Abnormal driving warning method, device, system and storage medium

Abstract

The application is suitable for the field of intelligent traffic technology, and provides an abnormal driving early warning method, device, system and computer readable storage medium. The method comprises the following steps: receiving road reference information from a roadside sensing device; judging whether there is an abnormal driving target vehicle in the sensing area of the roadside sensing device according to the road reference information; if yes, determining a specified vehicle which has an accident risk with the target vehicle in the sensing area according to the road reference information; and sending early warning information to the vehicle-mounted terminal of the specified vehicle. The application can timely find abnormal driving vehicles on the road, find out the specified vehicles affected by the abnormal driving vehicles, send early warning to the specified vehicles, greatly reduce the risk of normal driving vehicles, and will not disturb other vehicles not affected by the abnormal driving vehicles, which is conducive to maintaining the stability of traffic order.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of intelligent transportation, and particularly relates to an abnormal driving early warning method, device, system and computer readable storage medium. BACKGROUND

[0002] With the development of science and technology and the continuous improvement of people's living standards, the field of automobiles has also developed rapidly, widely affecting people's daily life and travel mode.

[0003] Maintaining correct driving awareness when driving is the basis for safe driving of drivers. However, the phenomenon of abnormal driving (running red lights, speeding, illegal parking, etc.) in reality brings great safety hazards to traffic driving, and if other drivers fail to notice in time, passive collision accidents may occur. SUMMARY

[0004] The application embodiment provides an abnormal driving early warning method, device, system and computer readable storage medium, which can determine a specified vehicle that has an accident risk with an abnormal driving vehicle, and send early warning information to a vehicle-mounted terminal of the specified vehicle, thereby reducing safety hazards.

[0005] In a first aspect, the application embodiment provides an abnormal driving early warning method, comprising:

[0006] receiving road reference information from a roadside perception device;

[0007] determining, according to the road reference information, whether there is a target vehicle that abnormally drives in a perception area of the roadside perception device;

[0008] if so, determining, according to the road reference information, a specified vehicle that has an accident risk with the target vehicle in the perception area;

[0009] sending early warning information to a vehicle-mounted terminal of the specified vehicle.

[0010] According to the road reference information, determining whether there is a target vehicle that abnormally drives in a perception area of the roadside perception device, comprising:

[0011] determining, according to vehicle state information and map information of each vehicle, whether there is a target vehicle that abnormally drives, wherein the road reference information comprises the vehicle state information of each vehicle in the perception area and the map information in the perception area;

[0012] and / or,

[0013] determine whether there is a target vehicle with a risk of running a red light according to vehicle state information of each vehicle, map information and signal light state information, wherein the road reference information comprises the vehicle state information of each vehicle in the perception area, the map information in the perception area and the signal light state information in the perception area;

[0014] and / or,

[0015] determine whether there is an emergency vehicle according to a vehicle type of each vehicle, wherein the road reference information comprises the vehicle state information of each vehicle in the perception area, and the vehicle state information comprises the vehicle type.

[0016] wherein the vehicle state information comprises a current position, a current speed and an acceleration, and the map information comprises a speed limit road section start point, a speed limit road section end point and a speed limit value; determine whether there is a target vehicle with speeding according to the vehicle state information of each vehicle and the map information, comprising:

[0017] obtain the speed limit value of the road section to which the current position of each vehicle belongs from the map information, and if the current speed is greater than the speed limit value, determine that the vehicle is a target vehicle with speeding;

[0018] and / or,

[0019] calculate a speed limit road section distance according to the speed limit road section start point and the speed limit road section end point of the road section to which the current position of each vehicle belongs; calculate a future speed in a preset time according to the current speed and the acceleration of each vehicle, wherein the preset time is obtained by dividing the speed limit road section distance by the speed limit value; obtain the speed limit value of the road section to which the current position of each vehicle belongs from the map information, and if the future speed is greater than the speed limit value, determine that the vehicle is a target vehicle with speeding.

[0020] wherein the vehicle state information comprises a current position, a driving direction and a current speed, the map information comprises a first position of a signal light, and the signal light state information comprises a second position of the signal light and a phase of the signal light; determine whether there is a target vehicle with a risk of running a red light according to the vehicle state information of each vehicle, the map information and the signal light state information, comprising:

[0021] obtain the first position of the signal light in front of the driving direction of each vehicle from the map information according to the current position of each vehicle;

[0022] determine the signal light state information corresponding to the signal light located at the first position according to the first position and the second position of the signal light, and obtain the phase of the signal light located at the first position from the signal light state information;

[0023] calculating a distance from the current position to the first position of the signal light;

[0024] calculating a remaining distance from the current position to the first position of the signal light, the remaining distance = the distance - vehicle length / 2 - a preset distance from the vehicle head to the stop line;

[0025] if the remaining distance is less than a preset total warning distance, a safety distance corresponding to the current speed is greater than the remaining distance, and the phase of the signal light at the second position is a red light or a yellow light, determining that the vehicle is a target vehicle with a risk of running a red light;

[0026] wherein the total warning distance = a preset signal light speed guidance distance + a preset warning time * current speed.

[0027] wherein, according to the road reference information, determining a specified vehicle in the perception area that has an accident risk with the target vehicle, comprises:

[0028] determining, according to the vehicle state information and the map information of each vehicle, a specified vehicle in the perception area that is on the same road segment, in the same lane, and travels in the same direction as the target vehicle and has a risk of being collided;

[0029] or, according to the vehicle state information and the map information of each vehicle, determining a specified vehicle in the perception area that is on a cross road segment and has a risk of being collided when intersecting.

[0030] wherein, the vehicle state information includes vehicle length, vehicle width, current position, driving direction, and current speed; according to the vehicle state information and the map information of each vehicle, determining a specified vehicle in the perception area that is on the same road segment, in the same lane, and travels in the same direction as the target vehicle and has a risk of being collided, comprises:

[0031] determining the road segment where each vehicle is located according to the current position of each vehicle and the map information;

[0032] selecting, from the other vehicles, a vehicle that is on the same road segment as the target vehicle, as a first candidate vehicle;

[0033] obtaining a first distance from the center axis of the first candidate vehicle to the center axis of the target vehicle, and selecting, from the set of first candidate vehicles, a vehicle whose first distance is less than a two-vehicle safety distance, as a second candidate vehicle, the two-vehicle safety distance = an average of the vehicle width of the target vehicle and the vehicle width of the first candidate vehicle + a preset safety distance value;

[0034] According to the driving direction and the current position of the target vehicle and the second candidate vehicle, a vehicle in front of the target vehicle and in the same driving direction as the target vehicle is selected from the set of second candidate vehicles as a third candidate vehicle;

[0035] According to the length, current position and current speed of the target vehicle and the third candidate vehicle, a collision time is calculated, the collision time = (real-time distance between the target vehicle and the third candidate vehicle - average value of the length of the target vehicle and the third candidate vehicle) / (current speed of the target vehicle - current speed of the third candidate vehicle);

[0036] If the collision time is less than a preset collision time, the third candidate vehicle is a designated vehicle at risk of being collided.

[0037] The vehicle state information includes current speed, current position and driving direction; according to the road reference information, a designated vehicle in the intersection section with the target vehicle and at risk of being collided when intersecting is determined, including:

[0038] According to the current position of each vehicle and the map information, the road section where each vehicle is located is determined respectively;

[0039] The upstream node and the downstream node of the road section where the target vehicle is located are obtained, and the upstream node and the downstream node of the road section where the other vehicle is located are obtained, the upstream node being the node in front in the driving direction of the two nodes of the road section, and the downstream node being the node behind in the driving direction of the two nodes of the road section;

[0040] From the other vehicles, a vehicle whose upstream node is the same as the upstream node of the road section where the target vehicle is located and whose downstream node is different from the downstream node of the road section where the target vehicle is located is selected as a first candidate vehicle;

[0041] According to the current speed, current position and driving direction of the first candidate vehicle and the target vehicle, a minimum encounter time of the first candidate vehicle and the target vehicle is calculated;

[0042] The intersection closest point of the first candidate vehicle and the target vehicle is calculated with the target vehicle as the center;

[0043] If the minimum encounter time is less than a preset collision time, and it is confirmed that the first candidate vehicle overlaps with the target vehicle at the intersection closest point, the first candidate vehicle is a designated vehicle at risk of being collided.

[0044] The vehicle in the same road section as the target vehicle is selected from the other vehicles as a first candidate vehicle, including:

[0045] obtaining an upstream node and a downstream node of a road section where the target vehicle is located, and obtaining an upstream node and a downstream node of a road section where the other vehicle is located, the upstream node being a node in front in a driving direction of two nodes of the road section, and the downstream node being a node behind in the driving direction of the two nodes of the road section;

[0046] selecting, from the other vehicles, a vehicle whose upstream node is the same as the upstream node of the road section where the target vehicle is located and whose downstream node is the same as the downstream node of the road section where the target vehicle is located, as a first candidate vehicle.

[0047] wherein, according to the current speed, the current position and the driving direction of the first candidate vehicle and the target vehicle, a minimum encounter time of the first candidate vehicle and the target vehicle is calculated, and a closest intersection point of the first candidate vehicle and the target vehicle is calculated with the target vehicle as the center, comprising:

[0048] according to the current position of the first candidate vehicle and the current position of the target vehicle, a distance between the two vehicles is calculated;

[0049] determining a heading angle and an azimuth angle of the first candidate vehicle according to the driving direction of the first candidate vehicle, and determining a heading angle and an azimuth angle of the target vehicle according to the driving direction of the target vehicle;

[0050] according to the current speed and the heading angle of the first candidate vehicle and the target vehicle, a relative speed is calculated, the relative speed = square root of a sum of square of a positive east direction relative speed vector and square of a positive north direction relative speed vector, the positive east direction relative speed vector = current speed of the second candidate vehicle * sine value of the heading angle of the second candidate vehicle - current speed of the target vehicle * sine value of the heading angle of the target vehicle, and the positive north direction relative speed vector = current speed of the second candidate vehicle * cosine value of the heading angle of the second candidate vehicle - current speed of the target vehicle * cosine value of the heading angle of the target vehicle;

[0051] according to the positive east direction relative speed vector and the positive north direction relative speed vector, a relative heading angle is calculated, the relative heading angle = arctan(positive east direction relative speed vector / positive north direction relative speed vector);

[0052] according to the azimuth angle of the first candidate vehicle and the target vehicle, a relative azimuth angle is calculated;

[0053] the minimum encounter time is calculated, the minimum encounter time = distance between the two vehicles * cos(relative heading angle - relative azimuth angle - π) / relative speed;

[0054] the closest encounter distance is calculated, the closest encounter distance = distance between the two vehicles * sin(relative heading angle - relative azimuth angle - π);

[0055] According to the two-vehicle distance, the closest encounter distance, the relative azimuth angle and the relative heading angle, a closest encounter point of the first candidate vehicle and the target vehicle is calculated with the target vehicle as the center.

[0056] The vehicle state information further includes a vehicle width and a vehicle length; and the confirming that the first candidate vehicle overlaps with the target vehicle at the closest encounter point includes:

[0057] According to the driving direction, the vehicle width and the vehicle length, four vertices of a second rectangle representing the target vehicle and four vertices of a first rectangle representing the first candidate vehicle are determined with the position of the target vehicle at the closest encounter point as the center;

[0058] Two edges of the four edges of the first rectangle intersecting at a vertex farthest from the second rectangle and two edges of the four edges of the second rectangle intersecting at a vertex farthest from the first rectangle are selected, and four projection axes are constructed using the selected four edges;

[0059] The first rectangle is projected onto each of the projection axes to obtain a first projection, and the second rectangle is projected onto each of the projection axes to obtain a second projection;

[0060] If the first projection and the second projection on the four projection axes overlap, it is confirmed that the first candidate vehicle overlaps with the target vehicle at the closest encounter point.

[0061] The current positions of the vehicles and the map information are used to determine the road segments on which the vehicles are located, respectively.

[0062] Two nodes of each road segment are obtained from the map information to form a node set.

[0063] Any two nodes in the node set are determined as a first candidate node pair.

[0064] The squares of the distances from the current position of a vehicle to the two nodes in the first candidate node pair are calculated to obtain a first distance value and a second distance value, and the square of the distance between the two nodes in the first candidate node pair is calculated to obtain a third distance value.

[0065] It is determined whether the sum of the first distance value and the third distance value is greater than or equal to the second distance value, or whether the sum of the second distance value and the third distance value is greater than or equal to the first distance value, and if so, the first candidate node pair is determined as a second candidate node pair.

[0066] calculate a perpendicular distance of the vehicle to a node link of two nodes in the second candidate node pair, determine the second candidate node pair with the perpendicular distance less than a preset road section width as a third candidate node pair;

[0067] perform a weighted operation on an included angle of a node link formed by two nodes in the third candidate node pair and the driving direction and the perpendicular distance to obtain a weight value, the weight value R = W1 * a numerical value of the perpendicular distance + W2 * a numerical value of the included angle, W1 is a weight coefficient of a distance feature, W2 is a weight coefficient of an angle feature, and W1 + W2 = 1;

[0068] determine a road section to which the third candidate node pair corresponding to the minimum weight value belongs as the road section on which the vehicle is located.

[0069] In a second aspect, an abnormal driving early warning device is provided, including:

[0070] a receiving module configured to receive road reference information from a roadside perception device;

[0071] a target determining module configured to determine, according to the road reference information, whether there is a target vehicle that abnormally drives, and further configured to determine, according to the road reference information, a specified vehicle that has an accident risk with the target vehicle.

[0072] In a third aspect, an abnormal driving early warning system is provided, including an abnormal driving early warning device and a roadside perception device;

[0073] the roadside perception device is configured to acquire road reference information and send the road reference information to the abnormal driving early warning device;

[0074] the abnormal driving early warning device is configured to determine, according to the road reference information, whether there is a target vehicle that abnormally drives, and further configured to determine, according to the road reference information, a specified vehicle that has an accident risk with the target vehicle.

[0075] In the third aspect, the abnormal driving early warning system further includes a vehicle terminal, and the roadside perception device includes a roadside detection module and a roadside communication terminal;

[0076] the vehicle terminal is in communication connection with the roadside communication terminal, configured to send vehicle terminal information to the roadside communication terminal, and further configured to receive early warning information from the roadside communication terminal;

[0077] the roadside detection module is in communication connection with the roadside communication terminal, configured to send perception information obtained by detection to the abnormal driving early warning device through the roadside communication terminal;

[0078] The road-side communication terminal is in communication connection with the abnormal driving early warning device, configured to send the received road reference information to the abnormal driving early warning device, wherein the road reference information comprises the perception information and the vehicle-end information; further configured to receive early warning information from the abnormal driving early warning device; and further configured to send the early warning information to the vehicle-mounted terminal.

[0079] In a fourth aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method of any one of the first aspect when executing the computer program.

[0080] In a fifth aspect, a computer readable storage medium is provided, which includes a computer program stored therein, and the computer program is executable on a processor to implement the method of any one of the first aspect.

[0081] In a sixth aspect, a computer program product is provided, which, when executed on an electronic device, causes the electronic device to perform the method of any one of the first aspect.

[0082] It can be understood that the beneficial effects of the above-mentioned second aspect to the sixth aspect can be referred to the related description of the first aspect, which will not be repeated here.

[0083] Compared with the prior art, the beneficial effects of the embodiments of the present application are as follows: the present application collects road reference information from a road-side perception device, judges whether there is an abnormal driving target vehicle in the perception area of the road-side perception device, and determines a specified vehicle in the perception area which has an accident risk with the target vehicle, so as to send early warning information to the vehicle-mounted terminal of the specified vehicle. The present application can timely find abnormal driving vehicles on the road, find out the specified vehicles affected by the abnormal driving vehicles, and send early warning to them, which greatly reduces the risk of normal driving vehicles, and at the same time, does not disturb other vehicles not affected by the abnormal driving vehicles, which is conducive to maintaining the stability of traffic order. BRIEF DESCRIPTION OF DRAWINGS

[0084] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0085] Figure 1 is a flowchart of an abnormal driving early warning method provided by an embodiment of the present application;

[0086] Figure 2 is a flowchart of a method for determining a specified vehicle according to an embodiment of the present application;

[0087] Figure 3 is a flowchart of a method for determining a specified vehicle according to an embodiment of the present application;

[0088] Figure 4 is a flowchart of a method for determining a specified vehicle according to an embodiment of the present application;

[0089] Figure 5 is a flowchart of a method for determining a specified vehicle according to an embodiment of the present application;

[0090] Figure 6 is a flowchart of a method for determining a specified vehicle according to an embodiment of the present application;

[0091] Figure 7 is a structural diagram of an abnormal driving early warning device according to an embodiment of the present application;

[0092] Figure 8 is a structural diagram of an abnormal driving early warning device according to an embodiment of the present application;

[0093] Figure 9 is a structural diagram of an abnormal driving early warning device according to an embodiment of the present application. DETAILED DESCRIPTION

[0094] In the following description, for purposes of explanation and not limitation, specific details are set forth, such as a particular sequence of actions, or techniques, in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, and circuits are omitted so as not to obscure the description of the present application with unnecessary detail.

[0095] It is to be understood that the terminology "includes", "has", "holds", "contains" and / or "comprising", when used in this specification and in the following claims, indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0096] It is also to be understood that the terminology "and / or" when used in this specification and in the following claims, refers to at least one of the items, or any combination of the items, that are possibly included in the associated list of items.

[0097] In addition, in the description of the present application and the appended claims, the terms "first", "second", "third", etc. are used only to distinguish descriptions and cannot be understood as indicating or implying relative importance.

[0098] Reference in the description of the present application to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Thus, the appearances of the phrases "in one embodiment", "in some embodiments", "in other embodiments", "in additional embodiments", and so on, in various places in the specification are not necessarily all referring to the same embodiment, unless otherwise specified. The terms "comprise", "comprising", "have", "having", "include", "including", and "contain", "containing", or variants thereof, mean "including but not limited to", unless otherwise specified.

[0099] The abnormal driving early warning method provided by the embodiments of the present application can be applied to the scene of road traffic safety management. The method is executed by an abnormal driving early warning device composed of software and / or hardware, which is generally integrated into an electronic device. The electronic device includes, but is not limited to, desktop computers, notebooks, palmtop computers, and cloud servers, and the like. The electronic device has the ability to communicate with vehicle-mounted devices and roadside sensing devices, and the communication mode can be selected from one or more of wireless network communication, ETC communication, and V2X communication. The vehicle-mounted device is, for example, a car control unit, a navigation device, a driving recorder, an ETC on-board unit, or a V2X on-board unit, and can also be a device held by a driver or passenger, such as a smart phone. The roadside sensing device includes one or more of a radar, a camera, an ETC roadside unit, or a V2X roadside unit.

[0100] Figure 1 is a flowchart of the abnormal driving early warning method provided by an embodiment of the present application. As shown in Figure 1 , the method includes the following steps:

[0101] S11, receiving road reference information from a roadside sensing device.

[0102] The road reference information includes vehicle state information of each vehicle in the target road within the sensing area of the roadside sensing device, as well as map information of the target road, intersection signal light state information, and the like. The vehicle state information of each vehicle includes the position and driving parameters of each vehicle, and can also include vehicle type, external size (length, width), and the like.

[0103] The vehicle state information is provided by an on-board device or a smart device on the vehicle to the roadside perception device, the roadside perception device collects the target detection result of the radar, the audio and video data of the camera, and the position and phase information of the traffic signal light, and comprehensively obtains the road reference information.

[0104] S12, according to the road reference information, judging whether there is an abnormally driving target vehicle in the perception area of the roadside perception device; if there is an abnormally driving target vehicle, executing step S13, otherwise, not doing anything.

[0105] The situation of judging whether there is an abnormally driving target vehicle includes but is not limited to the following situations:

[0106] Firstly, according to the vehicle state information and the map information of each vehicle in the perception area, whether there is a target vehicle driving at a speed exceeding the speed limit is judged, which is specifically as follows:

[0107] In the road reference information, the vehicle state information of each vehicle further includes the current position, the current speed and the acceleration, and the map information further includes the speed limit section start point, the speed limit section end point and the speed limit value. The speed limit includes the maximum speed limit and the minimum speed limit, and the speed limit value can be the maximum speed limit value, the minimum speed limit value or the average value of the two.

[0108] The speed limit value of the road section to which the current position of each vehicle belongs is obtained from the map information, and if the current speed is greater than the speed limit value, the vehicle is determined as a target vehicle driving at a speed exceeding the speed limit.

[0109] And / or, according to the speed limit section start point and the speed limit section end point of the road section to which the current position of each vehicle belongs, the speed limit section distance is calculated; the preset time for passing the speed limit section is obtained by dividing the speed limit section distance by the speed limit value, the future speed at a certain time within the preset time is calculated according to the current speed and the acceleration of each vehicle; the maximum speed limit value of the road section to which the current position of each vehicle belongs is obtained from the map information, and if the future speed is greater than the maximum speed limit value, the vehicle is determined as a target vehicle driving at a speed exceeding the speed limit.

[0110] Secondly, according to the vehicle state information, the map information and the signal light state information of each vehicle, whether there is a target vehicle with the risk of running a red light is judged, which is specifically as follows:

[0111] In the road reference information, the vehicle state information of each vehicle includes the current position, the driving direction, the current speed and the vehicle length, the map information includes the first position of the signal light, and the signal light state information includes the second position of the signal light and the phase of the signal light.

[0112] The roadside perception device obtains a traffic light phase and timing message (SPAT) of a traffic light signal to obtain the phase of the signal light, which can be used for vehicle speed guidance, green wave pushing scenarios, etc. The map information and the SPAT are used together to describe the correspondence between a road intersection and the traffic light at the intersection.

[0113] According to the current position of each vehicle, the first position of the signal light in front of the driving direction is obtained from the map information; according to the first position of the signal light in the map information and the second position of the signal light in the signal light state information, the first position is matched with the second position, the signal light state information corresponding to the signal light at the first position is determined, and the phase of the signal light at the first position is obtained from the signal light state information.

[0114] The first position and the second position can be represented by latitude and longitude. By matching the first position with the second position (both latitude and longitude are the same or similar), the map information and the signal light state information can be combined to obtain the phase of the signal light in front of the driving direction of the vehicle.

[0115] The distance from the current position to the first position of the signal light is calculated. It can be understood that the distance from the current position to the first position of the signal light is the actual driving track length of the vehicle, rather than the straight-line distance from the current position to the first position.

[0116] The remaining distance from the current position to the first position of the signal light is calculated, and the remaining distance = the distance - the vehicle length / 2 - the preset distance of the vehicle head to the stop line. The driving behavior is controlled by humans, and the distance of the vehicle head to the stop line when stopping can only be controlled within a certain range, and it is difficult to be absolutely accurate, so a preset distance of the vehicle head to the stop line is needed. If it is considered that there are already vehicles parked behind the stop line waiting for the red light, the position of the farthest parked vehicle can be used to determine the preset distance of the vehicle head to the stop line.

[0117] If the remaining distance is less than the total warning distance, the remaining distance is less than the safety distance corresponding to the current speed, and the phase of the signal light at the second position is red or yellow, the vehicle is determined to be a target vehicle with a risk of running a red light; wherein the total warning distance = the preset signal light speed guidance distance + the preset warning time * the current speed; the signal light speed guidance distance can be understood as: according to the current vehicle speed and the time required for the signal light phase to change to green, if the vehicle wants to pass the stop line exactly when the signal light changes to green, the distance from the current position of the vehicle to the stop line at least needs; the warning time is the time required for the warning system to detect an abnormal driving vehicle and make a warning; the safety distance corresponding to the current speed is generally valued at a speed value, for example, the safety distance of 100 km / h is at least 100 meters.

[0118] Thirdly, it is determined whether there is an emergency vehicle according to the vehicle type of each vehicle. The emergency vehicle includes but is not limited to a police car, a fire engine, an ambulance, a road rescue vehicle, a road engineering vehicle and the like.

[0119] S13, determining a specified vehicle in the perception area which has a collision risk with the target vehicle according to the road reference information.

[0120] For example, the specified vehicle in the perception area which has a collision risk with the target vehicle is determined to be in the same road section, the same lane and the same driving direction according to the vehicle state information and the map information of each vehicle; or the specified vehicle in the perception area which has a collision risk with the target vehicle is determined to be in the intersection road section according to the vehicle state information and the map information of each vehicle.

[0121] S14, sending the early warning information to the vehicle terminal of the specified vehicle.

[0122] If there is a specified vehicle which may be collided by the target vehicle abnormally driving, the decision information is generated, and the decision information is used to inform the specified vehicle to take the avoidance measures such as speed reduction or lane changing.

[0123] Further, the embodiment refines the screening method of the specified vehicle on the basis of the above embodiment.

[0124] The vehicle state information includes the length, the width, the current position, the driving direction and the current speed of the vehicle.

[0125] Figure 2 is a flowchart of the method for determining the specified vehicle provided by an embodiment of the application. As shown in Figure 2 the specified vehicle in the perception area which has a collision risk with the target vehicle is determined to be in the same road section, the same lane and the same driving direction according to the vehicle state information and the map information of each vehicle, comprising:

[0126] S1311, determining the road section where each vehicle is located according to the current position of each vehicle and the map information.

[0127] Two nodes (the starting point and the ending point) of each road section are obtained from the map information to form a node set; any two nodes in the node set are determined as a first candidate node pair; the square of the distance from the current position of the vehicle to each node in the first candidate node pair is calculated to obtain a first distance value and a second distance value, and the square of the distance between the two nodes in the first candidate node pair is calculated to obtain a third distance value; it is determined whether the sum of the first distance value and the third distance value is greater than or equal to the second distance value, or the sum of the second distance value and the third distance value is greater than or equal to the first distance value, if yes, the first candidate node pair is determined as a second candidate node pair.

[0128] The perpendicular distance of the node connecting line of the vehicle to two nodes in the second candidate node pair is calculated, and the second candidate node pair with a perpendicular distance less than the preset road section width is determined as the third candidate node pair.

[0129] The angle and the perpendicular distance of the node connecting line formed by the two nodes in the third candidate node pair and the driving direction are weighted to obtain a weight value, the weight value R = W1*value of the perpendicular distance + W2*value of the angle, W1 is a weight coefficient of the distance feature, W2 is a weight coefficient of the angle feature, and W1 + W2 = 1.

[0130] The weight value obtained by weighting the numerical values of the perpendicular distance and the angle represents the possibility of the vehicle moving away from the node connecting line, and the smaller the weight value, the closer the vehicle is to the node connecting line; the weight value of the vehicle and each third candidate node pair is calculated, and the road section to which the third candidate node pair corresponding to the minimum weight value belongs is determined as the road section where the vehicle is located. It can be understood that before calculation, the unit of measurement of the perpendicular distance of each vehicle to each node connecting line should be unified.

[0131] Figure 3 is a schematic diagram of a method for determining the road section where the vehicle is located according to an embodiment of the present application. As shown in Figure 3 (B1, B2) is one of the first candidate node pairs composed of any two nodes, and the current position A of the vehicle includes A1, A2, A3 and A4. Among them, for vehicles A1, A2 and A4, AB1 2 +B1B2 2 ≥AB2 2 , or AB2 2 +B1B2 2 ≥AB1 2 , then (B1, B2) is determined as the second candidate node pair of A1, A2 and A4. For vehicle A3, (B1, B2) does not satisfy the above formula, so (B1, B2) is not the second candidate node pair of A3. d1 is the perpendicular distance from A1 to the road section B1B2, and d2 is the perpendicular distance from A2 to the road section B1B2. If d1 < preset road section width < d2, then for vehicle A1, (B1, B2) can be determined as the third candidate node pair. When there are multiple third candidate node pairs for A1, the road section to which the third candidate node pair corresponding to the minimum weight value belongs is determined as the road section where the vehicle is located by calculating the weight value. If it is calculated that (B1, B2) is the third candidate node pair corresponding to the minimum weight value, it is determined that A1 is on the road section B1B2.

[0132] S1312, from other vehicles, a vehicle on the same road section as the target vehicle is selected as a first candidate vehicle.

[0133] The upstream node is the node in front of the driving direction of the two nodes of the road section, and the downstream node is the node behind the driving direction of the two nodes of the road section; using the above example, for the road section B1B2, if the vehicle A1 drives from B1 to B2, B1 is the downstream node, and B2 is the upstream node.

[0134] The upstream node and the downstream node of the road section where the target vehicle is located are obtained, the upstream node and the downstream node of the road section where the other vehicle is located are obtained, and the vehicle whose upstream node is the same as the upstream node of the road section where the target vehicle is located and whose downstream node is the same as the downstream node of the road section where the target vehicle is located is selected from the other vehicles as the first candidate vehicle.

[0135] S1313, the first distance from the center axis of the first candidate vehicle to the center axis of the target vehicle is obtained, and the vehicle whose first distance is less than the safe distance between two vehicles is selected from the set of first candidate vehicles as the second candidate vehicle.

[0136] Figure 4 It is a schematic diagram of the same lane and same direction driving judgment method provided by an embodiment of the application. As shown in the figure, Figure 4 A plane rectangular coordinate system with the target vehicle C as the origin and the driving direction of the target vehicle as the positive direction of the longitudinal axis is constructed; according to the current position of the first candidate vehicle D, the coordinate value (x, y) of the first candidate vehicle D in the coordinate system is obtained; the absolute value of the horizontal coordinate x of the first candidate vehicle D is the first distance from the center axis of the first candidate vehicle D to the center axis of the target vehicle C.

[0137] If |x|≤safe distance between two vehicles, it is determined that the first candidate vehicle D and the target vehicle C are in the same lane and can be used as the second candidate vehicle.

[0138] The safe distance between two vehicles is the average of the vehicle width of the target vehicle and the vehicle width of the first candidate vehicle + a preset safe distance value; the preset safe distance value is generally the distance that can avoid scratching between two vehicles, for example, at least the sum of the widths of the rearview mirrors of the two vehicles.

[0139] S1314, according to the driving direction and the current position of the target vehicle and the second candidate vehicle, the vehicle in front of the target vehicle and in the same driving direction as the target vehicle is selected from the set of second candidate vehicles as the third candidate vehicle.

[0140] If the longitudinal coordinate y of the second candidate vehicle D in the above coordinate system is greater than zero, it can be determined that the second candidate vehicle is in front of the target vehicle C;

[0141] According to the driving direction of the second candidate vehicle, the third candidate vehicle driving in the same direction as the target vehicle can be selected.

[0142] S1315, according to the length of the target vehicle and the third candidate vehicle, the current position and the current speed, the collision time is calculated.

[0143] Collision time = (real-time distance between the target vehicle and the third candidate vehicle - average value of the length of the target vehicle and the third candidate vehicle) / (current speed of the target vehicle - current speed of the third candidate vehicle).

[0144] S1316, if the collision time is less than the preset collision time, the third candidate vehicle is the designated vehicle with the risk of being collided.

[0145] If the collision time is less than the preset collision time, it is considered as a lower level warning that the target vehicle may have a forward collision; if the collision time is less than the preset collision time / 3, it is considered as a high level warning that the target vehicle may have a forward collision. According to the current speed of the two vehicles, the shortest time required for the target vehicle to brake to a stop or avoid collision with its current acceleration can be calculated as the preset collision time.

[0146] Both of the above situations can be considered as the third candidate vehicle having the risk of being collided from behind (being rear-ended), and the third candidate vehicle is determined as the designated vehicle, and the lane changing driving suggestion can be sent to the designated vehicle to avoid the risk.

[0147] Figure 5 is the flowchart of the method for determining the designated vehicle provided by another embodiment of the application. As shown in Figure 5 According to the road reference information, the designated vehicle in the perception area which is at the intersection section with the target vehicle and has the risk of being collided when converging is determined, comprising:

[0148] S1321, according to the current position of each vehicle and the map information, the road section where each vehicle is located is determined respectively.

[0149] S1322, from the other vehicles, the vehicle whose upstream node is the same as the upstream node of the road section where the target vehicle is located and whose downstream node is different from the downstream node of the road section where the target vehicle is located is selected as the first candidate vehicle.

[0150] If the upstream node of the other vehicle is the same as the upstream node of the road section where the target vehicle is located, but the downstream node is different from the downstream node of the road section where the target vehicle is located, the road section where the other vehicle is located and the road section where the target vehicle is located are intersection sections. The other vehicle is the vehicle coming from different roads but converging to the same road as the target vehicle, which is the first candidate vehicle.

[0151] S1323, according to the current speed, the current position and the driving direction of the first candidate vehicle and the target vehicle, the minimum encounter time of the first candidate vehicle and the target vehicle is calculated.

[0152] According to the current position of the first candidate vehicle and the current position of the target vehicle, the distance between the two vehicles is calculated in real time;

[0153] According to the driving direction of the first candidate vehicle, the heading angle and azimuth angle of the first candidate vehicle are determined, and according to the driving direction of the target vehicle, the heading angle and azimuth angle of the target vehicle are determined;

[0154] According to the current speed V b of the first candidate vehicle and the heading angle b, the current speed V a of the target vehicle and the heading angle a, the relative speed V r is calculated.

[0155] The relative speed vector of the first candidate vehicle and the target vehicle in the east direction is V x , and the relative speed vector of the second candidate vehicle and the target vehicle in the north direction is V y , the east direction relative speed vector = the current speed of the second candidate vehicle * the sine value of the heading angle of the second candidate vehicle - the current speed of the target vehicle * the sine value of the heading angle of the target vehicle, and the north direction relative speed vector = the current speed of the second candidate vehicle * the cosine value of the heading angle of the second candidate vehicle - the current speed of the target vehicle * the cosine value of the heading angle of the target vehicle.

[0156] The relative speed vector of the first candidate vehicle and the target vehicle in the east direction is V x , and the relative speed vector of the second candidate vehicle and the target vehicle in the north direction is V y , the east direction relative speed vector = the current speed of the second candidate vehicle * the sine value of the heading angle of the second candidate vehicle - the current speed of the target vehicle * the sine value of the heading angle of the target vehicle, and the north direction relative speed vector = the current speed of the second candidate vehicle * the cosine value of the heading angle of the second candidate vehicle - the current speed of the target vehicle * the cosine value of the heading angle of the target vehicle. x b a y b a ;

[0157] The relative speed = the square of the east direction relative speed vector and the square of the north direction relative speed vector, expressed as

[0158] According to the east direction relative speed vector and the north direction relative speed vector, the relative heading angle φ r is calculated, and the relative heading angle = arctan (east direction relative speed vector / north direction relative speed vector), expressed as

[0159] According to the azimuth angles of the first candidate vehicle and the target vehicle, the relative azimuth angle is calculated.

[0160] The minimum encounter time is calculated, and the minimum encounter time = the distance between the two vehicles * cos (relative heading angle - relative azimuth angle - π) / relative speed.

[0161] S1324, the first candidate vehicle and the target vehicle are calculated as the center of the target vehicle. ​

[0162] calculate the closest approach distance, the closest approach distance = the distance between the two vehicles * sin (the relative heading angle - the relative bearing angle - π);

[0163] According to the distance between the two vehicles, the closest approach distance, the relative bearing angle and the relative heading angle, a first candidate vehicle and the target vehicle are calculated to intersect at a closest approach point.

[0164] S1325, if the minimum approach time is less than the preset collision time, and it is confirmed that the first candidate vehicle overlaps the target vehicle at the closest approach point, the first candidate vehicle is the designated vehicle at risk of being collided.

[0165] Confirming that the first candidate vehicle overlaps the target vehicle at the closest approach point includes:

[0166] According to the driving direction, the vehicle width and the vehicle length, four vertices of a second rectangle representing the target vehicle and four vertices of a first rectangle representing the first candidate vehicle are determined, with the position of the target vehicle at the closest approach point as the center.

[0167] Select two edges of the four edges of the first rectangle that intersect at the vertex farthest from the second rectangle, and select two edges of the four edges of the second rectangle that intersect at the vertex farthest from the first rectangle, to build four projection axes with the selected four edges.

[0168] Project the first rectangle onto each projection axis to obtain a first projection, and project the second rectangle onto each projection axis to obtain a second projection.

[0169] If the first projection and the second projection on the four projection axes overlap, it is confirmed that the first candidate vehicle overlaps the target vehicle at the closest approach point.

[0170] Figure 6 is a schematic diagram of a two-vehicle overlap judgment method provided by an embodiment of the present application. As shown in Figure 6 A plane rectangular coordinate system is established with the position of the target vehicle C at the closest approach point as the center and the driving direction of the target vehicle C as the positive direction of the Y axis, and four vertices of a rectangle representing the target vehicle C and four vertices of a rectangle representing the first candidate vehicle E are determined on the coordinate system. Four projection axes Axis1, Axis2, Axis3 and Axis4 are established by taking two outer edges of each of the two rectangles, and the four vertices of the two vehicles are projected onto Axis1 to obtain the scalar of each vertex of the two vehicles on Axis1, and the maximum and minimum values of the projection points are obtained by comparison. If Y minE > Y maxC (indicates that E approaches before C after intersection) or Y maxE < Y minC(Indicates that E is behind C after intersection), which means that there is no collision risk between the two vehicles; otherwise, it means that there is overlap between the two vehicles when projected on Axis1 axis, and C collides with E after intersection; similarly, continue to calculate whether there is overlap between the projected points on Axis2, Axis3, Axis4 according to the above method, if there is overlap between them, it means that there is a collision risk between the two vehicles.

[0171] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. Steps with the same or similar content can be referred to each other and will not be described repeatedly.

[0172] The abnormal driving early warning method corresponding to the above embodiment, Figure 7 The structure block diagram of the abnormal driving early warning device provided by the embodiments of the present application is shown, only the parts related to the embodiments of the present application are shown for the convenience of description.

[0173] Referring to Figure 7 The device 70 comprises:

[0174] The receiving module 71 is configured to receive road reference information from the roadside perception device;

[0175] The target determination module 72 is configured to determine whether there is a target vehicle with abnormal driving according to the road reference information, and is further configured to determine a specified vehicle with accident risk with the target vehicle according to the road reference information.

[0176] Further, Figure 8 is a structure example diagram of the abnormal driving early warning system provided by the embodiments of the present application. As Figure 8 shown, the abnormal driving early warning system comprises: an abnormal driving early warning device 70 and a roadside perception device 80;

[0177] The roadside perception device 80 is configured to obtain road reference information and send the road reference information to the abnormal driving early warning device 70;

[0178] The abnormal driving early warning device 70 is configured to determine whether there is a target vehicle with abnormal driving according to the road reference information, and is further configured to determine a specified vehicle with accident risk with the target vehicle according to the road reference information.

[0179] Among them, the abnormal driving early warning system further comprises a vehicle terminal 90, and the roadside perception device 80 comprises a roadside detection module and a roadside communication terminal;

[0180] The vehicle-mounted terminal 90 includes a GNSS module, an antenna module, a central processing module, a security authentication module, and a CAN module, etc. It is connected to the roadside communication terminal to send vehicle-mounted information to the roadside communication terminal; it is also used to receive early warning information from the roadside communication terminal.

[0181] The roadside detection module includes a radar module, a camera module, etc., and is connected to the roadside communication terminal to send the detected perception information to the abnormal driving warning device 70 through the roadside communication terminal.

[0182] The roadside communication terminal is connected to the abnormal driving warning device 70 and is used to send the received road reference information to the abnormal driving warning device 70. The road reference information includes perception information and vehicle-side information. It is also used to receive warning information from the abnormal driving warning device 70 and to send the warning information to the vehicle-mounted terminal 90.

[0183] It should be noted that the information interaction and execution process between the above-mentioned devices / modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0184] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0185] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 9 As shown, the electronic device of this embodiment includes: at least one processor 60 ( Figure 9 (Only one is shown in the diagram), memory 61, and computer program 62 stored in said memory 61 and executable on said at least one processor 60, which, when executed, implements the steps in any of the above method embodiments.

[0186] The electronic device can be a desktop computer, a notebook computer, a palm computer, a cloud server, and the like. Those skilled in the art can understand that Figure 9 The electronic device is only an example and does not constitute a limitation, and can include more or fewer components than shown, or combine certain components, or include different components, such as an input / output device, a network access device, and the like.

[0187] The processor 60 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0188] The memory 61 can be an internal storage unit of the electronic device, such as a hard disk or a memory, in some embodiments. The memory 61 can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like, in other embodiments. Further, the memory 61 can include both an internal storage unit and an external storage device. The memory 61 is used to store an operating system, application programs, a boot loader, data, and other programs, such as program codes of the computer program, and the like. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0189] The embodiments of the present application also provide a computer readable storage medium storing a computer program, and the computer program is executed by a processor to implement the steps in the above various method embodiments.

[0190] The embodiments of the present application provide a computer program product, and when the computer program product is run on a mobile terminal, the mobile terminal is caused to implement the steps in the above various method embodiments.

[0191] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the present application can implement all or part of the processes in the above-mentioned embodiment methods through a computer program to instruct relevant hardware to complete, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can at least include any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium can not be an electrical carrier signal and a telecommunication signal.

[0192] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0193] Those of ordinary skill in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0194] In the embodiments provided by the present application, it should be understood that the disclosed devices / apparatuses and methods can be implemented in other ways. For example, the above-described device / apparatus embodiments are merely illustrative, and the division of the modules or units is merely a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0195] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may also be distributed to multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiment scheme according to actual needs.

[0196] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. An abnormal travel warning method characterized by comprising: The method comprises the following steps: receiving road reference information from a roadside perception device, wherein the roadside perception device collects radar target detection results, camera audio and video data, and traffic signal lamp position and phase information to obtain the road reference information; determining whether there is an abnormally driving target vehicle in a perception area of the roadside perception device according to the road reference information; if yes, determining a specified vehicle in the perception area which has an accident risk with the target vehicle according to the road reference information; sending early warning information to a vehicle terminal of the specified vehicle; determining a specified vehicle in the perception area which has an accident risk with the target vehicle according to the road reference information, comprising: determining a specified vehicle in the perception area which has a collision risk when intersecting with the target vehicle according to vehicle state information and map information of each vehicle; the vehicle state information comprises current speed, current position and driving direction; determining a specified vehicle in the perception area which has a collision risk when intersecting with the target vehicle according to the road reference information, comprising: determining a road segment where each vehicle is located according to the current position of each vehicle and the map information; obtaining an upstream node and a downstream node of the road segment where the target vehicle is located, and obtaining an upstream node and a downstream node of the road segment where the other vehicle is located, wherein the upstream node is the node in front of the driving direction among the two nodes of the road segment, and the downstream node is the node behind the driving direction among the two nodes of the road segment; selecting a vehicle whose upstream node is the same as the upstream node of the road segment where the target vehicle is located and whose downstream node is different from the downstream node of the road segment where the target vehicle is located from the other vehicles as a first candidate vehicle; calculating the minimum encounter time of the first candidate vehicle and the target vehicle according to the current speed, current position and driving direction of the first candidate vehicle and the target vehicle, comprising: calculating the distance between the two vehicles in real time according to the current position of the first candidate vehicle and the current position of the target vehicle; determining the heading angle and azimuth angle of the first candidate vehicle according to the driving direction of the first candidate vehicle, and determining the heading angle and azimuth angle of the target vehicle according to the driving direction of the target vehicle; According to the current speed V b of the first candidate vehicle and the current speed V a of the target vehicle and the heading angle a, the relative speed V r is calculated; The relative speed vector of the first candidate vehicle and the target vehicle in the east direction is V x The relative speed vector of the second candidate vehicle and the target vehicle in the north direction is V y The east direction relative speed vector = the current speed of the second candidate vehicle * the sine value of the heading angle of the second candidate vehicle - the current speed of the target vehicle * the sine value of the heading angle of the target vehicle, and the north direction relative speed vector = the current speed of the second candidate vehicle * the cosine value of the heading angle of the second candidate vehicle - the current speed of the target vehicle * the cosine value of the heading angle of the target vehicle. relative speed = square root of the sum of the square of the relative speed vector in the east direction and the square of the relative speed vector in the north direction; The relative heading angle φ is calculated from the eastward relative velocity vector and the northward relative velocity vector r relative heading angle = arctan(eastward relative velocity vector / northward relative velocity vector) calculating the relative azimuth angle according to the azimuth angle of the first candidate vehicle and the target vehicle; minimum encounter time = distance between the two vehicles * cos (relative heading angle - relative azimuth angle - π) / relative speed; calculating the intersection closest point of the first candidate vehicle and the target vehicle with the target vehicle as the center, comprising: calculating the closest encounter distance, closest encounter distance = distance between the two vehicles * sin (relative heading angle - relative azimuth angle - π); calculating the intersection closest point of the first candidate vehicle and the target vehicle with the target vehicle as the center according to the distance between the two vehicles, the closest encounter distance, the relative azimuth angle and the relative heading angle. If the minimum encounter time is less than a preset collision time, and it is confirmed that the first candidate vehicle has an overlap with the target vehicle at the intersection closest point, the first candidate vehicle is a designated vehicle with a risk of being collided.

2. The abnormal travel early warning method according to claim 1, characterized by, According to the road reference information, it is determined whether there is an abnormally driving target vehicle in the sensing area of the road side sensing device, including: According to the vehicle state information and the map information of each vehicle, it is determined whether there is a target vehicle driving at a speed exceeding the speed limit, and the road reference information includes the vehicle state information of each vehicle in the sensing area and the map information in the sensing area. And / or, According to the vehicle state information, the map information and the signal light state information of each vehicle, it is determined whether there is a target vehicle with a risk of running a red light, and the road reference information includes the vehicle state information of each vehicle in the sensing area, the map information in the sensing area and the signal light state information in the sensing area. And / or, According to the vehicle type of each vehicle, it is determined whether there is an emergency vehicle, and the road reference information includes the vehicle state information of each vehicle in the sensing area, and the vehicle state information includes the vehicle type.

3. The abnormal travel warning method according to claim 2, characterized by, The vehicle state information includes the current position, the current speed and the acceleration, and the map information includes the speed limit section start point, the speed limit section end point and the speed limit value. According to the vehicle state information and the map information of each vehicle, it is determined whether there is a target vehicle driving at a speed exceeding the speed limit, including: The speed limit value of the section to which the current position of each vehicle belongs is obtained from the map information, and if the current speed is greater than the speed limit value, the vehicle is determined as a target vehicle driving at a speed exceeding the speed limit. And / or, The speed limit section distance is calculated according to the speed limit section start point and the speed limit section end point of the section to which the current position of each vehicle belongs, the future speed in a preset time is calculated according to the current speed and the acceleration of each vehicle, the preset time is obtained by dividing the speed limit section distance by the speed limit value, and the speed limit value of the section to which the current position of each vehicle belongs is obtained from the map information, and if the future speed is greater than the speed limit value, the vehicle is determined as a target vehicle driving at a speed exceeding the speed limit.

4. The abnormal travel warning method according to claim 2, characterized by, The vehicle state information includes the current position, the driving direction and the current speed, the map information includes the first position of the signal light, and the signal light state information includes the second position of the signal light and the phase of the signal light. According to the vehicle state information, the map information and the signal light state information of each vehicle, it is determined whether there is a target vehicle with a risk of running a red light, including: According to the current position of each vehicle, the first position of the signal light in front of the driving direction is obtained from the map information. According to the first position and the second position of the signal light, the signal light state information corresponding to the signal light at the first position is determined, and the phase of the signal light at the first position is obtained from the signal light state information. The distance from the current position to the first position of the signal light is calculated. The remaining distance from the current position to the first position of the signal light is calculated. If the remaining distance is less than the total warning distance, the remaining distance is less than the safety distance corresponding to the current speed, and the phase of the signal light at the first position is a red light or a yellow light, it is determined that the vehicle is a target vehicle with a risk of running a red light. The total warning distance = a preset signal light speed guidance distance + a preset warning time * a current speed.

5. An abnormal travel warning device characterized by comprising: The method comprises the following steps: The receiving module is configured to receive road reference information from a roadside perception device, wherein the roadside perception device collects target detection results of a radar, audio and video data of a camera, and position and phase information of a traffic signal light, and comprehensively obtains the road reference information. The target determination module is configured to determine whether there is a target vehicle that abnormally travels according to the road reference information, and is further configured to determine a specified vehicle that has an accident risk with the target vehicle according to the road reference information. The method comprises the following steps: According to the vehicle state information and the map information of each vehicle, a specified vehicle that has a risk of being collided when intersecting with the target vehicle in a cross section is determined in the perception area. The vehicle state information comprises a current speed, a current position and a driving direction. According to the road reference information, a specified vehicle that has a risk of being collided when intersecting with the target vehicle in a cross section is determined in the perception area, comprising: According to the current position of each vehicle and the map information, the road section where each vehicle is located is determined. The upstream node and the downstream node of the road section where the target vehicle is located are obtained, and the upstream node and the downstream node of the road section where the other vehicle is located are obtained, wherein the upstream node is the node in front of the driving direction among the two nodes of the road section, and the downstream node is the node behind the driving direction among the two nodes of the road section. From the other vehicles, a vehicle whose upstream node is the same as the upstream node of the road section where the target vehicle is located and whose downstream node is different from the downstream node of the road section where the target vehicle is located is selected as a first candidate vehicle. According to the current speed, the current position and the driving direction of the first candidate vehicle and the target vehicle, the minimum encounter time of the first candidate vehicle and the target vehicle is calculated, comprising: The distance between the first candidate vehicle and the target vehicle is calculated in real time according to the current position of the first candidate vehicle and the current position of the target vehicle. According to the current speed V b of the first candidate vehicle and the current speed V a of the target vehicle and the heading angle a, the relative speed V r is calculated; The relative speed vector of the first candidate vehicle and the target vehicle in the east direction is V x The relative speed vector of the second candidate vehicle and the target vehicle in the north direction is V y The east direction relative speed vector = the current speed of the second candidate vehicle * the sine value of the heading angle of the second candidate vehicle - the current speed of the target vehicle * the sine value of the heading angle of the target vehicle, and the north direction relative speed vector = the current speed of the second candidate vehicle * the cosine value of the heading angle of the second candidate vehicle - the current speed of the target vehicle * the cosine value of the heading angle of the target vehicle. The heading angle and the azimuth angle of the first candidate vehicle are determined according to the driving direction of the first candidate vehicle, and the heading angle and the azimuth angle of the target vehicle are determined according to the driving direction of the target vehicle. The relative heading angle φ is calculated from the eastward relative velocity vector and the northward relative velocity vector r relative heading angle = arctan(eastward relative velocity vector / northward relative velocity vector) The relative speed = square root of the sum of the square of the relative speed vector in the east direction and the square of the relative speed vector in the north direction; The relative azimuth angle is calculated according to the azimuth angle of the first candidate vehicle and the azimuth angle of the target vehicle. The minimum encounter time = the distance between the two vehicles * cos (relative heading angle - relative azimuth angle - π) / relative speed; The closest intersection point of the first candidate vehicle and the target vehicle is calculated with the target vehicle as the center, comprising: The closest encounter distance = the distance between the two vehicles * sin (relative heading angle - relative azimuth angle - π). According to the distance between the two vehicles, the closest meeting distance, the relative azimuth angle and the relative heading angle, a first candidate vehicle and the target vehicle are calculated to obtain a closest intersection point of the first candidate vehicle and the target vehicle, with the target vehicle as the center; If the minimum meeting time is less than a preset collision time, and it is confirmed that the first candidate vehicle overlaps with the target vehicle at the closest intersection point, the first candidate vehicle is a designated vehicle that has a risk of being collided.

6. An abnormal travel warning system characterized by comprising: Comprise: Abnormal driving early warning device and roadside sensing equipment; The roadside sensing equipment is used for acquiring road reference information and sending the road reference information to the abnormal driving early warning device, wherein the roadside sensing equipment collects target detection results of a radar, audio and video data of a camera, and position and phase information of a traffic signal lamp, and comprehensively obtains road reference information; The abnormal driving early warning device is used for judging whether there is a target vehicle that abnormally drives according to the road reference information, and is also used for determining a designated vehicle that has a risk of an accident with the target vehicle according to the road reference information; According to the road reference information, the designated vehicle that has a risk of an accident with the target vehicle in a sensing area is determined, comprising: According to vehicle state information and map information of each vehicle, the designated vehicle that has a risk of being collided when intersecting with the target vehicle in a cross section is determined in the sensing area; The vehicle state information comprises a current speed, a current position and a driving direction; according to the road reference information, the designated vehicle that has a risk of being collided when intersecting with the target vehicle in a cross section is determined in the sensing area, comprising: According to the current position of each vehicle and the map information, the road section where each vehicle is located is determined respectively; The upstream node and the downstream node of the road section where the target vehicle is located are acquired, and the upstream node and the downstream node of the road section where other vehicles are located are acquired, wherein the upstream node is the node in front of the two nodes of the road section in the driving direction, and the downstream node is the node behind the two nodes of the road section in the driving direction; From the other vehicles, the vehicle whose upstream node is the same as the upstream node of the road section where the target vehicle is located and whose downstream node is different from the downstream node of the road section where the target vehicle is located is selected as a first candidate vehicle; According to the current speed, the current position and the driving direction of the first candidate vehicle and the target vehicle, the minimum meeting time of the first candidate vehicle and the target vehicle is calculated, comprising: The distance between the two vehicles is calculated in real time according to the current position of the first candidate vehicle and the current position of the target vehicle; The heading angle and the azimuth angle of the first candidate vehicle are determined according to the driving direction of the first candidate vehicle, and the heading angle and the azimuth angle of the target vehicle are determined according to the driving direction of the target vehicle; According to the current speed V b of the first candidate vehicle and the current speed V a of the target vehicle and the heading angle a, the relative speed V r is calculated. The relative speed vector of the first candidate vehicle and the target vehicle in the east direction is V x The relative speed vector of the second candidate vehicle and the target vehicle in the north direction is V y The east direction relative speed vector = the current speed of the second candidate vehicle * the sine value of the heading angle of the second candidate vehicle - the current speed of the target vehicle * the sine value of the heading angle of the target vehicle, and the north direction relative speed vector = the current speed of the second candidate vehicle * the cosine value of the heading angle of the second candidate vehicle - the current speed of the target vehicle * the cosine value of the heading angle of the target vehicle. The relative speed is the square root of the sum of the square of the relative speed vector in the east direction and the square of the relative speed vector in the north direction; The relative heading angle φ is calculated from the eastward relative velocity vector and the northward relative velocity vector r relative heading angle = arctan(eastward relative velocity vector / northward relative velocity vector) The relative azimuth angle is calculated according to the azimuth angle of the first candidate vehicle and the azimuth angle of the target vehicle; The minimum meeting time is the distance between the two vehicles*cos(relative heading angle-relative azimuth angle-π) / relative speed; The closest intersection point of the first candidate vehicle and the target vehicle is calculated with the target vehicle as the center, comprising: calculating a closest approach distance, the closest approach distance = the distance between the two vehicles * sin (the relative heading angle - the relative bearing angle - π); calculating a closest approach point between the first candidate vehicle and the target vehicle, taking the target vehicle as the center, according to the distance between the two vehicles, the closest approach distance, the relative bearing angle and the relative heading angle; if the minimum approach time is less than the preset collision time, and it is confirmed that the first candidate vehicle overlaps with the target vehicle at the closest approach point, the first candidate vehicle is the designated vehicle with the collision risk.

7. A computer-readable storage medium storing a computer program, wherein the computer program comprises the following steps of: receiving a request for a resource from a client; determining whether the client is authorized to access the resource; and if the client is authorized to access the resource, providing the resource to the client. The computer program, when executed by a processor, implements the method of any one of claims 1 to 4.

Images