CN113935392A - Driver identity recognition method and device, electronic equipment and readable storage medium - Google Patents
Driver identity recognition method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN113935392A CN113935392A CN202010607021.5A CN202010607021A CN113935392A CN 113935392 A CN113935392 A CN 113935392A CN 202010607021 A CN202010607021 A CN 202010607021A CN 113935392 A CN113935392 A CN 113935392A
- Authority
- CN
- China
- Prior art keywords
- driving
- driver
- identity
- vehicle
- state information
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 230000006399 behavior Effects 0.000 claims abstract description 200
- 230000008569 process Effects 0.000 claims abstract description 31
- 230000001133 acceleration Effects 0.000 claims description 53
- 230000015654 memory Effects 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 22
- 238000004891 communication Methods 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000007635 classification algorithm Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 125000004122 cyclic group Chemical group 0.000 claims description 5
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention provides a driver identity recognition method, a driver identity recognition device, electronic equipment and a readable storage medium, wherein the driver identity recognition method comprises the following steps: acquiring running state information of a vehicle in the process of controlling the vehicle to run by a driver; identifying different types of driving behaviors based on the driving state information, and determining characteristic data of at least one type of driving behaviors; and inputting the determined characteristic data into an identity recognition model to recognize the identity of the current driver. According to the invention, under the conditions that no complicated operation burden is brought to the driver and no biological privacy information of the driver is collected and recorded, the identity of the driver is identified only by depending on the driving state information of the vehicle when the driver drives the vehicle, so that the driving experience of the driver is ensured, the privacy of the driver is protected, the intelligent automobile can provide differentiated driving mode services for different drivers, and the use experience of a user is improved.
Description
Technical Field
The invention relates to the technical field of intelligent automobiles, in particular to a driver identity recognition method and device, electronic equipment and a readable storage medium.
Background
Along with the development of automobile intellectualization, people are required for good experience of automobiles, so that people hope that automobiles can understand themselves more and more, and corresponding service contents and auxiliary driving can be customized according to the states and the requirements of the people. The prerequisite for providing corresponding services and assistance for different drivers is the ability to recognize the driver's identity and then provide the driver with the desired functionality based on his identity and the driver's driving habits.
In the prior art, when the identity of a driver is identified, the biological characteristics of the driver are usually collected and recorded, and the identity of the driver is verified based on the comparison of the biological characteristics, such as collecting head portrait information and fingerprint information of the driver for verification. However, when the driver performs the identity authentication through the biometric feature, the biometric information of the driver is easily leaked, which is not beneficial to protecting the privacy of the user.
Disclosure of Invention
The embodiment of the invention provides a driver identity identification method and device, electronic equipment and a readable storage medium, and aims to solve the problems that information is easy to leak and user privacy protection is not facilitated when driver identity authentication is carried out through biological characteristics in the prior art.
In a first aspect, an embodiment of the present invention provides a driver identity identification method, including:
acquiring running state information of a vehicle in the process of controlling the vehicle to run by a driver;
identifying different types of driving behaviors based on the driving state information, and determining characteristic data of at least one type of driving behaviors;
and inputting the determined characteristic data into an identity recognition model to recognize the identity of the current driver.
Optionally, the acquiring the driving state information of the vehicle includes:
collecting CAN data of a vehicle controller local area network;
and analyzing the CAN data to acquire the running state information of the vehicle.
Optionally, the identifying different types of driving behaviors based on the driving state information and determining feature data of at least one type of driving behavior include:
identifying driving behaviors of a straight type, at least three types of turning types and an acceleration type according to the driving state information, wherein the turning angles corresponding to the driving behaviors of the at least three types of turning types are in different angle intervals respectively, and the acceleration corresponding to the driving behavior of the acceleration type is larger than a first acceleration threshold value;
aiming at least one type of driving behaviors, respectively extracting at least one target signal from the driving state information, and acquiring at least one characteristic value of the target signal in the driving time period of the current driving behavior;
wherein the characteristic data comprises at least one target signal and at least one characteristic value corresponding to the target signal.
Optionally, the identifying the driving behaviors of the straight-driving category, the driving behaviors of the at least three turning categories, and the driving behaviors of the acceleration categories according to the driving state information includes:
and adopting a threshold-based classification algorithm to classify the driving behavior into a straight-going category, at least three turning categories and an acceleration category according to the steering wheel rotation angle, the depth and the change rate of an accelerator pedal and the vehicle speed in the running state information.
Optionally, the extracting, for at least one type of driving behavior, at least one target signal from the driving state information, and obtaining at least one characteristic value of the target signal in a driving period of the current driving behavior respectively includes:
for at least one type of driving behavior, extracting at least one of the following target signals from the driving state information: steering wheel angle, steering wheel angular velocity, longitudinal acceleration, accelerator pedal depth, vehicle lateral acceleration, vehicle torque, brake pedal depth, motor speed and motor speed change rate;
for each target signal extracted from each type of driving behavior, acquiring at least one of the following characteristic values within a driving period of the current driving behavior: the maximum value, the minimum value, the average value, the standard deviation, the kurtosis, the skewness, the peak value factor, the waveform factor, the margin factor and the pulse factor of the amplitude value in the frequency domain corresponding to the target signal.
Optionally, after determining the characteristic data of at least one type of driving behavior, the method further includes:
arranging and storing the characteristic data of at least one type of driving behaviors according to a preset time period to generate a characteristic data set in a matrix form;
inputting the determined characteristic data into an identity recognition model to recognize the identity of the current driver, wherein the identity recognition comprises the following steps:
inputting the feature data set into the identification model to identify the identity of the current driver.
Optionally, the inputting the determined feature data into an identification model to identify the current driver includes:
inputting the determined characteristic data into the identity recognition model, and outputting probability values corresponding to identity labels in the identity recognition model, wherein the identity labels represent identity information of a driver;
and determining the identity label with the maximum probability value as a target identity label matched with the current driver, and determining the identity information of the current driver according to the target identity label.
Optionally, the method further includes:
and generating the identity recognition model according to the characteristic data of various driving behaviors respectively corresponding to the plurality of drivers when the plurality of drivers operate the vehicle and the identity information of the plurality of drivers.
Optionally, the generating the identification model according to the feature data of various driving behaviors respectively corresponding to the plurality of drivers when the plurality of drivers operate the vehicle and the identity information of the plurality of drivers includes:
setting a network architecture of a long-time memory cyclic neural network, wherein the network architecture at least comprises the number of network layers, the number of hidden node units, a propagation direction, a batch size, a gradient threshold, a node characteristic length and a data size;
respectively setting an identity label corresponding to each driver according to the identity information of the plurality of drivers;
performing multi-round model training according to the characteristic data of various driving behaviors corresponding to the drivers, the identity labels corresponding to the drivers and the network architecture, determining model convergence when a target function value meeting a preset condition is detected in the model training process, and determining and generating the identity recognition model;
the characteristic data of each type of driving behaviors comprises a plurality of target signals and a plurality of characteristic values of each target signal in a driving time period of the current driving behaviors.
In a second aspect, an embodiment of the present invention provides a driver identification apparatus, including:
the acquisition module is used for acquiring the running state information of the vehicle in the process of controlling the vehicle to run by a driver;
the processing module is used for identifying different types of driving behaviors based on the driving state information and determining characteristic data of at least one type of driving behaviors;
and the identification module is used for inputting the determined characteristic data into an identity identification model to identify the current driver.
Optionally, the obtaining module is further configured to:
collecting CAN data of a vehicle controller local area network;
and analyzing the CAN data to acquire the running state information of the vehicle.
Optionally, the processing module includes:
the recognition submodule is used for recognizing the driving behaviors of straight driving types, the driving behaviors of at least three types of turning types and the driving behaviors of acceleration types according to the driving state information, the turning angles corresponding to the driving behaviors of the at least three types of turning types are respectively in different angle intervals, and the acceleration corresponding to the driving behaviors of the acceleration types is larger than a first acceleration threshold value;
the processing submodule is used for respectively extracting at least one target signal from the running state information aiming at least one type of driving behaviors and acquiring at least one characteristic value of the target signal in the driving time period of the current driving behaviors;
wherein the characteristic data comprises at least one target signal and at least one characteristic value corresponding to the target signal.
Optionally, the identifier module is further configured to:
and adopting a threshold-based classification algorithm to classify the driving behavior into a straight-going category, at least three turning categories and an acceleration category according to the steering wheel rotation angle, the depth and the change rate of an accelerator pedal and the vehicle speed in the running state information.
Optionally, the processing sub-module includes:
an extraction unit configured to extract, for at least one type of driving behavior, at least one of the following target signals in the driving state information, respectively: steering wheel angle, steering wheel angular velocity, longitudinal acceleration, accelerator pedal depth, vehicle lateral acceleration, vehicle torque, brake pedal depth, motor speed and motor speed change rate;
an acquisition unit, configured to acquire, for each of the target signals extracted for each type of driving behavior, at least one of the following characteristic values within a driving period of a current driving behavior: the maximum value, the minimum value, the average value, the standard deviation, the kurtosis, the skewness, the peak value factor, the waveform factor, the margin factor and the pulse factor of the amplitude value in the frequency domain corresponding to the target signal.
Optionally, the apparatus further comprises:
the first generation module is used for arranging and storing the characteristic data of at least one type of driving behaviors according to a preset time period after the processing module determines the characteristic data of at least one type of driving behaviors, and generating a characteristic data set in a matrix form;
the identification module is further to:
inputting the feature data set into the identification model to identify the identity of the current driver.
Optionally, the identification module includes:
the output sub-module is used for inputting the determined characteristic data into the identity recognition model and outputting probability values corresponding to identity labels in the identity recognition model, wherein the identity labels represent identity information of a driver;
and the determining submodule is used for determining the identity label with the maximum probability value as a target identity label matched with the current driver and determining the identity information of the current driver according to the target identity label.
Optionally, the apparatus further comprises:
and the second generation module is used for generating the identity recognition model according to the characteristic data of various driving behaviors respectively corresponding to the plurality of drivers when the plurality of drivers operate the vehicle and the identity information of the plurality of drivers.
Optionally, the second generating module includes:
the first setting submodule is used for setting a network architecture of the long-time memory cyclic neural network, and the network architecture at least comprises the number of network layers, the number of hidden node units, a propagation direction, a batch size, a gradient threshold value, a node characteristic length and a data size;
the second setting submodule is used for respectively setting an identity tag corresponding to each driver according to the identity information of the plurality of drivers;
the training submodule is used for carrying out multi-round model training according to characteristic data of various driving behaviors corresponding to a plurality of drivers, the identity tags corresponding to the drivers and the network architecture, determining model convergence when a target function value meeting a preset condition is detected in the model training process, and determining and generating the identity recognition model;
the characteristic data of each type of driving behaviors comprises a plurality of target signals and a plurality of characteristic values of each target signal in a driving time period of the current driving behaviors.
In a third aspect, an embodiment of the present invention provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus; the processor, the communication interface and the memory complete mutual communication through a communication bus;
a memory for storing a computer program;
a processor, configured to implement the steps of the driver identification method according to the first aspect when executing the program stored in the memory.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps in the driver identification method according to the first aspect.
Aiming at the prior art, the invention has the following advantages:
according to the embodiment of the invention, the driving state information of the vehicle when the driver operates the vehicle is obtained, the driving behaviors of different types are identified based on the driving state information, the characteristic data of at least one type of driving behaviors are determined, the determined characteristic data is input into the identity identification model, and the identity of the driver is identified, so that the driving experience of the driver is ensured, the privacy of the driver is protected, the intelligent vehicle can provide differentiated driving mode services for different drivers, and the active safety and the good user experience of the vehicle are improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments will be briefly described below.
Fig. 1 is a schematic diagram of a driver identification method according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating an implementation of driver identification according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating an implementation of generating an identity recognition model and performing identity recognition through the identity recognition model according to an embodiment of the present invention;
FIG. 4 is a schematic view of a driver identification apparatus according to an embodiment of the present invention;
fig. 5 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 is a driver identity recognition method provided in an embodiment of the present invention, including:
The driver identity recognition method provided by the embodiment of the invention is applied to an identity recognition system, and the identity recognition system can be arranged on a vehicle. The identity recognition system can automatically activate the identity recognition function when a driver enters a cab to start and starts to operate the vehicle, and can acquire the driving state information of the vehicle after the identity recognition function is activated. The driving state information of the vehicle may include driving information and state information of related devices on the entire vehicle during driving. After acquiring the traveling state information of the vehicle, step 102 may be performed based on the traveling state information of the vehicle.
And 102, identifying different types of driving behaviors based on the driving state information, and determining characteristic data of at least one type of driving behaviors.
After acquiring the driving state information, different categories of driving behaviors may be identified based on the driving state information, and corresponding characteristic data may be determined in the driving state information for at least one category of driving behavior. When different types of driving behaviors are recognized, the driving behaviors of the driver such as acceleration, deceleration, turning, straight running and lane changing can be recognized according to the driving state information. After determining the characteristic data of the at least one type of driving behavior, step 103 may be performed based on the characteristic data of the at least one type of driving behavior.
And 103, inputting the determined characteristic data into an identity recognition model to recognize the identity of the current driver.
After determining the characteristic data of the at least one type of driving behavior, the characteristic data of the at least one type of driving behavior may be input into an identity recognition model, where the identity recognition model is generated through model training using a specific neural network according to driving state information of a plurality of drivers when operating the vehicle and the identity information of the drivers. After the characteristic data of at least one type of driving behaviors are input into the identity recognition model, the identity of the current driver can be effectively recognized.
After different types of driving behaviors are recognized, the characteristic data of two or more types of driving behaviors can be determined, the validity and the accuracy of identity recognition can be ensured through the characteristic data of at least two types of driving behaviors, and the situation that the driving behaviors of the same type of two drivers are small in difference and cannot be recognized accurately only according to the characteristic data of one type of driving behaviors is avoided. And the more the types of the driving behaviors are, the higher the accuracy rate is when the identity recognition is carried out according to the characteristic data of the driving behaviors of different types.
It should be noted that, the identification requires that the driving state information of the driver operating the vehicle participates in the training process of the identification model, and the identification system can output the identification result of the driver. The identity recognition model can be located in the identity recognition system and generated by the identity recognition system through model training.
Above-mentioned implementation process, can be without bringing loaded down with trivial details operation burden and not gathering and recording under the condition of driver biological privacy information for the driver, the travel state information of vehicle when only relying on the driver to drive the vehicle, discern driver's identity, guaranteed driver's driving experience, driver's privacy has been protected simultaneously, can also make intelligent automobile provide the driving mode service of differentiation to different drivers, use experience with the initiative security and the good user that promote the car.
Optionally, in an embodiment of the present invention, the acquiring the driving state information of the vehicle includes:
collecting CAN data of a vehicle controller local area network;
and analyzing the CAN data to acquire the running state information of the vehicle.
When the driving state information of the vehicle is acquired, CAN data generated by a CAN (Controller Area Network) bus of the vehicle itself CAN be collected, and then the original CAN data is analyzed into available driving state information of the vehicle according to a protocol.
The CAN bus is used for acquiring the CAN data, and the CAN data is analyzed to acquire the driving state information of the vehicle, so that the data CAN be acquired under the condition of not adding an additional sensor, and the hardware cost is saved.
Optionally, in an embodiment of the present invention, the identifying different types of driving behaviors based on the driving state information and determining characteristic data of at least one type of driving behavior includes:
identifying driving behaviors of a straight type, at least three types of turning types and an acceleration type according to the driving state information, wherein the turning angles corresponding to the driving behaviors of the at least three types of turning types are in different angle intervals respectively, and the acceleration corresponding to the driving behavior of the acceleration type is larger than a first acceleration threshold value;
aiming at least one type of driving behaviors, respectively extracting at least one target signal from the driving state information, and acquiring at least one characteristic value of the target signal in the driving time period of the current driving behavior;
wherein the characteristic data comprises at least one target signal and at least one characteristic value corresponding to the target signal.
In identifying different types of driving behaviors based on the driving state information, a driving behavior of a straight type, a driving behavior of at least three types of turning types, and a driving behavior of an acceleration type may be identified according to the driving state information. For the driving behaviors of the three types of turning categories, the corresponding turning angles are respectively in different angle intervals, namely the turning angle corresponding to the first type of turning category is in a first angle interval, the turning angle corresponding to the second type of turning category is in a second angle interval, the turning angle corresponding to the third type of turning category is in a third angle interval, and the first angle interval, the second angle interval and the third angle interval are not overlapped with each other. For example, driving behavior is classified into a first type of turning category according to driving state information for changing from a current lane to an adjacent lane; dividing driving behaviors into a second type of turning categories according to driving state information changed from a current lane to an interval lane; and dividing the driving behaviors into a third type of turning categories according to the driving state information of turning left or right at the intersection.
The rapid acceleration behavior can reflect the driving difference between different drivers obviously, so that the corresponding acceleration needs to be greater than the first acceleration threshold for the acceleration type, and the rapid acceleration behavior of the driver is ensured.
After identifying different classes of driving behavior, corresponding characteristic data may be determined for at least one class of driving behavior. The characteristic data comprises at least one target signal and at least one characteristic value corresponding to the target signal, when the characteristic data of at least one type of driving behaviors is determined, the at least one target signal needs to be extracted from the driving state information respectively aiming at the at least one type of driving behaviors, and meanwhile, at least one characteristic value in a driving time period corresponding to the current driving behaviors needs to be acquired aiming at each target signal.
In the process, different types of driving behaviors can be identified based on the driving state information, the characteristic data of at least one type of driving behavior is determined, the identity identification of the driver is guaranteed based on the characteristic data of at least one type of driving behavior, and effective data can be extracted from the driving state information for identity identification by determining the characteristic data of at least one type of driving behavior.
Optionally, in an embodiment of the present invention, the identifying, according to the driving state information, driving behaviors of a straight-driving category, driving behaviors of at least three types of turning categories, and driving behaviors of an acceleration category includes:
and adopting a threshold-based classification algorithm to classify the driving behavior into a straight-going category, at least three turning categories and an acceleration category according to the steering wheel rotation angle, the depth and the change rate of an accelerator pedal and the vehicle speed in the running state information.
When different types of driving behaviors are identified according to the driving state information, the steering wheel rotation angle, the depth and the change rate of the accelerator pedal, and the vehicle speed may be extracted from the driving state information, and the driving behaviors may be classified into a straight type, at least three types of turning types, and an acceleration type using a threshold-based classification algorithm according to the extracted information.
For example, whether the driving behavior belongs to straight running or turning can be identified according to the rotation angle of the steering wheel and the vehicle speed, and whether the driving behavior belongs to acceleration can be identified according to the depth and the change rate of the accelerator pedal and the vehicle speed.
In the process, the classification algorithm based on the threshold is adopted, the driving behaviors are classified according to the steering wheel rotation angle, the depth and the change rate of the accelerator pedal and the vehicle speed, different types of driving behaviors can be obtained, the feature data of at least one type of driving behaviors are extracted from the feature data of the different types of driving behaviors, and the identity of the driver is identified according to the feature data of the at least one type of driving behaviors.
Optionally, in an embodiment of the present invention, for at least one type of driving behavior, extracting at least one target signal from the driving state information, and acquiring at least one characteristic value of the target signal in a driving period of a current driving behavior respectively includes:
for at least one type of driving behavior, extracting at least one of the following target signals from the driving state information: steering wheel angle, steering wheel angular velocity, longitudinal acceleration, accelerator pedal depth, vehicle lateral acceleration, vehicle torque, brake pedal depth, motor speed and motor speed change rate;
for each target signal extracted from each type of driving behavior, acquiring at least one of the following characteristic values within a driving period of the current driving behavior: the maximum value, the minimum value, the average value, the standard deviation, the kurtosis, the skewness, the peak value factor, the waveform factor, the margin factor and the pulse factor of the amplitude value in the frequency domain corresponding to the target signal.
When extracting target signals from the driving state information for at least one type of driving behaviors, the driving information of the vehicle and the state information of related devices on the whole vehicle during driving need to be acquired according to the driving state information, wherein the driving information may include longitudinal acceleration and lateral acceleration of the vehicle, and the state information of the related devices may include: steering wheel angle, steering wheel angular velocity, accelerator pedal depth, vehicle torque, brake pedal depth, motor speed, and motor speed rate of change. And then extracting at least one of a steering wheel angle, a steering wheel angular velocity, a longitudinal acceleration, an accelerator pedal depth, a vehicle lateral acceleration, a vehicle torque, a brake pedal depth, a motor rotation speed and a motor rotation speed change rate based on the driving information and the state information of the related devices.
When at least one characteristic value in a driving period of the current driving behavior is obtained for each extracted target signal of each type of driving behavior, at least one of a maximum value, a minimum value, an average value, a standard deviation, a kurtosis, a skewness, a peak factor, a form factor, a margin factor, and a pulse factor of the amplitude of the target signal in a corresponding frequency domain may be obtained. The frequency domain here corresponds to the time domain of the current driving behavior, and the time domain and the frequency domain can be converted through fourier transform or other methods.
Wherein, the kurtosis is a numerical statistic reflecting the distribution characteristics of random variables; skewness is a digital characteristic of the asymmetric degree of statistical data distribution; the form factor is the ratio of the root mean square value and the average value of the signal; the peak factor is the ratio of the signal peak value to the effective value (RMS), and RMS (Root Mean Square Root) can represent the true effective value; the pulse factor is the ratio of the signal peak value to the rectified mean value (mean value of absolute values); the margin factor is the ratio of the signal peak to the square root amplitude.
The above process may specifically be: at least one of a steering wheel angle, a steering wheel angular velocity, a longitudinal acceleration, an accelerator pedal depth, a vehicle lateral acceleration, a vehicle torque, a brake pedal depth, a motor rotating speed and a motor rotating speed change rate can be obtained correspondingly to at least one of straight running, turning and accelerating, and at least one of a maximum value, a minimum value, an average value, a standard deviation, a kurtosis, a skewness, a peak value factor, a waveform factor, a margin factor and a pulse factor of the amplitude in a corresponding frequency domain can be obtained for each target signal extracted from each driving behavior. Where 9 target signals are acquired for each type of driving behavior, and 10 feature values are acquired for each target signal, 90-dimensional feature data may be acquired for each type of driving behavior.
In the process, at least one target signal and at least one characteristic value of the target signal can be respectively acquired aiming at least one type of driving behaviors, so that the characteristic data of at least one type of driving behaviors is acquired, and the identity of the driver can be conveniently identified based on the characteristic data of at least one type of driving behaviors.
Optionally, in an embodiment of the present invention, after determining the characteristic data of at least one type of driving behavior, the method further includes: arranging and storing the characteristic data of at least one type of driving behaviors according to a preset time period to generate a characteristic data set in a matrix form;
inputting the determined characteristic data into an identity recognition model to recognize the identity of the current driver, wherein the identity recognition comprises the following steps: inputting the feature data set into the identification model to identify the identity of the current driver.
After determining the characteristic data of the at least one type of driving behavior, the characteristic data of the at least one type of driving behavior may be arranged and stored according to a preset time period to generate a characteristic data set corresponding to the driving state information of the current driver. When the sequencing storage is performed, time periods with equal time lengths can be determined for each type of driving behaviors, and the feature data of the driving behaviors corresponding to each time period are sequentially arranged in the row direction of the matrix to generate a feature data set in the form of the matrix.
After generating the feature data set, the feature data set may be input into an identification model to identify the identity of the current driver. Because the characteristic data set comprises the characteristic data of at least one type of driving behaviors, the identity recognition is carried out according to the characteristic data set, the characteristic data of at least one type of driving behaviors can be ensured to be input into the identity recognition model at one time, and the complexity caused by carrying out data input for many times is avoided.
In the process, the characteristic data set can be generated according to the characteristic data corresponding to at least one type of driving behaviors, so that the characteristic data can be input into the identity recognition model at one time, and the identity recognition of the driver can be conveniently carried out by utilizing the characteristic data set.
Optionally, in an embodiment of the present invention, the inputting the determined feature data into an identification model to identify the current driver includes:
inputting the determined characteristic data into the identity recognition model, and outputting probability values corresponding to identity labels in the identity recognition model, wherein the identity labels represent identity information of a driver;
and determining the identity label with the maximum probability value as a target identity label matched with the current driver, and determining the identity information of the current driver according to the target identity label.
When the driver is identified, the determined feature data may be input into an identification model, and the identification model outputs probability values corresponding to the identity tags, where each identity tag indicates identity information of one driver, for example, identity tag 1 indicates identity information of driver a, identity tag 2 indicates identity information of driver B, and identity tag 3 indicates identity information of driver C. And after the probability values corresponding to the identity labels are output by the identity recognition model, determining the target identity label with the maximum probability value, and determining the identity information of the current driver according to the target identity label. If the identity recognition model outputs a probability value 5% corresponding to the identity tag 1, a probability value 7% corresponding to the identity tag 2, and a probability value 95% corresponding to the identity tag 3, the identity tag 3 may be determined as a target identity tag, and since the identity tag 3 represents the identity information of the driver C, the current driver may be determined as the driver C.
The identity recognition model is a Long Short-Term Memory (LSTM) classification model, and LSTM is a machine learning method for classifying sequence data. After the identity information of the current driver is determined, corresponding driving mode service can be provided for the current driver, and the active safety and good user experience of the automobile are further improved.
The following explains the process of identifying the driver by using a specific implementation flow, as shown in fig. 2, including:
And step 203, identifying different types of driving behaviors based on the driving state information.
And step 204, determining characteristic data of at least one type of driving behaviors.
And step 205, inputting the determined characteristic data into an identity recognition model, and determining the identity information of the current driver.
Above-mentioned process, can be without increasing extra sensor, do not bring loaded down with trivial details operation burden and not gather and take notes under the condition of driver biological privacy information for the driver, the travel state information of vehicle when only relying on the driver to drive the vehicle, discern driver's identity, hardware cost has been practiced thrift, driver's driving experience has been guaranteed, driver's privacy has been protected simultaneously, can also make intelligent automobile provide the driving mode service of differentiation to different drivers, the initiative security and the good user of car use experience have been promoted.
In the above embodiment, when the driver operates the vehicle to generate the driving CAN data, the identity recognition function is automatically activated, but the driving state information corresponding to the driver must be required to participate in the training of the identity recognition model, and the identity recognition system CAN output the identity recognition result of the driver.
Optionally, in an embodiment of the present invention, the method further includes:
and generating the identity recognition model according to the characteristic data of various driving behaviors respectively corresponding to the plurality of drivers when the plurality of drivers operate the vehicle and the identity information of the plurality of drivers.
The embodiment of the invention firstly needs to generate an identity recognition model, when the identity recognition model is generated, the characteristic data of various driving behaviors respectively corresponding to a plurality of drivers operating vehicles needs to be acquired, the identity information of each driver is acquired, and the identity recognition model is generated according to the characteristic data of various driving behaviors and the identity information of the plurality of drivers. When the characteristic data of various driving behaviors respectively corresponding to a plurality of drivers operating the vehicle are obtained, the driving state information of the vehicle is obtained firstly in the process that each driver operates the vehicle to operate, the driving behaviors of different categories are identified according to the driving state information, and the characteristic data of various driving behaviors are determined.
The generating of the identity recognition model according to the characteristic data of various driving behaviors respectively corresponding to a plurality of drivers when the drivers operate the vehicle and the identity information of the plurality of drivers includes:
setting a network architecture of a long-time memory cyclic neural network, wherein the network architecture at least comprises the number of network layers, the number of hidden node units, a propagation direction, a batch size, a gradient threshold, a node characteristic length and a data size;
respectively setting an identity label corresponding to each driver according to the identity information of the plurality of drivers;
performing multi-round model training according to the characteristic data of various driving behaviors corresponding to the drivers, the identity labels corresponding to the drivers and the network architecture, determining model convergence when a target function value meeting a preset condition is detected in the model training process, and determining and generating the identity recognition model;
the characteristic data of each type of driving behaviors comprises a plurality of target signals and a plurality of characteristic values of each target signal in a driving time period of the current driving behaviors.
The identity recognition model is an LSTM classification model, when the identity recognition model is generated, network structures such as the number of network layers, the number of hidden node units, the propagation direction, the batch size, the gradient threshold, the node characteristic length and the data size of the recurrent neural network are required to be designed, and identity tags corresponding to each driver are required to be respectively set according to identity information of a plurality of drivers. And then, performing multi-round model training according to the characteristic data of various driving behaviors corresponding to the drivers, the identity labels corresponding to the drivers and the network architecture. Whether an objective function value (namely an LOSS value) meets a preset condition or not can be monitored in the model training process, and under the condition that the objective function value meets the preset condition, model convergence can be determined, namely, training can be stopped, and an identity recognition model is determined to be generated.
After the identity recognition model is generated, the identity recognition model can be used for identifying the identity of the driver who participates in the identity recognition model training, so that differentiated driving mode services can be provided according to the identity information of the driver, and the active safety and good user experience of the automobile are improved.
The following describes a process of generating an identification model and performing identification through the identification model, as shown in fig. 3, with a specific example, including:
301, when the driver controls the vehicle to be in a running state, the driver automatically activates an identity recognition function, collects CAN data generated by a CAN bus of the vehicle and acquires running state information of the vehicle.
And 302, identifying different types of driving behaviors based on the driving state information, and determining characteristic data of various types of driving behaviors.
And 304, acquiring characteristic data of various driving behaviors corresponding to other drivers, setting identity labels for the other drivers and the current driver respectively, and training an identity recognition model according to the characteristic data of various driving behaviors corresponding to the other drivers and the current driver, the identity labels and a network architecture of a long-term memory recurrent neural network. Then, the process returns to step 301 to acquire the driving state information of the corresponding vehicle when the current driver operates the vehicle again, and step 302, step 303, and step 305 are executed.
And 305, inputting the determined characteristic data of various driving behaviors into an identity recognition model to recognize the identity information of the driver.
The above process can obtain characteristic data of various driving behaviors according to corresponding driving state information when a driver controls a vehicle, the identity recognition model is trained based on the characteristic data and the identity labels corresponding to a plurality of drivers respectively, the driver is subjected to identity recognition according to the identity recognition model, and corresponding driving mode services are provided for different drivers conveniently.
The driver identity recognition method provided by the embodiment of the invention identifies different types of driving behaviors based on the driving state information by acquiring the driving state information of the vehicle when the driver operates the vehicle, determines the characteristic data of at least one type of driving behaviors, inputs the determined characteristic data into the identity recognition model, the identity of the current driver is identified, and the driver can only rely on the driving state information of the vehicle when driving the vehicle without adding an additional sensor, bringing a complicated operation burden to the driver and collecting and recording the biological privacy information of the driver, the identity of the driver is identified, the hardware cost is saved, the driving experience of the driver is ensured, meanwhile, the privacy of the driver is protected, the intelligent automobile can provide differentiated driving mode services for different drivers, and the active safety and good user experience of the automobile are improved.
Fig. 4 is a schematic diagram of a driver identification apparatus provided in an embodiment of the present invention, including:
the obtaining module 401 is configured to obtain driving state information of a vehicle in a process that a driver operates the vehicle;
a processing module 402, configured to identify different types of driving behaviors based on the driving state information, and determine feature data of at least one type of driving behavior;
and the identification module 403 is configured to input the determined feature data into an identity identification model, so as to identify the current driver.
Optionally, the obtaining module is further configured to:
collecting CAN data of a vehicle controller local area network;
and analyzing the CAN data to acquire the running state information of the vehicle.
Optionally, the processing module includes:
the recognition submodule is used for recognizing the driving behaviors of straight driving types, the driving behaviors of at least three types of turning types and the driving behaviors of acceleration types according to the driving state information, the turning angles corresponding to the driving behaviors of the at least three types of turning types are respectively in different angle intervals, and the acceleration corresponding to the driving behaviors of the acceleration types is larger than a first acceleration threshold value;
the processing submodule is used for respectively extracting at least one target signal from the running state information aiming at least one type of driving behaviors and acquiring at least one characteristic value of the target signal in the driving time period of the current driving behaviors;
wherein the characteristic data comprises at least one target signal and at least one characteristic value corresponding to the target signal.
Optionally, the identifier module is further configured to:
and adopting a threshold-based classification algorithm to classify the driving behavior into a straight-going category, at least three turning categories and an acceleration category according to the steering wheel rotation angle, the depth and the change rate of an accelerator pedal and the vehicle speed in the running state information.
Optionally, the processing sub-module includes:
an extraction unit configured to extract, for at least one type of driving behavior, at least one of the following target signals in the driving state information, respectively: steering wheel angle, steering wheel angular velocity, longitudinal acceleration, accelerator pedal depth, vehicle lateral acceleration, vehicle torque, brake pedal depth, motor speed and motor speed change rate;
an acquisition unit, configured to acquire, for each of the target signals extracted for each type of driving behavior, at least one of the following characteristic values within a driving period of a current driving behavior: the maximum value, the minimum value, the average value, the standard deviation, the kurtosis, the skewness, the peak value factor, the waveform factor, the margin factor and the pulse factor of the amplitude value in the frequency domain corresponding to the target signal.
Optionally, the apparatus further comprises:
the first generation module is used for arranging and storing the characteristic data of at least one type of driving behaviors according to a preset time period after the processing module determines the characteristic data of at least one type of driving behaviors, and generating a characteristic data set in a matrix form;
the identification module is further to:
inputting the feature data set into the identification model to identify the identity of the current driver.
Optionally, the identification module includes:
the output sub-module is used for inputting the determined characteristic data into the identity recognition model and outputting probability values corresponding to identity labels in the identity recognition model, wherein the identity labels represent identity information of a driver;
and the determining submodule is used for determining the identity label with the maximum probability value as a target identity label matched with the current driver and determining the identity information of the current driver according to the target identity label.
Optionally, the apparatus further comprises:
and the second generation module is used for generating the identity recognition model according to the characteristic data of various driving behaviors respectively corresponding to the plurality of drivers when the plurality of drivers operate the vehicle and the identity information of the plurality of drivers.
Optionally, the second generating module includes:
the first setting submodule is used for setting a network architecture of the long-time memory cyclic neural network, and the network architecture at least comprises the number of network layers, the number of hidden node units, a propagation direction, a batch size, a gradient threshold value, a node characteristic length and a data size;
the second setting submodule is used for respectively setting an identity tag corresponding to each driver according to the identity information of the plurality of drivers;
the training submodule is used for carrying out multi-round model training according to characteristic data of various driving behaviors corresponding to a plurality of drivers, the identity tags corresponding to the drivers and the network architecture, determining model convergence when a target function value meeting a preset condition is detected in the model training process, and determining and generating the identity recognition model;
the characteristic data of each type of driving behaviors comprises a plurality of target signals and a plurality of characteristic values of each target signal in a driving time period of the current driving behaviors.
For the above device embodiment, since it is basically similar to the driver identification method embodiment, reference may be made to the partial description of the method embodiment for relevant points.
The driver identity recognition device provided by the embodiment of the invention identifies different types of driving behaviors based on the driving state information by acquiring the driving state information of the vehicle when the driver operates the vehicle, determines the characteristic data of at least one type of driving behaviors, inputs the determined characteristic data into the identity recognition model, the identity of the current driver is identified, and the driver can only rely on the driving state information of the vehicle when driving the vehicle without adding an additional sensor, bringing a complicated operation burden to the driver and collecting and recording the biological privacy information of the driver, the identity of the driver is identified, the hardware cost is saved, the driving experience of the driver is ensured, meanwhile, the privacy of the driver is protected, the intelligent automobile can provide differentiated driving mode services for different drivers, and the active safety and good user experience of the automobile are improved.
An embodiment of the present invention further provides an electronic device, as shown in fig. 5, including a processor 501, a communication interface 502, a memory 503 and a communication bus 504, where the processor 501, the communication interface 502 and the memory 503 complete mutual communication through the communication bus 504.
The memory 503 stores a computer program.
When the processor 501 is configured to execute the program stored in the memory 503, the following steps are implemented: acquiring running state information of a vehicle in the process of controlling the vehicle to run by a driver; identifying different types of driving behaviors based on the driving state information, and determining characteristic data of at least one type of driving behaviors; and inputting the determined characteristic data into an identity recognition model to recognize the identity of the current driver.
The processor 501 may also implement other steps in the driver identification method, which are not described herein again.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In still another embodiment of the present invention, a computer-readable storage medium is further provided, which stores instructions that, when executed on a computer, cause the computer to execute the driver identification method described in the above embodiment.
In yet another embodiment of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the driver identification method described in the above embodiment.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. For embodiments of the apparatus, the electronic device, the computer-readable storage medium, and the computer program product containing instructions, which are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (12)
1. A driver identification method, comprising:
acquiring running state information of a vehicle in the process of controlling the vehicle to run by a driver;
identifying different types of driving behaviors based on the driving state information, and determining characteristic data of at least one type of driving behaviors;
and inputting the determined characteristic data into an identity recognition model to recognize the identity of the current driver.
2. The driver identification method according to claim 1, wherein the acquiring of the driving state information of the vehicle includes:
collecting CAN data of a vehicle controller local area network;
and analyzing the CAN data to acquire the running state information of the vehicle.
3. The driver identification method according to claim 1, wherein the identifying different types of driving behaviors based on the driving state information and determining the characteristic data of at least one type of driving behavior comprises:
identifying driving behaviors of a straight type, at least three types of turning types and an acceleration type according to the driving state information, wherein the turning angles corresponding to the driving behaviors of the at least three types of turning types are in different angle intervals respectively, and the acceleration corresponding to the driving behavior of the acceleration type is larger than a first acceleration threshold value;
aiming at least one type of driving behaviors, respectively extracting at least one target signal from the driving state information, and acquiring at least one characteristic value of the target signal in the driving time period of the current driving behavior;
wherein the characteristic data comprises at least one target signal and at least one characteristic value corresponding to the target signal.
4. The driver identification method according to claim 3, wherein the identifying of the driving behavior of the straight traveling category, the driving behavior of the at least three types of turning categories, and the driving behavior of the acceleration category from the traveling state information includes:
and adopting a threshold-based classification algorithm to classify the driving behavior into a straight-going category, at least three turning categories and an acceleration category according to the steering wheel rotation angle, the depth and the change rate of an accelerator pedal and the vehicle speed in the running state information.
5. The driver identification method according to claim 3, wherein the extracting at least one target signal from the driving state information and obtaining at least one characteristic value of the target signal in a driving period of a current driving behavior, respectively, for at least one type of driving behavior comprises:
for at least one type of driving behavior, extracting at least one of the following target signals from the driving state information: steering wheel angle, steering wheel angular velocity, longitudinal acceleration, accelerator pedal depth, vehicle lateral acceleration, vehicle torque, brake pedal depth, motor speed and motor speed change rate;
for each target signal extracted from each type of driving behavior, acquiring at least one of the following characteristic values within a driving period of the current driving behavior: the maximum value, the minimum value, the average value, the standard deviation, the kurtosis, the skewness, the peak value factor, the waveform factor, the margin factor and the pulse factor of the amplitude value in the frequency domain corresponding to the target signal.
6. The driver identification method according to claim 1, after determining the characteristic data of at least one type of driving behavior, further comprising:
arranging and storing the characteristic data of at least one type of driving behaviors according to a preset time period to generate a characteristic data set in a matrix form;
inputting the determined characteristic data into an identity recognition model to recognize the identity of the current driver, wherein the identity recognition comprises the following steps:
inputting the feature data set into the identification model to identify the identity of the current driver.
7. The method for identifying the driver as claimed in claim 1, wherein the step of inputting the determined feature data into an identification model to identify the current driver comprises:
inputting the determined characteristic data into the identity recognition model, and outputting probability values corresponding to identity labels in the identity recognition model, wherein the identity labels represent identity information of a driver;
and determining the identity label with the maximum probability value as a target identity label matched with the current driver, and determining the identity information of the current driver according to the target identity label.
8. The driver identification method according to claim 1, further comprising:
and generating the identity recognition model according to the characteristic data of various driving behaviors respectively corresponding to the plurality of drivers when the plurality of drivers operate the vehicle and the identity information of the plurality of drivers.
9. The method for identifying the driver according to claim 8, wherein the generating the identification model according to the characteristic data of various driving behaviors respectively corresponding to the plurality of drivers operating the vehicle and the identification information of the plurality of drivers comprises:
setting a network architecture of a long-time memory cyclic neural network, wherein the network architecture at least comprises the number of network layers, the number of hidden node units, a propagation direction, a batch size, a gradient threshold, a node characteristic length and a data size;
respectively setting an identity label corresponding to each driver according to the identity information of the plurality of drivers;
performing multi-round model training according to the characteristic data of various driving behaviors corresponding to the drivers, the identity labels corresponding to the drivers and the network architecture, determining model convergence when a target function value meeting a preset condition is detected in the model training process, and determining and generating the identity recognition model;
the characteristic data of each type of driving behaviors comprises a plurality of target signals and a plurality of characteristic values of each target signal in a driving time period of the current driving behaviors.
10. A driver identification device, comprising:
the acquisition module is used for acquiring the running state information of the vehicle in the process of controlling the vehicle to run by a driver;
the processing module is used for identifying different types of driving behaviors based on the driving state information and determining characteristic data of at least one type of driving behaviors;
and the identification module is used for inputting the determined characteristic data into an identity identification model to identify the current driver.
11. An electronic device, comprising: a processor, a communication interface, a memory, and a communication bus; the processor, the communication interface and the memory complete mutual communication through a communication bus;
a memory for storing a computer program;
a processor for implementing the steps of the driver identification method according to any one of claims 1 to 9 when executing the program stored in the memory.
12. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the driver identification method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010607021.5A CN113935392B (en) | 2020-06-29 | 2020-06-29 | Driver identity recognition method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010607021.5A CN113935392B (en) | 2020-06-29 | 2020-06-29 | Driver identity recognition method and device, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113935392A true CN113935392A (en) | 2022-01-14 |
| CN113935392B CN113935392B (en) | 2024-10-15 |
Family
ID=79273072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010607021.5A Active CN113935392B (en) | 2020-06-29 | 2020-06-29 | Driver identity recognition method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113935392B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114550147A (en) * | 2022-04-26 | 2022-05-27 | 天津大学 | Automobile data acquisition, analysis and processing method and system based on Internet of things |
| CN115186770A (en) * | 2022-09-08 | 2022-10-14 | 北京邮电大学 | Driver identity recognition method and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107492251A (en) * | 2017-08-23 | 2017-12-19 | 武汉大学 | It is a kind of to be identified and driving condition supervision method based on the driver identity of machine learning and deep learning |
| CN107704918A (en) * | 2017-09-19 | 2018-02-16 | 平安科技（深圳）有限公司 | Driving model training method, driver's recognition methods, device, equipment and medium |
| CN108009463A (en) * | 2016-10-27 | 2018-05-08 | 中国移动通信有限公司研究院 | A kind of method and device of identification |
| CN108280482A (en) * | 2018-01-30 | 2018-07-13 | 广州小鹏汽车科技有限公司 | Driver's recognition methods based on user behavior, apparatus and system |
| CN108482187A (en) * | 2018-04-26 | 2018-09-04 | 浙江吉利汽车研究院有限公司 | The control method for vehicle and system of identity-based identification |
| CN109145719A (en) * | 2018-07-06 | 2019-01-04 | 北京理工大学 | A kind of driver fatigue state recognition method and system |
| US20190051069A1 (en) * | 2017-08-10 | 2019-02-14 | GM Global Technology Operations LLC | User recognition system and methods for autonomous vehicles |
| KR20190027657A (en) * | 2017-09-07 | 2019-03-15 | 삼성전자주식회사 | Apparatus and method for assisting driving of a vehicle |
-
2020
- 2020-06-29 CN CN202010607021.5A patent/CN113935392B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009463A (en) * | 2016-10-27 | 2018-05-08 | 中国移动通信有限公司研究院 | A kind of method and device of identification |
| US20190051069A1 (en) * | 2017-08-10 | 2019-02-14 | GM Global Technology Operations LLC | User recognition system and methods for autonomous vehicles |
| CN107492251A (en) * | 2017-08-23 | 2017-12-19 | 武汉大学 | It is a kind of to be identified and driving condition supervision method based on the driver identity of machine learning and deep learning |
| KR20190027657A (en) * | 2017-09-07 | 2019-03-15 | 삼성전자주식회사 | Apparatus and method for assisting driving of a vehicle |
| CN107704918A (en) * | 2017-09-19 | 2018-02-16 | 平安科技（深圳）有限公司 | Driving model training method, driver's recognition methods, device, equipment and medium |
| CN108280482A (en) * | 2018-01-30 | 2018-07-13 | 广州小鹏汽车科技有限公司 | Driver's recognition methods based on user behavior, apparatus and system |
| CN108482187A (en) * | 2018-04-26 | 2018-09-04 | 浙江吉利汽车研究院有限公司 | The control method for vehicle and system of identity-based identification |
| CN109145719A (en) * | 2018-07-06 | 2019-01-04 | 北京理工大学 | A kind of driver fatigue state recognition method and system |
Non-Patent Citations (1)
| Title |
|---|
| 胡宏宇;刘家瑞;高菲;高振海;梅兴泰;杨光;: "基于一维卷积神经网络的驾驶人身份识别方法", 中国公路学报, no. 08, 27 February 2020 (2020-02-27) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114550147A (en) * | 2022-04-26 | 2022-05-27 | 天津大学 | Automobile data acquisition, analysis and processing method and system based on Internet of things |
| CN115186770A (en) * | 2022-09-08 | 2022-10-14 | 北京邮电大学 | Driver identity recognition method and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113935392B (en) | 2024-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110569783B (en) | Method and system for identifying lane changing intention of driver | |
| CN113486822B (en) | Surrounding vehicle track prediction method and system based on driving intention | |
| Meng et al. | Human driving behavior recognition based on hidden markov models | |
| CN107848478A (en) | The automatic identification of low speed collision and assessment | |
| CN108701229B (en) | Driving behavior analysis method and driving behavior analysis device | |
| Burton et al. | Driver identification and authentication with active behavior modeling | |
| Jeong et al. | Real-time driver identification using vehicular big data and deep learning | |
| CN110143202A (en) | A kind of dangerous driving identification and method for early warning and system | |
| CN108549911B (en) | Driver steering intervention identification method based on neural network | |
| CN113935392B (en) | Driver identity recognition method and device, electronic equipment and readable storage medium | |
| Tanprasert et al. | Combining unsupervised anomaly detection and neural networks for driver identification | |
| KR101519217B1 (en) | Apparatus for judging driver inattention and method thereof | |
| CN107944425A (en) | The recognition methods of road sign and device | |
| CN105539026A (en) | Tire pressure detection system and method | |
| CN114655227A (en) | Driving style recognition method, driving assistance method and device | |
| Park et al. | This car is mine!: Automobile theft countermeasure leveraging driver identification with generative adversarial networks | |
| Silva et al. | Finding manoeuvre motifs in vehicle telematics | |
| CN110263664A (en) | A kind of more occupant lanes are broken rules and regulations recognition methods and device | |
| CN110271557B (en) | Vehicle user feature recognition system | |
| Azadani et al. | Convolutional and recurrent neural networks for driver identification: An empirical study | |
| CN114475641B (en) | Lane departure warning method, lane departure warning device, lane departure warning control device, and storage medium | |
| CN114612919B (en) | Bill information processing system, method and device | |
| JPH08315265A (en) | Doppler microwave sensor | |
| CN111959517B (en) | Distance prompting method and device, computer equipment and storage medium | |
| Micale et al. | Cahoot: a context-aware vehicular intrusion detection system |
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 |