of the vehicle behind The maximum speed difference reflects the danger level of the target vehicle traveling at the current speed.

[0097] If the maximum speed difference is the difference between the target vehicle and the preceding vehicle, label is front, otherwise it is next; label is the speed feature label corresponding to the target vehicle. Then, the collision reaction time of the target vehicle can be determined. :

[0098]

[0099] is the collision reaction time of the target vehicle; Indicates the distance between the target vehicle and the vehicle with label label, Indicates the maximum driving speed difference; The larger the value, the longer the vehicle's collision response time. For example, when the target vehicle presents a higher risk, it has a longer time to adjust the vehicle, so the corresponding vehicle accident risk is actually smaller.

[0100] Step S4, determining a risk index of the target vehicle using the collision risk possibility and the collision reaction time;

[0101] Specifically, step S4 includes:

[0102] Determine the current speed of the target vehicle at the current moment and the average speed of all vehicles in the target lane;

[0103] The risk index of the target vehicle is determined by using the current driving speed, the average vehicle speed, the collision risk possibility, and the collision reaction time.

[0104] The above analysis is performed on each vehicle in the target lane to obtain the corresponding collision reaction time of each vehicle. The smaller the collision reaction time, if the vehicle speed deviates significantly from the normal traffic speed, if the traffic volume is small at this time, the vehicle speed is allowed to deviate from the normal traffic speed, and the estimated risk of the vehicle is appropriately reduced; if the traffic volume is large at this time, vehicle accidents are more likely to occur, and the estimated risk of the vehicle is appropriately increased. As mentioned above, the size of the traffic volume and the corresponding risk can be expressed by the collision risk probability obtained by the traffic volume. Based on the above analysis, the risk index of each vehicle can be determined by combining the following factors such as traffic volume and driving speed :

[0105]

[0106] Where, Indicates the risk index of the target vehicle; Indicates the possibility of collision risk; represents the collision reaction time; Indicates the target vehicle's speed at the current moment; Represents the average speed of all vehicles in the target lane where the target vehicle is located. It should be noted that to ensure that the calculation results are meaningful, when performing fractional operations in the embodiments of the present invention, when the denominator is 0, a parameter adjustment factor greater than 0 must be added to the denominator to prevent the denominator from being 0. The value of the parameter adjustment factor is set by the implementer according to actual conditions and is not specifically limited in this application.

[0107] Step S5, using the risk indicator sequence of all vehicles in the target lane where the target vehicle is located, determining the vehicle driving state stability of the target lane;

[0108] Specifically, step S5 includes:

[0109] Using the risk index sequence of all vehicles in the target lane where the target vehicle is located, determine the risk index difference between the target vehicle and the vehicle in front of it, as well as the mean risk index difference of the target lane;

[0110] The vehicle driving state stability in the target lane is calculated using the risk indicator difference, the mean of the risk indicator difference and the collision reaction time.

[0111] Considering that the accident risk of a vehicle is manifested by multiple vehicles, and passing through a highway tunnel is a dynamic process, although the vehicles traveling at the current moment have a longer reaction time, if the distance is small, the risk index of the same vehicle in a short period of time will be There will be drastic changes, resulting in inaccurate accident predictions and warnings for vehicles.

[0112] If the target vehicle experiences significant speed fluctuations in the target lane ahead of the vehicle, the vehicle behind it should also adjust its speed accordingly to prevent a collision. For example, if there is a tunnel exit ahead, the driver may need to slow down to adjust to the change in light intensity. The overall spacing between these vehicles is relatively small, resulting in a shorter collision reaction time t, and thus a higher risk index for the corresponding vehicle. However, the vehicle behind is traveling at a higher speed and therefore also has a higher risk index. Therefore, vehicles behind are more likely to cause traffic accidents. Considering the changes in risk index between vehicles, if there are significant differences in risk indexes between adjacent vehicles in the same lane, this indicates significant differences in vehicle characteristics, such as speed, between the vehicle ahead and the vehicle behind, and the vehicle behind needs to make corresponding adjustments.

[0113] Therefore, a risk index sequence for the vehicles in the target lane is obtained (these vehicles can be sorted based on their order in the target lane). The difference in risk index between each vehicle and the preceding vehicle is obtained. The greater the difference, the worse the relative stability of the vehicle's driving state. Under this condition, if the target vehicle has a long reaction time, a large difference in risk index between vehicles is allowed, and the actual stability is relatively high. Therefore, it is necessary to combine factors such as the difference in risk index between vehicles and the collision reaction time to evaluate the driving stability of each target vehicle. :

[0114]

[0115] Indicates the stability of vehicle driving status. This value reflects the stability of the running status of these vehicles in the same lane. The more stable the running status of vehicles in the lane, the lower the accident risk. Indicates the difference in risk index between the target vehicle and the preceding vehicle in the same target lane; It represents the mean of the risk index differences of all vehicles in the risk index sequence, reflecting the normal fluctuation of the average vehicle operation status of the lane; is the risk index of the target vehicle, and t is the collision reaction time.

[0116] Step S6: using the vehicle driving state stability, determine a corresponding target warning signal.

[0117] The safety status of a tunnel section can be reflected by the driving stability of each target vehicle. Safety thresholds can be set to assess the tunnel's safety characteristics. For example, if a lane exhibits an abnormal safety characteristic, a warning signal will be sent to that section of the tunnel.

[0118] After the target tunnel area receives the corresponding warning signal, it indicates that a traffic accident may or is likely to occur in this tunnel area. The tunnel area number can be sent to the electromechanical system's emergency broadcast to remind drivers to pay attention to driving safety. For example, it can remind drivers to pay attention to speed if the traffic volume in this area is too heavy, or to pay attention to driving safety and increase the safe distance between vehicles if a vehicle is driving too fast or has a short collision reaction time. The warning signal can also be sent to patrol machines to maintain traffic order. Afterwards, emergency broadcasts can be made to all tunnels after the target tunnel area, and corresponding driving regulations and safety adjustments can be made.

[0119] In addition, in one embodiment, please refer to Figure 2 After step S5, the method further includes:

[0120] Step S60, determining a reference reaction time range for all vehicles in the target lane;

[0121] Step S70, determining a safety index of the target lane by utilizing a change in vehicle driving state stability and a change in driving speed of the target vehicle within a reference reaction time range;

[0122] Step S80: Determine a corresponding target warning signal using the safety index of the target lane.

[0123] Specifically, step S70 includes:

[0124] Step a, determining a driving safety characteristic value of the target vehicle by using a change in vehicle driving state stability and a change in driving speed of the target vehicle;

[0125] More specifically, step a includes:

[0126] Determining a first vehicle driving state stability of the target vehicle at a current moment and a second vehicle driving state stability at an initial moment of a reference reaction time range;

[0127] Determining a first driving speed of the target vehicle at a current moment and a second driving speed at an initial moment of a reference reaction time range;

[0128] A driving safety characteristic value of the target vehicle is determined using the first vehicle driving state stability, the second vehicle driving state stability, the first driving speed, and the second driving speed.

[0129] Step b: using the driving safety characteristic value to determine the safety index of the target vehicle, and using the safety index of the target vehicle to determine the safety index mean of the target lane.

[0130] On the other hand, a vehicle's operating state is constantly changing, making it difficult to accurately reflect the vehicle's actual accident risk by relying solely on its stability at a given moment. Warnings may be delayed, and by the time the tunnel's electromechanical system reports a risk warning, an accident has already occurred. Therefore, it's necessary to adjust warning parameters based on historical vehicle data to determine vehicle safety indicators.

[0131] The specific process is as follows:

[0132] The collision reaction time of each vehicle in the target lane can be obtained first. From these collision reaction times, a reference reaction time range for each vehicle in the target lane can be determined. Specifically, the minimum collision reaction time of all vehicles in the target lane and the corresponding time period can be selected as the reference reaction time range for each vehicle in the target lane. The reference reaction time range can be the time range from the initial time T to the current time. The minimum collision reaction time and the corresponding time period are selected to prevent obvious vehicle accidents from occurring within this time period, thereby providing proactive prevention.

[0133] The position of the target vehicle at the initial time T of the reference reaction time range can also be determined. It should be noted that if the target vehicle has not entered the tunnel at time T, the time calculation starts from the time of entering the tunnel, which corresponds to the modified time T.

[0134] Obtain the vehicle data of the target vehicle at time T and obtain the change in driving speed ; is the first driving speed at the current moment; The second speed represents the vehicle's speed at time T. The speed change reflects the change in the target vehicle's operating state. A larger value indicates a sudden acceleration or deceleration, which increases the risk of an accident and reduces the vehicle's safety.

[0135] If the vehicle ahead in the lane also experiences the same degree of speed change, it means that the target vehicle's state change is a normal response to the state change of the vehicle ahead, and the actual safety is higher; on the contrary, if it does not conform to the operating characteristics of the vehicle ahead, the driver may not be able to make timely adjustments to the vehicle within a short period of time, thus reducing safety.

[0136] Therefore, if the changes in the vehicle's driving state stability and driving speed are adjusted to match the corresponding changes in the preceding vehicle, the safety of the target vehicle will be higher.

[0137] Among them, the safety indicators of the target vehicle can be evaluated through the following specific methods:

[0138]

[0139]

[0140] Indicates the driving safety characteristic value of the target vehicle at the current moment; Indicates the vehicle driving state stability at the current moment, here refers to the driving state stability of the first vehicle; represents the driving state stability of the second vehicle at time T; For the change of driving speed;

[0141] Since the vehicle driving state stability and speed changes of different vehicle time series are included in the characteristic value c, the safety characteristic value Changes in the vehicle's operating characteristics before and after the reaction; Indicates the driving safety characteristic value of the vehicle ahead of the target vehicle; It is the safety index of the target vehicle.

[0142] Furthermore, the safety index of each vehicle in each target lane of the target tunnel area and the mean safety index of each target lane at the current moment are obtained to form a lane safety index vector (the dimension is the number of lanes). The safety status of each target lane in this section of the tunnel area can be reflected by the mean safety index. Corresponding safety thresholds are set to judge the safety characteristics of the tunnel. For example, if there is an abnormal safety feature in a certain lane, a corresponding warning signal will be sent to this section of the tunnel area.

[0143] After the target tunnel area receives the corresponding warning signal, it indicates that a traffic accident may or is likely to occur in this tunnel area. The number of the tunnel area and the target lane can be sent to the emergency broadcast of the electromechanical system to remind drivers to pay attention to driving safety. For example, it can remind drivers to pay attention to speed when the traffic volume in this area is too heavy, remind drivers to pay attention to speed when a vehicle is driving too fast or has a short collision reaction time, and remind them to pay attention to driving safety and increase the safe distance between vehicles. The warning signal can also be sent to patrol machines to maintain traffic order. Afterwards, emergency broadcasts can be made to all tunnels after the target tunnel area, and corresponding driving regulations and safety adjustments can be made.

[0144] The present invention predicts the possibility of collision risk in each target tunnel area through traffic flow data, predicts the collision reaction time of each vehicle through vehicle driving data, and then combines the collision risk possibility of the target tunnel area and the collision reaction time of each vehicle to comprehensively judge the risk index faced by each vehicle itself, and then comprehensively identifies and analyzes the risk indicators of all vehicles in the same lane, predicts the vehicle driving state stability of the lane, and finally, based on the vehicle driving state stability obtained after the fusion of traffic flow data and vehicle driving data, obtains different risk signals and releases different warning signals, so that the monitoring results and warning means are not just speed limit measures, and the warning and management measures are more comprehensive and targeted, and the risk probability of accident occurrence is predicted more accurately, so that risk prevention and warning can be carried out in a timely manner for possible accidents, greatly reducing the probability of accidents, ensuring driving safety, and effectively improving the efficiency of tunnel passage.

[0145] Example 2:

[0146] The embodiment of the present invention also provides an intelligent monitoring and early warning device for highway tunnel traffic status based on electromechanical data. The intelligent monitoring and early warning device for highway tunnel traffic status based on electromechanical data can be a data computing and processing device such as a computer, a server, or a combination of multiple devices.

[0147] like Figure 5 As shown, Figure 5 It is a structural diagram of the hardware operating environment of the intelligent monitoring and early warning equipment for traffic status in highway tunnels based on electromechanical data involved in the embodiment of the present invention.

[0148] like Figure 5 As shown, the intelligent monitoring and early warning device for highway tunnel traffic status based on electromechanical data may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Communication bus 1002 is used to enable communication between these components. User interface 1003 may include a display and an input unit, such as a control panel. Optionally, user interface 1003 may also include a standard wired interface or a wireless interface. Network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). Memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Memory 1005 may also be a storage device independent of processor 1001. Memory 1005, a computer storage medium, may include an intelligent monitoring and early warning program for highway tunnel traffic status based on electromechanical data.

[0149] Those skilled in the art will understand that Figure 5 The hardware structure shown in the figure does not constitute a limitation of the device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0150] Continue to refer to Figure 5 , Figure 5 The memory 1005 as a computer-readable storage medium may include an operating system, a user interface module, a network communication module, and an intelligent monitoring and early warning program for highway tunnel traffic status based on electromechanical data.

[0151] exist Figure 5 In the embodiment, the network communication module is mainly used to connect to the server and can communicate data with the server; and the processor 1001 can call the highway tunnel traffic status intelligent monitoring and early warning program based on electromechanical data stored in the memory 1005, and execute the steps in the above embodiments.

[0152] The hardware structure of the above-mentioned intelligent monitoring and early warning device for traffic status in highway tunnels based on electromechanical data is used to implement various embodiments of the method for monitoring and early warning traffic status in highway tunnels based on electromechanical data of the present invention.

[0153] In addition, the present invention also provides a highway tunnel traffic status intelligent monitoring and early warning system based on electromechanical data, please refer to Figure 6 The intelligent monitoring and early warning system for highway tunnel traffic status based on electromechanical data includes:

[0154] Tunnel monitoring module A10, used to obtain traffic flow data and vehicle travel data in a target tunnel area of ​​a highway tunnel;

[0155] The risk prediction module A20 is configured to determine the collision risk probability of the target tunnel area using the traffic flow data; determine the collision reaction time of the target vehicle using the vehicle driving data; determine the risk index of the target vehicle using the collision risk probability and the collision reaction time; and determine the vehicle driving state stability of the target lane using the risk index sequence of all vehicles in the target lane where the target vehicle is located;

[0156] The safety warning module A30 is used to determine a corresponding target warning signal using the vehicle's driving state stability.

[0157] Furthermore, the tunnel monitoring module A10 is further configured to:

[0158] Divide the highway tunnel into multiple target tunnel areas;

[0159] Collect image information and radar information within the target tunnel area to obtain traffic flow data and vehicle driving data;

[0160] The vehicle driving data includes the driving speed of each vehicle and the distance between the vehicle and the front and rear vehicles.

[0161] Furthermore, the risk prediction module A20 is further configured to:

[0162] Determine the reference reaction time range for all vehicles in the target lane;

[0163] Within the reference reaction time range, the safety index of the target lane is determined by utilizing the vehicle driving state stability change and driving speed change of the target vehicle.

[0164] Furthermore, the risk prediction module A20 is further configured to:

[0165] Determining a driving safety characteristic value of the target vehicle by utilizing a change in vehicle driving state stability and a change in driving speed of the target vehicle;

[0166] The driving safety characteristic value is used to determine a safety index of a target vehicle, and the safety index of the target vehicle is used to determine a mean safety index of a target lane.

[0167] Furthermore, the risk prediction module A20 is further configured to:

[0168] Determining a first vehicle driving state stability of the target vehicle at a current moment and a second vehicle driving state stability at an initial moment of a reference reaction time range;

[0169] Determining a first driving speed of the target vehicle at a current moment and a second driving speed at an initial moment of a reference reaction time range;

[0170] A driving safety characteristic value of the target vehicle is determined using the first vehicle driving state stability, the second vehicle driving state stability, the first driving speed, and the second driving speed.

[0171] Furthermore, the risk prediction module A20 is further configured to:

[0172] Determine the traffic volume and traffic flow safety threshold in the target tunnel area;

[0173] Determine the standard deviation of traffic flow between the target tunnel area and the adjacent tunnel areas;

[0174] The collision risk probability of the target tunnel area is determined using the traffic volume, traffic flow safety threshold and traffic flow standard deviation.

[0175] Furthermore, the risk prediction module A20 is further configured to:

[0176] Determine the speed difference and vehicle distance between the target vehicle and the preceding and following vehicles respectively;

[0177] The target vehicle's collision reaction time is determined using the driving speed difference and vehicle distance.

[0178] Furthermore, the risk prediction module A20 is further configured to:

[0179] determining a maximum driving speed difference among the driving speed differences and a corresponding vehicle distance;

[0180] The maximum speed difference and the corresponding vehicle distance are used to determine the collision reaction time of the target vehicle.

[0181] Furthermore, the risk prediction module A20 is further configured to:

[0182] Determine the current speed of the target vehicle at the current moment and the average speed of all vehicles in the target lane;

[0183] The risk index of the target vehicle is determined by using the current driving speed, the average vehicle speed, the collision risk possibility, and the collision reaction time.

[0184] Furthermore, the risk prediction module A20 is further configured to:

[0185] Using the risk index sequence of all vehicles in the target lane where the target vehicle is located, determine the risk index difference between the target vehicle and the vehicle in front of it, as well as the mean risk index difference of the target lane;

[0186] The vehicle driving state stability in the target lane is calculated using the risk indicator difference, the mean of the risk indicator difference and the collision reaction time.

[0187] The specific implementation of the intelligent monitoring and early warning system for highway tunnel traffic status based on electromechanical data of the present invention is basically the same as the embodiments of the above-mentioned highway tunnel traffic status monitoring and early warning method based on electromechanical data, and will not be repeated here.

[0188] The present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a program for intelligently monitoring and warning traffic conditions in highway tunnels based on electromechanical data. When executed by a processor, the program implements the steps of the aforementioned method for monitoring and warning traffic conditions in highway tunnels based on electromechanical data.

[0189] Among them, the method implemented when the intelligent monitoring and early warning program for highway tunnel traffic status based on electromechanical data is executed can refer to the various embodiments of the highway tunnel traffic status monitoring and early warning method based on electromechanical data of the present invention, and will not be repeated here.

[0190] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0191] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0192] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0193] The above description is only a preferred embodiment of the present invention and does not limit the scope of protection of the present invention. All equivalent structural / method transformations made by using the contents of the present invention description and drawings under the inventive concept of the present invention, or direct / indirect application in other related technical fields are included in the scope of protection of the present invention.

Claims

1. A highway tunnel traffic status monitoring and early warning method based on electromechanical data, characterized in that: The method comprises: Obtain traffic flow data and vehicle driving data within the target tunnel area of ​​a highway tunnel; Determining a collision risk probability in a target tunnel area using the traffic flow data; Determine the target vehicle's collision reaction time using vehicle driving data; Determining a risk index of a target vehicle using the collision risk probability and the collision reaction time; The risk indicator sequence of all vehicles in the target lane where the target vehicle is located is used to determine the vehicle driving state stability of the target lane. The vehicle driving state stability is determined based on the risk indicator difference between the target vehicle and the vehicle in front of it, the mean risk indicator difference of the target lane, and the collision reaction time. The risk indicator difference and the mean risk indicator difference are determined based on the risk indicator sequence. The corresponding target warning signal is determined by utilizing the vehicle driving state stability.

2. The highway tunnel traffic status monitoring and early warning method based on electromechanical data according to claim 1 is characterized in that: Obtain traffic flow data and vehicle driving data within the target tunnel area of ​​a highway tunnel, including: Divide the highway tunnel into multiple target tunnel areas; Collect image information and radar information within the target tunnel area to obtain traffic flow data and vehicle driving data; The vehicle driving data includes the driving speed of each vehicle and the distance between the vehicle and the front and rear vehicles.

3. The highway tunnel traffic status monitoring and early warning method based on electromechanical data according to claim 1 is characterized in that: Determine the vehicle driving state stability in the target lane, followed by: Determine the reference reaction time range for all vehicles in the target lane; Within the reference reaction time range, the safety index of the target lane is determined by utilizing the vehicle driving state stability change and driving speed change of the target vehicle.

4. The highway tunnel traffic status monitoring and early warning method based on electromechanical data according to claim 3 is characterized in that: The target vehicle's driving state stability and driving speed changes are used to determine the safety indicators of the target lane, including: Determining a driving safety characteristic value of the target vehicle by utilizing a change in vehicle driving state stability and a change in driving speed of the target vehicle; The driving safety characteristic value is used to determine a safety index of a target vehicle, and the safety index of the target vehicle is used to determine a mean safety index of a target lane.

5. The highway tunnel traffic status monitoring and early warning method based on electromechanical data according to claim 4 is characterized in that: The driving safety characteristic values ​​of the target vehicle are determined by utilizing the vehicle driving state stability change and driving speed change of the target vehicle, including: Determining a first vehicle driving state stability of the target vehicle at a current moment and a second vehicle driving state stability at an initial moment of a reference reaction time range; Determining a first driving speed of the target vehicle at a current moment and a second driving speed at an initial moment of a reference reaction time range; A driving safety characteristic value of the target vehicle is determined using the first vehicle driving state stability, the second vehicle driving state stability, the first driving speed, and the second driving speed.

6. The highway tunnel traffic status monitoring and early warning method based on electromechanical data according to claim 1 is characterized in that: Determining the collision risk probability of a target tunnel area using the traffic flow data includes: Determine the traffic volume and traffic flow safety threshold in the target tunnel area; Determine the standard deviation of traffic flow between the target tunnel area and the adjacent tunnel areas; The collision risk probability of the target tunnel area is determined using the traffic volume, traffic flow safety threshold and traffic flow standard deviation.

7. The method for monitoring and warning traffic conditions in highway tunnels based on electromechanical data according to claim 1 is characterized in that: Determine the target vehicle's collision reaction time using vehicle driving data, including: Determine the speed difference and vehicle distance between the target vehicle and the preceding and following vehicles respectively; The target vehicle's collision reaction time is determined using the driving speed difference and vehicle distance.

8. The method for monitoring and warning traffic conditions in highway tunnels based on electromechanical data according to claim 7 is characterized in that: Using the speed difference and vehicle distance, the target vehicle's collision reaction time is determined, including: determining a maximum driving speed difference among the driving speed differences and a corresponding vehicle distance; The maximum speed difference and the corresponding vehicle distance are used to determine the collision reaction time of the target vehicle.

9. The highway tunnel traffic status monitoring and early warning method based on electromechanical data according to claim 1 is characterized in that: Determining a risk index of a target vehicle using the collision risk probability and the collision reaction time includes: Determine the current speed of the target vehicle at the current moment and the average speed of all vehicles in the target lane; The risk index of the target vehicle is determined by using the current driving speed, the average vehicle speed, the collision risk possibility, and the collision reaction time.

Images