Fatigue driving detection method, device, equipment, medium and product

Abstract

The invention discloses a fatigue driving detection method, device and equipment, a medium and a product, and relates to the technical field of image processing.The method comprises the steps that vehicle driving parameters, driver images and steering wheel pressure sensing parameters in the vehicle driving process are collected; wherein the driver image comprises a head image of the driver; analyzing the vehicle driving parameters to obtain driving behavior information; analyzing the driver image and the steering wheel pressure sensing parameter to obtain driver state information; wherein the driver state information at least comprises an eye state, a face state and steering wheel holding force information; the driving behavior information and the driver state information are used, the fatigue driving detection result is obtained through analysis, the vehicle driving parameters and the steering wheel pressure sensing parameters except the physiological parameters of the driver can be collected, the fatigue degree of the driver is detected jointly from multiple angles, and therefore the accuracy of the fatigue driving detection result is improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a fatigue driving detection method, device, equipment, medium and product. Background Art

[0002] With the rapid development of the global automobile industry and the significant improvement of people's living standards, cars have become an indispensable means of transportation in modern society. However, with the sharp increase in the number of cars, the incidence of road traffic accidents has also shown an upward trend year by year, seriously threatening people's lives and property safety. According to relevant statistics, fatigue driving is one of the important causes of road traffic accidents, and its proportion cannot be ignored.

[0003] At present, there are some detection systems for fatigue driving on the market, but most of these systems have significant limitations. These systems usually detect the driver's fatigue state by monitoring limited physiological parameters (such as eyelid closure time, driver's turning operation behavior, etc.). Although this method can provide early warning to a certain extent, due to the diversity of physiological parameters and individual differences, the accuracy of fatigue driving detection results still needs to be improved. Summary of the invention

[0004] The purpose of this application is to provide a fatigue driving detection method, device, equipment, medium and product, which can improve the accuracy of fatigue driving detection results.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for detecting fatigue driving, comprising:

[0007] Collecting vehicle driving parameters, driver images and steering wheel pressure sensing parameters during vehicle driving; wherein the driver image includes the driver's head image;

[0008] Analyzing the vehicle driving parameters to obtain driving behavior information; wherein the driving behavior information at least includes vehicle speed stability and vehicle steering state information;

[0009] Analyze the driver image and the steering wheel pressure sensing parameters to obtain driver status information; wherein the driver status information at least includes eye status, facial status and steering wheel grip strength information;

[0010] The driving behavior information and the driver status information are used to analyze and obtain a fatigue driving detection result.

[0011] Optionally, analyzing the vehicle driving parameters to obtain driving behavior information specifically includes:

[0012] Obtaining a vehicle straight-line driving trajectory, a vehicle acceleration number, and a vehicle deceleration number within a preset time period from the vehicle driving parameters;

[0013] Using the current duration of the preset time period and the number of times the vehicle is accelerated and the number of times the vehicle is decelerated, the vehicle acceleration frequency and the vehicle deceleration frequency are calculated; wherein the current duration is the total duration of the preset time period;

[0014] The vehicle speed stability is determined according to the vehicle acceleration frequency, the vehicle deceleration frequency and the preset frequency threshold; wherein, if the vehicle acceleration frequency is greater than the preset frequency threshold or the vehicle deceleration frequency is greater than the preset frequency threshold, the vehicle speed stability is unstable vehicle speed; if the vehicle acceleration frequency is less than or equal to the preset frequency threshold and the vehicle deceleration frequency is less than or equal to the preset frequency threshold, the vehicle speed stability is stable vehicle speed;

[0015] Using the straight-line driving trajectory of the vehicle, calculating the straight-line distance from the starting point to the end point of the straight-line driving trajectory of the vehicle and the trajectory distance from the starting point to the end point of the straight-line driving trajectory of the vehicle;

[0016] The vehicle steering state information is determined according to the current ratio between the track distance and the straight-line distance and a preset ratio threshold; wherein, if the current ratio is less than or equal to the preset ratio threshold, the vehicle steering state information indicates that the vehicle has no abnormally large steering; and if the current ratio is greater than the preset ratio threshold, the vehicle steering state information indicates that the vehicle has an abnormally large steering.

[0017] The vehicle speed stability and the vehicle steering state information are determined as driving behavior information.

[0018] Optionally, the analyzing the driver image and the steering wheel pressure sensing parameters to obtain the driver status information specifically includes:

[0019] Performing eye recognition on the driver image to obtain eye status; wherein the eye status at least includes eyelid closure status and eyelid closure frequency;

[0020] Performing facial recognition on the driver image, and obtaining a facial expression recognition result as a facial state;

[0021] evaluating the steering wheel pressure sensing parameter based on a standard steering wheel pressure value to obtain a steering wheel pressure evaluation result;

[0022] Determining the steering wheel pressure assessment result as steering wheel grip strength information;

[0023] The eye state, the facial state and the steering wheel grip strength information are determined as driver state information.

[0024] Optionally, the using the driving behavior information and the driver status information to analyze and obtain a fatigue driving detection result specifically includes:

[0025] A first detection result is determined according to the vehicle speed stability and the vehicle steering state information; wherein, if the vehicle speed stability is that the vehicle speed is stable and the vehicle steering state information is that the vehicle has no abnormal large-scale steering, then the first detection result is a normal driving state; if the vehicle speed stability is that the vehicle speed is unstable or the vehicle steering state information is that the vehicle has an abnormal large-scale steering, then the first detection result is a slightly fatigued driving state; if the vehicle speed stability is that the vehicle speed is unstable and the vehicle steering state information is that the vehicle has an abnormal large-scale steering, then the first detection result is a moderately fatigued driving state;

[0026] A second detection result is determined according to the eye state, the facial state and the steering wheel holding force information; wherein, if the eyelid closure state indicates that the driver's eyelids are completely closed, then the second detection result is a severe fatigue driving state; if the eyelid closure frequency is greater than a preset closure frequency, the facial state is a tired state or the steering wheel holding force information indicates that the steering wheel pressure sensing parameter is less than the standard steering wheel pressure value, then the second detection result is a moderate fatigue driving state; if the eyelid closure frequency is less than or equal to the preset closure frequency, the facial state is a normal state and the steering wheel holding force information indicates that the steering wheel pressure sensing parameter is greater than or equal to the standard steering wheel pressure value, then the second detection result is a normal driving state;

[0027] A fatigue driving detection result is determined based on the first detection result and the second detection result.

[0028] Optionally, determining a fatigue driving detection result according to the first detection result and the second detection result specifically includes:

[0029] If both the first detection result and the second detection result are the normal driving state, determining the normal driving state as the fatigue driving detection result;

[0030] If one of the first detection result and the second detection result is the normal driving state and the other is the slightly fatigued driving state, determining the slightly fatigued driving state as the fatigue driving detection result;

[0031] If one of the first detection result and the second detection result is the normal driving state or the slightly fatigued driving state and the other is the moderately fatigued driving state, determining the moderately fatigued driving state as the fatigue driving detection result;

[0032] If there is a severe fatigue driving state in the first detection result and the second detection result, the severe fatigue driving state is determined as the fatigue driving detection result.

[0033] Optionally, the fatigue driving detection method further includes:

[0034] If the fatigue driving detection result is the slight fatigue driving state, a slight fatigue warning message is output through the instrument panel, and a slight fatigue warning voice is output through the speaker;

[0035] If the fatigue driving detection result is the moderate fatigue driving state, a moderate fatigue warning message is output through the instrument panel, and a moderate fatigue warning voice is output through the speaker;

[0036] If the fatigue driving detection result is the severe fatigue driving state, an emergency parking plan is generated, and severe fatigue warning information and the emergency parking plan are output through the instrument panel, and severe fatigue warning voice is output through the speaker.

[0037] In a second aspect, the present application provides a fatigue driving detection device, comprising:

[0038] A collection unit, used to collect vehicle driving parameters, driver images and steering wheel pressure sensing parameters during vehicle driving; wherein the driver image includes a driver's head image;

[0039] A first analysis unit, configured to analyze the vehicle driving parameters to obtain driving behavior information; wherein the driving behavior information at least includes vehicle speed stability and vehicle steering state information;

[0040] A second analysis unit is used to analyze the driver image and the steering wheel pressure sensing parameters to obtain driver status information; wherein the driver status information at least includes eye status, facial status and steering wheel grip strength information;

[0041] The third analysis unit is used to use the driving behavior information and the driver status information to analyze and obtain a fatigue driving detection result.

[0042] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the above-mentioned fatigue driving detection methods.

[0043] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the above-mentioned fatigue driving detection methods.

[0044] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned fatigue driving detection methods.

[0045] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0046] The present application provides a fatigue driving detection method, device, equipment, medium and product, which can obtain vehicle driving parameters during driving and driver images including the driver's head and steering wheel pressure sensing parameters, and can obtain fatigue driving detection results through fatigue driving analysis of vehicle driving parameters, driver images and steering wheel pressure sensing parameters. It can be seen that through this implementation method, vehicle driving parameters and steering wheel pressure sensing parameters in addition to the driver's physiological parameters can be collected, and then the driver's fatigue level can be jointly detected from multiple angles, thereby improving the accuracy of fatigue driving detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 This is a flow chart of a fatigue driving detection method in one embodiment of the present application;

[0049] Figure 2 A schematic diagram of the functional modules of a fatigue driving detection device provided in one embodiment of the present application.

[0050] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0053] In an exemplary embodiment, Figure 1 As shown, a fatigue driving detection method is provided, which is executed by a computer device, and can be specifically executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In an embodiment of the present application, the method includes the following steps 101 to 104.

[0054] in:

[0055] Step 101 , collecting vehicle driving parameters, driver images, and steering wheel pressure sensing parameters during vehicle driving.

[0056] In the embodiment of the present application, the driver image includes the driver's head image; the driver image can be collected by a vehicle-mounted camera; the pressure generated by the driver holding the steering wheel can be collected by a pressure sensor set on the steering wheel to obtain the steering wheel pressure sensing parameters. The vehicle driving parameters can be collected by sensors such as accelerometers and gyroscopes in the vehicle system.

[0057] Step 102: Analyze the vehicle driving parameters to obtain driving behavior information.

[0058] In an embodiment of the present application, the driving behavior information includes at least vehicle speed stability and vehicle steering state information.

[0059] As an optional implementation manner, step 102 analyzes the vehicle driving parameters to obtain driving behavior information in the following manner:

[0060] Obtaining a vehicle straight-line driving trajectory, a vehicle acceleration number, and a vehicle deceleration number within a preset time period from the vehicle driving parameters;

[0061] Using the current duration of the preset time period and the number of times the vehicle is accelerated and the number of times the vehicle is decelerated, the vehicle acceleration frequency and the vehicle deceleration frequency are calculated; wherein the current duration is the total duration of the preset time period;

[0062] The vehicle speed stability is determined according to the vehicle acceleration frequency, the vehicle deceleration frequency and the preset frequency threshold; wherein, if the vehicle acceleration frequency is greater than the preset frequency threshold or the vehicle deceleration frequency is greater than the preset frequency threshold, the vehicle speed stability is unstable vehicle speed; if the vehicle acceleration frequency is less than or equal to the preset frequency threshold and the vehicle deceleration frequency is less than or equal to the preset frequency threshold, the vehicle speed stability is stable vehicle speed;

[0063] Using the straight-line driving trajectory of the vehicle, calculating the straight-line distance from the starting point to the end point of the straight-line driving trajectory of the vehicle and the trajectory distance from the starting point to the end point of the straight-line driving trajectory of the vehicle;

[0064] The vehicle steering state information is determined according to the current ratio between the track distance and the straight-line distance and a preset ratio threshold; wherein, if the current ratio is less than or equal to the preset ratio threshold, the vehicle steering state information indicates that the vehicle has no abnormally large steering; and if the current ratio is greater than the preset ratio threshold, the vehicle steering state information indicates that the vehicle has an abnormally large steering.

[0065] The vehicle speed stability and the vehicle steering state information are determined as driving behavior information.

[0066] Among them, by implementing this implementation method, the number of vehicle accelerations and vehicle decelerations within a preset time period can be evaluated, and the vehicle speed stability can be determined based on the obtained vehicle acceleration frequency and vehicle deceleration frequency. The vehicle speed stability is used to indicate whether the vehicle driving is stable and whether acceleration or deceleration occurs frequently. In addition, the straight-line driving trajectory of the vehicle within the preset time period can be analyzed to obtain the vehicle steering state information. The vehicle steering state information can be used to determine whether the vehicle's driving route is in a straight line. If the vehicle turns frequently, it can be considered that the vehicle has abnormally large turns. The driving behavior information obtained in the above manner can be used to more accurately analyze the vehicle's driving conditions.

[0067] In the embodiment of the present application, the calculation formula of the vehicle acceleration frequency can be:

[0068] Vehicle acceleration frequency = vehicle acceleration times / current duration;

[0069] And, the calculation formula of vehicle deceleration frequency can be:

[0070] Vehicle deceleration frequency = vehicle deceleration times / current duration.

[0071] In the embodiment of the present application, the straight-line driving trajectory of the vehicle may be the trajectory of the vehicle on a straight road. If the current ratio between the trajectory distance and the straight-line distance is greater than a preset ratio threshold (current ratio = trajectory distance / straight-line distance), it can be considered that the vehicle swings with a large amplitude during the driver's driving on the straight road, resulting in the phenomenon that the trajectory distance is too long relative to the straight-line distance. Therefore, the vehicle steering state information can be determined as the vehicle having an abnormally large steering amplitude.

[0072] Furthermore, the vehicle-mounted radar can be used to detect obstacles in front of the vehicle within a preset time period to obtain obstacle detection results;

[0073] When the current ratio between the track distance and the straight-line distance is greater than a preset ratio threshold, turning information can be identified from the straight-line driving track of the vehicle; wherein the turning information includes a turning moment within a preset time period;

[0074] Obtaining a current obstacle detection result corresponding to the turning moment from the obstacle detection result;

[0075] If the current obstacle detection result indicates that there is an obstacle in front of the vehicle at the turning moment, the vehicle turning state information can be determined as the vehicle has no abnormal large-scale turning;

[0076] If the current obstacle detection result indicates that there is no obstacle in front of the vehicle at the turning moment, the vehicle turning state information can be determined as the vehicle making an abnormally large turn.

[0077] Step 103: Analyze the driver image and the steering wheel pressure sensing parameters to obtain driver status information.

[0078] In the embodiment of the present application, the driver status information includes at least eye status, facial status and steering wheel grip strength information. The driver image can be analyzed by a pre-built image analysis model to obtain the eye status and facial status, and the image analysis model can be built based on a neural network processing unit (NPU).

[0079] As an optional implementation manner, step 103 analyzes the driver image and the steering wheel pressure sensing parameters to obtain the driver status information, which may include:

[0080] Performing eye recognition on the driver image to obtain eye status; wherein the eye status at least includes eyelid closure status and eyelid closure frequency;

[0081] Performing facial recognition on the driver image, and obtaining a facial expression recognition result as a facial state;

[0082] evaluating the steering wheel pressure sensing parameter based on a standard steering wheel pressure value to obtain a steering wheel pressure evaluation result;

[0083] Determining the steering wheel pressure evaluation result as the steering wheel holding force information; wherein the steering wheel pressure evaluation result represents the magnitude relationship between the steering wheel pressure sensing parameter and the standard steering wheel pressure value; the standard steering wheel pressure value can be calculated based on the driver's long-term historical force information to obtain a standard steering wheel pressure value for the driver personally;

[0084] The eye state, the facial state and the steering wheel grip strength information are determined as driver state information.

[0085] Among them, by implementing this embodiment, eye recognition can be performed on the driver's image to determine the driver's eyelid closure state and eyelid closure frequency; facial recognition can also be performed on the driver's image to determine the driver's facial expression, thereby determining the driver's facial state; and steering wheel pressure sensing parameters can also be evaluated to determine the steering wheel holding force information, which can be used to evaluate whether the driver's hand grip on the steering wheel is reduced. If the driver's hand grip on the steering wheel is reduced, the driver may be in a fatigued state. It can be seen that the driver state information obtained in the above manner is more consistent with the driver's actual situation.

[0086] In the embodiment of the present application, each image frame can be extracted from the driver image, and then eye recognition and facial recognition can be performed on each image frame to obtain the eyelid closure degree and mouth closure degree in each image frame. The eyelid closure degree can include the eyelid being completely closed and the eyelid being not closed, and the mouth closure degree can include the mouth being completely closed and the mouth being not closed.

[0087] The duration of the image frames in which the eyelids are completely closed is counted to obtain the eyelid closure duration; the eyelid closure duration can then be compared with the standard eyelid closure duration threshold. If the eyelid closure duration is less than or equal to the standard eyelid closure duration threshold, the eyelid closure state can be determined as the eyelid is not closed; if the eyelid closure duration is greater than the standard eyelid closure duration threshold, the eyelid closure state can be determined as the eyelid is completely closed.

[0088] In the embodiment of the present application, the standard eyelid closure duration threshold can be calculated based on the long-term historical eyelid closure duration of the driver to obtain the standard eyelid closure duration threshold for the driver personally.

[0089] In addition, the blinking action composed of the image frames with completely closed eyelids and the image frames with open eyelids in the driver's image can be counted according to the time sequence of the image frames to obtain the number of blinks. The eyelid closure frequency can be obtained by dividing the number of blinks by the image duration of the driver's image.

[0090] Furthermore, if there is an image frame in which the mouth closure degree is not closed, the facial expression recognition result can be determined as a tired expression, and then the tired state corresponding to the tired expression can be determined as the facial state.

[0091] Step 104: Analyze and obtain a fatigue driving detection result using the driving behavior information and the driver status information.

[0092] As an optional implementation manner, step 104 uses the driving behavior information and the driver status information to analyze and obtain the fatigue driving detection result, which may include:

[0093] A first detection result is determined according to the vehicle speed stability and the vehicle steering state information; wherein, if the vehicle speed stability is that the vehicle speed is stable and the vehicle steering state information is that the vehicle has no abnormal large-scale steering, then the first detection result is a normal driving state; if the vehicle speed stability is that the vehicle speed is unstable or the vehicle steering state information is that the vehicle has an abnormal large-scale steering, then the first detection result is a slightly fatigued driving state; if the vehicle speed stability is that the vehicle speed is unstable and the vehicle steering state information is that the vehicle has an abnormal large-scale steering, then the first detection result is a moderately fatigued driving state;

[0094] A second detection result is determined according to the eye state, the facial state and the steering wheel holding force information; wherein, if the eyelid closure state indicates that the driver's eyelids are completely closed, then the second detection result is a severe fatigue driving state; if the eyelid closure frequency is greater than a preset closure frequency, the facial state is a tired state or the steering wheel holding force information indicates that the steering wheel pressure sensing parameter is less than the standard steering wheel pressure value, then the second detection result is a moderate fatigue driving state; if the eyelid closure frequency is less than or equal to the preset closure frequency, the facial state is a normal state and the steering wheel holding force information indicates that the steering wheel pressure sensing parameter is greater than or equal to the standard steering wheel pressure value, then the second detection result is a normal driving state;

[0095] A fatigue driving detection result is determined based on the first detection result and the second detection result.

[0096] Among them, by implementing this implementation method, a first detection result can be obtained based on the analysis of the vehicle speed stability and the vehicle steering state information in the driving behavior information, and a second detection result can be determined based on the eye state, facial state and steering wheel grip strength information in the driver state information; then, a comprehensive analysis can be performed based on the first detection result and the second detection result to obtain a final fatigue driving detection result, and accurate first detection results and second detection results can be obtained by respectively evaluating the driving behavior information and the driver state information, and then based on the accurate first detection result and the second detection result, the final fatigue driving detection result can be made more accurate.

[0097] As an optional implementation manner, according to the first detection result and the second detection result, a method of determining the fatigue driving detection result may include:

[0098] If both the first detection result and the second detection result are the normal driving state, determining the normal driving state as the fatigue driving detection result;

[0099] If one of the first detection result and the second detection result is the normal driving state and the other is the slightly fatigued driving state, determining the slightly fatigued driving state as the fatigue driving detection result;

[0100] If one of the first detection result and the second detection result is the normal driving state or the slightly fatigued driving state and the other is the moderately fatigued driving state, determining the moderately fatigued driving state as the fatigue driving detection result;

[0101] If there is a severe fatigue driving state in the first detection result and the second detection result, the severe fatigue driving state is determined as the fatigue driving detection result.

[0102] Among them, by implementing this embodiment, the most serious fatigue driving state can be taken from the first detection result and the second detection result as the fatigue driving detection result, so that the obtained fatigue driving detection result can be more reliable.

[0103] As an optional implementation, after step 104, the following steps may also be included:

[0104] If the fatigue driving detection result is the slight fatigue driving state, a slight fatigue warning message is output through the instrument panel, and a slight fatigue warning voice is output through the speaker;

[0105] If the fatigue driving detection result is the moderate fatigue driving state, a moderate fatigue warning message is output through the instrument panel, and a moderate fatigue warning voice is output through the speaker;

[0106] If the fatigue driving detection result is the severe fatigue driving state, an emergency parking plan is generated, and severe fatigue warning information and the emergency parking plan are output through the instrument panel, and severe fatigue warning voice is output through the speaker.

[0107] Among them, by implementing this implementation method, different reminder schemes can be executed according to different fatigue driving detection results, so that the driver can understand his own fatigue state in time, and then take timely actions according to his own fatigue state, thereby improving the driver's personal safety.

[0108] In an embodiment of the present application, a screen can be provided on the upper part of the instrument panel, which can output mild fatigue warning information, moderate fatigue warning information, severe fatigue warning information and the emergency parking plan, so that the driver can intuitively see his fatigue status during driving.

[0109] For example, a slight fatigue warning message may be a yellow warning icon, and a slight fatigue warning voice may be a voice prompt of "please take a rest";

[0110] The moderate fatigue warning message may be an orange warning icon, and the moderate fatigue warning voice may be a voice prompt of "rest immediately";

[0111] The severe fatigue warning message may be a red warning icon, and the severe fatigue warning voice may be a voice prompt of “emergency stop”.

[0112] By implementing the above-mentioned steps 101 to 104, it is possible to collect vehicle driving parameters and steering wheel pressure sensing parameters in addition to the driver's physiological parameters, and then jointly detect the driver's fatigue level from multiple angles, thereby improving the accuracy of the fatigue driving detection results. In addition, the present application can also perform a more accurate analysis of the vehicle's driving conditions. In addition, the present application can also make the obtained driver status information more consistent with the driver's actual situation. In addition, the present application can also make the final fatigue driving detection results more accurate. In addition, the present application can also make the obtained fatigue driving detection results more reliable. In addition, the present application can also improve the personal safety of the driver.

[0113] The present application also provides an application scenario, which applies the above-mentioned fatigue driving detection method. Specifically: The fatigue driving detection method provided in this embodiment can be applied in a scenario where a driver is driving a vehicle. The fatigue driving detection method provided in this embodiment is to detect the fatigue state of a driver driving a vehicle.

[0114] Based on the same inventive concept, the embodiment of the present application also provides a fatigue driving detection device for implementing the fatigue driving detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more fatigue driving detection device embodiments provided below can refer to the limitations of the fatigue driving detection method above, and will not be repeated here.

[0115] In an exemplary embodiment, Figure 2 As shown, a fatigue driving detection device is provided, comprising:

[0116] The acquisition unit 201 is used to acquire vehicle driving parameters, driver images and steering wheel pressure sensing parameters during vehicle driving; wherein the driver images include driver's head images;

[0117] A first analysis unit 202 is used to analyze the vehicle driving parameters to obtain driving behavior information; wherein the driving behavior information at least includes vehicle speed stability and vehicle steering state information;

[0118] The second analysis unit 203 is used to analyze the driver image and the steering wheel pressure sensing parameters to obtain driver status information; wherein the driver status information at least includes eye status, facial status and steering wheel grip strength information;

[0119] The third analysis unit 204 is used to analyze and obtain a fatigue driving detection result using the driving behavior information and the driver status information.

[0120] As an optional implementation manner, the first analysis unit 202 analyzes the vehicle driving parameters to obtain the driving behavior information in the following manner:

[0121] Obtaining a vehicle straight-line driving trajectory, a vehicle acceleration number, and a vehicle deceleration number within a preset time period from the vehicle driving parameters;

[0122] Using the current duration of the preset time period and the number of times the vehicle is accelerated and the number of times the vehicle is decelerated, the vehicle acceleration frequency and the vehicle deceleration frequency are calculated; wherein the current duration is the total duration of the preset time period;

[0123] The vehicle speed stability is determined according to the vehicle acceleration frequency, the vehicle deceleration frequency and the preset frequency threshold; wherein, if the vehicle acceleration frequency is greater than the preset frequency threshold or the vehicle deceleration frequency is greater than the preset frequency threshold, the vehicle speed stability is unstable vehicle speed; if the vehicle acceleration frequency is less than or equal to the preset frequency threshold and the vehicle deceleration frequency is less than or equal to the preset frequency threshold, the vehicle speed stability is stable vehicle speed;

[0124] Using the straight-line driving trajectory of the vehicle, calculating the straight-line distance from the starting point to the end point of the straight-line driving trajectory of the vehicle and the trajectory distance from the starting point to the end point of the straight-line driving trajectory of the vehicle;

[0125] The vehicle steering state information is determined according to the current ratio between the track distance and the straight-line distance and a preset ratio threshold; wherein, if the current ratio is less than or equal to the preset ratio threshold, the vehicle steering state information indicates that the vehicle has no abnormally large steering; and if the current ratio is greater than the preset ratio threshold, the vehicle steering state information indicates that the vehicle has an abnormally large steering.

[0126] The vehicle speed stability and the vehicle steering state information are determined as driving behavior information.

[0127] Among them, by implementing this implementation method, the number of vehicle accelerations and vehicle decelerations within a preset time period can be evaluated, and the vehicle speed stability can be determined based on the obtained vehicle acceleration frequency and vehicle deceleration frequency. The vehicle speed stability is used to indicate whether the vehicle driving is stable and whether acceleration or deceleration occurs frequently. In addition, the straight-line driving trajectory of the vehicle within the preset time period can be analyzed to obtain the vehicle steering state information. The vehicle steering state information can be used to determine whether the vehicle's driving route is in a straight line. If the vehicle turns frequently, it can be considered that the vehicle has abnormally large turns. The driving behavior information obtained in the above manner can be used to more accurately analyze the vehicle's driving conditions.

[0128] As an optional implementation manner, the second analysis unit 203 analyzes the driver image and the steering wheel pressure sensing parameter to obtain the driver status information in the following manner:

[0129] Performing eye recognition on the driver image to obtain eye status; wherein the eye status at least includes eyelid closure status and eyelid closure frequency;

[0130] Performing facial recognition on the driver image, and obtaining a facial expression recognition result as a facial state;

[0131] evaluating the steering wheel pressure sensing parameter based on a standard steering wheel pressure value to obtain a steering wheel pressure evaluation result;

[0132] Determining the steering wheel pressure assessment result as steering wheel grip strength information;

[0133] The eye state, the facial state and the steering wheel grip strength information are determined as driver state information.

[0134] Among them, by implementing this embodiment, eye recognition can be performed on the driver's image to determine the driver's eyelid closure state and eyelid closure frequency; facial recognition can also be performed on the driver's image to determine the driver's facial expression, thereby determining the driver's facial state; and steering wheel pressure sensing parameters can also be evaluated to determine the steering wheel holding force information, which can be used to evaluate whether the driver's hand grip on the steering wheel is reduced. If the driver's hand grip on the steering wheel is reduced, the driver may be in a fatigued state. It can be seen that the driver state information obtained in the above manner is more consistent with the driver's actual situation.

[0135] As an optional implementation manner, the third analysis unit 204 uses the driving behavior information and the driver state information to analyze and obtain the fatigue driving detection result in the following manner:

[0136] A first detection result is determined according to the vehicle speed stability and the vehicle steering state information; wherein, if the vehicle speed stability is that the vehicle speed is stable and the vehicle steering state information is that the vehicle has no abnormal large-scale steering, then the first detection result is a normal driving state; if the vehicle speed stability is that the vehicle speed is unstable or the vehicle steering state information is that the vehicle has an abnormal large-scale steering, then the first detection result is a slightly fatigued driving state; if the vehicle speed stability is that the vehicle speed is unstable and the vehicle steering state information is that the vehicle has an abnormal large-scale steering, then the first detection result is a moderately fatigued driving state;

[0137] A second detection result is determined according to the eye state, the facial state and the steering wheel holding force information; wherein, if the eyelid closure state indicates that the driver's eyelids are completely closed, then the second detection result is a severe fatigue driving state; if the eyelid closure frequency is greater than a preset closure frequency, the facial state is a tired state or the steering wheel holding force information indicates that the steering wheel pressure sensing parameter is less than the standard steering wheel pressure value, then the second detection result is a moderate fatigue driving state; if the eyelid closure frequency is less than or equal to the preset closure frequency, the facial state is a normal state and the steering wheel holding force information indicates that the steering wheel pressure sensing parameter is greater than or equal to the standard steering wheel pressure value, then the second detection result is a normal driving state;

[0138] A fatigue driving detection result is determined based on the first detection result and the second detection result.

[0139] Among them, by implementing this implementation method, a first detection result can be obtained based on the analysis of the vehicle speed stability and the vehicle steering state information in the driving behavior information, and a second detection result can be determined based on the eye state, facial state and steering wheel grip strength information in the driver state information; then, a comprehensive analysis can be performed based on the first detection result and the second detection result to obtain a final fatigue driving detection result, and accurate first detection results and second detection results can be obtained by respectively evaluating the driving behavior information and the driver state information, and then based on the accurate first detection result and the second detection result, the final fatigue driving detection result can be made more accurate.

[0140] As an optional implementation manner, the third analysis unit 204 determines the fatigue driving detection result according to the first detection result and the second detection result in the following manner:

[0141] If both the first detection result and the second detection result are the normal driving state, determining the normal driving state as the fatigue driving detection result;

[0142] If one of the first detection result and the second detection result is the normal driving state and the other is the slightly fatigued driving state, determining the slightly fatigued driving state as the fatigue driving detection result;

[0143] If one of the first detection result and the second detection result is the normal driving state or the slightly fatigued driving state and the other is the moderately fatigued driving state, determining the moderately fatigued driving state as the fatigue driving detection result;

[0144] If there is a severe fatigue driving state in the first detection result and the second detection result, the severe fatigue driving state is determined as the fatigue driving detection result.

[0145] Among them, by implementing this embodiment, the most serious fatigue driving state can be taken from the first detection result and the second detection result as the fatigue driving detection result, so that the obtained fatigue driving detection result can be more reliable.

[0146] As an optional implementation manner, the third analysis unit 204 may also be used for:

[0147] If the fatigue driving detection result is the slight fatigue driving state, a slight fatigue warning message is output through the instrument panel, and a slight fatigue warning voice is output through the speaker;

[0148] If the fatigue driving detection result is the moderate fatigue driving state, a moderate fatigue warning message is output through the instrument panel, and a moderate fatigue warning voice is output through the speaker;

[0149] If the fatigue driving detection result is the severe fatigue driving state, an emergency parking plan is generated, and severe fatigue warning information and the emergency parking plan are output through the instrument panel, and severe fatigue warning voice is output through the speaker.

[0150] Among them, by implementing this implementation method, different reminder schemes can be executed according to different fatigue driving detection results, so that the driver can understand his own fatigue state in time, and then take timely actions according to his own fatigue state, thereby improving the driver's personal safety.

[0151] By implementing the above-mentioned implementation mode, it is possible to collect vehicle driving parameters and steering wheel pressure sensing parameters in addition to the driver's physiological parameters, and then jointly detect the driver's fatigue level from multiple angles, thereby improving the accuracy of the fatigue driving detection results. In addition, the present application can also perform a more accurate analysis of the vehicle's driving conditions. In addition, the present application can also make the obtained driver status information more consistent with the driver's actual situation. In addition, the present application can also make the final fatigue driving detection results more accurate. In addition, the present application can also make the obtained fatigue driving detection results more reliable. In addition, the present application can also improve the personal safety of the driver.

[0152] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video tag processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a fatigue driving detection method is implemented.

[0153] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0154] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0155] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0156] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0157] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0158] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0159] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0160] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for detecting fatigue driving, characterized in that: The fatigue driving detection method comprises: Collecting vehicle driving parameters, driver images and steering wheel pressure sensing parameters during vehicle driving; wherein the driver image includes the driver's head image; Analyzing the vehicle driving parameters to obtain driving behavior information; wherein the driving behavior information at least includes vehicle speed stability and vehicle steering state information; Analyze the driver image and the steering wheel pressure sensing parameters to obtain driver status information; wherein the driver status information at least includes eye status, facial status and steering wheel grip strength information; The driving behavior information and the driver status information are used to analyze and obtain a fatigue driving detection result.

2. The fatigue driving detection method according to claim 1, characterized in that: The analyzing the vehicle driving parameters to obtain driving behavior information specifically includes: Obtaining a vehicle straight-line driving trajectory, a vehicle acceleration number, and a vehicle deceleration number within a preset time period from the vehicle driving parameters; Using the current duration of the preset time period and the number of times the vehicle is accelerated and the number of times the vehicle is decelerated, the vehicle acceleration frequency and the vehicle deceleration frequency are calculated; wherein the current duration is the total duration of the preset time period; The vehicle speed stability is determined according to the vehicle acceleration frequency, the vehicle deceleration frequency and the preset frequency threshold; wherein, if the vehicle acceleration frequency is greater than the preset frequency threshold or the vehicle deceleration frequency is greater than the preset frequency threshold, the vehicle speed stability is unstable vehicle speed; if the vehicle acceleration frequency is less than or equal to the preset frequency threshold and the vehicle deceleration frequency is less than or equal to the preset frequency threshold, the vehicle speed stability is stable vehicle speed; Using the straight-line driving trajectory of the vehicle, calculating the straight-line distance from the starting point to the end point of the straight-line driving trajectory of the vehicle and the trajectory distance from the starting point to the end point of the straight-line driving trajectory of the vehicle; The vehicle steering state information is determined according to the current ratio between the track distance and the straight-line distance and a preset ratio threshold; wherein, if the current ratio is less than or equal to the preset ratio threshold, the vehicle steering state information indicates that the vehicle has no abnormally large steering; and if the current ratio is greater than the preset ratio threshold, the vehicle steering state information indicates that the vehicle has an abnormally large steering. The vehicle speed stability and the vehicle steering state information are determined as driving behavior information.

3. The fatigue driving detection method according to claim 2, characterized in that: The analyzing the driver image and the steering wheel pressure sensing parameters to obtain the driver status information specifically includes: Performing eye recognition on the driver image to obtain eye status; wherein the eye status at least includes eyelid closure status and eyelid closure frequency; Performing facial recognition on the driver image, and obtaining a facial expression recognition result as a facial state; evaluating the steering wheel pressure sensing parameter based on a standard steering wheel pressure value to obtain a steering wheel pressure evaluation result; Determining the steering wheel pressure assessment result as steering wheel grip strength information; The eye state, the facial state and the steering wheel grip strength information are determined as driver state information.

4. The fatigue driving detection method according to claim 3, characterized in that: The use of the driving behavior information and the driver status information to analyze and obtain a fatigue driving detection result specifically includes: A first detection result is determined according to the vehicle speed stability and the vehicle steering state information; wherein, if the vehicle speed stability is that the vehicle speed is stable and the vehicle steering state information is that the vehicle has no abnormal large-scale steering, then the first detection result is a normal driving state; if the vehicle speed stability is that the vehicle speed is unstable or the vehicle steering state information is that the vehicle has an abnormal large-scale steering, then the first detection result is a slightly fatigued driving state; if the vehicle speed stability is that the vehicle speed is unstable and the vehicle steering state information is that the vehicle has an abnormal large-scale steering, then the first detection result is a moderately fatigued driving state; A second detection result is determined according to the eye state, the facial state and the steering wheel holding force information; wherein, if the eyelid closure state indicates that the driver's eyelids are completely closed, then the second detection result is a severe fatigue driving state; if the eyelid closure frequency is greater than a preset closure frequency, the facial state is a tired state or the steering wheel holding force information indicates that the steering wheel pressure sensing parameter is less than the standard steering wheel pressure value, then the second detection result is a moderate fatigue driving state; if the eyelid closure frequency is less than or equal to the preset closure frequency, the facial state is a normal state and the steering wheel holding force information indicates that the steering wheel pressure sensing parameter is greater than or equal to the standard steering wheel pressure value, then the second detection result is a normal driving state; A fatigue driving detection result is determined based on the first detection result and the second detection result.

5. The fatigue driving detection method according to claim 4, characterized in that: The determining of the fatigue driving detection result according to the first detection result and the second detection result specifically includes: If the first detection result and the second detection result are both the normal driving state, determining the normal driving state as the fatigue driving detection result; If one of the first detection result and the second detection result is the normal driving state and the other is the slightly fatigued driving state, determining the slightly fatigued driving state as the fatigue driving detection result; If one of the first detection result and the second detection result is the normal driving state or the slightly fatigued driving state and the other is the moderately fatigued driving state, determining the moderately fatigued driving state as the fatigue driving detection result; If there is a severe fatigue driving state in the first detection result and the second detection result, the severe fatigue driving state is determined as the fatigue driving detection result.

6. The fatigue driving detection method according to claim 5, characterized in that: The fatigue driving detection method also includes: If the fatigue driving detection result is the slight fatigue driving state, a slight fatigue warning message is output through the instrument panel, and a slight fatigue warning voice is output through the speaker; If the fatigue driving detection result is the moderate fatigue driving state, a moderate fatigue warning message is output through the instrument panel, and a moderate fatigue warning voice is output through the speaker; If the fatigue driving detection result is the severe fatigue driving state, an emergency parking plan is generated, and severe fatigue warning information and the emergency parking plan are output through the instrument panel, and severe fatigue warning voice is output through the speaker.

7. A fatigue driving detection device, characterized in that: The fatigue driving detection device comprises: A collection unit, used to collect vehicle driving parameters, driver images and steering wheel pressure sensing parameters during vehicle driving; wherein the driver image includes a driver's head image; A first analysis unit, configured to analyze the vehicle driving parameters to obtain driving behavior information; wherein the driving behavior information at least includes vehicle speed stability and vehicle steering state information; A second analysis unit is used to analyze the driver image and the steering wheel pressure sensing parameters to obtain driver status information; wherein the driver status information at least includes eye status, facial status and steering wheel grip strength information; The third analysis unit is used to use the driving behavior information and the driver status information to analyze and obtain a fatigue driving detection result.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the fatigue driving detection method described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the fatigue driving detection method described in any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the fatigue driving detection method described in any one of claims 1 to 6 are implemented.

Images