CN109191788B - Driver fatigue driving judgment method, storage medium, and electronic device - Google Patents

Driver fatigue driving judgment method, storage medium, and electronic device Download PDF

Info

Publication number
CN109191788B
CN109191788B CN201811056490.1A CN201811056490A CN109191788B CN 109191788 B CN109191788 B CN 109191788B CN 201811056490 A CN201811056490 A CN 201811056490A CN 109191788 B CN109191788 B CN 109191788B
Authority
CN
China
Prior art keywords
driving
driver
vehicle
parameters
fatigue
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
Application number
CN201811056490.1A
Other languages
Chinese (zh)
Other versions
CN109191788A (en
Inventor
胡宏宇
于兹文
高振海
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jilin University
Original Assignee
Jilin University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jilin University filed Critical Jilin University
Priority to CN201811056490.1A priority Critical patent/CN109191788B/en
Publication of CN109191788A publication Critical patent/CN109191788A/en
Application granted granted Critical
Publication of CN109191788B publication Critical patent/CN109191788B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
    • 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)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a method for judging fatigue driving of a driver, a storage medium and an electronic device, wherein the method comprises the following steps: acquiring the driving parameters of the vehicle at a set sampling time point according to a preset sampling period; analyzing the collected driving parameters, judging whether each driving parameter is in an abnormal state, and associating the judgment result of each driving parameter with the corresponding sampling time; if the number of times that the driving parameters are in the abnormal state in the preset period exceeds a set threshold value, determining that the driver is in fatigue driving; wherein the preset period is more than three times the preset sampling period. According to the scheme provided by the invention, the driving state of the vehicle is judged according to the driving parameters acquired in a short time (sampling period), and then whether the driver is in a fatigue state or not is judged by counting the abnormal times of the information state of the vehicle in a long time (preset period), so that extra instruments and devices are not required to be added in the vehicle, and the detection precision and the false alarm rate are higher.

Description

Driver fatigue driving judgment method, storage medium, and electronic device
Technical Field
The invention relates to the technical field of automatic control of automobiles, in particular to a method for judging fatigue driving of a driver, a storage medium and electronic equipment.
Background
With the increasing automobile holding capacity, the number of traffic accidents caused by fatigue driving of drivers is increasing, so that it is necessary to give an early warning to the fatigue state of drivers during driving. At present, the domestic and foreign fatigue detection methods mainly have the following three modes:
firstly, wear some physiological equipment for the driver, detect driver's physiological information, judge whether driver is in fatigue state through physiological information. The fatigue detection method based on the physiological information is undoubtedly the most accurate, and the physiological equipment worn by the driver inevitably interferes with driving, so that the fatigue detection method based on the physiological information has some problems when being applied to an actual vehicle.
Secondly, a camera is arranged in the cab, the facial information of the driver is shot, whether the driver has behavior characteristics such as yawning, blinking and eye closing or not is determined, and whether the driver is in a fatigue state or not is judged. According to the method, a camera needs to be installed in a cab, and the detection result of the camera is easily affected by environmental factors such as illumination and the like, so that the judgment result is inaccurate.
Disclosure of Invention
The present invention is directed to solving the above-mentioned problems in detecting a fatigue state of a driver in the prior art, and provides a driver fatigue driving determination method, a storage medium, and an electronic device.
Therefore, the invention provides a method for judging fatigue driving of a driver, which comprises the following steps:
acquiring the driving parameters of the vehicle at a set sampling time point according to a preset sampling period;
analyzing the collected driving parameters, judging whether each driving parameter is in an abnormal state, and associating the judgment result of each driving parameter with the corresponding sampling time;
if the number of times that the driving parameters are in the abnormal state in the preset period exceeds a set threshold value, determining that the driver is in fatigue driving; the preset period is G times of the preset sampling period, G is an integer and G is larger than or equal to 3.
Optionally, in the method for determining fatigue driving of a driver, the collected driving parameter is analyzed by a first-layer limit learning machine, an abnormal value range of the driving parameter is pre-stored in the first-layer limit learning machine, the driving parameter is compared with the abnormal value range, and if the driving parameter falls into the abnormal value range, the driving parameter is determined to be in an abnormal state.
Optionally, in the method for determining fatigue driving of a driver, a second-layer limit learning machine is used to analyze a determination result of the first-layer limit learning machine, the second-layer limit learning machine stores the set threshold, and a start time node of a preset period is adjusted according to whether each driving parameter is in an abnormal state.
Optionally, in the method for determining fatigue driving of a driver, the second-layer limit learning machine adjusts a starting time node of a preset period by:
and if the judgment results obtained in P times continuously indicate that the driving parameters are in a normal state, taking the time node of the judgment result obtained in the P +1 th time as the starting time node of the next preset period, wherein P is an integer and P is less than G.
Optionally, in the method for determining driver fatigue, the value of P is [ G/2 ].
Optionally, in the method for determining fatigue driving of a driver, according to a preset sampling period, in the step of collecting the driving parameters of the vehicle at a set sampling time point:
the driving parameters include a mean and/or a standard deviation obtained from vehicle data, wherein the vehicle data includes: at least one of a steering wheel angle, a steering wheel angle rate, a yaw rate, and a lateral position.
Optionally, the method for determining fatigue driving of a driver further includes:
and sending out an alarm prompt signal to remind the driver of being in a fatigue driving state at present.
Optionally, the method for determining fatigue driving of a driver further includes:
and if the driver is continuously judged to be fatigue driving within the set time after the warning signal is sent out, controlling the vehicle to start the double-flash warning lamp, controlling the vehicle to continuously drive along the current driving lane, and simultaneously controlling the driving speed of the vehicle to be reduced to zero according to the set change rule.
The invention also provides a computer-readable storage medium, wherein the storage medium stores program instructions for being read by a computer, and the computer reads the program instructions and then executes the method for judging the fatigue driving of the driver.
The invention also provides electronic equipment which comprises at least one processor and at least one memory, wherein program instructions are stored in the at least one memory, and the at least one processor reads the program instructions and then executes the method for judging the fatigue driving of the driver.
Compared with the prior art, any technical scheme provided by the invention at least has the following beneficial effects:
the invention provides a method for judging fatigue driving of a driver, a storage medium and an electronic device, wherein the method comprises the following steps: acquiring the driving parameters of the vehicle at a set sampling time point according to a preset sampling period; analyzing the collected driving parameters, judging whether each driving parameter is in an abnormal state, and associating the judgment result of each driving parameter with the corresponding sampling time; if the number of times that the driving parameters are in the abnormal state in the preset period exceeds a set threshold value, determining that the driver is in fatigue driving; wherein the preset period is a multiple of the preset sampling period. According to the scheme provided by the invention, the driving state of the vehicle is judged according to the driving parameters acquired in a short time (sampling period), and then whether the driver is in a fatigue state or not is judged by counting the abnormal times of each vehicle information state in a long time (preset period), so that extra instruments and devices are not required to be added in the vehicle, and the vehicle has high detection precision and low false alarm rate.
Drawings
FIG. 1 is a flowchart of a method for determining fatigue driving of a driver according to an embodiment of the present invention;
FIG. 2 is a typical single hidden layer feedforward neural network structure;
FIG. 3 is a flowchart illustrating a method for determining fatigue driving of a driver according to another embodiment of the present invention;
FIG. 4 is a diagram illustrating a specific information flow for determining whether a driver is tired according to two layers of extreme learning machines according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be further described with reference to the accompanying drawings. In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description of the present invention, and do not indicate or imply that the device or assembly referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Wherein the terms "first position" and "second position" are two different positions.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; the two components can be directly connected or indirectly connected through an intermediate medium, and the two components can be communicated with each other. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
The embodiment provides a method for judging fatigue driving of a driver, which can be applied to a vehicle controller or other processing modules of a vehicle, and as shown in fig. 1, the method comprises the following steps:
s101: and acquiring the driving parameters of the vehicle at the set sampling time point according to the preset sampling period. The sampling period may be selected to be short, such as 1 second, 2 seconds, etc. The driving parameters are parameters that can reflect the driving stability of the vehicle, which are obtained from vehicle data including a steering wheel angle, a steering wheel angle rate, a yaw rate, a lateral position, and the like. These vehicle data CAN be read directly from the vehicle CAN bus or from basic sensors onboard the vehicle, without the need for additional equipment. And the running parameter may be an average value, and/or a standard deviation calculated from the above vehicle data. The following description will be given taking the mean and standard deviation of the steering wheel angle as an example. Acquiring the steering wheel angle through a CAN bus in a sampling period, and determining the mean value and the standard deviation of the steering wheel angle in Z detection periods by combining the currently acquired detection value and the previously acquired detection value, wherein:
the calculation formula of the steering wheel angle absolute value MEAN SA _ MEAN is as follows:
Figure BDA0001795918800000041
wherein, SAfThe f-th sampling period is the steering wheel angle.
The calculation formula of the steering wheel angle standard deviation SA _ STD is as follows:
Figure BDA0001795918800000051
wherein, SAmThe calculation formula of (a) is as follows:
Figure BDA0001795918800000052
accordingly, the calculation formulas of the mean value and the standard deviation of the parameters of the steering wheel angle rate, the yaw rate, and the lateral position can be referred to the calculation procedures of the mean value and the standard deviation of the steering wheel angle described above. Only the sampling value of the steering wheel angle needs to be replaced by the sampling value of the corresponding vehicle data.
S102: analyzing the collected driving parameters, judging whether each driving parameter is in an abnormal state, and associating the judgment result of each driving parameter with the corresponding sampling time. Specifically, each vehicle data has its normal change rule during the vehicle driving process, and if the deviation between the actually acquired driving parameters and its normal change rule is too large, it belongs to an abnormal state. As a real-time scheme, for example:
the controller of the vehicle can judge the road condition of the current vehicle according to the navigation device, the lane auxiliary keeping device and the like of the vehicle, for example, if the vehicle is currently running on the expressway according to the above devices, the vehicle should keep constant speed and straight running along the current lane under normal conditions, the steering wheel angle and the steering angle speed should be maintained at a stable level, the speed of the vehicle should be stably kept within the speed limit range of the expressway, and the vertical deviation is not too large. If the steering wheel angle of the vehicle obtained at this time changes suddenly greatly and is suddenly restored to the state before the change, it can be considered that the data of the steering wheel angle is abnormal, or the currently detected vehicle speed value obviously exceeds the speed average value in the past Z detection periods, it can be said that the data of the current speed is abnormal.
S103: if the number of times that the driving parameters are in the abnormal state in the preset period exceeds a set threshold value, determining that the driver is in fatigue driving; the preset period is G times of the preset sampling period, G is an integer and G is greater than or equal to 3, and the set threshold can be selected according to actual conditions, for example, can be [ G/3], wherein [ ] represents taking an integer. In this step, a longer period is used to determine the number of times that the vehicle has abnormal conditions during the driving process, for example, the preset period is 10 sampling periods, and if 3 times of the detected abnormal conditions of the vehicle driving data occur in the period, it can be determined that the driver is currently in a fatigue state. In the scheme, the driving state of the vehicle is judged according to the driving parameters acquired in a short time (sampling period), and then whether the driver is in a fatigue state or not is judged by counting the abnormal times of the information state of the vehicle in a long time (preset period), so that extra instruments and devices do not need to be added in the vehicle, and the vehicle has high detection precision and low false alarm rate. Preferably, step S102 in the above solution is implemented by a first-layer limit learning machine, and the first-layer limit learning machine analyzes the collected driving parameter, and the first-layer limit learning machine pre-stores an abnormal value range of the driving parameter, compares the driving parameter with the abnormal value range, and determines that the driving parameter is in an abnormal state if the driving parameter falls into the abnormal value range. The extreme learning machine is a simple, easy-to-use and effective SLFNs learning algorithm of the single hidden layer feedforward neural network. Was introduced in 2006 by professor yellow and extensively by university of southern ocean science and technology. Compared with the traditional neural network learning algorithm (such as BP algorithm), a large number of network training parameters need to be set artificially, the extreme learning machine only needs to set the number of hidden layer nodes of the network, the input weight of the network and the bias of hidden elements do not need to be adjusted in the algorithm execution process, and a unique optimal solution is generated, so that the neural network learning algorithm has the advantages of high learning speed and good generalization performance. A typical single hidden layer feed-forward neural network structure is shown in fig. 2. As can be seen from the figure, a typical single hidden layer feedforward neural network consists of an input layer, a hidden layer and an output layer, wherein the neurons of the input layer are fully connected with the neurons of the hidden layer, and the neurons of the hidden layer are fully connected with the neurons of the output layer. Wherein, the input layer has n neurons, corresponding to n input variables; the hidden layer has l neurons; the output layer has m neurons corresponding to m output variables. The connection weight ω between the input layer and the hidden layer is shown as follows:
Figure BDA0001795918800000061
wherein, ω isijAnd representing the connection weight between the ith neuron of the input layer and the jth neuron of the hidden layer.
The connection weights β between the hidden layer and the output layer are shown in the following formula:
Figure BDA0001795918800000062
wherein, βjkAnd representing the connection weight between the jth neuron of the hidden layer and the kth neuron of the output layer.
The bias b of the neurons of the hidden layer is shown as follows:
Figure BDA0001795918800000071
the training set input matrix X with Q samples can be represented as:
Figure BDA0001795918800000072
let the activation function of the hidden layer neurons be g (x), then the output matrix T of the network is: t ═ T1，t2，…，tQ]1×Q
Wherein, the calculation formula of t is shown as the following formula:
Figure BDA0001795918800000073
wherein, ω isi＝[ωi1，ωi2，…，ωin]，xj＝[x1j，x2j，...，xnj]T。
The above formula can be expressed as H β ═ T1，T1Is the transpose matrix of the matrix T, H is the output matrix of the hidden layer, and the calculation formula of H is shown as the following formula:
Figure BDA0001795918800000074
Figure BDA0001795918800000081
based on the previous research, SLFN is explored by the people and the following 2 theorems are proposed:
(1) for any given Q different samples (xi, ti), where xi＝[xi1，xi2，…，xin]T∈Rn，ti＝[ti1，ti2，…，tim]∈RmR → R, then for SLFN with Q hidden layer neurons, with arbitrary assignments ω i ∈ Rn and bi ∈ R, the hidden layer output matrix H is reversible and has H β -T1| | | 0.
(2) For any given Q different samples (x)i，ti) Wherein x isi＝[xi1，xi2，…，xin]T∈Rn，ti＝[ti1，ti2，…，tim]∈RmGiven an arbitrarily small error epsilon (epsilon)>0) And an activation function g infinitely differentiable in any interval: r → R, then there is always one SLFN containing K (K ≦ Q) hidden layer neurons, at any given value ωi∈RnAnd bi∈ R, there is | | | HN.MβM.m-T1||＜ε。
From theorem 1, it can be known that if the number of neurons in the hidden layer is equal to the number of samples in the training set, then SLFN can approximate the training samples with zero error for any of ω and b. However, if the number Q of samples in the training set is large, in order to simplify the calculation, the number K of neurons in the hidden layer is usually smaller than the number Q of samples in the training set, and it can be known from theorem 2 that the training error of SLFN can approach to an arbitrary epsilon (epsilon > 0).
Thus, if the activation function g (x) is infinitely differentiable, then the parameters of the SLFN need not all be adjusted, ω and b may be randomly selected before training and kept constant during training, while the connection weights β between the hidden and output layers may be adjusted by matching the equation set minβ||Hβ-T1Solving the least square solution to obtain the solution of the equation set
Figure BDA0001795918800000082
H+The generalized inverse of Moore-Penrose of the output matrix H for the hidden layer. The principle of the extreme learning machine is described above, and the following describes the above process in detail with reference to the scheme in the present embodiment. As an optional solution, in this embodiment, the algorithm of the limit learning machine in the training process includes the following steps:
1) determining the number of neurons in the hidden layer (set to 1000 in the text), and randomly setting a connection weight omega between the input layer and the hidden layer and a bias b of the neurons in the hidden layer; the neurons in this step may include driving parameters such as the mean and standard deviation of the steering wheel angle, the mean and standard deviation of the steering wheel angle rate, the mean and standard deviation of the yaw rate, and the mean and standard deviation of the lateral position. The weight values corresponding to different hidden layers may be determined according to their influence degrees on driving stability, for example, if it is considered that the steering wheel angle has a greater influence on driving stability than the steering wheel angle rate, the weight value corresponding to the steering wheel angle rate may be set to be higher than the weight value of the steering wheel angle. The offset b may be an initial reference value of a certain driving parameter, and may be set according to actual conditions, for example, the offset of the driving speed may be higher than the offset of the rotation angle of the steering wheel.
2) Selecting a Sigmoid function as an activation function of the hidden layer neurons, wherein the function is expressed as:
Figure BDA0001795918800000091
further calculating an output matrix H of the hidden layer;
3) calculating β an output layer weight;
and adjusting the connection weight omega according to the deviation between the actual output and the ideal output, so that the actual output and the ideal output can be kept consistent, thereby obtaining the final weight of each layer, correspondingly obtaining the weight β of the output layer, and further obtaining the model of the extreme learning machine.
Referring to fig. 4, where the vehicle information includes a steering wheel angle, a steering wheel angle rate, a yaw rate, and a lateral position, absolute standard deviations of the above parameters are used as inputs of the extreme learning machine, and each parameter may correspond to one ELM model, so as to obtain ELM models 1 to 4, where ELM model 1 may be a normal model or an abnormal model of a steering wheel angle, ELM model 2 may be a normal model or an abnormal model of a steering wheel angle rate, ELM model 3 may be a normal model or an abnormal model of a yaw rate, and ELM model 4 may be a normal model or an abnormal model of a lateral position. Therefore, the method can be used for training to obtain the vehicle information normal state model and the vehicle information abnormal state model, and the models can be further subdivided into: a normal model and an abnormal model of a steering wheel angle, a normal model and an abnormal model of a steering wheel angle rate, a normal model and an abnormal model of a yaw rate, and a normal model and an abnormal model of a lateral position. And applying the trained extreme learning machine to the scheme, and finally outputting a judgment result for judging whether the driving state is abnormal according to the driving parameters by taking the driving parameters as input.
Preferably, step S103 in the above solution is implemented by a second-layer limit learning machine, as the ELM model 5 in fig. 4, using the outputs of the ELM models 1 to 4 as the input parameters of the ELM model 5, analyzing the determination result of the first-layer limit learning machine by the second-layer limit learning machine, where the set threshold is stored, and adjusting the starting time node of the preset period according to whether each of the driving parameters is in an abnormal state. For the training process of the second-layer limit learning machine, the above scheme may be referred to, where the sample input adopts the output of the first-layer limit learning machine model, that is, the abnormal times of the driving parameters are used as samples, and may be further specifically subdivided into the abnormal times of the steering wheel angle, the abnormal times of the steering wheel angle rate, the abnormal times of the yaw angular velocity, and the abnormal times of the lateral position, and training is performed by using the determination result of whether fatigue driving is performed as an output, so that the driver awake state model and the driver fatigue state model may be obtained.
Further preferably, in the above scheme, the second-layer limit learning machine adjusts the starting time node of the preset period by: if the judgment results obtained in P consecutive times all indicate that the driving parameters are in a normal state, taking the time node of which the judgment result is obtained in the P +1 th time as the starting time node of the next preset period, wherein P is an integer and P < G, and preferably, the value of P is [ G/2 ]. That is, the starting time node of the preset period is not fixed, and may be set according to actual conditions, because the following conditions may occur in the actual operation process: if an abnormality occurs in the last two detection results of the first preset period and an abnormality occurs in the first two detection results of the second preset period, the above-mentioned situation may not be considered as driver fatigue driving if the preset period starting point is fixed.
After the scheme is adopted, if no abnormality is detected in P continuous periods in the first preset period, the P-th detection period of the first preset period can be used as the starting point of the second preset period, and after the conditions occur again, the abnormal conditions of four continuous times can be classified into the abnormal conditions occurring in the second preset period, so that the driver can be accurately judged to be fatigue-driven. Therefore, the judgment result in the scheme is more accurate.
Example 2
The present embodiment provides a method for determining fatigue driving of a driver, which may be applied to a vehicle controller or other processing modules of a vehicle, as shown in fig. 3, the method further includes the following steps based on the steps described in embodiment 1:
s104: and sending out an alarm prompt signal to remind the driver of being in a fatigue driving state at present. If the driver is detected to be in a fatigue driving state, the fact that the driver can not drive the vehicle normally is indicated, and the double-flash warning lamp is controlled to be turned on at the moment so as to remind the nearby vehicle to be far away from the vehicle, and traffic accidents are avoided.
S105: and if the driver is continuously judged to be fatigue driving within the set time after the warning signal is sent out, controlling the vehicle to start the double-flash warning lamp, controlling the vehicle to continuously drive along the current driving lane, and simultaneously controlling the driving speed of the vehicle to be reduced to zero according to the set change rule. That is, if the driver is continuously detected to be in a fatigue driving state, the vehicle is controlled to slowly decelerate and finally stop, and the driver of the vehicle behind is prompted to pay attention to the fact that the vehicle in front may need to stop by combining the double-flashing warning lamp, so that traffic accidents are avoided.
Example 3
The present embodiment provides a computer-readable storage medium, where program instructions for reading by a computer are stored in the storage medium, and the computer reads the program instructions and then executes the method for determining fatigue driving of a driver according to embodiment 1 or embodiment 2. The instruction information stored in the storage medium of the embodiment can judge the driving state of the vehicle according to the driving parameters acquired in a short time (sampling period), and then judge whether the driver is in a fatigue state or not by counting the abnormal times of each vehicle information state in a long time (preset period), so that extra instruments and devices are not required to be added in the vehicle, and the detection precision and the false alarm rate are high and low.
Example 4
The present embodiment provides an electronic device, as shown in fig. 5, which includes at least one processor 401 and at least one memory 402, where at least one memory 402 stores program instructions, and after at least one processor 401 reads the program instructions, the method for determining fatigue driving of a driver as described above may be performed. The above apparatus may further include: an input device 403 and an output device 404. The processor 401, memory 402, input device 403, and output device 404 may be connected by a bus or other means. The product can execute the method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the methods provided in the embodiments of the present application.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (7)

1. A method for judging fatigue driving of a driver is characterized by comprising the following steps:
acquiring the driving parameters of the vehicle at a set sampling time point according to a preset sampling period;
analyzing the collected driving parameters, judging whether each driving parameter is in an abnormal state, and associating the judgment result of each driving parameter with the corresponding sampling time;
if the number of times that the driving parameters are in the abnormal state in the preset period exceeds a set threshold value, determining that the driver is in fatigue driving; wherein the preset period is G times of the preset sampling period, G is an integer and G is more than or equal to 3;
analyzing the collected driving parameters through a first-layer extreme learning machine, wherein an abnormal value range of the driving parameters is pre-stored in the first-layer extreme learning machine, comparing the driving parameters with the abnormal value range, and if the driving parameters fall into the abnormal value range, judging that the driving parameters are in an abnormal state;
analyzing the judgment result of the first-layer extreme learning machine through a second-layer extreme learning machine, wherein the set threshold is stored in the second-layer extreme learning machine, and the starting time node of a preset period is adjusted according to whether each driving parameter is in an abnormal state;
the second-layer limit learning machine adjusts the starting time node of the preset period in the following mode: and if the judgment results obtained in P times continuously indicate that the driving parameters are in a normal state, taking the time node of the judgment result obtained in the P +1 th time as the starting time node of the next preset period, wherein P is an integer and P is less than G.
2. The driver fatigue driving determination method according to claim 1, characterized in that:
and the value of P is [ G/2 ].
3. The driver fatigue driving determination method according to claim 1 or 2, wherein in the step of acquiring the running parameters of the vehicle at set sampling time points according to a preset sampling period:
the driving parameters include a mean and/or a standard deviation obtained from vehicle data, wherein the vehicle data includes: at least one of a steering wheel angle, a steering wheel angle rate, a yaw rate, and a lateral position.
4. The driver fatigue driving determination method according to claim 3, further comprising the steps of:
and sending out an alarm prompt signal to remind the driver of being in a fatigue driving state at present.
5. The driver fatigue driving determination method according to claim 4, further comprising the steps of:
and if the driver is continuously judged to be fatigue driving within the set time after the warning signal is sent out, controlling the vehicle to start the double-flash warning lamp, controlling the vehicle to continuously drive along the current driving lane, and simultaneously controlling the driving speed of the vehicle to be reduced to zero according to the set change rule.
6. A computer-readable storage medium, wherein program instructions for reading by a computer are stored in the storage medium, and the computer executes the method for determining driver fatigue driving according to any one of claims 1 to 5 after reading the program instructions.
7. An electronic device, comprising at least one processor and at least one memory, wherein at least one memory stores program instructions, and at least one processor reads the program instructions and executes the method for determining driver fatigue according to any one of claims 1 to 5.
CN201811056490.1A 2018-09-11 2018-09-11 Driver fatigue driving judgment method, storage medium, and electronic device Active CN109191788B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811056490.1A CN109191788B (en) 2018-09-11 2018-09-11 Driver fatigue driving judgment method, storage medium, and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811056490.1A CN109191788B (en) 2018-09-11 2018-09-11 Driver fatigue driving judgment method, storage medium, and electronic device

Publications (2)

Publication Number Publication Date
CN109191788A CN109191788A (en) 2019-01-11
CN109191788B true CN109191788B (en) 2020-06-23

Family

ID=64910199

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811056490.1A Active CN109191788B (en) 2018-09-11 2018-09-11 Driver fatigue driving judgment method, storage medium, and electronic device

Country Status (1)

Country Link
CN (1) CN109191788B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110007316A (en) * 2019-04-16 2019-07-12 吉林大学 A kind of active steering obstacle avoidance system and method based on the identification of laser radar information of road surface
CN114435389B (en) * 2020-11-02 2024-01-30 上海汽车集团股份有限公司 Vehicle control method and device and vehicle
CN112668523A (en) * 2020-12-31 2021-04-16 深圳云天励飞技术股份有限公司 Vehicle driving abnormality detection method, device, electronic device, and storage medium
CN113119981B (en) * 2021-04-09 2022-06-17 东风汽车集团股份有限公司 Vehicle active safety control method, system and storage medium

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105096528B (en) * 2015-08-05 2017-07-11 广州云从信息科技有限公司 A kind of method for detecting fatigue driving and system
CN105261151B (en) * 2015-09-29 2018-08-03 中国第一汽车股份有限公司 High-grade highway driver fatigue condition detection method based on operation behavior feature
CN105389948A (en) * 2015-11-11 2016-03-09 上海斐讯数据通信技术有限公司 System and method for preventing fatigue driving of driver
CN105354988B (en) * 2015-12-11 2018-02-27 东北大学 A kind of driver tired driving detecting system and detection method based on machine vision
CN105632103A (en) * 2016-03-11 2016-06-01 张海涛 Method and device for monitoring fatigue driving
CN107316354B (en) * 2017-07-12 2019-07-16 哈尔滨工业大学 A kind of method for detecting fatigue driving based on steering wheel and GNSS data
CN107680338B (en) * 2017-11-06 2019-08-06 北京经纬恒润科技有限公司 A kind of method for detecting fatigue driving and device

Also Published As

Publication number Publication date
CN109191788A (en) 2019-01-11

Similar Documents

Publication Publication Date Title
CN109191788B (en) Driver fatigue driving judgment method, storage medium, and electronic device
CN109177982B (en) Vehicle driving risk degree evaluation method considering driving style
US7912796B2 (en) System and method for real-time recognition of driving patterns
CN110688877B (en) Danger early warning method, device, equipment and storage medium
CN110688729B (en) LSTM-IDM (least squares-inverse discrete cosine transform) following characteristic fusion method based on adaptive Kalman filtering, storage medium and equipment
CN108657188B (en) Driver driving technology online evaluation system
Peng et al. Intelligent method for identifying driving risk based on V2V multisource big data
CN116108717B (en) Traffic transportation equipment operation prediction method and device based on digital twin
US20190263419A1 (en) Autonomous vehicle control by comparative transition prediction
JP2021504218A (en) State estimator
KR20190111318A (en) Automobile, server, method and system for estimating driving state
CN114987539A (en) Individual collision grading early warning method and system for automatic driving automobile based on risk field model
CN116985803B (en) Self-adaptive speed control system and method for electric scooter
EP3640857A1 (en) Method, vehicle, system, and storage medium for indicating anomalous vehicle scenario using encoder network and discriminator network intermediate layer activation
CN113642114A (en) Modeling method for humanoid random car following driving behavior capable of making mistakes
CN113353083A (en) Vehicle behavior recognition method
CN110816531B (en) Control system and control method for safe distance between unmanned automobile vehicles
US20230001940A1 (en) Method and Device for Optimum Parameterization of a Driving Dynamics Control System for Vehicles
KR20180096235A (en) System and Method for estimating a state of road for a vehicle
CN109572692A (en) A kind of electric-controlled vehicle Anti-knocking system and its control method
CN109835333A (en) A kind of control system and control method for keeping vehicle to travel among lane
CN113291311B (en) Method for detecting abnormal behavior of driver under emergency collision avoidance working condition and storage medium
CN113822593A (en) Security situation assessment method and device, storage medium and electronic equipment
Butakov et al. Driver/vehicle response diagnostic system for the vehicle-following case
CN112801202B (en) Vehicle window fogging prediction method, system, electronic equipment and storage medium

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