Expressway tunnel video monitoring method and system

Abstract

The invention relates to the technical field of tunnel video monitoring and early warning, in particular to an expressway tunnel video monitoring method and system, and the method comprises the steps: obtaining the temperature, humidity and visibility in an expressway tunnel in real time, and obtaining a monitoring video in the expressway tunnel; determining the ring parameter goodness of the current expressway tunnel; extracting and tracking each vehicle in the monitoring video of the expressway tunnel through a neural network model; determining the visual field covering interference degree, the rear-end collision risk degree, the vehicle speed tending coefficient, the deceleration necessity degree and the deceleration urgency degree of each vehicle; and extracting a fault vehicle in the monitoring video of the expressway tunnel, determining a deceleration early warning value of each vehicle in the tunnel, and performing deceleration early warning on each vehicle in the current tunnel. Therefore, the accuracy of highway video monitoring early warning is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel video monitoring and early warning, in particular to a highway tunnel video monitoring method and system. BACKGROUND

[0002] Highway tunnels play a crucial role in the field of transportation. By shortening the vehicle travel route, it significantly improves traffic efficiency when crossing complex terrain. However, due to the confined environment inside the tunnel, the driving risk of vehicles is increased, and video monitoring is often used to monitor the vehicle conditions inside the tunnel. The tunnel electromechanical system analyzes the video monitoring, and then issues a warning to the vehicles that need to slow down inside the tunnel based on the analysis results, improving the safety level of vehicle traffic in the tunnel.

[0003] In the traditional process of highway tunnel video monitoring, each vehicle inside the tunnel is often identified and positioned based on video algorithms, and then the current vehicle is slowed down and warned based on the distance between the current vehicle and the preceding vehicle. However, in actual scenarios, the vehicle conditions and environmental changes inside the tunnel are complex. For example, the different speeds of the front and rear vehicles in the longitudinal direction affect the tendency of rear-end collisions, and different lateral shifts during driving can cause the front vehicle to block the rear vehicle's view, increasing the driving safety risk. In addition, the complex vehicle conditions result in insufficient accuracy of the monitoring analysis results obtained based solely on the vehicle distance, and the environment of the tunnel changes at different times. In low-temperature and high-humidity environments, the road surface is prone to icing, further increasing the error of the traditional vehicle speed reduction warning based solely on vehicle distance in complex vehicle conditions, and reducing the accuracy of highway tunnel video monitoring. SUMMARY

[0004] To solve the above technical problems, the purpose of the present application is to provide a highway tunnel video monitoring method and system, and the technical solution adopted is as follows: In a first aspect, the present application provides a highway tunnel video monitoring method, which comprises the following steps: Real-time acquisition of temperature, humidity, and visibility inside the highway tunnel, as well as monitoring video inside the highway tunnel; Based on the temperature-humidity ratio and the difference between the current visibility and the historical visibility inside the current highway tunnel, determine the ring parameter optimization degree of the current highway tunnel; Extract and track each vehicle in the monitoring video of the highway tunnel through a neural network model; analyze the width difference between each vehicle and its adjacent vehicle, as well as the lateral distance between the vehicle centers, to determine the visual occlusion interference degree of each vehicle; Determine the rear-end risk degree of each vehicle based on the speed difference and acceleration difference between each vehicle and its adjacent vehicle; determine the speed trend coefficient of each vehicle based on the length difference between each vehicle and its adjacent vehicle, combined with the ring parameter optimization degree and the rear-end risk degree; fusing the vehicle speed fast trend coefficient and the field of view covering interference degree, obtaining the deceleration necessity degree of each vehicle, combining the vehicle density in front of each vehicle in the tunnel, determining the deceleration urgency degree of each vehicle; extracting the fault vehicle in the monitoring video of the highway tunnel, analyzing the metric distance between each vehicle and the fault vehicle in the tunnel, and the interval vehicle, combining the deceleration urgency degree, determining the deceleration warning value of each vehicle in the tunnel, and warning the current each vehicle in the tunnel to decelerate.

[0005] In one of the embodiments, the determination of the ring parameter placement preference degree includes: determining the mean value of the visibility in the current preset historical time period in the tunnel, calculating the difference value between the current visibility in the tunnel and the mean value, and the ring parameter placement preference degree is positively correlated with the difference value and the temperature humidity ratio.

[0006] In one of the embodiments, the determination of the field of view covering interference degree includes: calculating the ratio of the width of each vehicle to its adjacent front vehicle, and the field of view covering interference degree is the product of the ratio and the lateral distance.

[0007] In one of the embodiments, the determination of the rear-end risk degree includes: calculating the ratio of the vehicle speed of each vehicle to its adjacent front vehicle, denoted as a first ratio, calculating the normalized result of the difference value of the acceleration of each vehicle and its adjacent front vehicle, and the rear-end risk degree is the product of the first ratio and the normalized result.

[0008] In one of the embodiments, the determination of the vehicle speed fast trend coefficient includes: calculating the mean value of the vehicle length of each vehicle and its adjacent front vehicle, denoted as a first mean value, determining the longitudinal distance between the center point of each vehicle and the center point of its adjacent front vehicle, calculating the ratio of the first mean value and the longitudinal distance, denoted as a second ratio; determining the reciprocal of the ring parameter placement preference degree, and the vehicle speed fast trend coefficient is the normalized result of the product of the second ratio, the reciprocal, and the rear-end risk degree.

[0009] In one of the embodiments, the deceleration necessity degree is the square root result of the sum value of the square of the vehicle speed fast trend coefficient and the square of the field of view covering interference degree.

[0010] In one of the embodiments, the determination of the deceleration urgency degree includes: calculating the ratio of the number of front vehicles of each vehicle in the tunnel and the distance from the tunnel exit, denoted as a third ratio, and the deceleration urgency degree is the product of the third ratio and the deceleration necessity degree.

[0011] In one embodiment, the determining of the deceleration warning value comprises: calculating a normalized value of the number of interval vehicles and the reciprocal of the metric distance, the deceleration warning value being positively correlated with the normalized value and the deceleration urgency.

[0012] In one embodiment, the deceleration warning of the vehicles in the current tunnel comprises: calculating a normalized value of the difference between the deceleration warning value of each vehicle in the current tunnel and the average of the deceleration warning values of all the passing vehicles in the preset historical time period, if the normalized value is greater than a preset threshold, the corresponding vehicle is a vehicle to be warned, otherwise, the corresponding vehicle is not a vehicle to be warned.

[0013] In a second aspect, the embodiments of the present application further provide a highway tunnel video monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the method in any of the above aspects when executing the computer program.

[0014] The present application has at least the following beneficial effects: The application determines the ring parameter optimization degree of the current highway tunnel based on the current temperature and humidity ratio in the highway tunnel and the difference between the visibility and the historical visibility. The determination of the ring parameter optimization degree quantifies the health degree of the tunnel environment in real time, improves the dynamic adaptability of the environmental risk identification, and enhances the correlation and prediction ability of the environmental and accident warning. The neural network model extracts and tracks each vehicle in the monitoring video of the highway tunnel. The width difference between each vehicle and its adjacent vehicle and the lateral spacing of the vehicle center are analyzed to determine the visual coverage interference degree of each vehicle. The determination of the visual coverage interference degree improves the perception accuracy of the visual blind area in vehicle driving, provides data support for the distance control and warning of vehicles in the tunnel, and optimizes the rationality of lane resource allocation. According to the speed difference and acceleration difference between each vehicle and its adjacent vehicle, the rear-end risk degree of each vehicle is determined. The rear-end risk degree strengthens the forward-looking prediction of the collision risk, avoids the passive response of rear-end accidents, improves the granularity of vehicle risk positioning, and helps to publish warning information targeted at vehicles. Based on the length difference between each vehicle and its adjacent vehicle, combined with the ring parameter optimization degree and the rear-end risk degree, the speed-up coefficient of each vehicle is determined. The speed-up coefficient and the visual coverage interference degree are fused to obtain the deceleration necessity of each vehicle, and the deceleration urgency of each vehicle is determined combined with the vehicle density in front of each vehicle in the tunnel. The decision comprehensiveness of the vehicle risk warning in the tunnel is improved, the misjudgment caused by single index decision is avoided, the allocation efficiency of warning resources is optimized, and the calculation of the deceleration urgency enhances the differentiation ability of the tunnel warning, which helps to improve the priority of emergency response. The malfunctioning vehicle in the monitoring video of the highway tunnel is extracted, the metric distance between each vehicle in the tunnel and the malfunctioning vehicle and the interval vehicle is analyzed, combined with the deceleration urgency, the deceleration warning value of each vehicle in the tunnel is determined, and the deceleration warning of each vehicle in the current tunnel is carried out. The application dynamically generates the deceleration warning value, comprehensively considers the multi-dimensional influencing factors of the tunnel warning, improves the accuracy of the tunnel warning, optimizes the tunnel passing efficiency, and improves the tunnel passing safety. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the application or the prior art, the drawings needed in the following embodiment or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and those skilled in the art can obtain other drawings according to these drawings without creating any inventive labor.

[0016] Figure 1 A step flow chart of a highway tunnel video monitoring method provided by an embodiment of the application; Figure 2 A lateral offset displacement schematic diagram; Figure 3 Flow chart for determining deceleration warning value for vehicles in the tunnel. DETAILED DESCRIPTION

[0017] In order to further clarify the technical means and effects taken by the present application to achieve the predetermined purpose of the application, the specific implementation, structure, features and effects of the expressway tunnel video monitoring method and system according to the present application are described in detail as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, 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 application belongs.

[0019] The specific scheme of the expressway tunnel video monitoring method and system provided by the present application is described in detail below in combination with the drawings.

[0020] Please refer to Figure 1 which shows the step flow chart of an expressway tunnel video monitoring method provided by an embodiment of the present application, and the method comprises the following steps: S1, real-time acquisition of temperature, humidity and visibility in the expressway tunnel, and monitoring video in the expressway tunnel.

[0021] The environment in the expressway tunnel is closed, especially in the case of complex vehicle conditions, which greatly increases the probability of vehicle accidents. Therefore, the vehicle condition video in the tunnel is often collected, and the vehicles in the video are analyzed and monitored by the tunnel electromechanical system.

[0022] When the traditional tunnel electromechanical system analyzes the deceleration warning of vehicles, it often evaluates according to the distance between vehicles. However, in the actual scene, the tunnel environment and vehicle conditions change complexly, and the monitoring accuracy obtained only according to the distance between vehicles is insufficient. Therefore, the present embodiment specifically analyzes the complex changes of the tunnel environment and vehicle conditions in the actual scene, obtains more accurate deceleration warning evaluation results of the tunnel electromechanical system for each vehicle, reduces the risk of vehicle driving, and improves the video monitoring accuracy of expressway tunnel warning.

[0023] Firstly, the monitoring video data of the vehicles on the road in the target expressway tunnel is read by the monitoring equipment in the tunnel, and the Retinex algorithm is used for preprocessing the monitoring video data to realize low-light enhancement and eliminate the visual impact caused by the sudden change of light inside and outside the tunnel. The Retinex algorithm is a known technology, and the implementer can choose other feasible image enhancement algorithms, which are not limited in the present embodiment.

[0024] Secondly, the visibility in the highway tunnel is measured in real time by using the forward scattering method, and a temperature and humidity sensor is installed at the center of the highway tunnel to collect the temperature and humidity in the highway tunnel in real time. The visibility, temperature and humidity are collected synchronously, and the collection frequency is 10 Hz in this embodiment, which can be set by the implementer according to the actual situation, and the embodiment does not limit this.

[0025] S2, based on the temperature and humidity ratio in the current highway tunnel and the difference between the visibility and the historical visibility, the ring parameter optimization degree of the current highway tunnel is determined.

[0026] The present application aims to slow down the vehicles in the tunnel by the highway tunnel electromechanical system, and the driving performance of the vehicles in the tunnel is related to the tunnel environment and the real-time vehicle condition, so the ring parameter optimization degree of the current tunnel is first evaluated according to the multi-source environmental factors in this embodiment, which is specifically: Since the driving performance of the vehicles in the tunnel is affected by the multi-source environmental parameters and the complex vehicle conditions in the tunnel, and the monitoring video cannot reflect the multi-source environmental performance in the tunnel, the monitoring video monitoring process is analyzed by the collected environmental parameters in this embodiment. The temperature and humidity and the visibility in the tunnel directly affect the vehicle performance and the driving safety of the driver, when the temperature in the tunnel is lower and the humidity is higher, the cold and humid environment in the tunnel will significantly reduce the road friction coefficient, and in severe cases, it may cause the road to freeze, further increasing the risk of vehicle skidding, reducing the operation performance of the vehicle, and the lower the visibility in the tunnel, the stronger the visual interference on the vehicle driver, at this time, the comprehensive environment has greater influence on the vehicle performance and greater interference on the driver, and the environmental optimization degree is worse.

[0027] Based on the above analysis, the ring parameter optimization degree of the current highway tunnel is calculated, and the specific calculation process is: In the formula, The ring parameter optimization degree of the current highway tunnel is represented by T, the temperature in the current highway tunnel, C, the humidity in the current highway tunnel, A, the visibility in the current highway tunnel, The average value of all visibilities collected in the current preset historical time period. The length of the historical time period in this embodiment is three months, which can be set by the implementer according to the actual situation, and the embodiment does not limit this.

[0028] In particular, in order to facilitate calculation, when the average value of all visibilities collected in the current preset historical time period is Zero, remove a maximum value and a minimum value to recalculate until the value is not zero.

[0029] It should be understood that the greater the temperature and humidity ratio in the highway tunnel The greater the friction performance of the tunnel road surface, the smaller the impact on the operating performance of the vehicle, and the clearer the visibility in the tunnel compared to the historical level, the smaller the degree of interference with the driver's field of view, and the better the real-time environmental parameters in the tunnel.

[0030] S3, extract and track each vehicle in the monitoring video of the highway tunnel through the neural network model; analyze the width difference between each vehicle and its adjacent vehicle, and the lateral spacing of the vehicle center, to determine the field of view interference degree of each vehicle.

[0031] The embodiment locates each vehicle in the monitoring video of the current highway tunnel through the neural network model, that is, the neural network model can frame each vehicle in the monitoring video through the frame. The neural network model selected in this embodiment is YOLOv5, and the neural network model for identifying vehicles in the monitoring video is a known technology. The implementer can select other feasible neural network models, and this embodiment does not limit this.

[0032] During driving, if the width of the front vehicle in a single lane is larger, it is more likely to cause a field of view obstruction to the rear vehicle. In addition, in the driving direction of the traffic flow, if the front vehicle is more offset to the left side in the vertical direction of the traffic flow compared to the rear vehicle, and the width of the front vehicle is relatively larger, it will cause stronger field of view obstruction interference to the driver of the rear vehicle. Therefore, this embodiment determines the field of view obstruction interference degree of each vehicle based on the width difference between each vehicle and its adjacent front vehicle, and the lateral spacing of the vehicle center, specifically: Since the neural network model uses a frame to frame the vehicle when identifying the vehicle in the monitoring video, the width of the frame of the vehicle in the monitoring video is used to represent the width of the vehicle, and the center point of the frame of the vehicle is recorded as the center point of the vehicle in the monitoring video. The field of view obstruction interference degree of each vehicle in the monitoring video in the current tunnel is calculated, and the specific expression is: ; In the formula, norm() is a normalization function, Q represents the field of view obstruction interference degree of each vehicle in the monitoring video in the current tunnel, is the width of the adjacent front vehicle of each vehicle in the monitoring video in the current tunnel, is the width of each vehicle in the monitoring video in the current tunnel, is the lateral spacing of each vehicle and its adjacent front vehicle in the monitoring video in the current tunnel, recorded as the lateral offset displacement. The lateral offset displacement is shown in Figure 2 .

[0033] It should be noted that when the center point of each vehicle in the monitoring video is on the same straight line as the current vehicle, the lateral distance Y is set to 0. In the monitoring video, the longitudinal direction represents the driving direction of the vehicle, and the lateral direction represents the direction perpendicular to the driving direction of the vehicle.

[0034] If the adjacent front vehicle of each vehicle is wider than the width of each vehicle , the wider the adjacent front vehicle of each vehicle is compared to the lateral offset of each vehicle in the vertical traffic direction , the greater the interference of the field of view of the front vehicle on each vehicle, and the more the vehicle should be warned to slow down.

[0035] S4, according to the speed difference and acceleration difference between each vehicle and its adjacent vehicle, determine the risk of rear-end collision of each vehicle; based on the length difference between each vehicle and its adjacent vehicle, combined with the ring parameter degree and the risk of rear-end collision, determine the speed increasing coefficient of each vehicle.

[0036] Rear-end collision between vehicles is a common accident in highway tunnels. When the real-time speed of the rear vehicle is faster, and the real-time speed of the front vehicle is slower, the speed of the two vehicles is more dangerous. Therefore, when warning in a highway tunnel, vehicle speed is also a necessary factor to consider. In addition, when the speed of the front vehicle is equal to the speed of the rear vehicle, there is a possibility that the rear vehicle is accelerating and the front vehicle is decelerating. At this time, although the speed of the front vehicle is equal to the speed of the rear vehicle, this situation is temporary, and there is still a possibility of rear-end collision between the front vehicle and the rear vehicle. Therefore, the acceleration of the vehicle also needs to be considered when calculating the risk of rear-end collision.

[0037] Based on the above analysis, the embodiment identifies vehicles in the monitoring video through a neural network model, tracks the vehicles to calculate the driving speed of the vehicles, and calculates the acceleration of the vehicles through the driving speed of the vehicles. The calculation of the driving speed and acceleration of the vehicles is a known technology, and will not be described in detail.

[0038] Therefore, the risk of rear-end collision of each vehicle in the monitoring video in the current tunnel is calculated, and the specific expression is: ; in the formula, represents the risk of rear-end collision of each vehicle in the monitoring video in the current tunnel, is the acceleration of each vehicle in the monitoring video in the current tunnel, is the acceleration of the adjacent front vehicle of each vehicle in the monitoring video in the current tunnel, is the speed of each vehicle in the monitoring video in the current tunnel, is the speed of the adjacent front vehicle of each vehicle in the monitoring video in the current tunnel, and norm() is a normalization function. Let be the first ratio.

[0039] It should be noted that, in order to ensure that the calculation result is meaningful, when performing fractional operation, if the denominator is 0, a parameter adjustment factor can be added to the denominator to prevent the denominator from being 0. The parameter adjustment factor is a very small positive number. For example, the value of the parameter adjustment factor can be 0.01. The specific value can be set by the implementer according to the actual situation, and the embodiment of the present application does not make specific limitations.

[0040] Specifically, the normalization (or normalization function) in the embodiment of the present application is specifically the min-max normalization.

[0041] It should be understood that, due to the relatively closed space in the tunnel, the sight distance is short, and the traffic flow is limited. When the acceleration and speed of the rear vehicle are large, the reaction time will become shorter, and it is easy to appear that the vehicle speed or brake cannot be adjusted in time, especially when the front vehicle suddenly slows down or stops, the probability of rear-end collision accidents significantly increases, therefore, the greater the rear-end risk degree is.

[0042] Secondly, the driving rear-end risk of the two adjacent vehicles in the tunnel is not only reflected by the vehicle speed, but also the smaller the real time distance between the center points of the front and rear two vehicles, the greater the rear-end risk will be. Considering that the size performance of different vehicles in the actual scene is different, for example, the length of a large truck is obviously longer than that of a small car, so for the vehicle with a longer size, the real distance between the adjacent vehicles is shorter than the distance reflected by the center points. The higher the vehicle rear-end risk degree is, the lower the ring parameter optimization degree of the real-time tunnel is, the greater the degree of influence on vehicle driving is, and the easier the vehicle accident is to be caused, therefore, vehicle warning needs to be performed in time.

[0043] Based on the above analysis, the embodiment calculates the vehicle speed trend coefficient of each vehicle in the current tunnel monitoring video, which is specifically: Firstly, the longitudinal distance between the center points of each vehicle and its adjacent front vehicle in the monitoring video is determined, and the average length of each vehicle and its adjacent front vehicle in the monitoring video is calculated, which is denoted as the first average value. The length of the vehicle in the embodiment is represented by the length of the selected square frame of the vehicle in the monitoring video. The expression of the vehicle speed trend coefficient of each vehicle in the monitoring video is: ; in the formula, is the vehicle speed trend coefficient of each vehicle in the current tunnel monitoring video, is the average length of each vehicle and its adjacent front vehicle in the current tunnel monitoring video, is the longitudinal distance between the center points of each vehicle and its adjacent front vehicle in the current tunnel monitoring video, and U represents the ring parameter optimization degree of the current highway tunnel, represents the rear-end risk degree of each vehicle in the current tunnel monitoring video. The rear-end risk degree of each vehicle in the current tunnel monitoring video is calculated by the following formula: This is denoted as the second ratio.

[0044] It should be understood that the larger the length of the vehicle in the tunnel compared to the vehicle in front, and the greater the distance between the center positioning coordinates of the two vehicles... The smaller the value, the more dangerous the distance between the analyzed vehicle and the vehicle in front, and the higher the risk of a rear-end collision. The higher the value, the worse the real-time environmental performance inside the tunnel, which further indicates that the current vehicle speed trend is too high, and the more necessary it is to issue a deceleration warning.

[0045] S5, by combining the vehicle speed acceleration coefficient and the field of vision obstruction interference degree, the deceleration necessity of each vehicle is obtained, and by combining the density of vehicles in front of each vehicle in the tunnel, the deceleration urgency of each vehicle is determined.

[0046] Furthermore, if the speed acceleration coefficient of each vehicle in the current tunnel monitoring video is larger in the direction of traffic flow, and the field of view obstruction interference in the direction perpendicular to traffic flow is higher, it further indicates that the real-time deceleration necessity of the vehicle is higher. Therefore, the deceleration necessity of each vehicle in the current tunnel monitoring video is calculated using the following expression: In the formula, To determine the necessary deceleration levels for each vehicle in the current tunnel surveillance video, Q represents the speed acceleration coefficient of each vehicle in the current tunnel surveillance video, and Q represents the field-of-view obstruction interference of each vehicle in the current tunnel surveillance video.

[0047] Secondly, for vehicles inside the tunnel, speed control needs to be determined not only by considering the driving performance of nearby vehicles but also by taking into account the real-time road congestion and vehicle density within the tunnel. If, for any given vehicle, the more concentrated the traffic is on the road segment not yet traversed by that vehicle, the more congested the traffic situation that vehicle is about to encounter, requiring speed control in advance. Therefore, based on the necessity of deceleration, the urgency of deceleration for each vehicle inside the tunnel is determined by analyzing the road congestion situation on the road segment ahead of the tunnel. Specifically: First, for each vehicle in the current tunnel surveillance video, count its distance from the tunnel exit, denoted as the untraveled distance within the tunnel. Simultaneously, count the number of vehicles within the untraveled distance of each vehicle in the surveillance video. Combining this with the deceleration necessity of each vehicle, calculate the deceleration urgency of each vehicle in the surveillance video. The specific expression is as follows: In the formula, This indicates the urgency of deceleration for each vehicle in the current tunnel surveillance video. This represents the number of vehicles within the tunnel's untraveled distance as shown in the current tunnel surveillance video. This represents the distance each vehicle has not traveled within the tunnel as shown in the current tunnel surveillance video. This determines the necessary deceleration level for each vehicle in the current tunnel surveillance video. This is denoted as the third ratio.

[0048] The greater the total number of vehicles within the tunnel's untraveled distance, the more congested the traffic conditions the vehicle will face, and the higher the necessity for the vehicle to decelerate. This further indicates that the vehicle urgently needs to decelerate in order to control its speed, hence the greater the urgency of deceleration.

[0049] S6. Extract the faulty vehicle from the monitoring video of the highway tunnel, analyze the measured distance between each vehicle and the faulty vehicle in the tunnel, as well as the interval between vehicles, and determine the deceleration warning value for each vehicle in the tunnel based on the aforementioned deceleration urgency, and issue a deceleration warning to each vehicle in the current tunnel.

[0050] Furthermore, considering the possibility of sudden special vehicle conditions within highway tunnels, such as abnormal situations like stopped vehicles, vehicles driving in the wrong direction, or vehicles using hazard lights detected by surveillance video, while dispatching backup vehicles, timely warnings should be issued to vehicles behind these vehicles within the tunnel. This helps them to be aware of the sudden road conditions, extending their reaction time and enabling them to react promptly. Therefore, this embodiment adjusts the deceleration urgency values ​​for each vehicle based on special vehicle conditions to determine the deceleration warning values ​​for each vehicle within the tunnel, specifically as follows: First, the YOLOv5 neural network model is used to mark vehicles with malfunctions in the tunnel monitoring video, locate the coordinates of the malfunctioning vehicles, and calculate the metric distance between the coordinates of each vehicle in the current tunnel monitoring video and the malfunctioning vehicle. Simultaneously, the number of vehicles in between each vehicle and the malfunctioning vehicle in the current tunnel monitoring video is extracted. Based on this, the deceleration warning value for each vehicle in the current tunnel is determined. The specific expression is as follows: In the formula, M represents the deceleration warning value for each vehicle in the current tunnel monitoring video, and M represents the number of vehicles between each vehicle and the disabled vehicle in the current tunnel monitoring video. The distance between each vehicle and the faulty vehicle in the current tunnel monitoring video is measured. In this embodiment, the distance is calculated using Euclidean distance. Implementers can choose other existing feasible distance calculation methods, and this embodiment does not impose any restrictions on this. This indicates the urgency of deceleration for each vehicle in the current tunnel monitoring video, where norm() is the normalization function. The flowchart for determining the deceleration warning value for vehicles in the tunnel is shown below. Figure 3 As shown.

[0051] It should be noted that if there is no fault vehicle in the current monitoring video tunnel, and there is a fault vehicle, but the fault vehicle is located behind the driving vehicle, at this time the fault vehicle has less impact on the driving vehicle, and the current embodiment will take the urgency of the driving vehicle to decelerate as the deceleration warning value.

[0052] It should be understood that if the distance between the current analysis vehicle and the fault vehicle is closer, and the number of vehicles between the two vehicles is more, the current analysis vehicle has a greater difficulty in controlling the vehicle speed in the face of subsequent sudden situations, and the urgency of deceleration is greater, which further indicates that the vehicle speed of the current analysis vehicle needs to be decelerated.

[0053] Further, the average of the deceleration warning values of all vehicles in the tunnel in the current preset historical time period is calculated, denoted as a second average, and the normalized value of the difference between the deceleration warning value of each vehicle in the current tunnel monitoring video and the second average is calculated. The greater the normalized value, the greater the deceleration warning value of the corresponding vehicle compared to the historical vehicle, the more complex the driving environment of the vehicle, and the more the vehicle needs to be decelerated.

[0054] Therefore, if the normalized value of the vehicle in the current tunnel monitoring video is greater than a preset threshold, the corresponding vehicle is taken as a vehicle that needs to be warned, and the highway tunnel electromechanical system sends a deceleration warning signal to the driver through the vehicle GPS navigation system, otherwise, the corresponding vehicle is not taken as a vehicle that needs to be warned. In the present embodiment, the preset threshold is set to 0.8, and the implementer can set it according to the actual situation, which is not limited in the present embodiment.

[0055] Based on the same inventive concept as the above method, the embodiments of the present application also provide a highway tunnel video monitoring system, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the method of any one of the above highway tunnel video monitoring methods are implemented.

[0056] It should be noted that the above sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0057] Each embodiment in the present specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments.

[0058] The above description is only the preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the principle of the present application should be included in the protection scope of the present application.

Claims

1. A video surveillance method for highway tunnels, characterized in that, The method includes the following steps: Real-time acquisition of temperature, humidity, visibility, and surveillance video inside highway tunnels; Based on the current temperature and humidity ratio inside the highway tunnel, and the difference between the visibility and historical visibility, the environmental parameter optimization of the current highway tunnel is determined. The video footage of a highway tunnel was extracted and tracked using a neural network model. The width difference between each vehicle and its neighboring vehicles, as well as the lateral distance between the vehicle centers, were analyzed to determine the visual obstruction interference of each vehicle. The rear-end collision risk of each vehicle is determined based on the speed and acceleration differences between each vehicle and its neighboring vehicles; the speed acceleration coefficient of each vehicle is determined based on the length differences between each vehicle and its neighboring vehicles, combined with the ring parameter dominance and the rear-end collision risk. By combining the vehicle speed acceleration coefficient and the field of vision obstruction interference, the deceleration necessity of each vehicle is obtained. Combined with the density of vehicles in front of each vehicle in the tunnel, the deceleration urgency of each vehicle is determined. Extract the faulty vehicle from the surveillance video of the highway tunnel, analyze the measured distance between each vehicle and the faulty vehicle in the tunnel, as well as the interval between vehicles, and combine the aforementioned deceleration urgency to determine the deceleration warning value for each vehicle in the tunnel, and issue deceleration warnings to each vehicle in the current tunnel.

2. The video surveillance method for highway tunnels as described in claim 1, characterized in that, The determination of the ring parameter dominance includes: The average visibility within the tunnel during a preset historical time period is determined, and the difference between the current visibility within the tunnel and the average is calculated. The environmental parameter goodness is positively correlated with the difference and the temperature-humidity ratio.

3. The video surveillance method for highway tunnels as described in claim 1, characterized in that, The determination of the field-of-view occlusion interference degree includes: Calculate the ratio of the width of each vehicle to its adjacent vehicle in front, and the field of view occlusion interference is the product of the ratio and the lateral spacing.

4. The video surveillance method for highway tunnels as described in claim 1, characterized in that, The determination of the rear-end collision risk level includes: The ratio of the speed of each vehicle to the speed of its nearest preceding vehicle is calculated and denoted as the first ratio. The normalized result of the difference in acceleration between each vehicle and its nearest preceding vehicle is calculated. The rear-end collision risk is the product of the first ratio and the normalized result.

5. The video surveillance method for highway tunnels as described in claim 1, characterized in that, The determination of the speed acceleration coefficient includes: Calculate the average length of each vehicle and its neighboring vehicle in front, and record it as the first average. Determine the longitudinal distance between the center point of each vehicle and the center point of its neighboring vehicle in front. Calculate the ratio of the first average to the longitudinal distance, and record it as the second ratio. The reciprocal of the ring parameter optimization is determined, and the vehicle speed acceleration coefficient is the normalized result of the product of the second ratio, the reciprocal, and the rear-end collision risk degree.

6. The video surveillance method for highway tunnels as described in claim 1, characterized in that, The deceleration necessity is the square root of the sum of the square of the vehicle speed acceleration coefficient and the square of the field of vision obstruction interference degree.

7. The video surveillance method for highway tunnels as described in claim 1, characterized in that, The determination of the urgency of deceleration includes: The ratio of the number of vehicles ahead of each vehicle in the tunnel to the distance to the tunnel exit is calculated and denoted as the third ratio. The urgency of deceleration is the product of the third ratio and the necessity of deceleration.

8. The video surveillance method for highway tunnels as described in claim 1, characterized in that, The determination of the deceleration warning value includes: The normalized value of the number of vehicles at intervals and the reciprocal of the measured distance is calculated. The deceleration warning value is positively correlated with both the normalized value and the deceleration urgency.

9. A video surveillance method for highway tunnels as described in claim 1, characterized in that, The method of issuing deceleration warnings to all vehicles currently in the tunnel includes: Calculate the normalized value of the difference between the current deceleration warning value of each vehicle in the tunnel and the average deceleration warning value of all vehicles passing through the tunnel in the current preset historical time period. If the normalized value is greater than a preset threshold, the corresponding vehicle is designated as a vehicle requiring a warning; otherwise, the corresponding vehicle is not designated as a vehicle requiring a warning.

10. A video surveillance system for highway tunnels, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-9.

Images