CN114916944A - Fatigue driving monitoring method and device, electronic equipment and readable storage medium - Google Patents
Fatigue driving monitoring method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN114916944A CN114916944A CN202210742551.XA CN202210742551A CN114916944A CN 114916944 A CN114916944 A CN 114916944A CN 202210742551 A CN202210742551 A CN 202210742551A CN 114916944 A CN114916944 A CN 114916944A
- Authority
- CN
- China
- Prior art keywords
- target
- fatigue
- fatigue driving
- brain wave
- detected
- 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.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
- G06N3/08—Learning methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/20—Workers
- A61B2503/22—Motor vehicles operators, e.g. drivers, pilots, captains
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pathology (AREA)
- Mathematical Physics (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Computational Linguistics (AREA)
- Psychiatry (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Physiology (AREA)
- Evolutionary Biology (AREA)
- Signal Processing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Fuzzy Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The application discloses a fatigue driving monitoring method, a device, an electronic device and a readable storage medium, which are applied to the technical field of fatigue driving monitoring, wherein the fatigue driving monitoring method comprises the following steps: acquiring an electroencephalogram signal corresponding to a target to be detected; selecting a target electroencephalogram signal in a preset time period from the electroencephalogram signals and converting the target electroencephalogram signal into electroencephalogram characteristic data; performing feature dimensionality reduction on the brain wave feature data to obtain dimension-reduced brain wave feature data of the brain wave feature data under a preset feature dimensionality; and predicting the fatigue of the target to be detected at the next time step according to the dimensionality reduction brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected to obtain a fatigue driving prediction result. The application provides a method and a system for monitoring fatigue driving in real time, which obviously improve the accuracy and the real-time performance of monitoring the fatigue driving.
Description
Technical Field
The present application relates to the field of fatigue driving monitoring technologies, and in particular, to a method and an apparatus for monitoring fatigue driving, an electronic device, and a readable storage medium.
Background
With the rapid development of science and technology, the number of motor vehicles is increasing, and the occurrence amount of traffic accidents is also increasing year by year. When a driver is in fatigue driving, the driver cannot timely and effectively react to the change of the traffic road condition due to the reduction of judgment capability, and further traffic accidents are caused. At present, when a shooting environment or a posture of a driver changes, the fatigue state prediction is inaccurate easily, and therefore the fatigue driving monitoring is poor in practicability and low in accuracy.
Disclosure of Invention
The application mainly aims to provide a method and a device for monitoring fatigue driving, an electronic device and a readable storage medium, and aims to solve the technical problems of poor practicability and low accuracy of fatigue driving monitoring in the prior art.
In order to achieve the above object, the present application provides a fatigue driving monitoring method applied to a fatigue driving monitoring device, the fatigue driving monitoring method including:
acquiring an electroencephalogram signal corresponding to a target to be detected;
selecting a target electroencephalogram signal in a preset time period from the electroencephalogram signals and converting the target electroencephalogram signal into electroencephalogram characteristic data;
performing feature dimensionality reduction on the brain wave feature data to obtain dimension-reduced brain wave feature data of the brain wave feature data under a preset feature dimensionality;
and predicting the fatigue of the target to be detected at the next time step according to the dimension-reduced brain wave characteristic data and the target fatigue driving prediction model corresponding to the target to be detected, so as to obtain a fatigue driving prediction result.
To achieve the above object, the present application further provides a fatigue driving monitoring device, which is applied to a fatigue driving monitoring apparatus, the fatigue driving monitoring device includes:
the acquisition module is used for acquiring an electroencephalogram signal corresponding to a target to be detected;
the conversion module is used for selecting a target brain electrical signal in a preset time period from the brain electrical signals and converting the target brain electrical signal into brain wave characteristic data;
the dimension reduction module is used for carrying out feature dimension reduction on the brain wave feature data to obtain dimension reduced brain wave feature data of the brain wave feature data under a preset feature dimension;
and the prediction module is used for predicting the fatigue of the target to be detected at the next time step according to the dimensionality reduction brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected, so as to obtain a fatigue driving prediction result.
The present application further provides an electronic device, the electronic device including: a memory, a processor and a program of the fatigue driving monitoring method stored on the memory and executable on the processor, which program, when executed by the processor, may implement the steps of the fatigue driving monitoring method as described above.
The present application also provides a computer-readable storage medium having stored thereon a program for implementing the fatigue driving monitoring method, which when executed by a processor, implements the steps of the fatigue driving monitoring method as described above.
The present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the fatigue driving monitoring method as described above.
Compared with the method that the fatigue state of a driver is predicted by acquiring the facial condition of the driver through a camera, the method and the device for monitoring the fatigue driving predict the fatigue state of the driver by acquiring the electroencephalogram signal corresponding to a target to be detected; selecting a target brain electrical signal in a preset time period from the brain electrical signals and converting the target brain electrical signal into brain wave characteristic data; performing feature dimensionality reduction on the brain wave feature data to obtain dimension-reduced brain wave feature data of the brain wave feature data under a preset feature dimension; according to the dimensionality reduction brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected, the fatigue degree of the target to be detected at the next time step is predicted to obtain a fatigue driving prediction result, the fatigue state of the driver is quantized into the fatigue degree according to the electroencephalogram signal of the driver, the fatigue state of the driver is predicted, the obtained fatigue driving prediction result is not influenced by external factors (factors irrelevant to driving), the technical defect that the fatigue state prediction is inaccurate when the shooting environment is changed or the posture of the driver is changed by the method for predicting the fatigue state of the driver by acquiring the facial state of the driver through the camera is overcome, and therefore the practicability and the accuracy of fatigue driving monitoring are improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic flow chart of a first embodiment of a fatigue driving monitoring method according to the present application;
FIG. 2 is a schematic flow chart of a second embodiment of the fatigue driving monitoring method of the present application;
fig. 3 is a schematic structural diagram of a hardware operating environment related to a fatigue driving monitoring method in an embodiment of the present application.
The implementation of the objectives, functional features, and advantages of the present application will be further described with reference to the accompanying drawings.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments of the present application are described in detail below with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Example one
In a first embodiment of the present disclosure, with reference to fig. 1, the method for monitoring fatigue driving includes:
step S10, acquiring an electroencephalogram signal corresponding to a target to be detected;
in this embodiment, it should be noted that the target to be detected is a target to be detected for fatigue driving, and the target to be detected may be a target for driving a motor vehicle or a target for driving any vehicle.
Exemplarily, step S10 includes: the electroencephalogram signals of the target to be detected are collected once at each preset time interval through an electroencephalogram signal sensor, and the electroencephalogram signals are sent to conversion equipment in communication connection with the electroencephalogram signal sensor, so that the conversion equipment can convert the electroencephalogram signals into electroencephalogram characteristic data. The electroencephalogram signal sensor is integrated in a wearable device, the wearable device is worn by a target to be detected, so that a front electrode of the electroencephalogram signal sensor is attached to the forehead of the target to be detected, the electroencephalogram signal of the target to be detected is acquired through the front electrode, the wearable device can be glasses, helmets or wearable devices with no influence on driving behaviors, the preset time interval is a preset time interval for acquiring the electroencephalogram signal of the target to be detected, the preset time interval can be 1s, the connection mode of communication connection can be a Bluetooth connection mode, a local area network connection mode or any connection mode.
Wearable equipment through integrated brain electrical signal sensor gathers the brain electrical signal who treats the detection target, treats that the driving action influence of detection target is minimum, has avoided when adopting the standard to place the electrode collection and treat the physiological characteristic signal of detection target, owing to wear the complicacy, and the interference of treating the driving action of detection target is great, and leads to the high technical defect of limitation of driver fatigue prediction to reduce the limitation of driver fatigue monitoring, also improved the practicality of driver fatigue monitoring.
Step S20, selecting a target brain wave signal in a preset time period from the brain wave signals and converting the target brain wave signal into brain wave characteristic data;
in this embodiment, it should be noted that the preset time period is a preset time period for selecting an electroencephalogram signal, and the preset time period may be the latest 10s, the latest 15s, or the latest 5 s.
Exemplarily, the step S20 includes: when the electroencephalogram signals sent by the electroencephalogram signal sensor are detected and received, selecting target electroencephalogram signals in a preset time period from the electroencephalogram signals; analyzing the target electroencephalogram signal according to an electroencephalogram communication protocol to obtain electroencephalogram characteristic data of the target electroencephalogram signal under different frequency bands, wherein the frequency bands include but are not limited to the following eight types: delta waves (frequency 0.1-4Hz), theta waves (frequency 4-8Hz), low _ alpha waves (frequency 8-10Hz), high _ alpha waves (frequency 10-13Hz), low _ beta waves (frequency 13-20Hz), high _ beta waves (frequency 20-30Hz), low _ gamma waves (frequency 30-46Hz), and midle _ gamma waves (frequency 46-70 Hz).
It should be noted that, the device that resolves the target electroencephalogram signal may be a resolving device, the electroencephalogram signal sensor may be in communication connection with the resolving device, the communication connection may be a bluetooth connection, for example, the first bluetooth module of the electroencephalogram signal sensor may be paired with the second bluetooth module of the resolving device, or may be a local area network connection, for example, wifi, hotspot, or the like.
Step S30, performing feature dimensionality reduction on the brain wave feature data to obtain dimension-reduced brain wave feature data of the brain wave feature data under a preset feature dimensionality;
in this embodiment, it should be noted that the preset feature dimension is a preset feature dimension for reducing the brain wave feature data, and the preset feature dimension may be three-dimensional, four-dimensional, or two-dimensional.
Exemplarily, step S30 includes: and mapping the electroencephalogram feature data to a preset feature dimension through a dimension reduction algorithm to obtain electroencephalogram feature data features, wherein the dimension reduction algorithm can be an LLE (local linear embedding) algorithm or a PCA (Principal Component Analysis).
The LLE algorithm is preferably selected in this embodiment, because the PCA algorithm does not consider the manifold structure among the brain wave characteristic data, and the characteristic association degree of the brain wave characteristic data is strong, the manifold structure among the brain wave characteristic data can be retained through the LLE algorithm, so that the accuracy of fatigue driving prediction is high, and the complexity of the LLE algorithm is lower than that of other dimension reduction algorithms, thereby effectively improving the accuracy and real-time performance of fatigue driving monitoring.
In this embodiment, the preset feature dimension is preferably three-dimensional, and if other feature dimensions are selected, the situation that the accuracy of a fatigue driving prediction result predicted according to the dimension-reduced brain wave feature data and the target fatigue driving prediction model is low due to too low preset feature dimension and more loss of the dimension-reduced brain wave features is easily caused, or the situation that the efficiency of fatigue driving prediction is low due to too high preset feature dimension and larger dimension-reduced brain wave feature data is easily caused, and then three-dimensional is adopted as the preset feature dimension, so that the high accuracy and the high efficiency of fatigue driving prediction are both considered.
And step S40, predicting the fatigue of the target to be detected at the next time step according to the dimensionality reduction brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected, and obtaining a fatigue driving prediction result.
In this embodiment, it should be noted that the target fatigue driving prediction model is a prediction model for predicting a fatigue state of a target to be detected, and the fatigue driving prediction model may be a GRU (gated cyclic unit) model, an LSTM (Long Short-Term Memory network) model, or any cyclic neural network model.
The GRU model is preferred in this embodiment because the GRU model combines the forgetting gate and the input gate in the LSTM model into the update gate, and combines the memory unit and the hidden state into the reset gate, so that the whole model structure becomes more simplified to improve the computation performance.
Before step S40, predicting the fatigue degree of the target to be detected at the next time step according to the dimension-reduced brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected, and obtaining a fatigue driving prediction result, the fatigue driving monitoring method further includes:
step A10, acquiring a fatigue driving prediction model to be trained, training sample data corresponding to driving targets of all age groups and real fatigue degrees corresponding to the training sample data;
in this embodiment, it should be noted that the fatigue driving prediction model to be trained is an untrained fatigue driving detection model, and the real fatigue degree is an actual fatigue degree corresponding to the training sample data.
In step a10, obtaining training sample data and a true fatigue degree corresponding to the training sample data includes:
step A11, constructing the training sample data according to the electroencephalogram amplitude values of the electroencephalogram characteristic data corresponding to the driving target in different frequency bands;
step A12, determining the real fatigue corresponding to the training sample data according to the reaction time of the driving target responding to the preset operation.
In this embodiment, it should be noted that the preset operation is an operation performed by a preset driving target, and the preset operation may be a left-turn operation, a right-turn operation, or a brake operation.
Illustratively, steps a11 through a12 include: acquiring electroencephalogram signals of driving targets of all ages at preset time intervals through an electroencephalogram signal sensor, analyzing the electroencephalogram signals into electroencephalogram amplitude values of corresponding electroencephalogram characteristic data in different frequency bands, and constructing training sample data according to the electroencephalogram amplitude values; and obtaining the reaction time of the driving target responding to the preset operation, and obtaining the real fatigue corresponding to the training sample data according to the mapping relation between the reaction time and the fatigue.
Optionally, the mapping relationship between the reaction time and the fatigue degree may specifically be:
wherein, F i For the degree of fatigue, Δ t i For the reaction time, t 1 Is the reaction time threshold.
The reaction time threshold value is a critical value of a reaction time in response to a preset operation when it is determined that the driving target is full, that is, the fatigue degree is 0, and may be set to 0.3 s.
Step A20, performing feature dimension reduction on the training sample data to obtain dimension reduction training sample data of the training sample data under the preset feature dimension;
step A30, performing iterative optimization on the fatigue driving prediction model to be trained according to the dimensionality reduction training sample data and the real fatigue degree to obtain a fatigue driving prediction model corresponding to each age group;
illustratively, steps a20 through a30 include: predicting the training fatigue of the driving target at the next time step according to the dimensionality reduction training sample data and the fatigue driving prediction model to be trained; calculating model loss corresponding to the fatigue driving prediction model to be trained according to the difference between the training fatigue degree and the real fatigue degree, further judging whether the model loss is converged, if the model loss is converged, using the fatigue driving prediction model to be trained as the fatigue driving prediction model, if the model loss is not converged, updating the fatigue driving prediction model to be trained through a preset model updating method based on the gradient of model loss calculation, and returning to the execution step: acquiring training sample data corresponding to driving targets of all age groups and real fatigue degrees corresponding to the training sample data, wherein the preset model updating method is a gradient descent method and the like.
In step S40, the step of predicting the fatigue of the target to be detected at the next time step according to the dimensionality-reduced electroencephalogram feature data and the target fatigue driving prediction model corresponding to the target to be detected includes:
step B10, selecting a target fatigue driving prediction model corresponding to the target to be detected from fatigue driving prediction models according to the age of the target to be detected;
step B20, determining an update gate value and a corresponding reset gate value corresponding to the target fatigue driving prediction model according to the dimensionality reduction brain wave feature data, the hidden layer output value of the last time step, the reset gate parameter and the update gate parameter;
and B30, predicting the fatigue of the target to be detected at the next time step according to the target fatigue driving prediction model, the updated threshold value corresponding to the target fatigue driving prediction model and the corresponding reset threshold value.
Exemplarily, the step B10 to the step B30 include: acquiring the age of the target to be detected, and selecting a target fatigue driving prediction model corresponding to the target age group from fatigue driving prediction models corresponding to the age groups according to the target age group of the age; acquiring a weight matrix of an update gate and a bias value of the update gate to obtain parameters of the update gate; acquiring a weight matrix of a reset gate and a bias value of the reset gate to obtain a parameter of the reset gate; determining an update gate value corresponding to the target fatigue driving prediction model according to the dimensionality reduction brain wave feature data, the hidden layer output value of the previous time step and the update gate parameter; determining a reset gate value corresponding to the target fatigue driving prediction model according to the dimensionality reduction brain wave feature data, the hidden layer output value of the last time step and the reset gate parameter; and determining an output value of a hidden layer according to the target fatigue driving prediction model, the corresponding update threshold value of the target fatigue driving prediction model and the corresponding reset threshold value, and obtaining the fatigue degree of the target to be detected at the next time step. Wherein the output value of the hidden layer comprises a hidden layer candidate value and a hidden layer update value.
Optionally, the obtaining of the update gate value may specifically be:
Z t ＝σ(X t W xz +H t-1 W hz +b z )
wherein Z is t To update the gate value; sigma is sigmoid function; x t The characteristic data of the brain wave at the time t; w xz Updating the weight matrix of the gate; h t-1 Is the hidden layer state before t time; b is a mixture of z To update the bias value of the gate; w hz The weight matrix of the gate is updated.
Optionally, the obtaining of the reset gate value may specifically be:
R t ＝σ(X t W xr +H t-1 W hr +b r )
wherein R is t To reset the gate value; sigma is sigmoid function; x t The characteristic data of the brain wave at the time t; w xr A weight matrix for reset gates; h t-1 Is the hidden layer state before t time; b r To reset the offset value of the gate; w is a group of hr The weight matrix of the gate is reset.
Optionally, the determining of the hidden layer candidate value may specifically be:
wherein the content of the first and second substances,
is the candidate hidden layer state; tan h is an activation function; x t The characteristic data of the brain wave at the time t; w xh Is a weight matrix; r is t To reset the gate value; h t-1 Is the hidden layer state before t time; an operation as a Hadamard product; w hh Is a weight matrix; b is a mixture of h Is an offset value.
Optionally, the determination of the hidden layer update value may specifically be:
wherein H t Hiding layer states for the updating; z is a linear or branched member t To update the gate value; an operation as a Hadamard product; h t-1 Is the hidden layer state before t time;
is the candidate hidden layer state.
The fatigue state of the target to be detected is obtained by predicting the fatigue degree of the target to be detected in the next time step according to the electroencephalogram signal of the target to be detected and the fatigue driving prediction model, the technical defect that the transportability of fatigue driving monitoring in different scenes is poor due to the fact that the calculation model is simple and depends on manual parameter adjustment when the electroencephalogram signal of the target to be detected and a normal electroencephalogram signal are compared to obtain an electroencephalogram fatigue parameter, and the electroencephalogram fatigue parameter and the blink frequency of the target to be detected are combined and calculated to obtain the fatigue state of the target to be detected is overcome, and the transportability of fatigue driving monitoring in different scenes is improved.
Compared with the method for monitoring fatigue driving, which is used for predicting the fatigue state of a driver by acquiring the facial condition of the driver through a camera, the method for monitoring fatigue driving comprises the steps of acquiring an electroencephalogram signal corresponding to a target to be detected; selecting a target electroencephalogram signal in a preset time period from the electroencephalogram signals and converting the target electroencephalogram signal into electroencephalogram characteristic data; performing feature dimensionality reduction on the brain wave feature data to obtain dimension-reduced brain wave feature data of the brain wave feature data under a preset feature dimension; according to the dimensionality reduction brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected, the fatigue degree of the target to be detected at the next time step is predicted to obtain a fatigue driving prediction result, the fatigue state of the driver is quantized into the fatigue degree according to the electroencephalogram signal of the driver, the fatigue state of the driver is predicted, the obtained fatigue driving prediction result is not influenced by external factors (factors irrelevant to driving), the technical defect that the fatigue state prediction is inaccurate when the shooting environment is changed or the posture of the driver is changed by the method for predicting the fatigue state of the driver by acquiring the facial state of the driver through the camera is overcome, and therefore the accuracy and the practicability of fatigue driving monitoring are improved.
Example two
Further, referring to fig. 2, based on the first embodiment of the present application, in another embodiment of the present application, the same or similar contents to those of the first embodiment of the present application may be referred to the above description, and are not repeated herein. On the basis, in step S30, the brain wave feature data at least includes a target brain wave feature sample data, and the step of performing feature dimensionality reduction on the brain wave feature data to obtain the dimension-reduced brain wave feature data of the brain wave feature data in a preset feature dimension includes:
step S31, obtaining target brain wave feature sample data, and determining neighbor brain wave feature sample data of the target brain wave feature sample data, wherein the distance between the neighbor brain wave feature sample data and the target brain wave feature sample data is not more than a preset distance threshold;
in this embodiment, it should be noted that the preset distance threshold is a preset critical value of a distance between the neighbor brain wave feature sample data and the target brain wave feature sample data, the number of the neighbor brain wave feature sample data is greater than or equal to the number of preset neighbor samples, the number of the preset neighbor samples is a preset critical value of the number of the neighbor brain wave feature sample data, the number of the preset neighbor samples is determined by a preset feature dimension, and the number of the preset neighbor samples and the preset feature dimension are in a positive correlation relationship.
Exemplarily, the step S31 includes: selecting target brain wave feature sample data acquired at a preset moment from the brain wave features, determining a preset distance threshold according to the number of preset neighbor samples, and selecting neighbor brain wave feature sample data of which the distance from the target brain wave feature sample data is not more than the preset distance threshold.
Step S32, determining a weight coefficient used by weighting each neighbor brain wave feature sample data to obtain a weighted sample by minimizing the distance between the weighted sample corresponding to each neighbor brain wave feature sample data and the target brain wave feature sample data;
and step S33, reducing the dimension of the target brain wave feature data to the preset feature dimension according to the weight coefficient to obtain dimension-reduced brain wave feature data.
The determining of the weight coefficient used for weighting the sample data of the feature of the brain wave of each neighbor to obtain the weighted sample may specifically be:
wherein, Y i Sampling data of the target brain wave characteristics; w is a group of ij For each of said weight coefficients; y is j Sample data of the neighbor brain wave features; i.e. i max The number of the target brain wave feature sample data is set; j is a function of max The number of the neighbor brain wave feature sample data.
The obtained dimension-reduced brain wave feature data may specifically be:
wherein, X i The dimensional-reduced brain wave characteristic data is obtained; w ij For each of said weight coefficients; i all right angle max The number of the target brain wave characteristic sample data is set; j is a unit of a group maX The number of the neighbor brain wave feature sample data is set; x j And the dimensionality reduction neighbor brain wave feature data of the neighbor brain wave feature sample data.
In step S40, the step of inputting the dimension-reduced electroencephalogram feature data into the fatigue driving prediction model to predict the fatigue of the target to be detected at the next time step, and obtaining a fatigue driving prediction result includes:
step S41, judging whether the fatigue degree of the target to be detected at the next time step exceeds a preset fatigue degree threshold value and whether the duration time of the fatigue degree exceeding the preset fatigue degree threshold value reaches a preset time threshold value;
step S42, if yes, the fatigue driving prediction result is judged to be the target fatigue driving to be detected;
and step S43, if not, determining that the fatigue driving prediction result is that the target to be detected is not fatigue driven.
In this embodiment, it should be noted that the preset fatigue degree threshold is a preset fatigue degree critical value for determining that the fatigue state of the target to be detected is fatigue, and the preset fatigue degree threshold may be 90; the preset time threshold is a critical value for judging the fatigue state duration of the target to be detected in fatigue driving, and the preset time threshold can be 3 s.
Exemplarily, the steps S41 to S43 include: judging whether the fatigue degree of the target to be detected at the next time step exceeds a preset fatigue degree threshold value or not and whether the duration time of the fatigue degree exceeding the preset fatigue degree threshold value reaches a preset time threshold value or not; if the fatigue degree of the target to be detected at the next time step exceeds a preset fatigue degree threshold value and the duration time of the fatigue degree exceeding the preset fatigue degree threshold value reaches a preset time threshold value, judging that the fatigue driving prediction result is the fatigue driving of the target to be detected, and carrying out fatigue driving reminding on the target to be detected so as to enable the target to be detected to timely stop at the side for rest after receiving the fatigue driving reminding; and if the fatigue degree of the target to be detected does not exceed a preset fatigue degree threshold value at the next time step and/or the duration time of the fatigue degree exceeding the preset fatigue degree threshold value does not reach a preset time threshold value, judging that the fatigue driving prediction result is the target to be detected is not in fatigue driving, wherein the fatigue driving prompt can be a sound prompt and can also be an information prompt.
Compared with the method for monitoring fatigue driving, which is used for predicting the fatigue state of a driver by acquiring the facial condition of the driver through a camera, the method for monitoring fatigue driving comprises the steps of acquiring an electroencephalogram signal corresponding to a target to be detected; selecting a target brain electrical signal in a preset time period from the brain electrical signals and converting the target brain electrical signal into brain wave characteristic data; performing feature dimensionality reduction on the brain wave feature data to obtain dimension-reduced brain wave feature data of the brain wave feature data under a preset feature dimensionality; according to the dimensionality reduction brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected, the fatigue degree of the target to be detected at the next time step is predicted, a fatigue driving prediction result is obtained, the fatigue state of the driver is quantized into the fatigue degree according to the electroencephalogram signal of the driver, the fatigue state of the driver is predicted, the obtained fatigue driving prediction result is not influenced by external factors (factors irrelevant to driving), and the technical defect that the fatigue state prediction is inaccurate easily occurs when the shooting environment is changed or the posture of the driver is changed when the facial state of the driver is collected through a camera to predict the fatigue state of the driver is overcome, so that the accuracy and the practicability of fatigue driving monitoring are improved.
EXAMPLE III
The embodiment of the present application still provides a driver fatigue monitoring devices, driver fatigue monitoring devices is applied to driver fatigue monitoring facilities, driver fatigue monitoring devices includes:
the acquisition module is used for acquiring an electroencephalogram signal corresponding to a target to be detected;
the conversion module is used for selecting a target brain electrical signal in a preset time period from the brain electrical signals and converting the target brain electrical signal into brain wave characteristic data;
the dimension reduction module is used for carrying out feature dimension reduction on the brain wave feature data to obtain dimension reduced brain wave feature data of the brain wave feature data under a preset feature dimension;
and the prediction module is used for predicting the fatigue of the target to be detected at the next time step according to the dimensionality reduction brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected, so as to obtain a fatigue driving prediction result.
Optionally, the brain wave feature data at least includes a target brain wave feature sample data, and the dimension reduction module is further configured to:
acquiring target brain wave feature sample data, and determining neighbor brain wave feature sample data of the target brain wave feature sample data, wherein the distance between the neighbor brain wave feature sample data and the target brain wave feature sample data is not greater than a preset distance threshold;
determining a weighting coefficient used for weighting the neighbor brain wave feature sample data to obtain the weighting sample by minimizing the distance between the weighting sample corresponding to the neighbor brain wave feature sample data and the target brain wave feature sample data;
and reducing the dimension of the target brain wave feature data to the preset feature dimension according to the weight coefficient to obtain the dimension-reduced brain wave feature data.
Optionally, the fatigue driving monitoring device is further configured to:
acquiring a fatigue driving prediction model to be trained, training sample data corresponding to driving targets of all ages and real fatigue degrees corresponding to the training sample data;
performing feature dimensionality reduction on the training sample data to obtain dimensionality reduction training sample data of the training sample data under the preset feature dimensionality;
and performing iterative optimization on the fatigue driving prediction model to be trained according to the dimensionality reduction training sample data and the real fatigue degree to obtain the fatigue driving prediction model corresponding to each age group.
Optionally, the fatigue driving monitoring device is further configured to:
constructing the training sample data according to the electroencephalogram amplitude values of the electroencephalogram characteristic data corresponding to the driving target in different frequency bands;
and determining the real fatigue degree corresponding to the training sample data according to the reaction time of the driving target responding to the preset operation.
Optionally, the target fatigue driving prediction model comprises a reset gate parameter and an update gate parameter, and the prediction module is further configured to:
selecting a target fatigue driving prediction model corresponding to the target to be detected from fatigue driving prediction models according to the age of the target to be detected;
determining an updated gate value and a corresponding reset gate value corresponding to the target fatigue driving prediction model according to the dimensionality-reduced brain wave feature data, the hidden layer output value of the previous time step, the reset gate parameter and the updated gate parameter;
and predicting the fatigue of the target to be detected at the next time step according to the target fatigue driving prediction model, the corresponding update threshold value of the target fatigue driving prediction model and the corresponding reset threshold value.
Optionally, the prediction module is further configured to:
judging whether the fatigue degree of the target to be detected at the next time step exceeds a preset fatigue degree threshold value or not and whether the duration time of the fatigue degree exceeding the preset fatigue degree threshold value reaches a preset time threshold value or not;
if so, judging that the fatigue driving prediction result is the target fatigue driving to be detected;
if not, judging that the fatigue driving prediction result is that the target to be detected is not fatigue driven.
The fatigue driving monitoring device provided by the application adopts the fatigue driving monitoring method in the embodiment, and the technical problems of poor practicability and low accuracy of fatigue driving monitoring are solved. Compared with the prior art, the beneficial effects of the fatigue driving monitoring device provided by the embodiment of the application are the same as the beneficial effects of the fatigue driving monitoring method provided by the embodiment, and other technical characteristics of the fatigue driving monitoring device are the same as those disclosed by the method of the embodiment, which are not repeated herein.
Example four
An embodiment of the present application provides an electronic device, which includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the fatigue driving monitoring method in the above embodiments.
Referring now to FIG. 3, shown is a schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 3, the electronic device may include a processing apparatus (e.g., a central processing unit, a graphic processor, etc.) that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) or a program loaded from a storage apparatus into a Random Access Memory (RAM). In the RAM, various programs and data necessary for the operation of the electronic apparatus are also stored. The processing device, the ROM, and the RAM are connected to each other by a bus. An input/output (I/O) interface is also connected to the bus.
Generally, the following systems may be connected to the I/O interface: input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, and the like; output devices including, for example, Liquid Crystal Displays (LCDs), speakers, vibrators, and the like; storage devices including, for example, magnetic tape, hard disk, etc.; and a communication device. The communication means may allow the electronic device to communicate wirelessly or by wire with other devices to exchange data. While the figures illustrate an electronic device with various systems, it is to be understood that not all illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.
In particular, the processes described above with reference to the flow diagrams may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means, or installed from a storage means, or installed from a ROM. The computer program, when executed by a processing device, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
The electronic equipment provided by the application adopts the fatigue driving monitoring method in the embodiment, and the technical problems of poor practicability and low accuracy of fatigue driving monitoring are solved. Compared with the prior art, the beneficial effects of the electronic device provided by the embodiment of the present application are the same as the beneficial effects of the fatigue driving monitoring method provided by the above embodiment, and other technical features of the electronic device are the same as those disclosed by the above embodiment method, which are not described herein again.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the foregoing description of embodiments, the particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
EXAMPLE five
The present embodiments provide a computer-readable storage medium having computer-readable program instructions stored thereon for performing the method of the fatigue driving monitoring method in the above-described embodiments.
The computer readable storage medium provided by the embodiments of the present application may be, for example, a usb disk, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the above. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer-readable storage medium may be embodied in an electronic device; or may be separate and not incorporated into the electronic device.
The computer-readable storage medium carries one or more programs which, when executed by an electronic device, cause the electronic device to: acquiring an electroencephalogram signal corresponding to a target to be detected; selecting a target electroencephalogram signal in a preset time period from the electroencephalogram signals and converting the target electroencephalogram signal into electroencephalogram characteristic data; performing feature dimensionality reduction on the brain wave feature data to obtain dimension-reduced brain wave feature data of the brain wave feature data under a preset feature dimensionality; and predicting the fatigue of the target to be detected at the next time step according to the dimensionality reduction brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected to obtain a fatigue driving prediction result.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Wherein the names of the modules do not in some cases constitute a limitation of the unit itself.
The computer-readable storage medium provided by the application stores computer-readable program instructions for executing the fatigue driving monitoring method, and solves the technical problems of poor practicability and low accuracy of fatigue driving monitoring. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the embodiment of the application are the same as the beneficial effects of the fatigue driving monitoring method provided by the implementation, and are not described herein again.
Example six
The present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the fatigue driving monitoring method as described above.
The computer program product solves the technical problems of poor practicability and low accuracy of fatigue driving monitoring. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as the beneficial effects of the fatigue driving monitoring method provided by the above embodiment, and are not described herein again.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all equivalent structures or equivalent processes, which are directly or indirectly applied to other related technical fields, and which are not limited by the present application, are also included in the scope of the present application.
Claims (9)
1. A method of monitoring fatigue driving, the method comprising:
acquiring an electroencephalogram signal corresponding to a target to be detected;
selecting a target electroencephalogram signal in a preset time period from the electroencephalogram signals and converting the target electroencephalogram signal into electroencephalogram characteristic data;
performing feature dimensionality reduction on the brain wave feature data to obtain dimension-reduced brain wave feature data of the brain wave feature data under a preset feature dimension;
and predicting the fatigue of the target to be detected at the next time step according to the dimensionality reduction brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected to obtain a fatigue driving prediction result.
2. The method for monitoring fatigue driving as claimed in claim 1, wherein the brain wave feature data at least comprises a target brain wave feature sample data, the performing feature dimensionality reduction on the brain wave feature data to obtain the brain wave feature data with the reduced dimensionality under a preset feature dimension comprises:
acquiring target brain wave feature sample data, and determining neighbor brain wave feature sample data of the target brain wave feature sample data, wherein the distance between the neighbor brain wave feature sample data and the target brain wave feature sample data is not greater than a preset distance threshold;
determining a weighting coefficient used for weighting the neighbor brain wave feature sample data to obtain the weighting sample by minimizing the distance between the weighting sample corresponding to the neighbor brain wave feature sample data and the target brain wave feature sample data;
and reducing the dimension of the target brain wave feature data to the preset feature dimension according to the weight coefficient to obtain the dimension-reduced brain wave feature data.
3. The fatigue driving monitoring method according to claim 1, wherein before the step of predicting the fatigue degree of the target to be detected at the next time step according to the dimension-reduced brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected to obtain the fatigue driving prediction result, the fatigue driving monitoring method further comprises:
acquiring a fatigue driving prediction model to be trained, training sample data corresponding to driving targets of all ages and real fatigue degrees corresponding to the training sample data;
performing feature dimensionality reduction on the training sample data to obtain dimensionality reduction training sample data of the training sample data under the preset feature dimensionality;
and performing iterative optimization on the fatigue driving prediction model to be trained according to the dimensionality reduction training sample data and the real fatigue degree to obtain the fatigue driving prediction model corresponding to each age group.
4. The fatigue driving monitoring method according to claim 3, wherein obtaining training sample data and a true fatigue degree corresponding to the training sample data comprises:
constructing the training sample data according to the electroencephalogram amplitude values of the electroencephalogram characteristic data corresponding to the driving target in different frequency bands;
and determining the real fatigue degree corresponding to the training sample data according to the reaction time of the driving target responding to the preset operation.
5. The fatigue driving monitoring method according to claim 1, wherein the target fatigue driving prediction model includes a reset gate parameter and an update gate parameter, and the step of predicting the fatigue degree of the target to be detected at the next time step according to the dimension-reduced brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected includes:
selecting a target fatigue driving prediction model corresponding to the target to be detected from fatigue driving prediction models according to the age of the target to be detected;
determining an updated gate value and a corresponding reset gate value corresponding to the target fatigue driving prediction model according to the dimensionality-reduced brain wave feature data, the hidden layer output value of the previous time step, the reset gate parameter and the updated gate parameter;
and predicting the fatigue degree of the target to be detected at the next time step according to the target fatigue driving prediction model, the corresponding update threshold value of the target fatigue driving prediction model and the corresponding reset threshold value.
6. The method for monitoring fatigue driving as claimed in claim 1, wherein the step of predicting the fatigue degree of the target to be detected at the next time step according to the dimension-reduced brain wave feature data and the target fatigue driving prediction model corresponding to the target to be detected to obtain a fatigue driving prediction result comprises:
judging whether the fatigue degree of the target to be detected at the next time step exceeds a preset fatigue degree threshold value or not and whether the duration time of the fatigue degree exceeding the preset fatigue degree threshold value reaches a preset time threshold value or not;
if so, judging that the fatigue driving prediction result is the target fatigue driving to be detected;
if not, judging that the fatigue driving prediction result is that the target to be detected is not fatigue driven.
7. A fatigue driving monitoring device, comprising:
the acquisition module is used for acquiring an electroencephalogram signal corresponding to a target to be detected;
the conversion module is used for selecting a target electroencephalogram signal in a preset time period from the electroencephalogram signals and converting the target electroencephalogram signal into electroencephalogram characteristic data;
the dimension reduction module is used for carrying out feature dimension reduction on the brain wave feature data to obtain dimension reduced brain wave feature data of the brain wave feature data under a preset feature dimension;
and the prediction module is used for predicting the fatigue degree of the target to be detected at the next time step according to the dimension-reduced brain wave characteristic data and the target fatigue driving prediction model corresponding to the target to be detected, so as to obtain a fatigue driving prediction result.
8. An electronic device, characterized in that the electronic device comprises:
at least one processor; and (c) a second step of,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the fatigue driving monitoring method of any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program implementing the fatigue driving monitoring method, the program being executed by a processor to implement the steps of the fatigue driving monitoring method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210742551.XA CN114916944A (en) | 2022-06-28 | 2022-06-28 | Fatigue driving monitoring method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210742551.XA CN114916944A (en) | 2022-06-28 | 2022-06-28 | Fatigue driving monitoring method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114916944A true CN114916944A (en) | 2022-08-19 |
Family
ID=82813877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210742551.XA Pending CN114916944A (en) | 2022-06-28 | 2022-06-28 | Fatigue driving monitoring method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114916944A (en) |
-
2022
- 2022-06-28 CN CN202210742551.XA patent/CN114916944A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9361409B2 (en) | Automatic driver modeling for integration of human-controlled vehicles into an autonomous vehicle network | |
| US10803324B1 (en) | Adaptive, self-evolving learning and testing platform for self-driving and real-time map construction | |
| CN114091617A (en) | Federal learning modeling optimization method, electronic device, storage medium, and program product | |
| CN113723338B (en) | Sensor abnormality detection method, device and computer-readable storage medium | |
| CN112380363A (en) | Multimedia content recommendation method, device, vehicle and storage medium | |
| CN113487863A (en) | Multi-factor traffic risk real-time quantitative evaluation system and method | |
| CN114710555A (en) | Infant monitoring method and device | |
| CN113869599A (en) | Fish epidemic disease development prediction method, system, equipment and medium | |
| CN110378936B (en) | Optical flow calculation method and device and electronic equipment | |
| CN110555861B (en) | Optical flow calculation method and device and electronic equipment | |
| CN114916944A (en) | Fatigue driving monitoring method and device, electronic equipment and readable storage medium | |
| CN115543638B (en) | Uncertainty-based edge calculation data collection and analysis method, system and equipment | |
| CN116101205A (en) | Intelligent cabin in-vehicle intelligent sensing system based on in-vehicle camera | |
| CN116088537A (en) | Vehicle obstacle avoidance method, device, electronic equipment and computer readable medium | |
| CN114548254A (en) | Equipment fault classification method, device, equipment and medium | |
| CN112990017B (en) | Smart city big data analysis method and monitoring system | |
| JP7281436B2 (en) | Vehicle accident prediction system, vehicle accident prediction program, and trained model generation system | |
| CN115662510A (en) | Method, device and equipment for determining causal parameters and storage medium | |
| CN114063964A (en) | Volume compensation optimization method and device, electronic equipment and readable storage medium | |
| CN113269301A (en) | Method and system for estimating parameters of multi-target tracking system based on neural network | |
| CN114399355B (en) | Information pushing method and device based on user conversion rate and electronic equipment | |
| CN111369795B (en) | Traffic flow statistical method, device, equipment and storage medium | |
| CN114863650B (en) | Obstacle early warning method and device, electronic equipment and readable storage medium | |
| CN114647721B (en) | Educational intelligent robot control method, device and medium | |
| CN114386523A (en) | Prediction method, device, equipment and medium based on multi-mode extreme learning machine |
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 |