CN111951548B - Vehicle driving risk determination method, device, system and medium - Google Patents
Vehicle driving risk determination method, device, system and medium Download PDFInfo
- Publication number
- CN111951548B CN111951548B CN202010751119.8A CN202010751119A CN111951548B CN 111951548 B CN111951548 B CN 111951548B CN 202010751119 A CN202010751119 A CN 202010751119A CN 111951548 B CN111951548 B CN 111951548B
- Authority
- CN
- China
- Prior art keywords
- motor vehicle
- flow
- driving risk
- current
- weather
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Abstract
The invention discloses a vehicle driving risk determining method, device, system and medium. The method comprises the following steps: when the vehicle is in a state of allowing the vehicle to pass through the indication, acquiring the current vehicle flow and the current non-vehicle flow of the corresponding target crosswalk area; acquiring historical motor vehicle flow and historical non-motor vehicle flow corresponding to the target crosswalk region; obtaining a first type of weather influence factor based on the motor vehicle traffic information corresponding to the current motor vehicle flow and the motor vehicle traffic information corresponding to the historical motor vehicle flow; obtaining a second type of weather influencing factor based on the non-motor vehicle traffic information corresponding to the current non-motor vehicle flow and the non-motor vehicle traffic information corresponding to the historical non-motor vehicle flow; and determining the driving risk corresponding to the current motor vehicle based on the first weather influence factors, the second weather influence factors and a preset threshold value. The invention improves the accuracy of determining the driving risk by using finer granularity of the judgment parameters.
Description
Technical Field
The present application relates to the field of internet communications technologies, and in particular, to a method, an apparatus, a system, and a medium for determining a driving risk of a vehicle.
Background
With the rapid development of science and technology, automobiles have become indispensable tools for riding instead of walking in people's life. With technological development and demands of people, technologies on automobiles are also greatly developed, and related auxiliary driving systems can help to improve driving experience of drivers and riding experience of passengers.
Crosswalk (Pedestrian crossing) is a walking range where a specified pedestrian on a roadway crosses a lane, which is marked by a marking such as a zebra line or other means, and is a place on the roadway where the marking is required to be decelerated to allow the pedestrian to cross the lane, in order to prevent the pedestrian from being injured when the vehicle is traveling rapidly. In the related art, when a vehicle approaches a crosswalk, considering that pedestrians which do not comply with traffic regulations can break a red light to pass through the crosswalk regardless of traffic instructions, a driving risk early warning notification is often directly generated so as to prompt the vehicle to decelerate or stop. The driving risk early warning notification for prompting the vehicle to change the driving state is not distinguished by the specific condition of the crosswalk, so that false warning is easy to occur, and the road passing efficiency is reduced. Accordingly, there is a need to provide a more accurate and efficient determination of vehicle driving risk.
Disclosure of Invention
In order to solve the problems of low determination accuracy and the like when determining the driving risk of a vehicle in the prior art, the application provides a vehicle driving risk determination method, device, system and medium:
according to an aspect of the present application, there is provided a vehicle driving risk determination method including:
when the vehicle is in a state of allowing the vehicle to pass through the indication, acquiring the current vehicle flow and the current non-vehicle flow of the corresponding target crosswalk area;
acquiring historical motor vehicle flow and historical non-motor vehicle flow corresponding to the target crosswalk region;
obtaining a first type of weather influence factor based on the motor vehicle traffic information corresponding to the current motor vehicle flow and the motor vehicle traffic information corresponding to the historical motor vehicle flow;
obtaining a second type of weather influencing factor based on the non-motor vehicle traffic information corresponding to the current non-motor vehicle flow and the non-motor vehicle traffic information corresponding to the historical non-motor vehicle flow;
and determining the driving risk corresponding to the current motor vehicle based on the first weather influence factors, the second weather influence factors and a preset threshold value.
According to another aspect of the present application, there is provided a vehicle driving risk determination apparatus including:
A first acquisition module: the method comprises the steps of acquiring current motor vehicle flow and current non-motor vehicle flow of a corresponding target crosswalk area when the motor vehicle is in a traffic permission indication state;
and a second acquisition module: the method comprises the steps of acquiring historical motor vehicle flow and historical non-motor vehicle flow corresponding to the target crosswalk area;
the first obtaining module: the weather-influencing factor obtaining module is used for obtaining a first type of weather-influencing factor based on the motor vehicle traffic information corresponding to the current motor vehicle flow and the motor vehicle traffic information corresponding to the historical motor vehicle flow;
and a second obtaining module: the method comprises the steps of obtaining a second type of weather influencing factor based on non-motor vehicle traffic information corresponding to the current non-motor vehicle flow and non-motor vehicle traffic information corresponding to the historical non-motor vehicle flow;
a driving risk determination module: and the method is used for determining the driving risk corresponding to the current motor vehicle based on the first weather influence factors, the second weather influence factors and a preset threshold value.
According to another aspect of the present application there is provided a vehicle driving risk determination system comprising an acquisition device, a data processing platform and a vehicle driving risk determination apparatus as described above:
The acquisition device: the image data is used for collecting image data indicating a target crosswalk area and sending the image data to the data processing platform;
the data processing platform: for determining a current motor vehicle flow, a current non-motor vehicle flow, a historical motor vehicle flow and a historical non-motor vehicle flow corresponding to the target crosswalk region based on the received image data, and for transmitting the corresponding motor vehicle flow and non-motor vehicle flow to the vehicle driving risk determination means.
According to another aspect of the present application, there is provided an electronic device comprising a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement a vehicle driving risk determination method as described above.
According to another aspect of the present application, there is provided a computer readable storage medium having stored therein at least one instruction or at least one program loaded and executed by a processor to implement a vehicle driving risk determination method as described above.
According to another aspect of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions so that the computer device performs the vehicle driving risk determination method described above.
The vehicle driving risk determining method, device, system and medium provided by the application have the following technical effects:
according to the application, for the same crosswalk, the driving risk of the current motor vehicle is determined according to the influence degree of the current weather conditions on the corresponding traffic flow of the motor vehicle and the traffic flow of the non-motor vehicle, wherein the determination of the influence degree is combined with the traffic information corresponding to the current flow and the traffic information corresponding to the historical flow, and the accuracy of determining the driving risk is improved by using finer granularity of the judging parameters. According to the method and the device, the weather influence factors can be determined according to specific road conditions (including the current road conditions and the historical road conditions) so as to realize dynamic determination of driving risks, and therefore early warning notification considering driving safety and road passing efficiency can be guaranteed to be output.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an application environment provided by an embodiment of the present invention;
FIG. 2 is a schematic diagram of an application environment provided by an embodiment of the present invention;
fig. 3 is a schematic flow chart of a vehicle driving risk determination method according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of obtaining a first type of weather influencing factor based on vehicle traffic information corresponding to a current vehicle flow and vehicle traffic information corresponding to a historical vehicle flow according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart of obtaining a second type of weather influencing factor based on non-motor vehicle traffic information corresponding to current non-motor vehicle traffic and non-motor vehicle traffic information corresponding to historical non-motor vehicle traffic;
FIG. 6 is a schematic flow chart of determining a driving risk corresponding to a current vehicle based on a first type of weather-influencing factor, a second type of weather-influencing factor and a preset threshold according to an embodiment of the present invention;
FIG. 7 is a schematic flow chart of generating a driving risk early warning notification according to an embodiment of the present invention;
FIG. 8 is a block diagram showing a vehicle driving risk determination apparatus according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It is noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention and in the foregoing figures, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server comprising a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1 and 2, fig. 1 and 2 are schematic diagrams of an application environment provided by an embodiment of the present invention, which may include a client 01 and a server 02, where the client 01 and the server 02 may be directly or indirectly connected through a wired or wireless communication manner. The client 01 may acquire the motor vehicle traffic and the non-motor vehicle traffic corresponding to the target crosswalk region from the server 02. It should be noted that fig. 1 is only an example.
The client 01 may include a smart phone, a desktop computer, a tablet computer, a notebook computer, an Augmented Reality (AR)/Virtual Reality (VR) device, a digital assistant, a smart speaker, a smart wearable device, a vehicle-mounted terminal device, or other type of physical device, and may also include software running in the physical device, such as a computer program. The operating systems corresponding to the client 01 may include, but are not limited to, android system (Android system), IOS system (mobile operating system developed by apple corporation), linux (an operating system), microsoft Windows (microsoft windows operating system).
The server 02 may include a network communication unit, a processor, a memory, and the like. The server 02 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligent platforms. The server may provide background services for the client. In practical applications, the server 02 may correspond to a cloud platform, and the setting of the cloud platform may be referred to fig. 2.
In an embodiment of the present invention, the scheme for determining the driving risk of the vehicle may utilize artificial intelligence (Artificial Intelligence, AI) technology and automatic driving technology. Artificial intelligence is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and expand human intelligence, sense the environment, acquire knowledge and use the knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision. Autopilot technology typically includes high-precision mapping, environmental awareness, behavioral decision-making, path planning, motion control, and the like.
In the following, a specific embodiment of a vehicle driving risk determination method according to the present invention is described, and fig. 3 is a schematic flow chart of a vehicle driving risk determination method according to an embodiment of the present invention, where the method operation steps described in the examples or the flow chart are provided, but more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When implemented in a real system or server product, the methods illustrated in the embodiments or figures may be performed sequentially or in parallel (e.g., in a parallel processor or multithreaded environment). As shown in fig. 3, the method may include:
S301: acquiring current motor vehicle flow and current non-motor vehicle flow of a corresponding target crosswalk area when the motor vehicle is in a traffic permission indication state;
in the embodiment of the invention, the client can directly acquire the current motor vehicle flow and the current non-motor vehicle flow corresponding to the target crosswalk area from the server. The client may also indirectly obtain the current motor vehicle flow and the current non-motor vehicle flow corresponding to the target crosswalk region from the server, for example, the server stores the current motor vehicle flow and the current non-motor vehicle flow into a relay database, and the client obtains from the relay database. The client points to the current motor vehicle, the client can be a vehicle-mounted terminal (which can be arranged in the vehicle), the client can be an Application program (such as a mobile phone APP; APP: application), the client can correspond to an Application scene in a vehicle-mounted version of the Application program (such as a small scene in the vehicle-mounted version of an instant messaging Application), and the client can also be an applet (such as an applet hosted in the instant messaging Application).
The traffic indication state of the allowed motor vehicles is a state that the target crosswalk does not allow pedestrians to pass through under traffic regulations, and correspondingly, the traffic signal lamp corresponding to the current motor vehicle lights up a green light, and the crosswalk signal lamp corresponding to the target crosswalk lights up a red light. Of course, traffic participants not allowed to pass through the target crosswalk here may include non-motor vehicles such as bicycles, in addition to pedestrians. In general, tricycles, electric bicycles, disabled wheelchair vehicles, and animal-drawn vehicles are also included in the category of non-vehicles according to road management practices.
The current motor vehicle flow corresponding to the target crosswalk region is the total number of motor vehicles that fall into the center region and the peripheral region at the current point in time. The current non-motor vehicle flow corresponding to the target crosswalk region is the total number of non-motor vehicles that fall into the central region and the peripheral region at the current point in time. The central area can be an area where the target crosswalk is located, and can also consist of an area where the target crosswalk is located and an area formed by a position point with the nearest distance of the boundary of the area within L. The peripheral region is a region which has a closest distance to the boundary of the central region outside L but which can be acquired by an acquisition device such as a crosswalk camera. In practice, the distance obtained can be used as a specific value of L, assuming that the pedestrian moves within its reaction time (the average reflection time of the human being is statistical, approximately 0.5 seconds) (the average walking speed of the human being is also statistical, approximately 1.5 meters per second).
In one embodiment, the client may directly obtain the total number of vehicles whose current time point falls within the central area and the peripheral area, that is, the current vehicle flow rate F motor . The current motor vehicle flow may carry corresponding traffic information indicating the number of motor vehicles in a traffic state (i.e., the number of motor vehicles that fall into the central area at the current point in time, noted as currently passing through the target crosswalk)Is a motor vehicle flow F motor_act (ii) and the number of vehicles in a waiting-for-passage (with intention to pass) (i.e., the number of vehicles whose current point in time falls in the surrounding area, noted as the current traffic flow F of the vehicle waiting through the target crosswalk) motor_wait ). In practical application, the client may also directly F motor_act And F motor_wait 。
The client can directly obtain the total number of non-motor vehicles with the current time point falling into the central area and the peripheral area, namely the current non-motor vehicle flow F nomotor . The current non-motor traffic may carry corresponding traffic information indicating the number of non-motor vehicles in the running state (i.e. the number of non-motor vehicles falling into the central area at the current point in time, noted as the non-motor traffic F currently passing through the target crosswalk nomotor_act (ii) and the number of non-motor vehicles in a waiting-for-traffic (with traffic intention) state (i.e., the number of non-motor vehicles whose current point in time falls in the surrounding area, noted as the non-motor vehicle flow rate F currently waiting through the target crosswalk) nomotor_wait ). In practical application, the client may also directly F nomotor_act And F nomotor_wait 。
In another embodiment, 1) the client may obtain the current motor vehicle flow, the current non-motor vehicle flow, and the historical motor vehicle flow and the historical non-motor vehicle flow described below in real time. Executing the steps of obtaining weather influence factors and determining the driving risk corresponding to the current motor vehicle when the current motor vehicle is in the state of allowing the motor vehicle to pass through the indication; 2) The method comprises the steps that a current motor vehicle is in a state allowing the motor vehicle to pass through to be used as a trigger condition, when the trigger condition is met, a client obtains current motor vehicle flow, current non-motor vehicle flow, historical motor vehicle flow and historical non-motor vehicle flow which are described later, and the steps of obtaining weather influence factors and determining driving risks corresponding to the current motor vehicle are executed; 3) The method comprises the steps of taking a state that the current motor vehicle is allowed to pass through and a state that the current motor vehicle is in bad weather as trigger conditions, obtaining the current motor vehicle flow, the current non-motor vehicle flow, the historical motor vehicle flow and the historical non-motor vehicle flow which are described later when the trigger conditions are met, obtaining weather influence factors, and determining driving risks corresponding to the current motor vehicle. Bad weather may refer to heavy snow, ice, low temperature, heavy wind (sand), hot high temperature, heavy rainfall, continuous rainfall, and the like. For example, when a non-motor vehicle encounters a crosswalk in a rainy day, it is often desirable to pass the crosswalk as soon as possible, and even make a red light (at this time, the crosswalk signal lights light up a red light, and if the traffic regulations are strict, the non-motor vehicle should wait for the red light to finish passing again). The probability that pedestrians, bicycles and other non-motor vehicles run through the pedestrian crosswalk directly in severe weather conditions such as rainy days is higher (compared with normal weather), and more accurate driving risk judgment can be provided for the current motor vehicle by combining the scenes with weather influence factors.
S302: acquiring historical motor vehicle flow and historical non-motor vehicle flow corresponding to the target crosswalk region;
in the embodiment of the invention, the client can directly acquire the historical motor vehicle flow and the historical non-motor vehicle flow corresponding to the target crosswalk area from the server. The client may also indirectly obtain the historical motor vehicle flow and the historical non-motor vehicle flow corresponding to the target crosswalk region from the server, for example, the server stores the historical motor vehicle flow and the historical non-motor vehicle flow into a transit database, and the client obtains from the transit database.
The historical motor vehicle flow corresponding to the target crosswalk area is the average value of the sum of the total number of motor vehicles falling into the central area and the peripheral area at each time point in the historical time period, namely, the sub-historical motor vehicle flow corresponding to the target crosswalk area at each time point is overlapped, and the average value is obtained by dividing the overlapped result. The historical non-motor vehicle flow corresponding to the target crosswalk area is the average value of the sum of the total number of non-motor vehicles falling into the central area and the peripheral area at each time point in the historical time period, namely, the sub-historical non-motor vehicle flow corresponding to the target crosswalk area at each time point is overlapped, and the average value is obtained by dividing the overlapped result. Of course, the mean value here can also be replaced by a median value.
The historical time period may indicate a time period immediately preceding the current time point, or may indicate a time period immediately preceding the current time point (including the current time point). The historical time period may be comprised of a plurality of reference time periods, each reference time period being determined based on a time attribution dimension of the current point in time. For example, the candidate historical time period (which may be determined by the selection logic of the "historical time period") is 30 days, and the time attribution dimension of the current time point is noon of each day, then the multiple reference time periods correspond to noon of each day in 30 days. For example, the candidate history period (which may be determined by the selection logic of the foregoing "history period") is 1 year, and the time attribute dimension of the current time point is the next ten days of each month, so that the multiple reference periods correspond to the next ten days of each month in 1 year. The historical time period is determined based on the candidate historical time period and the time attribution dimension of the current time point, so that the corresponding historical motor vehicle flow and historical non-motor vehicle flow are obtained, and the obtained historical flow can be guaranteed to have a higher value than the reference value to help obtain a more accurate weather influence factor. Of course, the granularity of the time attribution dimension can be flexibly adjusted as required.
In one embodiment, the client may directly obtain an average of the sum of the total number of vehicles falling within the central and peripheral regions at each point in time over the historical period of time, i.e., the historical vehicle flow F motor_history . The historical motor vehicle flow may carry corresponding traffic information indicating the number of motor vehicles in a traffic state (i.e. the average of the sum of the numbers of motor vehicles falling into the central zone at each point in time during the historical period, recorded as the historical motor vehicle flow F through the target crosswalk) motor_act_history (ii) and the number of vehicles in a waiting-for-traffic (with traffic intention) state (i.e., the average of the sum of the numbers of vehicles falling into the surrounding area at each time point in the history period, recorded as the historical traffic flow F of the vehicle waiting through the target crosswalk) motor_wait_history ). In practical application, the client may also directly F motor_act_history And F motor_wait_history 。
The client can directly obtain the average value of the sum of the total number of non-motor vehicles falling into the central area and the peripheral area at each time point in the history period, namely the history non-motor vehicle flow F nomotor_history . The historical non-motor vehicle flow may carry corresponding traffic information indicating the number of non-motor vehicles in a traffic state (average value of the sum of the numbers of non-motor vehicles falling into the central area at each time point in the historical period, recorded as the non-motor vehicle flow F of the historical passing through the target crosswalk nomotor_act_history (ii) and the number of non-motor vehicles in a waiting-for-traffic (with traffic intention) state (i.e., the sum of the number of non-motor vehicles falling into the surrounding area at each time point in the history period, recorded as the non-motor vehicle flow rate F of the history waiting through the target crosswalk) nomotor_wait_history ). In practical application, the client may also directly F nomotor_act_history And F nomotor_wait_history 。
S303: obtaining a first type of weather influence factor based on the motor vehicle traffic information corresponding to the current motor vehicle flow and the motor vehicle traffic information corresponding to the historical motor vehicle flow;
in the embodiment of the invention, the first weather influence factor is used for indicating the influence degree of the current weather condition on the flow of the motor vehicle. When determining the first type of weather-influencing factor, the current motor vehicle flow and the historical motor vehicle flow corresponding to the same type of traffic state can be compared.
In one embodiment, as shown in fig. 4, the obtaining a first weather-influencing factor based on the vehicle traffic information corresponding to the current vehicle flow and the vehicle traffic information corresponding to the historical vehicle flow includes:
s401: obtaining a first flow indicating a running state according to the motor vehicle running information corresponding to the current motor vehicle flow, and obtaining a first ratio according to the first flow and the current motor vehicle flow;
S402: obtaining a second flow indicating a running state according to the motor vehicle traffic information corresponding to the historical motor vehicle flow, and obtaining a second ratio according to the second flow and the historical motor vehicle flow;
s403: and obtaining the first weather influence factor based on the first ratio and the second ratio.
In combination with the related description in step S301, the first flow corresponds to F motor_act A first ratio of F motor_act /F motor That is F motor_act /(F motor_act +F motor_wait ). In combination with the related description in step S302, the second flow corresponds to F motor_act_history A second ratio of F motor_act_history /F motor_history I.e. F motor_act_history /(F motor_act_history +F motor_wait_history ). Correspondingly, the first weather effect factor is Q motor ＝(F motor_act /F motor )/(F motor_act_history /F motor_history ) That is (F) motor_act /(F motor_act +F motor_wait ))/(F motor_act_history /(F motor_act_history +F motor_wait_history ))。
S304: obtaining a second type of weather influencing factor based on the non-motor vehicle traffic information corresponding to the current non-motor vehicle flow and the non-motor vehicle traffic information corresponding to the historical non-motor vehicle flow;
in the embodiment of the invention, the second type of weather influence factors are used for indicating the influence degree of the current weather conditions on the flow of the non-motor vehicle. When the second type of weather-influencing factor is determined, the current non-motor vehicle flow and the historical non-motor vehicle flow corresponding to the same type of traffic state can be compared.
In one embodiment, as shown in fig. 5, the obtaining the weather-influencing factor of the second type based on the non-motor vehicle traffic information corresponding to the current non-motor vehicle flow and the non-motor vehicle traffic information corresponding to the historical non-motor vehicle flow includes:
S501: obtaining a third flow indicating a running state according to the non-motor vehicle running information corresponding to the current non-motor vehicle flow, and obtaining a third ratio according to the third flow and the current non-motor vehicle flow;
s502: obtaining a fourth flow indicating a passing state according to the non-motor vehicle passing information corresponding to the historical non-motor vehicle flow, and obtaining a fourth ratio according to the fourth flow and the historical non-motor vehicle flow;
s503: and obtaining the second type weather influence factor based on the third ratio and the fourth ratio.
In connection with the correlation in step S301, the third flow rate corresponds to F nomotor_act A third ratio of F nomotor_act /F nomotor That is F nomotor_act /(F nomotor_act +F nomotor_wait ). Combining the related records in the step S302, the fourth flow corresponds to F nomotor_act_history The fourth ratio is F nomotor_act_history /F nomotor_history I.e. F nomotor_act_history /(F nomotor_act_history +F nomotor_wait_history ). Correspondingly, the second weather effect factor is Q motor ＝(F nomotor_act /F nomotor )/(F nomotor_act_history /F nomotor_history ) That is (F) nomotor_act /(F nomotor_act +F nomotor_wait ))/(F nomotor_act_history /(F nomotor_act_history +F nomotor_wait_history ))。
In practical application, the current motor vehicle is in a state allowing the motor vehicle to pass through and in a state in bad weather as trigger conditions, and when the trigger conditions are met, the client acquires the current motor vehicle flow, the current non-motor vehicle flow, the historical motor vehicle flow and the historical non-motor vehicle flow, and executes the step of obtaining the weather influencing factors. For example, when a non-motor vehicle encounters a crosswalk in a rainy day, the duty ratio of the non-motor vehicle passing through the crosswalk in order to avoid rain is increased compared with the normal weather, and correspondingly, the duty ratio of the motor vehicle passing through the crosswalk in order to avoid collision with the non-motor vehicle is possibly reduced compared with the normal weather. Q can be used here motor Describing the influence degree of the motor vehicle flow on the rainy day and describing the influence degree of the motor vehicle traffic on the crosswalk on the rainy day, Q can be utilized nomotor The influence degree of the non-motor vehicle flow on the rainy day is described, and the influence degree of the non-motor vehicle flow on the crosswalk on the rainy day is described.
S305: and determining the driving risk corresponding to the current motor vehicle based on the first weather influence factors, the second weather influence factors and a preset threshold value.
In the embodiment of the invention, the preset threshold value can be based on the historical traffic accident rate p corresponding to the target crosswalk junction To determine. The traffic accident rate can represent the relative relation between the number of traffic accidents or injuries and deaths of a country, a region and the like, the population, the number of vehicles in home (motor) and the running mileage in a certain period of time. The preset threshold value can be obtained by the client from the server, and the server can obtain the historical traffic accident rate according to the stored historical traffic accident information statistics corresponding to the target crosswalk so as to set the preset threshold value.
In one embodiment, as shown in fig. 6, when the preset threshold includes a first threshold and a second threshold, and the second threshold is greater than the first threshold, the determining, based on the first type weather-influencing factor, the second type weather-influencing factor and the preset threshold, the driving risk corresponding to the current motor vehicle includes:
S601: obtaining a reference impact factor based on the first type weather impact factor and the second type weather impact factor;
s602: when the reference influence factor is smaller than or equal to the first threshold value, judging that the current motor vehicle corresponds to a first driving risk level;
s603: when the reference influence factor is larger than the first threshold value and the reference influence factor is smaller than or equal to the second threshold value, judging that the current motor vehicle corresponds to a second driving risk level;
s604: when the reference influence factor is larger than the second threshold value, judging that the current motor vehicle corresponds to a third driving risk level;
to determine the total degree of influence describing the flow of motor vehicles and the flow of non-motor vehicles by the current weather conditions, Q can be taken motor And Q nomotor The product of the two factors as the total influence factor Q total . The determination of the corresponding driving risk of the current motor vehicle is equivalent to judging whether the total influence of the current weather condition on the traffic of the crosswalk increases the traffic accident rate of the crosswalk. Can be Q total As a reference influencing factor with a first threshold value (e.g. taking 1), a second threshold value (e.g. taking p junction +1) comparison. Q can also be total 1 as reference influencing factor with a first threshold value (e.g. taking 0), a second threshold value (e.g. taking p junction ) A comparison is made.
Thus, a) when the relative change in the total impact of the current weather conditions (such as rainy days) on the traffic of the travelator is not positive (i.e., Q total -1.ltoreq.0), indicating that the current weather conditions have no substantial effect on the driving risk of the target crosswalk, the current motor vehicle being the lowest level corresponding to the first driving risk level. b) When the relative change amount of the total influence of the current weather condition (such as rainy days) on the traffic of the crosswalk is within the corresponding historical traffic accident rate of the target crosswalk (namely 0)<Q total -1≤p junction ) When the vehicle is in the middle level, the current weather condition has a substantial influence on the driving risk of the target crosswalk but does not improve the traffic accident rate corresponding to the target crosswalk, and the current motor vehicle corresponds to the second driving risk level (because the crosswalk has the functions of improving the driving safety of the road and reducing the existing traffic accident rate). c) When the relative change amount of the total influence of the current weather conditions (such as rainy days) on the traffic of the crosswalk is larger than the corresponding historical traffic accident rate (namely Q total -1>p junction ) When the vehicle is in the state of the first driving risk level, the current weather condition has a substantial influence on the driving risk of the target crosswalk, the traffic accident rate corresponding to the target crosswalk can be improved, and the second driving risk level corresponding to the current motor vehicle is the highest level.
Further, as shown in fig. 7, after the determining the driving risk corresponding to the current motor vehicle based on the first type of weather-influencing factors, the second type of weather-influencing factors and the preset threshold, the method further includes:
s701: acquiring current speed and acceleration information of the current motor vehicle;
s702: determining a reference braking distance of the current motor vehicle based on the current vehicle speed and the acceleration information;
s703: when the current motor vehicle corresponds to the first driving risk level, generating a driving risk early warning notification corresponding to the first driving risk level when the distance between the current motor vehicle and the target crosswalk region is the reference braking distance;
s704: when the current motor vehicle corresponds to the second driving risk level, generating a first distance according to the reference influence factor and the reference braking distance, and when the distance between the current motor vehicle and the target crosswalk area is the first distance, generating a driving risk early warning notice corresponding to the second driving risk level;
s705: and when the current motor vehicle corresponds to the third driving risk level, generating a second distance according to the reference influence factor and the reference braking distance, and when the distance between the current motor vehicle and the target crosswalk area is the second distance, generating a driving risk early warning notice corresponding to the third driving risk level.
The reference braking distance S of the current motor vehicle can be determined based on the current vehicle speed, the acceleration information and the basic motion equation brake ，S brake And is also the actual braking distance of the current motor vehicle. The timing of determining the reference braking distance may be real-time, or may be when the aforementioned trigger condition is satisfied (the current motor vehicle is in the traffic-allowed indication state as the trigger condition, or the current motor vehicle is in the traffic-allowed indication state and in the bad weather state as the trigger condition).
In combination with the relevant description in steps S601-S604, a) when the current motor vehicle corresponds to the first driving risk level, the distance from the current motor vehicle to the target crosswalk region may be S brake And generating a driving risk early warning notice corresponding to the first driving risk level: the current weather conditions (such as rainy days) do not present additional driving risks to guide the current motor vehicle to maintain the original driving state. b) When the current motor vehicle corresponds to the second driving risk level, on the one hand, if in a normal weather state, the distance from the current motor vehicle to the target crosswalk area can be S brake Generating a driving risk early warning notice corresponding to the second driving risk level; on the one hand, if in bad weather condition, the distance from the current motor vehicle to the target crosswalk area is S brake Q total And generating a driving risk early warning notice corresponding to the second driving risk level: the current weather conditions (such as rainy days) have substantial influence on the driving risk of the crosswalk but cannot improve the traffic accident rate of the crosswalk so as to guide the current motor vehicle to enter a running state of 'speed reduction at any time'; wherein the existence of bad weather is considered, the early warning should be advanced, i.e. the early warning distance should be increased. The relative change in the impact of the current weather conditions on the driving risk of the vehicle as it passes through the crosswalk is Q total -1, so the change of the pre-warning distance relative to the actual braking distance should be Q total -1, i.e. the first distance as the warning distance should be S brake (1+Q total -1)＝S brake *Q total . c) When the current motor vehicle corresponds to the third driving risk level, on the one hand, if in a normal weather state, the distance from the current motor vehicle to the target crosswalk area can be S brake Generating a driving risk early warning notice corresponding to the third driving risk level; on the one hand, if in bad weather condition, the distance from the current motor vehicle to the target crosswalk area is S brake Q total And generating a driving risk early warning notice corresponding to the third driving risk level: the current weather conditions (such as rainy days) bring additional driving risks and the risks can improve the traffic accident rate of crosswalk so as to guide the current motor vehicle to enter a running state of stopping at any time; wherein the existence of bad weather is considered, the early warning should be advanced, i.e. the early warning distance should be increased. Current weather conditions for a vehicle The relative change in the influence of the driving risk on a crosswalk is Q total -1, so the change of the pre-warning distance relative to the actual braking distance should be Q total -1, i.e. the first distance as the warning distance should be S brake (1+Q total -1)＝S brake *Q total . According to the method, the device and the system, the vehicle does not need to be reminded of decelerating or stopping blindly, the driving risk and the early warning distance corresponding to the current motor vehicle are determined by combining the current weather conditions (including normal weather and bad weather), and then corresponding driving risk early warning notification is generated when the distance between the current motor vehicle and the target crosswalk area is the early warning distance, so that the passing efficiency of the crosswalk can be relieved to a certain extent.
In another embodiment, after the second type of weather-influencing factor is obtained based on the non-motor vehicle traffic information corresponding to the current non-motor vehicle flow and the non-motor vehicle traffic information corresponding to the historical non-motor vehicle flow, the method further includes: inputting the first weather influence factors and the second weather influence factors into a driving risk prediction model to predict driving risk; the driving risk prediction model is determined by machine learning training based on a plurality of weather effect factor sample groups, each weather effect factor sample group carries a driving risk label (such as the driving risk level), and each weather effect factor sample group comprises a first type weather effect factor sample and a second type weather effect factor sample corresponding to the same motor vehicle.
Further, the driving risk prediction model may be trained by: firstly, acquiring a plurality of weather effect factor sample sets; then, inputting the plurality of weather effect factor sample sets into a preset machine learning model to conduct driving risk prediction training; in addition, model parameters of the preset machine learning model are adjusted in training until a driving risk prediction result output by the preset machine learning model is matched with a driving risk label carried by an input weather effect factor sample set; and finally, taking a preset machine learning model corresponding to the adjusted model parameters as the driving risk prediction model.
The driving risk prediction model can also be used as an intermediate model, and the related data in the floor application is used as sample data to continuously train the prediction model. The driving risk prediction model with high generalization capability can be obtained by training the neural network model, so that the adaptability is stronger and the accuracy is higher when the driving risk prediction model is used for predicting the driving risk of the vehicle, and false alarms can be reduced. The neural network model may be DNN (Deep Neural Networks, deep neural network) model, XGB (eXtreme Gradient Boosting, extreme gradient lifting) model, LR (Logistic Regression ) model, or the like.
In practical application, compared with the prior art scheme (experimental group 2) without the scheme, the vehicle driving risk determination scheme (experimental group 1) provided by the embodiment of the invention can effectively reduce the occurrence times of false alarm, missed alarm and other false alarm situations, and can be seen in the following table 1:
table 1 experimental results
As can be seen from the technical solutions provided in the embodiments of the present disclosure, for a same crosswalk, a driving risk of a current motor vehicle is determined according to a degree of influence of a current weather condition on a corresponding motor vehicle flow and a non-motor vehicle flow, where the determination of the influence degree is combined with traffic information corresponding to the current flow and traffic information corresponding to a historical flow, and accuracy of determining the driving risk is improved by using finer granularity determination parameters. The weather influence factors can be determined according to specific road conditions (including the current road conditions and the historical road conditions) so as to realize dynamic and timely determination of driving risks, and then the early warning notification considering driving safety and road traffic efficiency can be ensured to be output.
The embodiment of the invention also provides a vehicle driving risk determining device, as shown in fig. 8, which comprises:
the first acquisition module 810: the method comprises the steps of acquiring current motor vehicle flow and current non-motor vehicle flow of a corresponding target crosswalk area when the motor vehicle is in a traffic permission indication state;
The second acquisition module 820: the method comprises the steps of acquiring historical motor vehicle flow and historical non-motor vehicle flow corresponding to the target crosswalk area;
the first obtaining module 830: the weather-influencing factor obtaining module is used for obtaining a first type of weather-influencing factor based on the motor vehicle traffic information corresponding to the current motor vehicle flow and the motor vehicle traffic information corresponding to the historical motor vehicle flow;
the second obtaining module 840: the method comprises the steps of obtaining a second type of weather influencing factor based on non-motor vehicle traffic information corresponding to the current non-motor vehicle flow and non-motor vehicle traffic information corresponding to the historical non-motor vehicle flow;
the driving risk determination module 850: and the method is used for determining the driving risk corresponding to the current motor vehicle based on the first weather influence factors, the second weather influence factors and a preset threshold value.
It should be noted that the apparatus and method embodiments in the apparatus embodiments are based on the same inventive concept.
The embodiment of the invention also provides a vehicle driving risk determining system, which comprises acquisition equipment, a data processing platform and the vehicle driving risk determining device:
the acquisition device: the image data is used for collecting image data indicating a target crosswalk area and sending the image data to the data processing platform;
The data processing platform: for determining a current motor vehicle flow, a current non-motor vehicle flow, a historical motor vehicle flow and a historical non-motor vehicle flow corresponding to the target crosswalk region based on the received image data, and for transmitting the corresponding motor vehicle flow and non-motor vehicle flow to the vehicle driving risk determination means.
In one embodiment, the acquisition device may be at least one selected from the group consisting of a camera, a lidar, a millimeter wave radar. The data processing platform performs analysis based on the received image data, for example, the image data corresponding to the time point a is the image set a, and performs area positioning and traffic participant (motor vehicle or non-motor vehicle) positioning on each image in the image set a based on the records about the central area and the peripheral area in the step S301, and then comprehensively obtains the motor vehicle flow and the non-motor vehicle flow corresponding to the time point a according to the positioning object definition corresponding to each image.
In one embodiment, the data processing platform may be used as a server in combination with the related records in the foregoing steps S301 and S302. As shown in fig. 2, in practical application, the data processing platform may be presented in the form of a monitoring cloud platform.
It should be noted that the system and method embodiments in the system embodiments are based on the same inventive concept.
The embodiment of the invention provides electronic equipment, which comprises a processor and a memory, wherein at least one instruction or at least one section of program is stored in the memory, and the at least one instruction or the at least one section of program is loaded and executed by the processor to realize the vehicle driving risk determination method provided by the embodiment of the method.
Further, fig. 9 shows a schematic hardware structure of an electronic device for implementing the method for determining a risk of driving a vehicle according to the embodiment of the present invention, where the electronic device may participate in forming or including the apparatus for determining a risk of driving a vehicle according to the embodiment of the present invention. As shown in fig. 9, the electronic device 90 may include one or more processors 902 (shown in the figures as 902a, 902b, … …,902 n) (the processor 902 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA), a memory 904 for storing data, and a transmission device 906 for communication functions. In addition, the method may further include: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power supply, and/or a camera. It will be appreciated by those skilled in the art that the configuration shown in fig. 9 is merely illustrative and is not intended to limit the configuration of the electronic device. For example, the electronic device 90 may also include more or fewer components than shown in FIG. 9, or have a different configuration than shown in FIG. 9.
It should be noted that the one or more processors 902 and/or other data processing circuitry described above may be referred to herein generally as "data processing circuitry. The data processing circuit may be embodied in whole or in part in software, hardware, firmware, or any other combination. Further, the data processing circuitry may be a single stand-alone processing module, or incorporated, in whole or in part, into any of the other elements in the electronic device 90 (or mobile device). As referred to in embodiments of the application, the data processing circuit acts as a processor control (e.g., selection of the path of the variable resistor termination connected to the interface).
The memory 904 may be used to store software programs and modules of application software, and the processor 902 executes the software programs and modules stored in the memory 94 to perform various functional applications and data processing, i.e., to implement a vehicle driving risk determination method as described above, according to the program instructions/data storage device corresponding to the vehicle driving risk determination method according to the embodiment of the present application. The memory 904 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 904 may further include memory remotely located relative to the processor 902, which may be connected to the electronic device 90 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission means 906 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communications provider of the electronic device 90. In one example, the transmission means 906 includes a network adapter (NetworkInterfaceController, NIC) that can be connected to other network devices through a base station to communicate with the internet. In one embodiment, the transmission device 906 may be a radio frequency (RadioFrequency, RF) module for communicating wirelessly with the internet.
The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the electronic device 90 (or mobile device).
Embodiments of the present invention also provide a storage medium that may be disposed in an electronic device to store at least one instruction or at least one program related to a method for determining a risk of driving a vehicle in a method embodiment, where the at least one instruction or the at least one program is loaded and executed by the processor to implement the method for determining a risk of driving a vehicle provided in the method embodiment.
Alternatively, in this embodiment, the storage medium may be located in at least one network server among a plurality of network servers of the computer network. Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the apparatus and electronic device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and references to the parts of the description of the method embodiments are only required.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A vehicle driving risk determination method, characterized in that the method comprises:
when the vehicle is in a traffic indication state, acquiring the current vehicle flow and the current non-vehicle flow of the area where the target crosswalk is located and the peripheral area at the current time point, wherein the peripheral area is an area which is the nearest distance from the boundary of the target crosswalk area and is beyond a preset distance but can be used for acquiring images;
acquiring historical motor vehicle flow and historical non-motor vehicle flow of an area where the target crosswalk is located and the surrounding area at a historical time point, wherein the current time point and the historical time point indicate the same time attribution dimension;
obtaining a first flow indicating a running state according to the motor vehicle running information corresponding to the current motor vehicle flow, and obtaining a first ratio according to the first flow and the current motor vehicle flow; obtaining a second flow indicating a running state according to the motor vehicle traffic information corresponding to the historical motor vehicle flow, and obtaining a second ratio according to the second flow and the historical motor vehicle flow; obtaining a first weather influence factor based on the ratio of the first ratio to the second ratio, wherein the first weather influence factor is used for describing the influence degree of the motor vehicle flow by weather;
Obtaining a third flow indicating a running state according to the non-motor vehicle running information corresponding to the current non-motor vehicle flow, and obtaining a third ratio according to the third flow and the current non-motor vehicle flow; obtaining a fourth flow indicating a passing state according to the non-motor vehicle passing information corresponding to the historical non-motor vehicle flow, and obtaining a fourth ratio according to the fourth flow and the historical non-motor vehicle flow; obtaining a second type of weather influence factor based on the ratio of the third ratio to the fourth ratio, wherein the second type of weather influence factor is used for describing the influence degree of weather on the flow of the non-motor vehicle;
determining the driving risk corresponding to the current motor vehicle based on the first weather influence factors, the second weather influence factors and a preset threshold value: when the preset threshold value comprises a first threshold value and a second threshold value, and the second threshold value is larger than the first threshold value, obtaining a reference influence factor based on the product of the first type of weather influence factors and the second type of weather influence factors; when the reference influence factor is smaller than or equal to the first threshold value, judging that the current motor vehicle corresponds to a first driving risk level; when the reference influence factor is larger than the first threshold value and the reference influence factor is smaller than or equal to the second threshold value, judging that the current motor vehicle corresponds to a second driving risk level; and when the reference influence factor is larger than the second threshold, judging that the current motor vehicle corresponds to a third driving risk level, wherein the preset threshold is determined based on the historical traffic accident rate corresponding to the target crosswalk, the driving risk indicated by the first driving risk level is lower than the driving risk indicated by the second driving risk level, and the driving risk indicated by the second driving risk level is lower than the driving risk indicated by the third driving risk level.
2. The method of claim 1, wherein after the determining the driving risk corresponding to the current motor vehicle based on the first type of weather-influencing factor, the second type of weather-influencing factor and a preset threshold, the method further comprises:
acquiring current speed and acceleration information of the current motor vehicle;
determining a reference braking distance of the current motor vehicle based on the current vehicle speed and the acceleration information;
when the current motor vehicle corresponds to the first driving risk level, generating a driving risk early warning notification corresponding to the first driving risk level when the distance between the current motor vehicle and the target crosswalk region is the reference braking distance;
when the current motor vehicle corresponds to the second driving risk level, generating a first distance according to the product of the reference influence factor and the reference braking distance, and when the distance between the current motor vehicle and the target crosswalk area is the first distance, generating a driving risk early warning notice corresponding to the second driving risk level;
and when the current motor vehicle corresponds to the third driving risk level, generating a second distance according to the product of the reference influence factor and the reference braking distance, and when the distance between the current motor vehicle and the target crosswalk area is the second distance, generating a driving risk early warning notice corresponding to the third driving risk level.
3. A vehicle driving risk determination method, characterized in that the method comprises:
when the vehicle is in a traffic indication state, acquiring the current vehicle flow and the current non-vehicle flow of the area where the target crosswalk is located and the peripheral area at the current time point, wherein the peripheral area is an area which is the nearest distance from the boundary of the target crosswalk area and is beyond a preset distance but can be used for acquiring images;
acquiring historical motor vehicle flow and historical non-motor vehicle flow of the area where the target crosswalk is located and the surrounding area at a historical time point, wherein the current time point and the historical time point indicate the same time attribution dimension;
obtaining a first flow indicating a running state according to the motor vehicle running information corresponding to the current motor vehicle flow, and obtaining a first ratio according to the first flow and the current motor vehicle flow; obtaining a second flow indicating a running state according to the motor vehicle traffic information corresponding to the historical motor vehicle flow, and obtaining a second ratio according to the second flow and the historical motor vehicle flow; obtaining a first weather influence factor based on the ratio of the first ratio to the second ratio, wherein the first weather influence factor is used for describing the influence degree of the motor vehicle flow by weather;
Obtaining a third flow indicating a running state according to the non-motor vehicle running information corresponding to the current non-motor vehicle flow, and obtaining a third ratio according to the third flow and the current non-motor vehicle flow; obtaining a fourth flow indicating a passing state according to the non-motor vehicle passing information corresponding to the historical non-motor vehicle flow, and obtaining a fourth ratio according to the fourth flow and the historical non-motor vehicle flow; obtaining a second type of weather influence factor based on the ratio of the third ratio to the fourth ratio, wherein the second type of weather influence factor is used for describing the influence degree of weather on the flow of the non-motor vehicle:
inputting the first weather influence factors and the second weather influence factors into a driving risk prediction model to predict driving risk;
the driving risk prediction model is determined by machine learning training based on a plurality of weather effect factor sample groups, each weather effect factor sample group carries driving risk labels, and each weather effect factor sample group comprises a first type weather effect factor sample and a second type weather effect factor sample corresponding to the same motor vehicle.
4. A method according to claim 3, further comprising training the driving risk prediction model:
acquiring the plurality of weather effect factor sample sets;
inputting the weather effect factor sample sets into a preset machine learning model to conduct driving risk prediction training;
in training, adjusting model parameters of the preset machine learning model until a driving risk prediction result output by the preset machine learning model is matched with a driving risk mark carried by an input weather influence factor sample set;
and taking a preset machine learning model corresponding to the adjusted model parameters as the driving risk prediction model.
5. A vehicle driving risk determination apparatus, characterized in that the apparatus comprises:
a first acquisition module: when the vehicle is in a state of allowing the vehicle to pass, acquiring the current vehicle flow and the current non-vehicle flow of the area where the target crosswalk is located and the peripheral area at the current time point, wherein the peripheral area is an area which is the nearest distance from the boundary of the target crosswalk area and is beyond a preset distance but can be used for acquiring images;
and a second acquisition module: the method comprises the steps that historical motor vehicle flow and historical non-motor vehicle flow in a region where a target crosswalk is located and a surrounding region at a historical time point are obtained, and the current time point and the historical time point indicate the same time attribution dimension;
The first obtaining module: the method comprises the steps of obtaining a first flow indicating a running state according to motor vehicle running information corresponding to the current motor vehicle flow, and obtaining a first ratio according to the first flow and the current motor vehicle flow; obtaining a second flow indicating a running state according to the motor vehicle traffic information corresponding to the historical motor vehicle flow, and obtaining a second ratio according to the second flow and the historical motor vehicle flow; obtaining a first weather influence factor based on the ratio of the first ratio to the second ratio, wherein the first weather influence factor is used for describing the influence degree of the motor vehicle flow by weather;
and a second obtaining module: the method comprises the steps of obtaining a third flow indicating a running state according to non-motor vehicle running information corresponding to the current non-motor vehicle flow, and obtaining a third ratio according to the third flow and the current non-motor vehicle flow; obtaining a fourth flow indicating a passing state according to the non-motor vehicle passing information corresponding to the historical non-motor vehicle flow, and obtaining a fourth ratio according to the fourth flow and the historical non-motor vehicle flow; obtaining a second type of weather influence factor based on the ratio of the third ratio to the fourth ratio, wherein the second type of weather influence factor is used for describing the influence degree of weather on the flow of the non-motor vehicle;
A first driving risk determination module: the method comprises the steps of determining a driving risk corresponding to a current motor vehicle based on the first weather influence factors, the second weather influence factors and a preset threshold value: when the preset threshold value comprises a first threshold value and a second threshold value, and the second threshold value is larger than the first threshold value, obtaining a reference influence factor based on the product of the first type of weather influence factors and the second type of weather influence factors; when the reference influence factor is smaller than or equal to the first threshold value, judging that the current motor vehicle corresponds to a first driving risk level; when the reference influence factor is larger than the first threshold value and the reference influence factor is smaller than or equal to the second threshold value, judging that the current motor vehicle corresponds to a second driving risk level; and when the reference influence factor is larger than the second threshold, judging that the current motor vehicle corresponds to a third driving risk level, wherein the preset threshold is determined based on the historical traffic accident rate corresponding to the target crosswalk, the driving risk indicated by the first driving risk level is lower than the driving risk indicated by the second driving risk level, and the driving risk indicated by the second driving risk level is lower than the driving risk indicated by the third driving risk level.
6. A vehicle driving risk determination apparatus, characterized in that the apparatus comprises:
and a third acquisition module: when the vehicle is in a state of allowing the vehicle to pass, acquiring the current vehicle flow and the current non-vehicle flow of the area where the target crosswalk is located and the peripheral area at the current time point, wherein the peripheral area is an area which is the nearest distance from the boundary of the target crosswalk area and is beyond a preset distance but can be used for acquiring images;
a fourth acquisition module: the method comprises the steps that historical motor vehicle flow and historical non-motor vehicle flow in a region where a target crosswalk is located and a surrounding region at a historical time point are obtained, and the current time point and the historical time point indicate the same time attribution dimension;
and thirdly, obtaining a module: the method comprises the steps of obtaining a first flow indicating a running state according to motor vehicle running information corresponding to the current motor vehicle flow, and obtaining a first ratio according to the first flow and the current motor vehicle flow; obtaining a second flow indicating a running state according to the motor vehicle traffic information corresponding to the historical motor vehicle flow, and obtaining a second ratio according to the second flow and the historical motor vehicle flow; obtaining a first weather influence factor based on the ratio of the first ratio to the second ratio, wherein the first weather influence factor is used for describing the influence degree of the motor vehicle flow by weather;
Fourth, obtaining a module: the method comprises the steps of obtaining a third flow indicating a running state according to non-motor vehicle running information corresponding to the current non-motor vehicle flow, and obtaining a third ratio according to the third flow and the current non-motor vehicle flow; obtaining a fourth flow indicating a passing state according to the non-motor vehicle passing information corresponding to the historical non-motor vehicle flow, and obtaining a fourth ratio according to the fourth flow and the historical non-motor vehicle flow; obtaining a second type of weather influence factor based on the ratio of the third ratio to the fourth ratio, wherein the second type of weather influence factor is used for describing the influence degree of weather on the flow of the non-motor vehicle;
a second driving risk determination module: the method comprises the steps of inputting the first type of weather influence factors and the second type of weather influence factors into a driving risk prediction model to predict driving risk;
the driving risk prediction model is determined by machine learning training based on a plurality of weather effect factor sample groups, each weather effect factor sample group carries driving risk labels, and each weather effect factor sample group comprises a first type weather effect factor sample and a second type weather effect factor sample corresponding to the same motor vehicle.
7. A vehicle driving risk determination system, characterized in that the system comprises an acquisition device, a data processing platform and a vehicle driving risk determination apparatus as claimed in claim 5 or 6:
the acquisition device: the image data is used for collecting image data indicating a target crosswalk area and sending the image data to the data processing platform;
the data processing platform: and means for determining the current motor vehicle flow rate, the current non-motor vehicle flow rate, the historical motor vehicle flow rate, and the historical non-motor vehicle flow rate based on the received image data and transmitting the same to the vehicle driving risk determination means.
8. A computer-readable storage medium, characterized in that at least one instruction or at least one program is stored in the storage medium, which is loaded and executed by a processor to implement the vehicle driving risk determination method according to any one of claims 1-2 or the vehicle driving risk determination method according to claims 3-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010751119.8A CN111951548B (en) | 2020-07-30 | 2020-07-30 | Vehicle driving risk determination method, device, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010751119.8A CN111951548B (en) | 2020-07-30 | 2020-07-30 | Vehicle driving risk determination method, device, system and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111951548A CN111951548A (en) | 2020-11-17 |
| CN111951548B true CN111951548B (en) | 2023-09-08 |
Family
ID=73338589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010751119.8A Active CN111951548B (en) | 2020-07-30 | 2020-07-30 | Vehicle driving risk determination method, device, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111951548B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113192338B (en) * | 2021-03-31 | 2021-11-30 | 北京市运输管理技术支持中心 | Method and device for improving freight vehicle passing efficiency based on multi-source data |
| CN113724492A (en) * | 2021-07-29 | 2021-11-30 | 东南大学 | Method for predicting red light running behavior of rider by considering vehicle type and group |
| CN113808394B (en) * | 2021-08-27 | 2022-09-30 | 东南大学 | Cross-street channel safety evaluation method based on risk combination mode |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006085285A (en) * | 2004-09-14 | 2006-03-30 | Matsushita Electric Ind Co Ltd | Dangerous vehicle prediction device |
| CN109389824A (en) * | 2017-08-04 | 2019-02-26 | 华为技术有限公司 | A kind of appraisal procedure and device driving risk |
| CN110782706A (en) * | 2019-11-06 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Early warning method and device for driving risk of intelligent vehicle |
| CN111028505A (en) * | 2019-11-28 | 2020-04-17 | 北京世纪高通科技有限公司 | Traffic jam treatment method and device |
| US10699347B1 (en) * | 2016-02-24 | 2020-06-30 | Allstate Insurance Company | Polynomial risk maps |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013105869A1 (en) * | 2012-01-13 | 2013-07-18 | Pulse Function F6 Limited | Telematics system with 3d inertial sensors |
| CN108288312A (en) * | 2017-03-06 | 2018-07-17 | 腾讯科技（深圳）有限公司 | Driving behavior determines method and device |
| KR101826060B1 (en) * | 2017-05-15 | 2018-02-06 | 주식회사 퀀텀게이트 | System of Traffic Forecasting |
-
2020
- 2020-07-30 CN CN202010751119.8A patent/CN111951548B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006085285A (en) * | 2004-09-14 | 2006-03-30 | Matsushita Electric Ind Co Ltd | Dangerous vehicle prediction device |
| US10699347B1 (en) * | 2016-02-24 | 2020-06-30 | Allstate Insurance Company | Polynomial risk maps |
| CN109389824A (en) * | 2017-08-04 | 2019-02-26 | 华为技术有限公司 | A kind of appraisal procedure and device driving risk |
| CN110782706A (en) * | 2019-11-06 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Early warning method and device for driving risk of intelligent vehicle |
| CN111028505A (en) * | 2019-11-28 | 2020-04-17 | 北京世纪高通科技有限公司 | Traffic jam treatment method and device |
Non-Patent Citations (1)
| Title |
|---|
| 中国交通工程学术研究综述・2016;马建;孙守增;芮海田;马勇;王磊;刘辉;张伟伟;陈红燕;陈磊;;中国公路学报(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111951548A (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11521496B2 (en) | Lane-borrowing vehicle driving method and control center | |
| US11640174B2 (en) | Smart vehicle | |
| CN111951548B (en) | Vehicle driving risk determination method, device, system and medium | |
| KR102618445B1 (en) | Method and apparatus of estimating road condition, and method and apparatus of establishing road condition estimation model | |
| CA3016825A1 (en) | Predictive, integrated and intelligent system for control of times in traffic lights | |
| CN111402612A (en) | Traffic incident notification method and device | |
| CN110728844B (en) | Traffic light self-adaptive control method and device, traffic control equipment and storage medium | |
| CN112634611B (en) | Method, device, equipment and storage medium for identifying road conditions | |
| CN112885145B (en) | Crossing risk early warning method and device | |
| CN112106124A (en) | System and method for using V2X and sensor data | |
| WO2022110611A1 (en) | Pedestrian road-crossing behavior prediction method for plane intersection | |
| CN109584579B (en) | Traffic signal lamp control method based on face recognition and computer equipment | |
| WO2024027228A1 (en) | Method and apparatus for providing prompt on navigation interface, and device, storage medium, and program product | |
| CN113415275A (en) | Vehicle message processing method and device, readable medium and electronic equipment | |
| CN111882924A (en) | Vehicle testing system, driving behavior judgment control method and accident early warning method | |
| Gowtham et al. | An efficient monitoring of real time traffic clearance for an emergency service vehicle using iot | |
| Dodia et al. | EVATL: A novel framework for emergency vehicle communication with adaptive traffic lights for smart cities | |
| CN116129675A (en) | Method, device and equipment for early warning of collision between people and vehicles | |
| CN112362076B (en) | Intelligent display method and related device for navigation information of non-recommended road section | |
| CN111524389A (en) | Vehicle driving method and device | |
| US11967230B2 (en) | System and method for using V2X and sensor data | |
| US20230339508A1 (en) | Medical emergency detection in-vehicle caretaker | |
| US11830357B1 (en) | Road user vulnerability state classification and reporting system and method | |
| CN112232581B (en) | Driving risk prediction method and device, electronic equipment and storage medium | |
| US20240062658A1 (en) | Altruistic mobility by vehicular micro cloud |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |