CN110660270B - Method for establishing vehicle collision risk evaluation model and collision risk evaluation method - Google Patents
Method for establishing vehicle collision risk evaluation model and collision risk evaluation method Download PDFInfo
- Publication number
- CN110660270B CN110660270B CN201810714331.XA CN201810714331A CN110660270B CN 110660270 B CN110660270 B CN 110660270B CN 201810714331 A CN201810714331 A CN 201810714331A CN 110660270 B CN110660270 B CN 110660270B
- Authority
- CN
- China
- Prior art keywords
- evaluation
- collision risk
- information
- vehicle
- index
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 171
- 238000013210 evaluation model Methods 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012216 screening Methods 0.000 claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims description 56
- 238000001514 detection method Methods 0.000 claims description 32
- 238000004458 analytical method Methods 0.000 claims description 17
- 238000012502 risk assessment Methods 0.000 claims description 15
- 230000036541 health Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 230000008447 perception Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 5
- 230000011664 signaling Effects 0.000 claims 1
- 230000006870 function Effects 0.000 description 14
- 238000004364 calculation method Methods 0.000 description 13
- 238000005259 measurement Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011158 quantitative evaluation Methods 0.000 description 2
- 206010011878 Deafness Diseases 0.000 description 1
- 241000253999 Phasmatodea Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 231100000895 deafness Toxicity 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 208000016354 hearing loss disease Diseases 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012732 spatial analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/165—Anti-collision systems for passive traffic, e.g. including static obstacles, trees
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vehicle collision risk evaluation model establishing method and a vehicle collision risk evaluation method, wherein the vehicle collision risk evaluation method comprises the following steps: detecting the driving information of the current vehicle through a sensor; screening the driving information to acquire risk factor information of the current vehicle; preliminarily identifying the risk factor information of the current vehicle and generating an identification result; and calculating the recognition result by utilizing a pre-established vehicle collision risk evaluation model to generate an evaluation result. The collision risk evaluation method provided by the embodiment of the invention can accurately evaluate the vehicle collision risk and ensure the vehicle driving safety.
Description
Technical Field
The invention relates to the technical field of automobiles, in particular to a method for establishing a vehicle collision risk evaluation model and a collision risk evaluation method.
Background
With the continuous development of urbanization process, urban population and automobile holding capacity are rapidly increased, and the probability of collision risk between pedestrians and vehicles and between vehicles is increased. At present, image information or video information is mainly acquired through a front-view camera arranged on a vehicle, parameters of a front vehicle or a pedestrian are extracted through a feature recognition algorithm, and then the probability of collision risk is judged by combining information such as the speed and the acceleration of the vehicle. However, the above method detects image information or video information only by a forward-looking camera, and the field of view of the camera is narrow, and cannot be covered completely. When the vehicle or the pedestrian is identified, the characteristics of the vehicle or the pedestrian can be accurately identified only when the vehicle or the pedestrian in front is within a certain distance, and the collision risk cannot be analyzed in time when the identification distance is too short.
Disclosure of Invention
The invention provides a vehicle collision risk evaluation model establishing method and a vehicle collision risk evaluation method, and aims to solve at least one of the technical problems.
The embodiment of the invention provides a method for establishing a vehicle collision risk evaluation model, which comprises the following steps:
establishing a vehicle collision risk evaluation system, wherein the vehicle collision risk evaluation system comprises a plurality of first evaluation indexes, and each first evaluation index comprises at least one second evaluation index;
respectively establishing a first comparison judgment matrix corresponding to the plurality of first evaluation indexes and a second comparison judgment matrix corresponding to the at least one second evaluation index based on an analytic hierarchy process;
calculating the weights of the plurality of first evaluation indexes according to the first comparison judgment matrix, and calculating the weight of the second evaluation index according to the second comparison judgment matrix;
and establishing a vehicle collision risk evaluation model according to the weights of the plurality of first evaluation indexes and the weights of the second evaluation indexes.
Optionally, the first evaluation index includes a pedestrian index, a driver index, a road index, a time index, and a space index.
Optionally, the pedestrian indexes include second evaluation indexes including relative speed, position, distance, age and health degree, the driver indexes include second evaluation indexes including risk awareness, risk perception, risk tolerance and risk disposition, the road indexes include second evaluation indexes including gradient, curvature, maximum speed per hour, complexity and marking definition, the time indexes include second evaluation indexes including time period and date, and the space indexes include second evaluation indexes including facility integrity and weather severity.
Optionally, the method further comprises:
determining the first and second comparison determination matrices as a consistency matrix before calculating the weights of the plurality of first evaluation indices and the weights of the second evaluation indices.
According to the method for establishing the vehicle collision risk evaluation model, a vehicle collision risk evaluation system is established, a first comparison judgment matrix corresponding to a plurality of first evaluation indexes and a second comparison judgment matrix corresponding to at least one second evaluation index are respectively established based on an analytic hierarchy process, the weights of the plurality of first evaluation indexes are calculated according to the first comparison judgment matrix, the weights of the second evaluation indexes are calculated according to the second comparison judgment matrix, the vehicle collision risk evaluation model is established according to the weights of the plurality of first evaluation indexes and the weights of the second evaluation indexes, all factors of vehicle collision risk are considered, a comprehensive vehicle collision risk evaluation model with high reliability is established, and a reliable data basis is provided for vehicle collision risk evaluation.
Another embodiment of the present invention provides a collision risk evaluation method based on a vehicle collision risk evaluation model, including:
detecting the driving information of the current vehicle through a sensor;
screening the driving information to acquire risk factor information of the current vehicle;
preliminarily identifying the risk factor information of the current vehicle and generating an identification result;
and calculating the identification result by using a pre-established vehicle collision risk evaluation model to generate an evaluation result, wherein the vehicle collision risk evaluation model is established by adopting the method in the embodiment of the first aspect.
Optionally, the risk factor information of the current vehicle includes pedestrian information, driver information, road information, time information, and spatial information.
Optionally, the identification result includes a pedestrian state, a driver state, a road condition, a traffic flow condition, and a surrounding environment condition, and performs preliminary identification on the risk factor information of the current vehicle, and generates an identification result, including:
identifying a pedestrian state according to the pedestrian information;
identifying a driver state according to the driver information;
analyzing the road condition according to the road information;
analyzing the traffic flow condition according to the time information;
and analyzing the ambient environment condition according to the spatial information.
Optionally, calculating the recognition result by using a pre-established vehicle collision risk evaluation model to generate an evaluation result, including:
and inputting the recognition result into the vehicle collision risk evaluation model, and outputting the evaluation result through the vehicle collision risk evaluation model.
Optionally, the sensor includes a GPS sensor, a vehicle-mounted camera, a vehicle-mounted radar, a road measurement camera, a road measurement radar, a steering wheel pressure sensor, a traffic microwave detector, a traffic control time signal receiver, a rainfall sensor, and a temperature sensor.
Optionally, the method further includes:
and after the evaluation result is generated, determining an early warning level according to the evaluation result, and sending early warning information corresponding to the early warning level.
According to the collision risk evaluation method based on the vehicle collision risk evaluation model, the driving information of the current vehicle is detected through the sensor, the driving information is screened to obtain the risk factor information of the current vehicle, the risk factor information of the current vehicle is preliminarily identified, an identification result is generated, and the identification result is calculated by using the pre-established vehicle collision risk evaluation model to generate the evaluation result, so that the vehicle collision risk can be accurately evaluated, and the driving safety of the vehicle is ensured.
Another embodiment of the present invention provides a vehicle collision risk evaluation system, including:
the sensing module is used for detecting the running information of the current vehicle;
the detection module is used for screening the running information to acquire the risk factor information of the current vehicle and outputting the risk factor information of the current vehicle to the identification and analysis module;
the identification analysis module is used for carrying out primary identification on the risk factor information of the current vehicle, generating an identification result and outputting the identification result to the evaluation module;
the evaluation module is configured to calculate the recognition result by using a pre-established vehicle collision risk evaluation model to generate an evaluation result, where the vehicle collision risk evaluation model is established by using the method according to the embodiment of the first aspect.
Optionally, the risk factor information of the current vehicle includes pedestrian information, driver information, road information, time information, and spatial information, and the detection module specifically includes:
the pedestrian detection module is used for screening out pedestrian information from the driving information;
the driver detection module is used for screening out driver information from the driving information;
the road detection module is used for screening out road information from the driving information;
the time detection module is used for screening out time information from the running information;
and the space detection module is used for screening out space information from the driving information.
Optionally, the recognition result includes a pedestrian status, a driver status, a road condition, a traffic flow condition, and a surrounding environment condition, and the recognition analysis module specifically includes:
the pedestrian state identification module is used for receiving the pedestrian information and identifying the state of a person going out;
the driver state identification module is used for receiving the driver information and identifying the state of the driver;
the road condition analysis module is used for receiving the road information and analyzing the road condition;
the time analysis module is used for receiving the time information and analyzing the traffic flow condition;
and the space analysis module is used for receiving the space information and analyzing the surrounding environment condition.
Optionally, the evaluation module is specifically configured to:
summarizing the identification result, and inputting the identification result into the vehicle collision risk evaluation model;
and outputting the evaluation result through the vehicle collision risk evaluation model.
Optionally, the sensor includes a GPS sensor, a vehicle-mounted camera, a vehicle-mounted radar, a road measurement camera, a road measurement radar, a steering wheel pressure sensor, a traffic microwave detector, a traffic control time signal receiver, a rainfall sensor, and a temperature sensor.
Optionally, the system further includes:
and the early warning module is used for determining an early warning level according to the evaluation result after the evaluation result is generated and sending early warning information corresponding to the early warning level.
According to the collision risk evaluation system based on the vehicle collision risk evaluation model, the driving information of the current vehicle is detected through the sensor, the driving information is screened to obtain the risk factor information of the current vehicle, the risk factor information of the current vehicle is preliminarily identified, an identification result is generated, and the identification result is calculated by using the pre-established vehicle collision risk evaluation model to generate the evaluation result, so that the vehicle collision risk can be accurately evaluated, and the driving safety of the vehicle is ensured.
An embodiment of the present invention further provides a vehicle, which includes the collision risk evaluation system based on the vehicle collision risk evaluation model in the embodiment of the above aspect.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a method of building a vehicle collision risk assessment model according to one embodiment of the present invention;
FIG. 2 is a schematic diagram of a vehicle collision risk assessment system according to one embodiment of the present invention;
FIG. 3 is a flowchart of a method of building a vehicle collision risk assessment model according to another embodiment of the present invention;
FIG. 4 is a flow chart of a collision risk assessment method based on a vehicle collision risk assessment model according to one embodiment of the present invention;
FIG. 5 is a flow chart of a collision risk assessment method based on a vehicle collision risk assessment model according to another embodiment of the present invention;
FIG. 6 is a block diagram of a collision risk assessment system based on a vehicle collision risk assessment model according to one embodiment of the present invention;
FIG. 7 is a block diagram of a collision risk assessment system based on a vehicle collision risk assessment model according to an embodiment of the present invention;
fig. 8 is a block diagram of a collision risk evaluation system based on a vehicle collision risk evaluation model according to another embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
A method of establishing a vehicle collision risk evaluation model and a collision risk evaluation method according to an embodiment of the present invention will be described below with reference to the drawings.
Fig. 1 is a flowchart of a method of establishing a vehicle collision risk evaluation model according to an embodiment of the present invention.
As shown in fig. 1, the method for establishing the vehicle collision risk evaluation model includes:
and S101, establishing a vehicle collision risk evaluation system.
At present, in order to reduce the probability of vehicle collision, image information or video information is mainly acquired through a front-view camera mounted on a vehicle, parameters of a front vehicle or a pedestrian are extracted through a feature recognition algorithm, and then the probability of collision risk is judged by combining information such as the speed and the acceleration of the vehicle. However, this method has the following drawbacks: image information or video information is detected only by the forward-looking camera, the information source is single, and the situation that a single sensor fails is difficult to deal with; the visual field range of the camera is narrow, and the camera cannot be covered comprehensively; the characteristics of the front vehicle or the pedestrian can be accurately identified only when the front vehicle or the pedestrian is within a certain distance, and the collision risk cannot be analyzed in time when the identification distance is too close; only the objective factors of the pedestrians are considered independently, and the influence of the subjective mental state of the driver is not considered; the judgment result is incomplete and the reliability is low because the judgment result is not combined with the traffic control signal; and a static evaluation calculation mode is adopted, and parameters of dynamic development such as time, space and the like are not involved. Therefore, the invention provides a method for establishing a vehicle collision risk evaluation model, which comprehensively considers all factors of the vehicle collision risk, establishes a comprehensive vehicle collision risk evaluation model with high reliability and provides a reliable data basis for vehicle collision risk evaluation.
In one embodiment of the invention, a vehicle collision risk assessment system is established. The system can be divided into two levels, namely a first evaluation index at a first level and a second evaluation index at a second level. The first evaluation index may be a plurality of first evaluation indexes, and each first evaluation index includes at least one second evaluation index.
In the present embodiment, as shown in fig. 2, the first evaluation index may include a pedestrian index, a driver index, a road index, a time index, and a space index. Wherein the pedestrian indicators further include relative speed, location, distance, age, and health; the driver metrics further include risk awareness, risk perception, risk tolerance, and risk disposition; the road indicators further include grade, curvature, maximum speed per hour, complexity, and marking clarity; the time index further includes a time period and a date; the spatial indicators further include facility integrity and weather severity. That is to say, the vehicle collision risk evaluation system of the embodiment has 5 evaluation indexes in the first hierarchy and 18 evaluation indexes in the second hierarchy, and the influence of multi-dimensional multi-factors in an actual traffic scene is considered in a centralized manner, so that subjective evaluation and objective evaluation are combined, and qualitative evaluation and quantitative evaluation are combined.
S102, respectively establishing a first comparison judgment matrix corresponding to a plurality of first evaluation indexes and a second comparison judgment matrix corresponding to at least one second evaluation index based on an analytic hierarchy process.
And respectively establishing a first comparison judgment matrix corresponding to the plurality of first evaluation indexes and a second comparison judgment matrix corresponding to at least one second evaluation index by utilizing an analytic hierarchy process.
In one embodiment of the present invention, the pairwise comparison decision matrix may be established using a 0.1-0.9 scaling method. As shown in the table 1 below, the following examples,
TABLE 1
The establishing method of the first comparative judgment matrix corresponding to the first evaluation index compares every two according to the importance of the first evaluation index; the method for establishing the second comparison judgment matrix corresponding to the second evaluation index is the same as the method for establishing the first comparison judgment matrix, namely, the importance of the second evaluation index is compared pairwise under the same first evaluation index. It should be understood that the second evaluation index, which is not under the same first evaluation index, is not compared between them. The paired comparison judgment matrix is established by the method, different evaluation indexes can be compared to obtain the weights corresponding to the evaluation indexes, the hierarchy is clear, the calculation process is simplified, and the calculation amount is reduced.
For example, for the vehicle collision risk evaluation, it includes 5 elements of a pedestrian index, a driver index, a road index, a time index, and a space index. R11 represents the comparison result of the pedestrian index and the pedestrian index, R12 represents the comparison result of the pedestrian index and the driver index, R13 represents the comparison result of the pedestrian index and the road index, and so on, a matrix R can be established as follows:
wherein the element of R is represented by RijI and j can be changed correspondingly according to the number of the evaluation indexes.
According to the importance of the above indexes, the matrix can be obtained as follows:
s103, calculating the weights of the plurality of first evaluation indexes according to the first comparison judgment matrix, and calculating the weight of the second evaluation index according to the second comparison judgment matrix.
After the first comparison judgment matrix and the second comparison judgment matrix are established, the weight of each evaluation index in the matrixes can be calculated respectively.
Specifically, the weight calculation formula may be utilized to calculate the weight corresponding to each index.
Wherein the weight calculation formula is
rijN is the number of elements (index number) and wi is the weight.
For example, the driver index has a weight of 0.31, the pedestrian index has a weight of 0.24, the road index has a weight of 0.20, the space index has a weight of 0.15, and the time index has a weight of 0.10.
And S104, establishing a vehicle collision risk evaluation model according to the weights of the first evaluation indexes and the weights of the second evaluation indexes.
The vehicle collision risk evaluation model is a linear weighting model.
For example, the pedestrian indexes include five indexes, i.e., relative speed, position, distance, age, and health degree, and the five indexes are assumed to have weights of 0.19, 0.28, 0.23, 0.13, and 0.17. Then, the pedestrian index corresponds to the collision risk evaluation model of 0.19 × relative speed +0.28 × position +0.23 × distance +0.13 × age +0.17 × degree of health.
Similarly, the final vehicle collision risk evaluation model is 0.24 × pedestrian index +0.31 × driver index +0.20 × road index +0.10 × time index +0.15 × space index.
According to the method for establishing the vehicle collision risk evaluation model, a vehicle collision risk evaluation system is established, a first comparison judgment matrix corresponding to a plurality of first evaluation indexes and a second comparison judgment matrix corresponding to at least one second evaluation index are respectively established based on an analytic hierarchy process, the weights of the plurality of first evaluation indexes are calculated according to the first comparison judgment matrix, the weights of the second evaluation indexes are calculated according to the second comparison judgment matrix, the vehicle collision risk evaluation model is established according to the weights of the plurality of first evaluation indexes and the weights of the second evaluation indexes, all factors of vehicle collision risk are considered, a comprehensive vehicle collision risk evaluation model with high reliability is established, and a reliable data basis is provided for vehicle collision risk evaluation.
In another embodiment of the present invention, as shown in fig. 3, the method may comprise the steps of:
s105, before calculating the weights of the plurality of first evaluation indexes and the weights of the plurality of second evaluation indexes, determines the first comparison determination matrix and the second comparison determination matrix as a consistency matrix.
The traditional weight calculation method comprises multiple steps of element multiplication, evolution, normalization, maximum feature root solving and the like in a matrix. Especially, when the matrix does not conform to the consistency, repeated calculation is needed, and the calculation amount is large.
In the embodiment, the elements of the established matrix R, R are represented as Rij. As long as r is satisfiedij＝1-rjiAnd if the condition is met, the constructed matrix R can be confirmed to be a consistency matrix, consistency check is not required to be additionally carried out, and the calculated amount is reduced.
In order to implement the above embodiments, the present invention further provides a collision risk evaluation method based on a vehicle collision risk evaluation model, and fig. 4 is a flowchart of the collision risk evaluation method based on the vehicle collision risk evaluation model according to an embodiment of the present invention, as shown in fig. 4, the method includes:
s401, the running information of the current vehicle is detected by a sensor.
In one embodiment of the present invention, the traveling information of the current vehicle may be detected by various sensors. The sensor comprises a GPS sensor, a vehicle-mounted camera, a vehicle-mounted radar, a road measurement camera, a road measurement radar, a steering wheel pressure sensor, a traffic microwave detector, a traffic control time signal receiver, a rainfall sensor and a temperature sensor.
S402, screening the driving information to acquire the risk factor information of the current vehicle.
Specifically, the driving information may be screened, and risk factor information participating in risk evaluation may be screened from the driving information of the current vehicle. The running information may be information related to the running of the vehicle, such as vehicle speed, vehicle acceleration, GPS information, and the like, which are detected by all sensors mounted on the vehicle. And screening the driving information to screen out risk factor information related to collision risk evaluation, such as pedestrian information, driver information, road information, time information and space information.
For example, time information, longitude and latitude information, etc. in the GPS information may be extracted.
And S403, carrying out primary identification on the risk factor information of the current vehicle and generating an identification result.
The recognition result may include, among other things, a pedestrian status, a driver status, a road condition, a traffic flow condition, and a surrounding environment condition.
Specifically, the state of a trip person is identified according to pedestrian information; identifying a driver state according to the driver information; analyzing the road condition according to the road information; analyzing the traffic flow condition according to the time information; and analyzing the ambient environment condition according to the spatial information.
And S404, calculating the recognition result by using a pre-established vehicle collision risk evaluation model to generate an evaluation result.
Specifically, the recognition result may be input as an input to a vehicle collision risk evaluation model established in advance, and the evaluation result may be output by the vehicle collision risk evaluation model. The vehicle collision risk evaluation model is established by the establishing method of the vehicle collision risk evaluation model described in the embodiment of the first aspect.
According to the collision risk evaluation method based on the vehicle collision risk evaluation model, the driving information of the current vehicle is detected through the sensor, the driving information is screened to obtain the risk factor information of the current vehicle, the risk factor information of the current vehicle is preliminarily identified, an identification result is generated, and the identification result is calculated by using the pre-established vehicle collision risk evaluation model to generate the evaluation result, so that the vehicle collision risk can be accurately evaluated, and the driving safety of the vehicle is ensured.
In another embodiment of the present invention, as shown in fig. 5, the method may comprise the steps of:
s405, after the evaluation result is generated, determining an early warning level according to the evaluation result, and sending out early warning information corresponding to the early warning level.
According to the collision risk evaluation method based on the vehicle collision risk evaluation model, the early warning level is determined according to the evaluation result, and the early warning information corresponding to the early warning level is sent out, so that the early warning can be effectively carried out on the driver, the vehicle is prevented from colliding, and the safety is improved.
The following describes in detail a method for establishing a vehicle collision risk evaluation model and a collision risk evaluation method based on the vehicle collision risk evaluation model, with a specific example:
firstly, a vehicle collision risk evaluation system is established, and the system comprises 5 primary indexes and 18 secondary indexes. The first-level indexes are pedestrian indexes, driver indexes, road indexes, time indexes and space indexes.
The pedestrian indexes further comprise 5 secondary indexes: relative speed, location, distance, age, health. Relative speed refers to the speed of movement of the pedestrian relative to the vehicle, with greater speed giving higher risk. The position is a specific position of the pedestrian on a lane where the vehicle is located, the lane edge is used as an origin, the advancing direction of the pedestrian is used as a coordinate axis, and the risk is higher when the pedestrian stands in the middle of the road. The distance refers to a distance between the pedestrian and the vehicle in the lane direction, and the closer the distance, the higher the risk. Age refers to greater uncertainty in the activity of a child or elderly, with less or greater age and higher risk. The health degree refers to the condition that the pedestrians have physical defects such as deafness, dumb, blind people, walking sticks and wheelchairs, and the smaller the health degree is, the higher the risk is.
The driver indicators further include 4 secondary indicators: risk awareness, risk perception, risk tolerance, risk disposition. The risk awareness refers to awareness of potential driving risks of pedestrians, roads, time and space of a driver in an actual traffic environment. The risk perception refers to the perception capability of a driver on pedestrian risk, road risk, time risk and space risk, and the reduction of the risk perception capability of the driver due to the self state of the driver, such as sudden illness and driving fatigue. The risk tolerance refers to the tolerance degree of a driver to potential driving risks in the aspects of pedestrians, roads, time and space under an actual traffic environment, for example, if some drivers find that a pedestrian steps on the brake 2 meters ahead, and some drivers find that a pedestrian steps on the brake 5 meters ahead, the tolerance degrees of the two drivers to the pedestrian are different, and depend on the subjective habits of the individual. The secondary index risk handling means that the driver's emergency handling capability, driving experience, reaction time, attention concentration degree and the like directly influence the driver's control of the vehicle when a collision risk occurs.
The road indexes further include 5 secondary indexes: grade, curvature, maximum speed per hour, complexity, reticle definition. Grade means that the greater the grade, the higher the risk. Curvature refers to the degree of curvature of the road, with greater curvature giving higher risk. The highest hourly speed is the highest vehicle speed allowed, the higher the speed limit, the higher the risk. Complexity means that the more complex the road conditions, the higher the risk, e.g. a continuous downhill slope, multiple turns, a narrowing of the lane, a change from a straight road to a sharp turn, etc. The marking definition refers to the display definition of the marking of a guide arrow of straight running, left turning, right turning, turning around and the like on the road surface.
The time indicators further include 2 secondary indicators: time period and date. The time interval refers to the peak time on duty, the traffic jam is caused, and the risk is higher; or greater risk at night than during the day. The date means that the flow of people is large on weekends or holidays, and the risk is large.
The spatial index further includes 2 secondary indexes: facility sophistication and weather severity. The facility completeness refers to the completeness of facilities such as traffic lights, sidewalk indication boards, school indication boards, turning indication boards, speed limit indication boards and the like. Weather severity refers to high-temperature hot weather, and heavy rain, heavy snow cause the wet and slippery degree in road surface, and the visibility of haze serious influence, weather is abominable, and the risk is big more.
Then, the indexes are used as elements for establishing a pair comparison judgment matrix, so that the matrix is established.
For the vehicle collision risk evaluation, the vehicle collision risk evaluation comprises 5 elements of a pedestrian index, a driver index, a road index, a time index and a space index. R11 represents the comparison result of the pedestrian index and the pedestrian index, R12 represents the comparison result of the pedestrian index and the driver index, R13 represents the comparison result of the pedestrian index and the road index, R14 represents the comparison result of the pedestrian index and the time index, R15 represents the comparison result of the pedestrian index and the space index, and so on, the matrix R can be established as follows:
wherein the element of R is represented by RijI and j can be changed correspondingly according to the number of the evaluation indexes.
According to the importance of the above indexes, the matrix can be obtained as follows:
therefore, the driver index has the largest weight among the five factors, which shows that the driver has global control force on the driving behavior of the vehicle and bears the most main responsibility on the collision risk of the pedestrian.
In the same way, the pedestrian index matrix
Driver index matrix
Road index matrix
Time index matrix
Spatial index matrix
After the matrix is established, it may be determined whether the matrix is a consistency matrix. I.e. the elements in the matrix R are denoted RijAs long as r is satisfiedij＝1-rjiAnd if the condition is met, the matrix R can be determined to be a consistency matrix without additionally carrying out consistency check, so that the calculation amount is reduced.
Next, the weight corresponding to each index is calculated by using a weight calculation formula.
Wherein the weight calculation formula is
rijN is the number of elements (index number) and wi is the weight.
The importance ranking of the primary index is: the obtained weight values are 0.31, 0.24, 0.20, 0.15 and 0.10 in sequence.
Similarly, the importance of the pedestrian indexes is ranked as: position > distance > relative speed > health > age, the weight values obtained are 0.28, 0.23, 0.19, 0.17, 0.13 in that order.
Similarly, the importance ranking of the driver indicators is: risk tolerance > risk treatment > risk perception > risk awareness, and the obtained weight values are 0.35, 0.28, 0.22 and 0.15 in sequence.
Similarly, the importance of the road indexes is ranked as: complexity > curvature > maximum speed per hour > gradient > marking definition, and the obtained weight values are 0.27, 0.24, 0.20, 0.16 and 0.13 in sequence.
Similarly, the importance of the time index is ranked as: time period > date, the weight values obtained were 0.6 and 0.4 in order.
Similarly, the importance of the spatial index is ranked as: weather severity is greater than facility perfection, and the obtained weight values are 0.7 and 0.3 in sequence.
In summary, the weight of each evaluation index is shown in table 2.
TABLE 2
After the weights corresponding to the indexes are obtained, a quantitative value of the vehicle collision risk can be calculated by using a vehicle collision risk evaluation model.
Specifically, a linear weighting model is adopted as
Where risk is the risk of vehicle collision, Sp(x) Risk function (representing pedestrian status) for pedestrian index, Sd(x) A risk function (representing the driver state) for the driver indicator, Sr(x) Risk function (representing road conditions) for road indexes, St(x) A risk function (representing traffic flow situation) being a time index, Se(x) Is a risk function (representing the ambient conditions) for the spatial index, wi is the weight of each index, Si(x) And (4) risk functions corresponding to the indexes. Wherein, the value of the risk function is analyzed and processed by data collected by a plurality of sensors under the actual traffic environmentAnd then fusing to obtain the compound.
Finally, risk ═ 0.24S was obtainedp(x)+0.31Sd(x)+0.20Sr(x)+0.10St(x)+0.15Se(x)。
Wherein the value of the risk function represents the degree of risk of the vehicle collision, a smaller value represents a smaller risk of collision, and a larger value represents a larger risk of collision.
It should be understood that the risk function itself is also derived using a linear weighting model.
Such as Sp(x) Relative velocity +0.28 +0.23 distance +0.13 age +0.17 degree of health.
In the same way, Sd(x)、Sr(x)、St(x)、Se(x) All are obtained by using a linear weighting model, and details are not described here.
After the quantitative value (evaluation result) of the vehicle collision risk is obtained, early warning information can be sent to the driver according to the evaluation result to remind the driver to take measures so as to avoid collision. The early warning information can be divided into a low level, a medium level and a high level according to the danger degree. I.e. a quantified value of 1-3 indicates a low risk, a quantified value of 4-7 indicates a medium risk, and a quantified value of 8-10 indicates a high risk. The low risk early warning time may be set to 0-3s, the medium risk early warning time may be set to 3-10s, and the high risk early warning time may be set to 10-20 s.
The collision risk evaluation method based on the vehicle collision risk evaluation model has the following advantages:
the subjective evaluation and the objective evaluation are combined, the qualitative evaluation and the quantitative evaluation are combined, the evaluation indexes are comprehensive and complete, the reliability is high, the hierarchy is clear, the calculation process is simplified, and the calculation amount is reduced.
In order to realize the embodiment, the invention further provides a collision risk evaluation system based on the vehicle collision risk evaluation model.
Fig. 6 is a block diagram of a collision risk evaluation system based on a vehicle collision risk evaluation model according to an embodiment of the present invention, and as shown in fig. 6, the system includes a sensing module 610, a detection module 620, a recognition analysis module 630, and an evaluation module 640.
The sensing module 610 is used for detecting the running information of the current vehicle.
And the detection module 620 is configured to screen the driving information to obtain risk factor information of the current vehicle, and output the risk factor information of the current vehicle to the identification and analysis module.
And the identification analysis module 630 is configured to perform preliminary identification on the risk factor information of the current vehicle, and output an identification result to the evaluation module.
And the evaluation module 640 is used for calculating the recognition result by using a pre-established vehicle collision risk evaluation model so as to generate an evaluation result.
Wherein the vehicle collision risk evaluation model is established by using the method described in the embodiment of the first aspect.
Further, as shown in fig. 7, the detection module 620 further includes a pedestrian detection sub-module 621, a driver detection sub-module 622, a road detection sub-module 623, a time detection sub-module 624, and a space detection sub-module 625.
And a pedestrian detection submodule 621 configured to screen out pedestrian information from the driving information.
And a driver detection submodule 622 for screening out driver information from the travel information.
And a road detection sub-module 623 for screening road information from the driving information.
And the time detection submodule 624 is used for screening out time information from the running information.
And the space detection submodule 625 is configured to screen out space information from the driving information.
As shown in fig. 7, information detected by the GPS sensor, the vehicle-mounted camera, the vehicle-mounted radar, the drive test camera, and the drive test radar may be sent to the pedestrian detection submodule 621, and the pedestrian detection submodule 621 acquires pedestrian information; information detected by the vehicle-mounted camera and the steering wheel pressure sensor can be sent to the driver detection submodule 622, and driver information is obtained by the driver detection submodule 622; information detected by the vehicle-mounted camera, the road detection camera, the traffic microwave detector and the GPS sensor can be sent to the road detection submodule 623, and the road detection submodule 623 acquires road information; information detected by the signal receiver and the GPS sensor during traffic control can be sent to the time detection submodule 624, and the time detection submodule 624 acquires time information; information detected by the rainfall sensor, the temperature sensor, the vehicle-mounted camera and the drive test camera can be sent to the space detection submodule 625, and the space detection submodule 625 acquires space information.
As shown in fig. 7, the recognition analysis module 630 specifically includes: a pedestrian status identification submodule 631, a driver status identification submodule 632, a road condition analysis submodule 633, a time analysis submodule 634 and a space analysis submodule 635.
And the pedestrian state identification sub-module 631 is used for receiving the pedestrian information and identifying the state of the trip person.
And a driver status identification submodule 632, configured to receive the driver information and identify the driver status.
And the road condition analysis submodule 633 is used for receiving the road information and analyzing the road condition.
And the time analysis sub-module 634 is used for receiving the time information and analyzing the traffic flow condition.
The spatial analysis submodule 635 is configured to receive the spatial information and analyze the ambient environment.
For example: the pedestrian state is the quantification of 3 indexes of relative speed, position and distance. The vehicle-mounted camera and the vehicle-mounted radar can assist in judging the position of the pedestrian when the distance between the pedestrian and the vehicle is very short. The roadside camera and the roadside radar can assist in judging the age and the health degree of the pedestrian.
The state of the driver can be qualitatively judged by combining the data detected by the vehicle-mounted camera and the steering wheel pressure sensor with the basic information such as historical driving data, driver age, driving age and the like, so as to obtain a quantitative value. The vehicle-mounted camera mainly detects the state of a driver, for example, the fact that the driver does not decelerate during deceleration indicates that risk consciousness of the driver is weak, risk tolerance is strong, and risk handling capacity is weak. When the speed limit board exists, the driver does not see the speed limit board, and the driver is indicated to have weak risk perception if passing the overspeed.
The road condition can be obtained by the vehicle-mounted camera, the road side camera and the traffic microwave detector. 2 indexes of road gradient and marking line definition are mainly obtained through a vehicle-mounted camera, and a roadside camera is used as an auxiliary index; curvature, highest speed per hour, 3 indexes of complexity are mainly sent to the vehicle by the roadside camera through the vehicle-road communication technology, and the vehicle-mounted camera for identifying the speed limit board is assisted. Traffic microwave detectors are also capable of detecting the highest speed per hour and complexity.
The traffic flow condition can be acquired by a GPS sensor and a traffic control time signal receiver. The time period and date 2 indicators of time are derived primarily from GPS signals. The GPS sensor and the traffic control time signal receiver are complementary to each other. Namely, the traffic flow conditions in different time periods are different, and the traffic flow in saturday is large.
The sensors used for detecting the ambient environment condition are a rainfall sensor, a vehicle-mounted camera, a road side camera and a temperature sensor. The 2 indexes of the space are obtained by fusing information detected by vehicle-mounted sensors such as a rainfall sensor and roadside cameras. For example, a high rain load or a high temperature indicates a high degree of weather severity. And if the vehicle-mounted camera does not find the curve reminding sign or the speed limit sign in the curve road section, the facility perfectness is low.
The evaluation module 640 summarizes the recognition results, inputs the recognition results into a pre-established vehicle collision risk evaluation model, and calculates risk factor information by using the model to generate an evaluation result.
According to the collision risk evaluation system based on the vehicle collision risk evaluation model, the driving information of the current vehicle is detected through the sensor, the driving information is screened to obtain the risk factor information of the current vehicle, the risk factor information of the current vehicle is preliminarily identified, an identification result is generated, and the identification result is calculated by using the pre-established vehicle collision risk evaluation model to generate the evaluation result, so that the vehicle collision risk can be accurately evaluated, and the driving safety of the vehicle is ensured.
In another embodiment of the present invention, as shown in fig. 8, the system may further include an early warning module 650.
The early warning module 650 is configured to determine an early warning level according to the evaluation result after the evaluation result is generated, and send out early warning information corresponding to the early warning level.
According to the collision risk evaluation system based on the vehicle collision risk evaluation model, disclosed by the embodiment of the invention, the early warning level is determined according to the evaluation result, and the early warning information corresponding to the early warning level is sent out, so that the early warning can be effectively carried out on the driver, the vehicle collision is avoided, and the safety is improved.
In order to achieve the above embodiments, the present invention further provides a vehicle, which may include the collision risk evaluation system based on the vehicle collision risk evaluation model of the above aspect.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a random access memory (ram), a read-only memory (rom), an erasable programmable read-only memory (eeprom or flash memory), an optical fiber device, and a portable compact disc read-only memory (cdrom). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for realizing a logic function for a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a programmable gate array (pga), a field programmable gate array (fpga), and the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware that is related to instructions of a program, and the program may be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A method for establishing a vehicle collision risk evaluation model is characterized by comprising the following steps:
establishing a vehicle collision risk evaluation system, wherein the vehicle collision risk evaluation system comprises a plurality of first evaluation indexes, and each first evaluation index comprises at least one second evaluation index;
respectively establishing a first comparison judgment matrix corresponding to the plurality of first evaluation indexes and a second comparison judgment matrix corresponding to the at least one second evaluation index based on an analytic hierarchy process;
calculating the weights of the plurality of first evaluation indexes according to the first comparison judgment matrix, and calculating the weight of the second evaluation index according to the second comparison judgment matrix;
establishing a vehicle collision risk evaluation model according to the weights of the first evaluation indexes and the weights of the second evaluation indexes, wherein the vehicle collision risk evaluation model is a linear weighting model, and numerical values corresponding to the second evaluation indexes in the vehicle collision risk evaluation model are obtained through data collected by a sensor;
wherein the first evaluation index comprises a pedestrian index, a driver index, a road index, a time index and a space index;
the pedestrian index includes second evaluation indexes including relative speed, position, distance, age and health degree, the driver index includes second evaluation indexes including risk awareness, risk perception, risk tolerance and risk disposition, the road index includes second evaluation indexes including slope, curvature, highest speed per hour, complexity and marking definition, the time index includes second evaluation indexes including period and date, the space index includes second evaluation indexes including facility integrity and weather severity.
2. The method of claim 1, further comprising:
determining the first and second comparison determination matrices as a consistency matrix before calculating the weights of the plurality of first evaluation indices and the weights of the second evaluation indices.
3. A collision risk evaluation method based on a vehicle collision risk evaluation model is characterized by comprising the following steps:
detecting the driving information of the current vehicle through a sensor;
screening the driving information to acquire risk factor information of the current vehicle;
preliminarily identifying the risk factor information of the current vehicle and generating an identification result;
calculating the recognition result by using a pre-established vehicle collision risk evaluation model to generate an evaluation result, wherein the vehicle collision risk evaluation model is established by adopting the method of any one of claims 1-2.
4. The method of claim 3, wherein the risk factor information of the current vehicle includes pedestrian information, driver information, road information, time information, and spatial information.
5. The method of claim 4, wherein the recognition result includes a pedestrian status, a driver status, a road condition, a traffic flow condition, and a surrounding environment condition, the preliminary recognition of the risk factor information of the current vehicle is performed, and the generation of the recognition result includes:
identifying a pedestrian state according to the pedestrian information;
identifying a driver state according to the driver information;
analyzing the road condition according to the road information;
analyzing the traffic flow condition according to the time information;
and analyzing the ambient environment condition according to the spatial information.
6. The method of claim 5, wherein calculating the recognition result using a pre-established vehicle collision risk assessment model to generate an assessment result comprises:
and inputting the recognition result into the vehicle collision risk evaluation model, and outputting the evaluation result through the vehicle collision risk evaluation model.
7. The method of claim 3, wherein the sensor comprises a GPS sensor, an onboard camera, an onboard radar, a drive test camera, a drive test radar, a steering wheel pressure sensor, a traffic microwave detector, a traffic control signaling receiver, a rain sensor, a temperature sensor.
8. The method of claim 3, further comprising:
and after the evaluation result is generated, determining an early warning level according to the evaluation result, and sending early warning information corresponding to the early warning level.
9. A collision risk evaluation system based on a vehicle collision risk evaluation model, comprising:
the sensing module is used for detecting the running information of the current vehicle;
the detection module is used for screening the running information to acquire the risk factor information of the current vehicle and outputting the risk factor information of the current vehicle to the identification and analysis module;
the identification analysis module is used for carrying out primary identification on the risk factor information of the current vehicle, generating an identification result and outputting the identification result to the evaluation module;
the evaluation module is used for calculating the identification result by utilizing a pre-established vehicle collision risk evaluation model to generate an evaluation result, wherein the vehicle collision risk evaluation model is established by adopting the method of any one of claims 1-2.
10. A vehicle comprising a collision risk assessment system based on a vehicle collision risk assessment model according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810714331.XA CN110660270B (en) | 2018-06-29 | 2018-06-29 | Method for establishing vehicle collision risk evaluation model and collision risk evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810714331.XA CN110660270B (en) | 2018-06-29 | 2018-06-29 | Method for establishing vehicle collision risk evaluation model and collision risk evaluation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110660270A CN110660270A (en) | 2020-01-07 |
| CN110660270B true CN110660270B (en) | 2021-09-21 |
Family
ID=69027739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810714331.XA Active CN110660270B (en) | 2018-06-29 | 2018-06-29 | Method for establishing vehicle collision risk evaluation model and collision risk evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110660270B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112740295B (en) * | 2020-03-31 | 2022-05-10 | 华为技术有限公司 | Method and device for detecting complexity of vehicle driving scene |
| CN111422189A (en) * | 2020-04-16 | 2020-07-17 | 北京首汽智行科技有限公司 | Vehicle anti-collision system |
| CN112002112B (en) * | 2020-08-25 | 2021-11-02 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Security and protection efficiency evaluation method and system for perimeter intrusion alarm system of high-speed railway |
| US11524703B2 (en) * | 2020-11-24 | 2022-12-13 | GM Global Technology Operations LLC | Method and system for interactive hypothesis estimation of multi-vehicle traffic for autonomous driving |
| CN113487912B (en) * | 2021-06-21 | 2023-03-28 | 上汽通用五菱汽车股份有限公司 | Traffic accident early warning and protecting method, automobile and readable storage medium |
| CN113506036A (en) * | 2021-07-29 | 2021-10-15 | 清华大学 | Vehicle collision risk evaluation method and device based on pedestrian psychological safety distance |
| CN114620013A (en) * | 2022-03-16 | 2022-06-14 | 中国第一汽车股份有限公司 | Method, device, equipment and medium for protecting pedestrians in front of vehicle |
| CN114822018A (en) * | 2022-04-02 | 2022-07-29 | 北华大学 | Detection method for improving road traffic safety |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104978492A (en) * | 2015-07-09 | 2015-10-14 | 彩虹无线（北京）新技术有限公司 | Safety driving evaluation method based on telematics data flow |
| CN105930975A (en) * | 2016-04-26 | 2016-09-07 | 天津大学 | Sudden water pollution event risk evaluation method for water conveyance project |
| CN106228499A (en) * | 2016-07-06 | 2016-12-14 | 东南大学 | A kind of cargo security evaluation model based on people's bus or train route goods multi-risk System source |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6380930B2 (en) * | 2014-08-22 | 2018-08-29 | 株式会社テクトム | Information processing apparatus and information processing method |
| CN104299450B (en) * | 2014-10-23 | 2016-11-09 | 西安电子科技大学 | Vehicle collision prewarning method based on analytic hierarchy process (AHP) and grey fuzzy |
| CN107784251A (en) * | 2016-08-25 | 2018-03-09 | 大连楼兰科技股份有限公司 | The method evaluated based on image recognition technology driving behavior |
| CN107784587B (en) * | 2016-08-25 | 2021-09-14 | 大连楼兰科技股份有限公司 | Driving behavior evaluation system |
| CN106491144B (en) * | 2016-09-22 | 2019-07-05 | 昆明理工大学 | A kind of test and evaluation method of the latent risk perceptions ability of driver |
| CN107169202A (en) * | 2017-05-17 | 2017-09-15 | 河海大学 | A kind of computational methods kept at a distance safely between traveling vehicle |
-
2018
- 2018-06-29 CN CN201810714331.XA patent/CN110660270B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104978492A (en) * | 2015-07-09 | 2015-10-14 | 彩虹无线（北京）新技术有限公司 | Safety driving evaluation method based on telematics data flow |
| CN105930975A (en) * | 2016-04-26 | 2016-09-07 | 天津大学 | Sudden water pollution event risk evaluation method for water conveyance project |
| CN106228499A (en) * | 2016-07-06 | 2016-12-14 | 东南大学 | A kind of cargo security evaluation model based on people's bus or train route goods multi-risk System source |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110660270A (en) | 2020-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110660270B (en) | Method for establishing vehicle collision risk evaluation model and collision risk evaluation method | |
| Peng et al. | Multi-parameter prediction of drivers' lane-changing behaviour with neural network model | |
| JP4396597B2 (en) | Dangerous reaction point recording system and driving support system | |
| US9082285B2 (en) | System and method for determining vehicle driving status information-based driving concentration | |
| CN105405321A (en) | Safety early warning method during running of vehicles on freeway and system | |
| US10008118B2 (en) | Vehicle collision avoidance system and method | |
| CN109522784A (en) | For distinguishing the device and method that can be crossed object and object can not be crossed | |
| CN104115186A (en) | Three-dimensional object detection device | |
| US11745745B2 (en) | Systems and methods for improving driver attention awareness | |
| JP2010086070A (en) | Road traffic information providing system and method | |
| CA3056611A1 (en) | Automatic warning generation system intended for the users of a road | |
| CN112758088A (en) | Dangerous source reminding method and advanced driving assistance system | |
| US20230234618A1 (en) | Method and apparatus for controlling autonomous vehicle | |
| CN116312045A (en) | Vehicle danger early warning method and device | |
| CN116052475A (en) | Vehicle risk early warning method, system, storage medium and device | |
| CN113428160B (en) | Dangerous scene prediction method, device and system, electronic equipment and storage medium | |
| CN114664085A (en) | Dangerous road section reminding method and device, electronic equipment and medium | |
| Cho et al. | Operational Design Domain (ODD) Framework for Driver-Automation Systems | |
| CN116461546A (en) | Vehicle early warning method, device, storage medium and processor | |
| JP7276276B2 (en) | Dangerous driving detection device, dangerous driving detection system, and dangerous driving detection program | |
| JP7347390B2 (en) | Driving evaluation device, driving evaluation system, and driving evaluation program | |
| CN107813821B (en) | Early warning method and device | |
| CN116168542B (en) | Early warning method and system based on behavior monitoring of large vehicle | |
| Saffarzadeh et al. | Development of a new integrated surrogate safety measure for applying in intelligent vehicle systems | |
| US20240219556A1 (en) | Method for determining a speed of traffic in a route section, detection device, vehicle and central computer |
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 |