CN113569699B - Attention analysis method, vehicle, and storage medium - Google Patents
Attention analysis method, vehicle, and storage medium Download PDFInfo
- Publication number
- CN113569699B CN113569699B CN202110833696.6A CN202110833696A CN113569699B CN 113569699 B CN113569699 B CN 113569699B CN 202110833696 A CN202110833696 A CN 202110833696A CN 113569699 B CN113569699 B CN 113569699B
- Authority
- CN
- China
- Prior art keywords
- driver
- event
- data
- parameter information
- steering wheel
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 230000001133 acceleration Effects 0.000 claims description 45
- 230000006399 behavior Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000036039 immunity Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
Abstract
The invention discloses an attention analysis method, a vehicle and a storage medium, wherein the method comprises the following steps: acquiring parameter information corresponding to a road state and parameter information corresponding to at least one driving item, and discretizing the parameter information corresponding to the road state and the parameter information corresponding to the driving item; calculating a mean value and a variance value corresponding to the road state and the driving project according to the discretized parameter information; calculating to obtain prior probability corresponding to the parameter information according to the mean value and the variance value corresponding to the parameter information; and respectively calculating posterior probabilities of the driver attention concentrating event and the attention non-concentrating event according to the prior probability and a preset naive Bayesian algorithm, and judging whether the driver is concentrated according to the posterior probabilities. The invention improves the accuracy of the attention analysis of the driver and the safety of the driver in the driving process.
Description
Technical Field
The present invention relates to the field of vehicles, and more particularly, to an attention analysis method, a vehicle, and a computer-readable storage medium.
Background
The more concentrated the driver's attention during the running of the vehicle, the faster the reaction speed against the emergency situation, and the more effective the handling can be. The existing method for judging whether the driver is focused is to judge whether the driver is focused through sensor information, such as through the corner information on the steering wheel, and if the corner is larger than a threshold value, the current driver is considered to be not focused. However, in the prior art, when a method of judging information of a single sensor is adopted, data transmitted by the sensor floats in a threshold range, so that frequent judgment of a driver without focusing attention at the moment is caused, influence on a user is caused, influence caused by lane information is not fully considered, and when a road is curved, misjudgment is caused due to large steering angle, and judgment accuracy is not high.
Disclosure of Invention
The invention mainly aims to provide an attention analysis method, a vehicle and a computer readable storage medium, and aims to solve the problem that the accuracy of the existing driver attention judgment method is not high.
In order to achieve the above object, the present invention provides an attention analysis method, comprising the steps of:
acquiring parameter information corresponding to a road state and parameter information corresponding to at least one driving item, and discretizing the parameter information corresponding to the road state and the parameter information corresponding to the driving item;
calculating a mean value and a variance value corresponding to the road state and the driving project according to the discretized parameter information;
calculating to obtain prior probability corresponding to the parameter information according to the mean value and the variance value corresponding to the parameter information;
and respectively calculating posterior probabilities of the driver attention concentrating event and the attention non-concentrating event according to the prior probability and a preset naive Bayesian algorithm, and judging whether the driver is concentrated according to the posterior probabilities.
Optionally, the parameter information corresponding to the road state includes road information corresponding to the road state; the parameter information corresponding to the driving project comprises driver behavior information corresponding to driver behaviors and vehicle dynamic behavior information corresponding to vehicle dynamic behaviors; the driver behavior information includes steering wheel hand torque value data and steering wheel corner value data, the vehicle dynamic behavior information includes lateral acceleration data, and the road information includes lateral deviation data.
Optionally, the step of obtaining the parameter information corresponding to the road state and the parameter information corresponding to the at least one driving item, and performing discretization processing on the parameter information corresponding to the road state and the parameter information corresponding to the driving item includes:
and acquiring steering wheel hand force torque value data, steering wheel corner value data, vehicle transverse acceleration data and transverse deviation data in a preset time period in the driving process according to a preset time interval, and discretizing the parameter information corresponding to the road state and the parameter information corresponding to the driving project, wherein the preset time interval is smaller than the preset time period.
Optionally, the step of calculating the mean value and the variance value corresponding to the road state and the driving item according to the discretized parameter information includes:
and respectively calculating the mean value and the variance corresponding to each parameter information according to the discretized steering wheel hand force torque value data, the steering wheel corner value data, the vehicle transverse acceleration data and the transverse deviation data.
Optionally, the step of calculating the prior probability corresponding to the parameter information according to the mean value and the variance value corresponding to the parameter information includes:
and inputting average values and variance values corresponding to the hand force torque value data of the steering wheel, the steering wheel rotation angle value data, the vehicle transverse acceleration data and the transverse deviation data, and respectively calculating the prior probabilities corresponding to the hand force torque value data of the steering wheel, the steering wheel rotation angle value data, the vehicle transverse acceleration data and the transverse deviation data through the preset conditional probability formula.
Optionally, the step of calculating the posterior probability of the driver attention concentrating event and the attention non-concentrating event according to the prior probability and a preset naive bayes algorithm, and judging whether the driver is concentrated according to the posterior probability includes:
respectively calculating posterior probabilities of driver concentration and driver inattention acquired according to preset time intervals in each preset time period according to the prior probability and a preset naive Bayesian algorithm;
if the probability of the driver's inattention obtained according to the preset time interval each time within the preset time period is larger than the posterior probability of the driver's inattention, judging that the driver's inattention;
and if the probability of the driver concentration acquired according to the preset time interval at any time within the preset time period is larger than the posterior probability of the driver concentration, judging that the driver concentration is achieved.
Optionally, the posterior probability of driver inattention is calculated by the following formula:
P(y 1 |x)＝p(x 1 |y 1 )*p(x 2 |y 1 )*p(x 3 |y 1 )*p(x 4 |y 1 )*p(y 1 )；
the posterior probability of driver concentration is calculated by the following formula:
P(y 2 |x)＝p(x 1 |y 2 )*p(x 2 |y 2 )*p(x 3 |y 2 )*p(x 4 |y 2 )*p(y 2 )；
wherein X is a combination of an event in which steering wheel hand torque data effectively exist, an event in which steering wheel angle data effectively exist, an event in which lateral deviation data effectively exist, and an event in which lateral acceleration data effectively exist, the y is as follows 1 X is the event of inattention of the driver 1 Event, x, effectively present for steering wheel hand torque data 2 Event, x, valid for steering wheel angle data 3 Event effectively present as lateral deviation data, x 4 Events effectively present for lateral acceleration data, y 1 The x is an event in which the driver is not focused among the combination of all events, P (y 1 I x) is the probability of occurrence of an event in which the driver is not focused in the combination of all events, P (x) 1 |y 1 ) For the prior probability of occurrence of an event in which steering wheel hand torque data effectively exists in the event of driver inattention, P (x 2 |y 1 ) For the prior probability of occurrence of an event in which steering wheel angle data effectively exists in the event that the driver is not attentive, P (x 3 |y 1 ) For the prior probability of occurrence of an event in which lateral deviation data effectively exist in the event of driver inattention, P (x 4 |y 1 ) A priori probability of occurrence of an event for which lateral acceleration data effectively exists in the event that the driver is not focused;
y 2 the x is an event in which the driver is focused in the combination of all events, P (y 2 |x) is the probability of occurrence of an event that the driver is focused on in the combination of all events, P (x) 1 |y 2 ) For the prior probability of occurrence of an event in which steering wheel hand torque data effectively exists in the event of driver concentration, P (x 2 |y 2 ) For the prior probability of occurrence of an event in which steering wheel angle data effectively exists in the event of driver concentration, P (x 3 |y 2 ) For the effective presence of lateral deviation data in the event of driver concentrationPrior probability of event occurrence, P (x 4 |y 2 ) The prior probability of occurrence of an event that is effectively present for lateral acceleration data at the event that the driver is focused.
Optionally, the step of calculating the posterior probabilities of the driver attention concentrating event and the attention non-concentrating event according to the prior probability and the preset naive bayes algorithm, and judging whether the driver is concentrated includes:
and processing according to a normal distribution formula to obtain a normal distribution preset conditional probability function of the hand force torque value data of the steering wheel, the steering wheel angle value data, the vehicle transverse acceleration data and the transverse deviation data.
To achieve the above object, the present invention also provides a vehicle comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which when executed by the processor implements the steps of the attention analysis method as described above.
To achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the attention analysis method as described above.
According to the attention analysis method, the vehicle and the computer readable storage medium, the discretization processing is carried out on the parameter information corresponding to the driving item by acquiring the parameter information corresponding to the road state and the parameter information corresponding to at least one driving item, so that the data analysis is conveniently carried out by adopting the parameter information, the time and space occupation of a Bayesian algorithm are reduced, and the classification clustering capacity and the noise immunity of the system on the road information and the driving item are improved; calculating a mean value and a variance value corresponding to the driving item according to the discretized parameter information, so as to reduce errors in calculation of whether the driver is focused or not; the prior probability corresponding to the parameter information is obtained through calculation according to the mean value and the variance value corresponding to the parameter information, so that the accuracy of probability judgment on the concentration of the driver and the lack of concentration of the driver is ensured; by respectively calculating the posterior probability of the driver attention concentrating event and the attention non-concentrating event according to the prior probability and the preset naive Bayesian algorithm and judging whether the driver is concentrated according to the posterior probability, the accurate judgment of whether the driver is concentrated according to the road state and the driving project in combination with the Bayesian algorithm is realized, the influence caused by the road state is fully considered, the misjudgment caused by the lack of road information is eliminated, and meanwhile, the efficient judgment of whether the driver is concentrated is realized on the basis of not increasing the hardware cost.
Drawings
FIG. 1 is a schematic diagram of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of a first embodiment of the attention analysis method of the present invention;
fig. 3 is a detailed flowchart of step S40 in the second embodiment of the attention analysis method of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a hardware structure of a vehicle according to various embodiments of the present invention. The vehicle comprises a communication module 01, a memory 02, a processor 03 and the like. Those skilled in the art will appreciate that the vehicle illustrated in FIG. 1 may also include more or fewer components than shown, or may combine certain components, or a different arrangement of components. The processor 03 is connected to the memory 02 and the communication module 01, respectively, and a computer program is stored in the memory 02 and executed by the processor 03 at the same time.
The communication module 01 is connectable to an external device via a network. The communication module 01 can receive data sent by external equipment, and can also send data, instructions and information to the external equipment, wherein the external equipment can be electronic equipment such as a mobile phone, a tablet personal computer, a notebook computer, a desktop computer and the like.
The memory 02 is used for storing software programs and various data. The memory 02 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data or information created according to the use of the vehicle, or the like. In addition, memory 02 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
The processor 03, which is a control center of the vehicle, connects various parts of the entire vehicle using various interfaces and lines, performs various functions of the vehicle and processes data by running or executing software programs and/or modules stored in the memory 02, and calling data stored in the memory 02, thereby performing overall monitoring of the vehicle. The processor 03 may include one or more processing units; preferably, the processor 03 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, an application program, etc., and the modem processor mainly processes wireless communication. It will be appreciated that the modem processor described above may not be integrated into the processor 03.
Those skilled in the art will appreciate that the vehicle structure shown in FIG. 1 is not limiting of the vehicle and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
According to the above hardware structure, various embodiments of the method of the present invention are presented.
Referring to fig. 2, in a first embodiment of the attention analysis method of the present invention, the attention analysis method includes the steps of:
step S10, acquiring parameter information corresponding to a road state and parameter information corresponding to at least one driving item, and performing discretization processing on the parameter information corresponding to the road state and the parameter information corresponding to the driving item;
the parameter information corresponding to the road state includes road information corresponding to the road state, for example, the road information includes lateral deviation data; the parameter information corresponding to the driving item includes driver behavior information corresponding to driver behavior and vehicle dynamic behavior information corresponding to vehicle dynamic behavior. For example, the driver behavior information includes steering wheel hand torque value data and steering wheel angle value data, the vehicle dynamic behavior information includes lateral acceleration data, and the road information includes lateral deviation data. In this embodiment, the above parameter information is discretized by a supervised learning method.
Step S20, calculating a mean value and a variance value corresponding to the road state and the driving project according to the discretized parameter information;
in one embodiment, the step S20 includes:
and respectively calculating the mean value and the variance corresponding to each parameter information according to the discretized steering wheel hand force torque value data, the steering wheel corner value data, the vehicle transverse acceleration data and the transverse deviation data.
In this embodiment, the average value may be calculated by the following formula:
wherein mu is the mean value, n is the statistical number of the parameter information, and x i And the parameter information is respectively the numerical values of the hand force torque value data of the steering wheel, the steering wheel angle value data, the vehicle transverse acceleration data, the transverse deviation data and the like.
The variance can be calculated by the following formula:
wherein sigma 2 N is the number, x, of the parameter information involved in calculation, such as the steering wheel hand torque value data, the steering wheel angle value data, the vehicle lateral acceleration data, the lateral deviation data and the like i And the parameter information is respectively the numerical values of the hand force torque value data of the steering wheel, the steering wheel angle value data, the vehicle transverse acceleration data, the transverse deviation data and the like.
Step S30, calculating to obtain prior probability corresponding to the parameter information according to the mean value and the variance value corresponding to the parameter information;
the step S30 further includes the steps of:
and inputting average values and variance values corresponding to the hand force torque value data of the steering wheel, the steering wheel rotation angle value data, the vehicle transverse acceleration data and the transverse deviation data, and respectively calculating prior probabilities corresponding to the hand force torque value of the steering wheel, the steering wheel rotation angle value, the vehicle transverse acceleration and the transverse deviation through the preset conditional probability formula.
In this embodiment, the preset conditional probability formula specifically includes:
wherein x is i Parameter information respectively represented by the hand force torque value data of the steering wheel, the steering wheel angle value data, the vehicle transverse acceleration data and the transverse deviation data; y is a combination of inattentive and inattentive events, X is a combination of an event for which steering wheel hand torque data is effectively present, an event for which steering wheel corner data is effectively present, an event for which lateral deviation data is effectively present, and an event for which lateral acceleration data is effectively present; sigma (sigma) 2 The variance value is given, and mu is the mean value; wherein the effective existence of the data refers to the lateral acceleration data of the vehicle according to the acquired hand force torque data of the steering wheel, the steering wheel angle data and the lateral deviation dataAnd the sensor corresponding to the equal parameter information acquires data in a preset range.
Step S40, according to the prior probability and a preset naive Bayesian algorithm, the posterior probability of the driver attention concentrating event and the attention non-concentrating event is calculated respectively, and whether the driver is concentrated or not is judged according to the posterior probability;
according to the attention analysis method, the vehicle and the computer readable storage medium, the discretization processing is carried out on the parameter information corresponding to the driving item by acquiring the parameter information corresponding to the road state and the parameter information corresponding to at least one driving item, so that the data analysis is conveniently carried out by adopting the parameter information, the time and space occupation of a Bayesian algorithm are reduced, and the classification clustering capacity and the noise immunity of the system on the road information and the driving item are improved; calculating a mean value and a variance value corresponding to the driving item according to the discretized parameter information, so as to reduce errors in calculation of whether the driver is focused or not; the prior probability corresponding to the parameter information is obtained through calculation according to the mean value and the variance value corresponding to the parameter information, so that the accuracy of probability judgment on the concentration of the driver and the lack of concentration of the driver is ensured; by respectively calculating the posterior probability of the driver attention concentrating event and the attention non-concentrating event according to the prior probability and the preset naive Bayesian algorithm and judging whether the driver is concentrated according to the posterior probability, the accurate judgment of whether the driver is concentrated according to the road state and the driving project in combination with the Bayesian algorithm is realized, the influence caused by the road state is fully considered, the misjudgment caused by the lack of road information is eliminated, and meanwhile, the efficient judgment of whether the driver is concentrated is realized on the basis of not increasing the hardware cost.
Further, in the attention analyzing method of the present invention according to the first embodiment of the present invention, the present invention proposes a second embodiment, and the step S10 includes:
and acquiring steering wheel hand force torque value data, steering wheel corner value data, vehicle transverse acceleration data and transverse deviation data in a preset time period in the driving process according to a preset time interval, and discretizing the parameter information corresponding to the road state and the parameter information corresponding to the driving project, wherein the preset time interval is smaller than the preset time period.
In this embodiment, the preset time interval may be 1 second, 2 seconds, 3 seconds, or 4 seconds, the preset time period is longer than the preset time interval, and when the preset time interval is 1 second, the preset time period may be any time period longer than 1 second, for example, 3 seconds, 5 seconds, 8 seconds, and so on; when the preset time interval is 3 seconds, the preset time period may be any time period greater than 2 seconds, for example, 3 seconds, 5 seconds, 8 seconds, etc.; and when the preset time interval is 3 seconds or 4 seconds, the steps are analogized in sequence, and the details are not repeated here. In addition, the parameter information can be obtained according to the obtained multiple parameter information in a journey.
The hand force torque data of the steering wheel, the steering wheel rotation angle data, the vehicle transverse acceleration data and the transverse deviation data can be obtained through corresponding sensors arranged on the vehicle, wherein the transverse deviation is the error between a real-time center point of the vehicle and a driving route expected by a vehicle system when the vehicle is driven on a road, and the vehicle transverse acceleration is the physical quantity of which the acceleration value is the same as the acceleration value and is opposite to the centripetal acceleration direction in the driving process of the vehicle.
In the embodiment, the parameter information in the preset time length in the running process is acquired at intervals of the preset time interval, so that the parameter information in the preset time length is acquired for multiple times, errors are reduced, and accurate judgment of data and whether the attention of a driver is concentrated is ensured.
Further, referring to fig. 3, in the attention analysis method according to the present invention proposed based on the first embodiment of the present invention, the present invention proposes a third embodiment, and the step S40 includes:
step S41, respectively calculating posterior probabilities of driver concentration and driver concentration lack acquired according to preset time intervals in each preset time period according to the prior probability and a preset naive Bayesian algorithm;
in this embodiment, the posterior probability of concentration and non-concentration of the driver may also be calculated according to obtaining a path shorter than the preset travel path in the preset travel path;
step S42, if the probability of the driver ' S inattention obtained according to the preset time interval in the preset time period is larger than the posterior probability of the driver ' S inattention each time, judging that the driver ' S inattention;
step S43, if the probability of the driver concentration acquired at any time according to the preset time interval within the preset time period is greater than the posterior probability of the driver concentration, judging that the driver concentration is achieved;
the probability of the driver not focusing is greater than the posterior probability of the driver focusing each time acquired according to the preset time interval, for example, 20 times of the probability of the driver focusing and not focusing can be calculated within 1 minute, and if the probability of the driver focusing and not focusing is greater than the probability of focusing in 20 times, the driver focusing can be judged as not focusing;
the probability that the driver is concentrated according to the preset time interval is larger than the posterior probability that the driver is not concentrated, namely that the probability that the driver is concentrated once in 20 times is larger than the probability that the driver is not concentrated, namely that the driver is concentrated.
In the present invention, the posterior probability of the driver's distraction is calculated by the following formula:
P(y 1 |x)＝p(x 1 |y 1 )*p(x 2 |y 1 )*p(x 3 |y 1 )*p(x 4 |y 1 )*p(y 1 )；
the posterior probability of driver concentration is calculated by the following formula:
P(y 2 |x)＝p(x 1 |y 2 )*p(x 2 |y 2 )*p(x 3 |y 2 )*p(x 4 |y 2 )*p(y 2 )；
wherein X is the effective hand force torque data of the steering wheelA combination of an event present, an event for which steering wheel angle data is effectively present, an event for which lateral deviation data is effectively present, and an event for which lateral acceleration data is effectively present, said y 1 X is the event of inattention of the driver 1 Event, x, effectively present for steering wheel hand torque data 2 Event, x, valid for steering wheel angle data 3 Event effectively present as lateral deviation data, x 4 Events effectively present for lateral acceleration data, y 1 The x is an event in which the driver is not focused among the combination of all events, P (y 1 I x) is the probability of occurrence of an event in which the driver is not focused in the combination of all events, P (x) 1 |y 1 ) For the prior probability of occurrence of an event in which steering wheel hand torque data effectively exists in the event of driver inattention, P (x 2 |y 1 ) For the prior probability of occurrence of an event in which steering wheel angle data effectively exists in the event that the driver is not attentive, P (x 3 |y 1 ) For the prior probability of occurrence of an event in which lateral deviation data effectively exist in the event of driver inattention, P (x 4 |y 1 ) A priori probability of occurrence of an event for which lateral acceleration data effectively exists in the event that the driver is not focused;
y 2 the x is an event in which the driver is focused in the combination of all events, P (y 2 |x) is the probability of occurrence of an event that the driver is focused on in the combination of all events, P (x) 1 |y 2 ) For the prior probability of occurrence of an event in which steering wheel hand torque data effectively exists in the event of driver concentration, P (x 2 |y 2 ) For the prior probability of occurrence of an event in which steering wheel angle data effectively exists in the event of driver concentration, P (x 3 |y 2 ) For the prior probability of occurrence of an event in which lateral deviation data effectively exist in the event of driver concentration, P (x 4 |y 2 ) Prior probability of event occurrence for effective presence of lateral acceleration data in event of driver concentration
According to the invention, the posterior probabilities of the concentration and the non-concentration of the driver, which are acquired according to the preset time interval in each preset time period, are respectively calculated according to the prior probability and the preset naive Bayesian algorithm, and whether the driver is concentrated or not is judged according to the concentrated and non-concentrated times, so that the judgment accuracy of whether the driver is concentrated or not is ensured, and the safety in the driving process is improved.
Further, in the attention analyzing method according to the present invention proposed based on the first embodiment of the present invention, the present invention proposes a fourth embodiment, and the step S40 is preceded by:
processing according to a normal distribution formula to obtain hand force torque value data of the steering wheel, wherein a preset conditional probability function of normal distribution of the steering wheel angle value data, the vehicle transverse acceleration data and the transverse deviation data is obtained;
in this embodiment, the normal distribution formula is:
the conditional probability function can be obtained according to a normal distribution formula as follows:
in this embodiment, the formula of conditional probability is obtained by a formula of normal distribution, and the steering wheel hand torque value data, the steering wheel rotation angle value data, the vehicle lateral acceleration data and the lateral deviation data are smoothed, so that frequent response to driver's attention due to threshold judgment is reduced.
The present invention also proposes a computer-readable storage medium on which a computer program is stored. The computer readable storage medium may be the Memory 02 in the vehicle of fig. 1, or may be at least one of ROM (Read-Only Memory)/RAM (Random Access Memory ), magnetic disk, optical disk, etc., and the computer readable storage medium includes a plurality of information for causing the vehicle to perform the method according to the embodiments of the present invention.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (7)
1. A method of attention analysis comprising the steps of:
acquiring parameter information corresponding to a road state and parameter information corresponding to at least one driving item, and performing discretization processing on the parameter information corresponding to the road state and the parameter information corresponding to the driving item, wherein the parameter information corresponding to the road state comprises road information corresponding to the road state; the parameter information corresponding to the driving project comprises driver behavior information corresponding to driver behaviors and vehicle dynamic behavior information corresponding to vehicle dynamic behaviors; the driver behavior information comprises steering wheel hand force torque value data and steering wheel corner value data, the vehicle dynamic behavior information comprises transverse acceleration data, the road information comprises transverse deviation data, the transverse deviation is an error between a real-time center point of a vehicle and a driving route expected by a vehicle system when the vehicle is driven on a road, the vehicle transverse acceleration is a physical quantity with the same acceleration value and opposite direction to centripetal acceleration in the driving process of the vehicle;
calculating a mean value and a variance value corresponding to the road state and the driving project according to the discretized parameter information;
calculating to obtain prior probability corresponding to the parameter information according to the mean value and the variance value corresponding to the parameter information;
according to the prior probability and a preset naive Bayesian algorithm, the posterior probability of the driver attention concentrating event and the attention non-concentrating event is calculated respectively, and whether the driver is concentrated or not is judged according to the posterior probability;
the step of respectively calculating posterior probabilities of the driver attention concentrating event and the attention non-concentrating event according to the prior probability and a preset naive bayes algorithm, and judging whether the driver is concentrated according to the posterior probabilities comprises the following steps:
respectively calculating posterior probabilities of driver concentration and driver inattention acquired according to preset time intervals in each preset time period according to the prior probability and a preset naive Bayesian algorithm;
if the probability of the driver's inattention obtained according to the preset time interval each time within the preset time period is larger than the posterior probability of the driver's inattention, judging that the driver's inattention;
if the probability of the driver focusing on the preset time interval is larger than the posterior probability of the driver focusing on the non-focusing on the driver, judging that the driver focusing on the driver is achieved;
wherein the posterior probability of driver inattention is calculated by the following formula:
；
the posterior probability of driver concentration is calculated by the following formula:
；
wherein X is a combination of an event in which steering wheel hand torque data is effectively present, an event in which steering wheel angle data is effectively present, an event in which lateral deviation data is effectively present, and an event in which lateral acceleration data is effectively present, the followingFor events of inattention of the driver, said +.>For the event of driver concentration, x1 is the event of effective existence of hand torque data of steering wheel, x2 is the event of effective existence of steering wheel angle data, x3 is the event of effective existence of transverse deviation data, x4 is the event of effective existence of transverse acceleration data, and->For events in which the driver is not attentive in the combination of all events +.>For the probability of occurrence of an event of which the driver is not focused in the combination of all events +.>To effectively present the hand torque data of the steering wheel with a priori probability of occurrence of an event in which the driver is not focused,for the prior probability of occurrence of an event for which steering wheel angle data effectively exist in the event of inattention of the driver, +.>For the prior probability of occurrence of an event for which lateral deviation data effectively exist in the event of inattention of the driver, +.>For the prior probability of occurrence of an event for which lateral acceleration data effectively exist in the event of inattention of the driver, +.>A priori probability of occurrence of an event that is inattentive to the driver;
for the event of driver concentration in the combination of all events>For the probability of occurrence of an event of driver concentration in the combination of all events>For the prior probability of occurrence of an event for which the steering wheel hand torque data effectively exist in the event of driver concentration +.>For the prior probability of occurrence of an event for which steering wheel angle data effectively exist in the event of driver concentration, +.>Event occurrence for effective presence of lateral deviation data in event of driver concentrationRaw prior probability>For the prior probability of occurrence of an event for which lateral acceleration data effectively exist in the event of driver concentration,/or->Is the prior probability of occurrence of an event that is focused on by the driver.
2. The attention analyzing method of claim 1, wherein the step of acquiring the parameter information corresponding to the road state and the parameter information corresponding to the at least one driving item, and discretizing the parameter information corresponding to the road state and the parameter information corresponding to the driving item includes:
and acquiring steering wheel hand force torque value data, steering wheel corner value data, vehicle transverse acceleration data and transverse deviation data in a preset time period in the driving process according to a preset time interval, and discretizing the parameter information corresponding to the road state and the parameter information corresponding to the driving project, wherein the preset time interval is smaller than the preset time period.
3. The attention analyzing method according to claim 1, wherein the step of calculating a mean value and a variance value corresponding to the road state and the driving item from the discretized parameter information includes:
and respectively calculating the mean value and the variance corresponding to each parameter information according to the discretized steering wheel hand force torque value data, the steering wheel corner value data, the vehicle transverse acceleration data and the transverse deviation data.
4. The attention analysis method of claim 3, wherein the step of calculating a priori probability corresponding to the parameter information based on the mean and variance values corresponding to the parameter information includes:
and inputting average values and variance values corresponding to the hand force torque value data of the steering wheel, the steering wheel rotation angle value data, the vehicle transverse acceleration data and the transverse deviation data, and respectively calculating the prior probabilities corresponding to the hand force torque value data of the steering wheel, the steering wheel rotation angle value data, the vehicle transverse acceleration data and the transverse deviation data through a preset conditional probability formula.
5. The method of claim 1, wherein the steps of calculating posterior probabilities of the driver's attention concentrating event and the attention non-concentrating event, respectively, according to the prior probability and a preset naive bayes algorithm, and determining whether the driver is concentrating, respectively, include:
and processing according to a normal distribution formula to obtain a normal distribution preset conditional probability function of the hand force torque value data of the steering wheel, the steering wheel angle value data, the vehicle transverse acceleration data and the transverse deviation data.
6. A vehicle comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which when executed by the processor carries out the steps of the attention analysis method as claimed in any one of claims 1 to 5.
7. A computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the steps of the attention analysis method as claimed in any one of claims 1 to 5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110833696.6A CN113569699B (en) | 2021-07-22 | 2021-07-22 | Attention analysis method, vehicle, and storage medium |
| PCT/CN2022/091487 WO2023000762A1 (en) | 2021-07-22 | 2022-05-07 | Attention analysis method, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110833696.6A CN113569699B (en) | 2021-07-22 | 2021-07-22 | Attention analysis method, vehicle, and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113569699A CN113569699A (en) | 2021-10-29 |
| CN113569699B true CN113569699B (en) | 2024-03-08 |
Family
ID=78166548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110833696.6A Active CN113569699B (en) | 2021-07-22 | 2021-07-22 | Attention analysis method, vehicle, and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113569699B (en) |
| WO (1) | WO2023000762A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113569699B (en) * | 2021-07-22 | 2024-03-08 | 上汽通用五菱汽车股份有限公司 | Attention analysis method, vehicle, and storage medium |
| CN114043992A (en) * | 2021-11-12 | 2022-02-15 | 东风柳州汽车有限公司 | Vehicle control method, device, equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182618A (en) * | 2014-08-06 | 2014-12-03 | 西安电子科技大学 | Rear-end early warning method based on Bayesian network |
| WO2016028228A1 (en) * | 2014-08-21 | 2016-02-25 | Avennetz Technologies Pte Ltd | System, method and apparatus for determining driving risk |
| WO2017029443A1 (en) * | 2015-08-18 | 2017-02-23 | Renault S.A.S | Method for determining the level of attention of a driver of a motor vehicle and method for stimulating the attention of a driver of a motor vehicle |
| CN107730835A (en) * | 2017-11-14 | 2018-02-23 | 吉林大学 | A kind of fatigue of automobile driver recognition methods based on stress reaction ability |
| CN108154095A (en) * | 2017-12-14 | 2018-06-12 | 北京汽车集团有限公司 | A kind of method, apparatus and vehicle of determining fatigue driving |
| CN108696366A (en) * | 2017-02-28 | 2018-10-23 | 大唐高鸿信息通信研究院（义乌）有限公司 | A kind of fatigue driving recognition methods suitable for vehicle-mounted short distance communication network |
| CN109927731A (en) * | 2017-12-15 | 2019-06-25 | 蔚来汽车有限公司 | Driver lets go detection method, device, controller and storage medium |
| CN110287916A (en) * | 2019-06-28 | 2019-09-27 | 浙江吉利控股集团有限公司 | It is a kind of for judging the method and system of driver attention |
| CN110472556A (en) * | 2019-08-12 | 2019-11-19 | 一汽轿车股份有限公司 | Driver attention's state analysis system and analysis method based on monocular vision |
| CN111738126A (en) * | 2020-06-16 | 2020-10-02 | 湖南警察学院 | Driver fatigue detection method and device based on Bayesian network and HMM |
| CN112381025A (en) * | 2020-11-23 | 2021-02-19 | 恒大新能源汽车投资控股集团有限公司 | Driver attention detection method and device, electronic equipment and storage medium |
| CN112438729A (en) * | 2019-08-28 | 2021-03-05 | 福特全球技术公司 | Driver alertness detection system |
| CN112529341A (en) * | 2021-02-09 | 2021-03-19 | 西南石油大学 | Drilling well leakage probability prediction method based on naive Bayesian algorithm |
| CN113056390A (en) * | 2018-06-26 | 2021-06-29 | 伊泰·卡茨 | Situational driver monitoring system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5311793B2 (en) * | 2007-10-16 | 2013-10-09 | トヨタ自動車株式会社 | Aside look status determination device |
| US20180032891A1 (en) * | 2016-07-29 | 2018-02-01 | International Business Machines Corporation | Adaptive architecture for crash prediction in vehicle collision avoidance systems |
| CN113569699B (en) * | 2021-07-22 | 2024-03-08 | 上汽通用五菱汽车股份有限公司 | Attention analysis method, vehicle, and storage medium |
-
2021
- 2021-07-22 CN CN202110833696.6A patent/CN113569699B/en active Active
-
2022
- 2022-05-07 WO PCT/CN2022/091487 patent/WO2023000762A1/en unknown
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182618A (en) * | 2014-08-06 | 2014-12-03 | 西安电子科技大学 | Rear-end early warning method based on Bayesian network |
| WO2016028228A1 (en) * | 2014-08-21 | 2016-02-25 | Avennetz Technologies Pte Ltd | System, method and apparatus for determining driving risk |
| WO2017029443A1 (en) * | 2015-08-18 | 2017-02-23 | Renault S.A.S | Method for determining the level of attention of a driver of a motor vehicle and method for stimulating the attention of a driver of a motor vehicle |
| CN108696366A (en) * | 2017-02-28 | 2018-10-23 | 大唐高鸿信息通信研究院（义乌）有限公司 | A kind of fatigue driving recognition methods suitable for vehicle-mounted short distance communication network |
| CN107730835A (en) * | 2017-11-14 | 2018-02-23 | 吉林大学 | A kind of fatigue of automobile driver recognition methods based on stress reaction ability |
| CN108154095A (en) * | 2017-12-14 | 2018-06-12 | 北京汽车集团有限公司 | A kind of method, apparatus and vehicle of determining fatigue driving |
| CN109927731A (en) * | 2017-12-15 | 2019-06-25 | 蔚来汽车有限公司 | Driver lets go detection method, device, controller and storage medium |
| CN113056390A (en) * | 2018-06-26 | 2021-06-29 | 伊泰·卡茨 | Situational driver monitoring system |
| CN110287916A (en) * | 2019-06-28 | 2019-09-27 | 浙江吉利控股集团有限公司 | It is a kind of for judging the method and system of driver attention |
| CN110472556A (en) * | 2019-08-12 | 2019-11-19 | 一汽轿车股份有限公司 | Driver attention's state analysis system and analysis method based on monocular vision |
| CN112438729A (en) * | 2019-08-28 | 2021-03-05 | 福特全球技术公司 | Driver alertness detection system |
| CN111738126A (en) * | 2020-06-16 | 2020-10-02 | 湖南警察学院 | Driver fatigue detection method and device based on Bayesian network and HMM |
| CN112381025A (en) * | 2020-11-23 | 2021-02-19 | 恒大新能源汽车投资控股集团有限公司 | Driver attention detection method and device, electronic equipment and storage medium |
| CN112529341A (en) * | 2021-02-09 | 2021-03-19 | 西南石油大学 | Drilling well leakage probability prediction method based on naive Bayesian algorithm |
Non-Patent Citations (8)
| Title |
|---|
| 危险换道驾驶行为预测方法研究;熊晓夏;陈龙;梁军;蔡英凤;江浩斌;陈月霞;;汽车工程(第09期);全文 * |
| 基于时域与时间间隔视角的疲劳驾驶检测研;王先朋;中国优秀硕士学位论文全文数据库社会科学Ⅱ辑(第07期);正文第8-25页 * |
| 基于贝叶斯网络的疲劳度及注意力检测;张建明;计算机工程;第38卷(第9期);全文 * |
| 多特征融合的驾驶员疲劳检测研究;黄占鳌;史晋芳;;机械科学与技术(第11期);全文 * |
| 朴素贝叶斯模型在驾驶员伤情预测中的应用;陆颖;殷越洲;谢君平;;机械设计与制造(第01期);全文 * |
| 熊晓夏 ; 陈龙 ; 梁军 ; 蔡英凤 ; 江浩斌 ; 陈月霞 ; .危险换道驾驶行为预测方法研究.汽车工程.2017,(第09期),全文. * |
| 陆颖 ; 殷越洲 ; 谢君平 ; .朴素贝叶斯模型在驾驶员伤情预测中的应用.机械设计与制造.2020,(第01期),全文. * |
| 黄占鳌 ; 史晋芳 ; .多特征融合的驾驶员疲劳检测研究.机械科学与技术.2018,(第11期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113569699A (en) | 2021-10-29 |
| WO2023000762A1 (en) | 2023-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113569699B (en) | Attention analysis method, vehicle, and storage medium | |
| CN106251430B (en) | System and method for controlling vehicle access components | |
| US20210309261A1 (en) | Driver and environment monitoring to predict human driving maneuvers and reduce human driving errors | |
| US9111400B2 (en) | System for detecting abnormal driving behavior | |
| US11270689B2 (en) | Detection of anomalies in the interior of an autonomous vehicle | |
| US20220121213A1 (en) | Hybrid planning method in autonomous vehicle and system thereof | |
| CN112298070A (en) | Pedal fault diagnosis method and device | |
| CN105818772B (en) | Two-dimensional pedestrian impact sensing | |
| JP2020091525A (en) | Information processing system, program, and control method | |
| CN110949379A (en) | Determination of a control signal for a semi-autonomous vehicle | |
| US9747801B2 (en) | Method and device for determining surroundings | |
| CN114329306A (en) | Method and device for calculating braking distance, automobile and medium | |
| Abdelrahman et al. | Driver behavior classification in crash and near-crash events using 100-CAR naturalistic data set | |
| US9102333B2 (en) | Enhanced crosswind estimation | |
| US9821812B2 (en) | Traffic complexity estimation | |
| CN110450788B (en) | Driving mode switching method, device, equipment and storage medium | |
| US20180357580A1 (en) | Vehicle driver workload management | |
| Kim et al. | Implementation of a fuzzy-inference-based, low-speed, close-range collision-warning system for urban areas | |
| KR102338067B1 (en) | Driver monitoring system for using interest area | |
| US10696307B2 (en) | Anomaly detector for vehicle control signals | |
| CN114056425B (en) | Vehicle steering control method and device, vehicle and storage medium | |
| EP4258242A1 (en) | Electronic apparatus, information processing device, degree of concentration calculation program, and degree of concentration calculation method | |
| US20220374745A1 (en) | Electronic device and method for scoring driving behavior using vehicle inputs and outputs | |
| JP5664462B2 (en) | Roadside obstacle detection device for emergency vehicle evacuation device | |
| JP6987167B2 (en) | Lane change judgment device |
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 |