Road vehicle targeted early warning method for driving safety risk of complex underground road

Abstract

The invention discloses a complex underground road driving safety risk road vehicle targeted early warning method comprising the following steps: carrying out identification and trajectory tracking on a vehicle to obtain a vehicle identification tracking result; based on the vehicle identification tracking result, determining the traffic safety field intensity at the target point in the road space; and if the field intensity of the traffic safety field at the target point exceeds a set threshold value, taking the vehicle closest to the target point as a risk vehicle, and sending early warning information to the risk vehicle. According to the invention, the driving safety risk of the vehicle on the road section can be comprehensively sensed, and the early warning information is accurately pushed to the risk vehicle, so that the operation safety level of the complex underground road and the three-dimensional traffic is improved.

Description

Technical Field

[0001] The present invention relates to the field of road traffic, and in particular to a road-vehicle targeted early warning method for driving safety risks on complex underground roads. Background Art

[0002] As an important means of expanding the transportation system in the high-density core areas of megacities, underground roads are gradually developing towards networking, systematization, and scale in the form of complex tunnels with multiple entry and exit points and circular radiation. In terms of traffic operation functions, complex underground roads and ground elevated roads play similar roles. However, the unique road environment of underground roads makes their traffic characteristics different. In order to avoid underground spaces occupied by buildings and subways, the small radius curve sections and the linear conditions of the merge and diverge areas of complex underground roads are usually limited in sight distance, and the changes in lighting and the side wall effects in the tunnels create visual loads and a sense of oppression for drivers, resulting in frequent traffic accidents.

[0003] At present, driving safety risk identification and active prevention and control technologies have been applied to the vehicle side (including the driver's mobile phone side) on some platforms, such as AutoNavi / Baidu Map Navigation and the National Road Freight Vehicle Public Supervision and Service Platform. Among them, AutoNavi / Baidu Map Navigation uses Beidou high-precision positioning technology to identify the real-time trajectory of the mobile phone (i.e., the vehicle), and can identify the relative status between vehicles using the same map navigation, determine risk vehicles through indicators such as sudden acceleration, sudden deceleration, sudden lane change, speeding / low speed, and inform the driver of this vehicle and nearby drivers using the same map navigation through navigation voice, and achieve targeted early warning; the National Road Freight Vehicle Public Supervision and Service Platform uses Beidou high-precision positioning technology to identify the real-time trajectory of built-in on-board equipment (i.e., vehicles) for all trucks with an axle load of more than 12 tons in the country, and determines whether the vehicle has driving safety risks through indicators such as speeding / low speed, and informs the driver of this vehicle through the text and voice of the on-board equipment, and achieves targeted early warning.

[0004] However, the above technical solutions are only for vehicles navigating on the same map, or trucks with an axle load of more than 12 tons, and are not sufficient to fully perceive the driving safety risks of all vehicles on a certain road section. More importantly, for complex underground roads, their semi-enclosed spaces will cause the Beidou high-precision positioning technology to fail, making it impossible to achieve risk perception based on the vehicle side.

[0005] Therefore, a road-vehicle targeted early warning method for driving safety risks on complex underground roads is needed, which can effectively solve the operational management technical problems of limited vehicle identification of driving safety risks based on the vehicle side, and improve the operational safety level of complex underground roads and the three-dimensional traffic in which they are located. Summary of the invention

[0006] In view of this, the purpose of the present invention is to overcome the defects in the prior art and provide a road-vehicle targeted early warning method for driving safety risks on complex underground roads, which can comprehensively perceive the driving safety risks of vehicles on the road section and accurately push early warning information to risk vehicles, thereby improving the operating safety level of complex underground roads and the three-dimensional transportation where they are located.

[0007] The road-vehicle targeted early warning method for driving safety risks on complex underground roads of the present invention comprises:

[0008] Identify and track the vehicle to obtain vehicle identification and tracking results;

[0009] Based on the vehicle identification and tracking results, determine the driving safety field strength at the target point in the road space;

[0010] If the intensity of the driving safety field at the target point exceeds the set threshold, the vehicle closest to the target point will be regarded as a risk vehicle and a warning message will be sent to the risk vehicle.

[0011] Furthermore, the driving safety field strength E(x,y) at the target point in the road space is determined according to the following formula:

[0012]

[0013] Among them, E B (x,y) is the field strength of the road boundary field at the target point (x,y), is the field strength of the driving potential energy field generated by vehicle i at (x, y), |·| represents the modulus of the vector, ω B ,ω V is the weight coefficient, ω B +ω V =1.

[0014] Further, the field strength E of the road boundary field at the target point (x, y) is determined according to the following formula: B (x,y):

[0015]

[0016] Among them, (y left -y) is the distance vector from the target point (x, y) to the left boundary line of the road, (y right -y) is the distance vector from the target point (x, y) to the right boundary line of the road, and η is the road boundary field coefficient.

[0017] Furthermore, the field strength of the driving potential energy field generated by vehicle i at (x, y) is determined according to the following formula:

[0018]

[0019] Among them, m i is the mass of vehicle i; λ and β are coefficients; θ is the spatial coordinates of the target point (x, y) to the center of mass of vehicle i The angle of is the position of vehicle i at time t; is the speed of vehicle i at time t; is the acceleration of vehicle i at time t; is the pseudo-distance vector:

[0020]

[0021] in,

[0022] is the direction angle of vehicle i at time t; α is the coefficient, and τ is the safety distance threshold related to the ambient brightness.

[0023] Furthermore, the safety distance threshold τ related to the ambient brightness is determined according to the following formula:

[0024]

[0025] Among them, τ0 is the safety distance threshold of non-tunnel scenario; is the ambient brightness of the location of vehicle i at time t.

[0026] Furthermore, early warning information is sent to risky vehicles, including:

[0027] The vehicle ID is determined using machine vision-based license plate recognition technology and matched with the vehicle ID of the map navigation and / or the vehicle ID of trucks with an axle load of more than 12 tons in the national road freight vehicle public supervision and service platform. For successfully matched vehicles, early warning information is sent to the mobile phone and / or on-board equipment in the vehicle.

[0028] Furthermore, the method further includes: obtaining the risk type of the risk vehicle; the risk type includes being too close to the vehicle in front, lane deviation, and being too close to the side wall of the tunnel.

[0029] The beneficial effects of the present invention are as follows: a method for targeted road-vehicle early warning of driving safety risks on complex underground roads disclosed by the present invention, under the background of increasingly mature vehicle identification and tracking technology based on machine vision, identifies risky vehicles through the road side, and transmits information on risky vehicles to platforms such as Amap / Baidu Map Navigation and the National Road Freight Vehicle Public Supervision and Service Platform, and then uses these platforms to send early warning information to risky vehicles identified at the road side, thereby realizing targeted early warning based on road-vehicle communication and improving the operating safety level of complex underground roads and the three-dimensional transportation in which they are located. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0031] Figure 1 It is a schematic diagram of the process flow of the targeted early warning method of the present invention;

[0032] Figure 2 It is a schematic diagram of the targeted early warning based on road-vehicle communication of the present invention. DETAILED DESCRIPTION

[0033] The present invention is further described below in conjunction with the accompanying drawings, as shown in the drawings:

[0034] This embodiment discloses a road-vehicle targeted early warning method for driving safety risks on complex underground roads, including the following steps:

[0035] Identify and track the vehicle to obtain vehicle identification and tracking results;

[0036] Based on the vehicle identification and tracking results, determine the driving safety field strength at the target point in the road space;

[0037] If the intensity of the driving safety field at the target point exceeds the set threshold, the vehicle closest to the target point will be regarded as a risk vehicle and a warning message will be sent to the risk vehicle.

[0038] According to the environmental characteristics of semi-closed road areas of complex underground roads, the present invention aims at the technical problem of operation management in which the identification of vehicles with driving safety risks at the vehicle end is limited. A road-vehicle communication targeted early warning method based on road-side risk vehicle identification is proposed, which can improve the operation safety level of complex underground roads and the three-dimensional transportation system in which they are located.

[0039] In this embodiment, by identifying and tracking the vehicles, the position, speed, direction angle and acceleration of each vehicle i at time t can be obtained. The direction along the road is the x-axis, and the vertical direction is the y-axis. The direction angle is the angle between the moving direction of vehicle i at time t and the direction along the road (i.e., the x-axis direction). The existing technology can be used to identify and track the vehicle, thereby obtaining the above-mentioned vehicle identification and tracking results, which will not be repeated here.

[0040] In this embodiment, the traditional speed / acceleration-based driving safety risk identification method has the problem of separation between lateral and longitudinal risks. Therefore, in recent years, many scholars have proposed a risk quantification model based on driving safety fields, which enables unified quantification of lateral and longitudinal risks between vehicles.

[0041] Complex underground roads exist in the form of complex tunnels with multiple entry and exit points, circular radiation, etc. The small radius curve sections and the linear conditions of the merge and diverge areas usually have limited visibility, and the lighting changes and side wall effects in the tunnels create visual burden and oppression for the driver. Therefore, lateral deviations of vehicles often occur during driving, and lane changing behavior in merge and diverge areas will cause a large number of lateral and longitudinal conflicts. Therefore, the risk quantification model based on the driving safety field is currently a more suitable method for identifying vehicles with driving safety risks on complex underground roads.

[0042] However, the existing driving safety field model does not consider the impact of ambient light on driving safety risks. Since low light will increase the driver's reaction time, the lower the ambient brightness is at the same speed, the greater the driving safety risk is. Therefore, the present invention considers the impact of ambient brightness in the existing driving safety field model.

[0043] At time t, the driving safety field strength E(x,y) at the target point (x,y) in space is calculated using the following formula:

[0044]

[0045] Among them, E B (x,y) is the field strength of the road boundary field at the target point (x,y), is the field strength of the driving potential energy field generated by vehicle i at (x, y), |·| represents the modulus of the vector, ω B ,ω V is the weight coefficient, ω B +ω V = 1. The target point (x, y) can be any point.

[0046] The field strength of the road boundary field at (x, y) is calculated as follows:

[0047]

[0048] Among them, (y left -y) is the distance vector from the target point (x, y) to the left boundary line of the road, (y right -y) is the distance vector from the target point (x, y) to the right boundary line of the road, and η=3 is the road boundary field coefficient.

[0049] The field strength of the driving potential energy field generated by vehicle i at (x, y) is calculated as follows:

[0050]

[0051] Among them, m i is the mass of vehicle i; coefficient λ = 0.056, β = -0.169; θ is the spatial coordinates of the target point (x, y) to the center of mass of vehicle i The angle of is the position of vehicle i at time t; is the speed of vehicle i at time t; is the acceleration of vehicle i at time t; is a pseudo-distance vector, expressed as follows:

[0052]

[0053] in,

[0054] is the direction angle of vehicle i at time t; α = -0.029, τ is the safety distance threshold related to the ambient brightness, that is:

[0055]

[0056] Among them, τ0 = 2.717 is the safety distance threshold for non-tunnel scenarios, which can be set according to actual working conditions; is the ambient brightness of the location of vehicle i at time t. Indicates base 10 The logarithm of .

[0057] In this embodiment, when |E(x,y)| exceeds a given threshold, it can be considered that the vehicle i closest to the point (x,y) is ^ The system identifies risky vehicles and obtains the risk type of risky vehicles, such as being too close to the vehicle in front, lane deviation, or being too close to the tunnel sidewall. The threshold is set according to the actual working conditions. At the same time, the vehicle ID is determined by license plate recognition technology based on machine vision, and matched with the vehicle ID of map navigation such as Amap and Baidu (the driver will enter the vehicle license plate in the navigation to avoid restricted traffic function) / the vehicle ID of trucks with an axle load of more than 12 tons in the National Road Freight Vehicle Public Supervision and Service Platform (all trucks with an axle load of more than 12 tons have license plates), so as to send early warning information to the mobile phone / vehicle-mounted device in the vehicle. The information targeted transmission diagram is as follows: Figure 2 shown.

[0058] The present invention provides an objective and scientific targeted early warning method for vehicle driving risks, which can effectively solve the operational management technical problem of limited identification of vehicles with driving safety risks based on the vehicle side, and realize targeted early warning of risk vehicles based on road-to-vehicle communication, thereby improving the operational safety level of complex underground roads and the three-dimensional transportation system in which they are located.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A targeted early warning method for vehicles on complex underground roads with safety risks, characterized by: include: Identify and track the vehicle to obtain vehicle identification and tracking results; Based on the vehicle identification and tracking results, determine the driving safety field strength at the target point in the road space; If the intensity of the driving safety field at the target point exceeds the set threshold, the vehicle closest to the target point will be regarded as a risk vehicle and a warning message will be sent to the risk vehicle.

2. The method for targeted early warning of vehicle driving safety risks on complex underground roads according to claim 1 is characterized by: The driving safety field strength E(x,y) at the target point in the road space is determined according to the following formula: Among them, E B (x,y) is the field strength of the road boundary field at the target point (x,y), is the field strength of the driving potential energy field generated by vehicle i at (x, y), |·| represents the modulus of the vector, ω B ,ω V is the weight coefficient, ω B +ω V =1.

3. The method for targeted early warning of vehicle driving safety risks on complex underground roads according to claim 2 is characterized by: The field strength E of the road boundary field at the target point (x, y) is determined according to the following formula: B (x,y): Among them, (y left -y) is the distance vector from the target point (x, y) to the left boundary line of the road, (y right -y) is the distance vector from the target point (x, y) to the right boundary line of the road, and η is the road boundary field coefficient.

4. The method for targeted early warning of vehicle driving safety risks on complex underground roads according to claim 2 is characterized by: Determine the field strength of the driving potential energy field generated by vehicle i at (x, y) according to the following formula: Among them, m i is the mass of vehicle i; λ and β are coefficients; θ is the spatial coordinates of the target point (x, y) to the center of mass of vehicle i The angle of is the position of vehicle i at time t; is the speed of vehicle i at time t; is the acceleration of vehicle i at time t; is the pseudo-distance vector: is the direction angle of vehicle i at time t; α is the coefficient, and τ is the safety distance threshold related to the ambient brightness.

5. The method for targeted early warning of vehicle driving safety risks on complex underground roads according to claim 4 is characterized by: The safety distance threshold τ related to the ambient brightness is determined according to the following formula: Among them, τ0 is the safety distance threshold of non-tunnel scenario; is the ambient brightness of the location of vehicle i at time t.

6. The method for targeted early warning of vehicle driving safety risks on complex underground roads according to claim 4 is characterized by: Send warning information to risk vehicles, including: The vehicle ID is determined using machine vision-based license plate recognition technology and matched with the vehicle ID of the map navigation and / or the vehicle ID of trucks with an axle load of more than 12 tons in the national road freight vehicle public supervision and service platform. For successfully matched vehicles, early warning information is sent to the mobile phone and / or on-board equipment in the vehicle.

7. The method for targeted early warning of vehicle driving safety risks on complex underground roads according to claim 1 is characterized by: Also includes: Obtain the risk type of the risk vehicle; The risk types include being too close to the vehicle ahead, lane departure and being too close to the tunnel wall.

Images