Driver state monitoring method and vehicle

Abstract

The invention relates to a driver state monitoring method and a vehicle, and the method comprises the steps: carrying out the feature extraction of the real-time pressure information of a driver seat, and obtaining the real-time pressure distribution features of the driver seat; comparing the real-time pressure distribution characteristic with a reference pressure distribution characteristic of a driver on the driver seat to obtain a pressure distribution characteristic difference; and determining a state monitoring result of the driver based on the pressure distribution characteristic difference. Pressure information of a driver seat is adopted as a data source, different from a visual sensor, a pressure sensor is slightly influenced by the environment, signal collection is not influenced by factors such as strong light, weak light and the condition that a driver wears sunglasses or masks, and stability and accuracy are improved; and meanwhile, the pressure information of the driver seat belongs to physical quantity of non-identity recognition, and the privacy is weaker than that of visual information, so that the privacy of the user is protected.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of vehicles, and particularly relates to a driver state monitoring method and a vehicle. BACKGROUND

[0002] This section is intended to provide background information to the embodiments of the present disclosure recited in the claims. The description herein does not constitute admission that the information provided herein is prior art to the present disclosure.

[0003] With the intelligent development of vehicles, the DMS driver monitoring system has become one of the key technologies to improve driving safety.

[0004] In the related art, the DMS scheme mainly relies on visual sensors (such as cameras) to capture and analyze the facial features (such as eyelid state, head posture, gaze direction, etc.) of the driver to determine the fatigue or distraction state.

[0005] However, the DMS scheme relying on visual sensors has the following problems: in the case of strong light, weak light, the driver wearing sunglasses or a mask, etc., the recognition performance is significantly reduced or even fails; at the same time, continuous visual monitoring (such as facial information collection) also raises concerns about privacy leakage of users. SUMMARY

[0006] In order to overcome the above problems or at least partially solve the above problems, the present disclosure provides a driver state monitoring method and a vehicle.

[0007] A first aspect of the embodiments of the present disclosure provides a driver state monitoring method, comprising: extracting features of real-time pressure information of a driver seat to obtain real-time pressure distribution features of the driver seat; comparing the real-time pressure distribution features with reference pressure distribution features of a driver on the driver seat to obtain pressure distribution feature differences; determining a state monitoring result of the driver based on the pressure distribution feature differences.

[0008] Based on the same inventive concept, a second aspect of the embodiments of the present disclosure provides a vehicle, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to the first aspect.

[0009] The technical solutions provided by the embodiments of the present disclosure have the following advantages: The pressure information of the driver seat is taken as a data source, unlike a visual sensor, the pressure sensor is less affected by the environment, and the signal acquisition is not affected by factors such as strong light, weak light, and the driver wearing sunglasses or a mask, thereby improving stability and accuracy; at the same time, the pressure information of the driver seat is a non-identity-recognized physical quantity, and the privacy is weaker than visual information, thereby protecting the privacy of the user. BRIEF DESCRIPTION OF DRAWINGS

[0010] The drawings incorporated in the specification and constituting a part thereof illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure.

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0012] Figure 1 is a schematic diagram of an application scenario of a driver state monitoring method provided by an exemplary embodiment of the present disclosure; Figure 2 is a schematic diagram of a flow of a driver state monitoring method provided by an exemplary embodiment of the present disclosure; Figure 3 is a schematic diagram of a structure of a driver state monitoring device provided by an exemplary embodiment of the present disclosure; Figure 4 is a schematic diagram of a structure of an electronic device provided by an exemplary embodiment of the present disclosure; Figure 5 is a schematic diagram of a structure of a vehicle provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] It can be understood that, before using the technical solutions disclosed in the embodiments of the present application, the type, use range, use scenario, etc. of the personal information involved in the present application should be informed to the user and the authorization of the user should be obtained in a proper manner according to relevant laws and regulations.

[0014] It can be understood that the data (including but not limited to the data itself, the acquisition or use of the data) involved in the present technical solution should comply with the requirements of the relevant laws and regulations and the relevant provisions.

[0015] In order to more clearly understand the above-mentioned purposes, features and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0016] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, the present disclosure can be practiced without the specific details. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to obscure the present disclosure.

[0017] It should be understood that each of the steps recited in the method embodiments of the present disclosure can be performed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit performing the steps shown. The scope of the present disclosure is not limited in this regard.

[0018] It should be noted that, in this document, relational terms such as "first" and "second", and the like, are used solely to distinguish one entity or action from another entity or action, without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0019] It should be noted that the modification of "one" or "multiple" mentioned in the present disclosure is illustrative but not restrictive, and those skilled in the art should understand that, unless otherwise explicitly indicated in the context, it should be understood as "one or more".

[0020] DMS driver monitoring system is a system that uses visual sensors (mainly in-vehicle cameras) to monitor the state of the driver (such as fatigue, distraction). It analyzes visual features such as facial expressions, eye openness, head position, and issues an alarm when an anomaly is detected.

[0021] The driver state monitoring method provided by the present disclosure works as an independent information channel in parallel with the DMS driver monitoring system in the related art, and can complement the DMS driver monitoring system in the related art to improve driving safety.

[0022] When either the DMS driver monitoring system in the related art or the driver state monitoring scheme provided by the present disclosure fails or is uncertain in judgment, as long as the other scheme detects an anomaly, the system can still issue a warning, forming an effective double safety guarantee.

[0023] After introducing the basic principles of the present disclosure, the various non-limiting embodiments of the present disclosure will be specifically introduced below.

[0024] Referring to Figure 1 FIG. 1 is a schematic diagram of an application scenario of a driver state monitoring method according to an example embodiment of the present disclosure.

[0025] The application scenario includes a vehicle terminal 110, a sensor set 120, and a server 130.

[0026] The vehicle terminal 110 is a terminal arranged on a vehicle and has the capability of data acquisition and data processing, and can be a vehicle controller or a central processor in an automatic driving system. The vehicle terminal 110 can acquire relevant information and process the acquired information, and in the example embodiment of the present disclosure, the vehicle terminal 110 is an electronic device that finally controls the vehicle.

[0027] The sensor set 120 includes multiple sensors, which can be installed at different positions of the vehicle to collect as much environmental perception information as possible. The multiple sensors can be sensors of the same type or sensors of different types.

[0028] As an example, the sensor set 120 includes pressure sensors, multiple pressure sensors are installed inside and / or on the surface of the seat cushion and backrest of the driver's seat (which can be flexible sensors), forming a dense sensor network (for example, arranged in a matrix), and continuously collecting pressure distribution data of the seat cushion.

[0029] The vehicle terminal 110 and the sensor set 120 can be connected through a wired or wireless communication network to realize data interaction, and the vehicle terminal 110 can acquire the environmental perception information collected by the sensor set 120.

[0030] The server 130 can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN (Content Delivery Network), and big data and artificial intelligence platform.

[0031] The vehicle terminal 110 and the server 130 can be connected through a wired or wireless communication network to realize data interaction.

[0032] In some example embodiments, when the driver state monitoring method runs on the server 130, the server 130 is configured to provide a driver state monitoring service to the vehicle terminal 110.

[0033] The vehicle terminal 110 collects pressure information through the sensor set 120 and sends the pressure information to the server 130.

[0034] The server 130 extracts features from real-time pressure information of the driver seat to obtain real-time pressure distribution features of the driver seat, compares the real-time pressure distribution features with reference pressure distribution features of the driver on the driver seat to obtain pressure distribution feature differences, and determines a state monitoring result of the driver based on the pressure distribution feature differences.

[0035] The server 130 can send the determined state monitoring result of the driver to the vehicle terminal 110 to help improve driving safety.

[0036] The application scenarios of the application will be described below. Figure 1 It should be noted that the above application scenarios are only shown for the purpose of facilitating understanding of the spirit and principles of the present disclosure, and the embodiments of the present disclosure are not limited in this respect. On the contrary, the embodiments of the present disclosure can be applied to any applicable scenario.

[0037] Reference is made to Figure 2 , which is a first flowchart of a driver state monitoring method provided by an exemplary embodiment of the present disclosure.

[0038] The driver state monitoring method comprises the following steps: Step S210, extracting features from real-time pressure information of the driver seat to obtain real-time pressure distribution features of the driver seat.

[0039] Next, the determination method of the real-time pressure information of the driver seat will be introduced: In specific implementation, the hardware basis for collecting the real-time pressure information of the driver seat includes: As an example, a plurality of pressure sensors are installed inside and / or on the surface of the seat cushion and backrest of the driver seat (which can be a flexible sensor), forming a dense sensor network (for example, arranged in a matrix), continuously collecting pressure distribution data of the seat.

[0040] As an example, a high-resolution flexible pressure sensor array is used, specifically, a piezoresistive or capacitive sensing unit is used, embedded under the foam layer of the seat cushion and backrest in a grid form (such as 32x32), with a sampling rate not less than 50Hz.

[0041] The pressure distribution data refers to the pressure distribution on the contact interface between the human body and the seat. The objective evaluation indexes include maximum pressure, average pressure, pressure gradient, contact area, and asymmetry coefficient, etc. When focusing on driving, the body pressure distribution is usually stable and symmetrical; when distracted, it may be chaotic, greatly deviated, or asymmetrical.

[0042] In the above exemplary embodiments, the hardware basis for collecting real-time pressure information of the driver's seat is introduced. Next, the timing of collecting real-time pressure information of the driver's seat, i.e., the activation condition or trigger condition, will be introduced. Specifically: In some exemplary embodiments, the determination manner of the real-time pressure information includes: In response to the real-time vehicle speed of the vehicle to which the driver's seat belongs being greater than a preset vehicle speed threshold, the real-time pressure information is collected based on the pressure sensor arranged on the driver's seat; Or, In response to receiving at least one of the auxiliary scene information, the real-time pressure information is collected based on the pressure sensor arranged on the driver's seat, wherein the auxiliary scene information includes at least one of the following: driving behavior information, driving environment information, and driving vehicle information.

[0043] In specific implementation, the value of the preset vehicle speed threshold can be set according to a specific application scenario. The greater the value of the preset vehicle speed threshold, the lower the cost. The smaller the value of the preset vehicle speed threshold, the higher the safety. Therefore, if the demand for safety is high, the value of the preset vehicle speed threshold can be configured to be small. If the demand for reducing cost is high, the value of the preset vehicle speed threshold can be configured to be large.

[0044] As an example, the value of the preset vehicle speed threshold is configured to be 60 km / h.

[0045] In specific implementation, the driver state monitoring method provided by the present disclosure can also be continuously operated at all times. However, if it is continuously operated at all times, unnecessary power consumption and calculation resource consumption will be caused, and the energy efficiency of the vehicle will be reduced. When the vehicle is driving at low speed or is stationary (such as parking or being stuck in traffic), the risk of driver distraction is relatively low. At this time, the necessity of starting high-precision monitoring is insufficient, and invalid data or interference may be generated.

[0046] Through the above exemplary embodiments, on-demand activation is realized, energy consumption is reduced, and high-risk scenarios are focused on: through vehicle speed threshold judgment, the monitoring function is only started when the vehicle reaches a certain speed (such as high-speed cruising), which significantly reduces the average power consumption of the system. It ensures that system resources are concentrated in truly high-concentration driving scenarios (such as highway driving), which improves the scenario targeting and practicality of monitoring.

[0047] In the above exemplary embodiments, relying only on the vehicle speed threshold value may not cover all high-risk scenarios (such as urban congestion following, bad weather, complex road conditions), resulting in the system failing to activate when needed. Therefore, the present disclosure also provides another timing for collecting real-time pressure information of the driver's seat, i.e., an activation condition or trigger condition, which is specific to: In response to receiving at least one of the auxiliary scene information, collecting the real-time pressure information based on a pressure sensor provided on the driver's seat; Among them, the auxiliary scene information includes at least one of: Driving behavior information, driving environment information, driving vehicle information.

[0048] In specific implementation, the driving behavior information includes: historical driving behavior information, continuous driving time information, intense driving behavior information, etc.

[0049] As an example, the intense driving behavior information, for example, monitoring the vehicle to perform irregular operations such as sudden acceleration, sudden deceleration, sharp turning, etc. Such operations may indicate that the driver's emotions fluctuate, is road-angry or drives in a hurry, and the distraction risk is high.

[0050] The driving environment information includes: high-risk road section information, bad weather information, accident-prone point information, etc.

[0051] As an example, the high-risk road section information, for example, a highway ramp, a continuous curve, a school area, a construction road section.

[0052] As an example, the bad weather information, for example, heavy rain, heavy snow, thick fog, night, etc.

[0053] The driving vehicle information includes: DMS driver monitoring system failure information.

[0054] As an example, the DMS driver monitoring system failure information, for example, receiving a self-state signal from the DMS driver monitoring system, such as "camera obstruction", "excessive light / darkness leading to function degradation".

[0055] Through the above exemplary embodiments, the rich environmental and state information provided by other sensors or systems of the vehicle is utilized, the breadth of high-risk scenarios applicable to the present disclosure is improved, and it is ensured that the system can be started in time under any high-risk working condition; The linkage with other perception systems of the vehicle forms an active and preventive activation mechanism, improves the intelligent degree of activation decision, and further improves the driving safety.

[0056] In the above exemplary embodiments, the hardware basis for collecting real-time pressure information of the driver's seat and the timing, i.e., the activation condition or trigger condition, for collecting the real-time pressure information of the driver's seat are introduced. Next, the manner of extracting the real-time pressure distribution characteristics of the driver's seat will be introduced. As an example, before extracting the real-time pressure distribution characteristics of the driver's seat, the original signal of the collected real-time pressure information of the driver's seat is preprocessed, such as filtering, amplification, etc.

[0057] In some exemplary embodiments, the real-time pressure information includes a time-series pressure distribution data stream, and each frame of data in the time-series pressure distribution data stream is a pressure distribution matrix. The feature extraction on the real-time pressure information of the driver's seat obtains the real-time pressure distribution characteristics of the driver's seat, and includes: For each pressure distribution matrix, based on a preset pressure sensor position coordinate, a pressure center coordinate of the pressure distribution matrix is determined to obtain a pressure center coordinate sequence. In a preset time length sliding time window, a moving trajectory analysis is performed on the pressure center coordinate sequence in the sliding time window to obtain the real-time pressure distribution characteristics.

[0058] In implementation, the value of the preset time length can be set according to a specific application scenario. As an example, the preset time length is 5 seconds to 15 seconds, for example, 10 seconds.

[0059] The pressure center refers to the combined action point of all pressure distributions on the contact surface between the driver's body and the seat.

[0060] The pressure center coordinate can be calculated by the data of the seat pressure sensor matrix, and the formula is as follows:

[0061]

[0062] wherein, , represents the pressure center coordinate, n represents the total number of pressure sensors, represents the pressure value of the i-th pressure sensor, i X i , Y i represents the position coordinate of the pressure sensor.

[0063] The moving trajectory of the pressure center directly reflects the change of the center of gravity of the driver's body.

[0064] ​In some example embodiments, the moving trajectory analysis on the pressure center coordinate sequence in the sliding time window obtains the real-time pressure distribution feature, including: At least one of the following trajectory features of the pressure center coordinate sequence in the sliding time window is extracted to constitute the real-time pressure distribution feature: Trajectory space features, trajectory motion features, and trajectory frequency domain features.

[0065] As an example, the trajectory space features include a total length of trajectory and an enclosed area; The trajectory motion features include a moving average speed and an acceleration; The trajectory frequency domain features include a motion power spectral density.

[0066] The total length of trajectory and the enclosed area are used to reflect the overall amplitude and range of body sway.

[0067] The moving average speed and the acceleration are used to identify sudden and large-amplitude body adjustment actions.

[0068] The motion power spectral density is used to analyze the frequency characteristics of body sway. Unconscious actions when distracted may have significant energy concentration in a specific frequency band (such as low frequency).

[0069] In this way, the instantaneous and unconscious body micro-movements caused by distraction can be captured, and the continuous change rule of the driver's body center of gravity can be comprehensively reflected.

[0070] Through the above example embodiments, by calculating the pressure center coordinate sequence and analyzing the moving trajectory, the dynamic instability modes such as body sway and center of gravity drift when distracted can be sensitively identified, and the identification sensitivity of the distracted state is significantly improved. The extracted trajectory length, area, speed, acceleration, and frequency domain features constitute a multi-dimensional and high-information feature vector describing body stability, which provides a solid data foundation for subsequent accurate classification.

[0071] In step S220, the real-time pressure distribution feature is compared with a reference pressure distribution feature of the driver on the driver seat to obtain a pressure distribution feature difference.

[0072] Next, the determination method of the reference pressure distribution feature of the driver on the driver seat will be introduced: In some example embodiments, the determination method of the reference pressure distribution feature includes: In response to real-time driving information of a vehicle to which the driver seat belongs satisfying a preset driving condition, reference pressure information is collected based on a pressure sensor arranged on the driver seat. The reference pressure information is feature extracted to obtain the reference pressure distribution feature.

[0073] In specific implementation, the hardware basis for collecting the reference pressure information of the driver on the driver seat includes: As an example, a plurality of pressure sensors are installed inside and / or on the surface of the seat cushion and the backrest of the driver seat to form a dense sensor network to collect the reference pressure information of the driver seat.

[0074] In the above example embodiment, the hardware basis for collecting the reference pressure information of the driver on the driver seat is introduced, and the timing, i.e., the activation condition or trigger condition, for collecting the reference pressure information of the driver on the driver seat is introduced as follows. In specific implementation, the reference pressure information is collected based on the pressure sensors arranged on the driver seat in response to the real-time driving information of the vehicle to which the driver seat belongs satisfying a preset driving condition.

[0075] Through the above example embodiment, the data collection timing is screened through the preset driving condition (such as smooth acceleration and constant speed cruising), and it is ensured that the samples used to establish the reference are all derived from the normal driving state of the driver, thereby ensuring the representativeness and reliability of the reference model. At the same time, a unique reference feature is established for each driver, so that the monitoring system can adapt to different body types, sitting postures and driving styles, and the false positives caused by individual differences are greatly reduced.

[0076] In the above example embodiment, the hardware basis for collecting the reference pressure information of the driver on the driver seat and the timing, i.e., the activation condition or trigger condition, for collecting the reference pressure information of the driver on the driver seat are introduced, and the way of extracting the reference pressure distribution feature of the driver seat is introduced as follows. In some example embodiments, the reference pressure information includes a time-series pressure distribution data stream, and each frame of data in the time-series pressure distribution data stream is a pressure distribution matrix. The feature extraction on the reference pressure information to obtain the reference pressure distribution feature includes: For each pressure distribution matrix, a pressure center coordinate of the pressure distribution matrix is determined based on a preset pressure sensor position coordinate to obtain a pressure center coordinate sequence. In a preset time length sliding time window, a moving trajectory analysis is performed on the pressure center coordinate sequence in the sliding time window to obtain the reference pressure distribution feature.

[0077] In some examples, the real-time pressure distribution feature is compared with a reference pressure distribution feature of the driver on the driver seat to obtain a pressure distribution feature difference.

[0078] In some examples, the real-time pressure distribution feature is compared with a reference pressure distribution feature of the driver on the driver seat to obtain a pressure distribution feature difference.

[0079] In some examples, the real-time pressure distribution feature is compared with a reference pressure distribution feature of the driver on the driver seat to obtain a pressure distribution feature difference.

[0080] In some examples, the real-time pressure distribution feature is compared with a reference pressure distribution feature of the driver on the driver seat to obtain a pressure distribution feature difference. The real-time pressure distribution feature is represented as P. The reference pressure distribution feature is represented as P.

[0081] In some examples, the real-time pressure distribution feature is compared with a reference pressure distribution feature of the driver on the driver seat to obtain a pressure distribution feature difference. In some examples, the real-time pressure distribution feature is compared with a reference pressure distribution feature of the driver on the driver seat to obtain a pressure distribution feature difference.

[0082] In some examples, the real-time pressure distribution feature is compared with a reference pressure distribution feature of the driver on the driver seat to obtain a pressure distribution feature difference. The real-time pressure distribution feature is represented as P. The reference pressure distribution feature is represented as P.

[0083] In some examples, the real-time pressure distribution feature is compared with a reference pressure distribution feature of the driver on the driver seat to obtain a pressure distribution feature difference. In some examples, the real-time pressure distribution feature is compared with a reference pressure distribution feature of the driver on the driver seat to obtain a pressure distribution feature difference. In some examples, the real-time pressure distribution feature is compared with a reference pressure distribution feature of the driver on the driver seat to obtain a pressure distribution feature difference.

[0084] As an example, the real-time pressure distribution feature is compared with the reference pressure distribution feature of the driver on the driver seat, and a pressure distribution feature difference calculation formula can be obtained as follows:

[0085] wherein, represents the real-time pressure distribution feature, represents the reference pressure distribution feature, represents the standard deviation of the reference pressure distribution feature.

[0086] Through the above example embodiment, statistical tolerance is introduced, a model is constructed using the mean and standard deviation, the comparison between the real-time feature and the reference is converted into a standardized deviation calculation, and the measurement contains information about the normal fluctuations of the feature, making the judgment more scientific and robust. At the same time, the pressure distribution feature difference obtained is a continuous and interpretable scalar value, which intuitively reflects the statistical significance of the current state deviating from the individual normal reference, and provides accurate input for subsequent grading decisions.

[0087] Step S230, determining the state monitoring result of the driver based on the pressure distribution feature difference.

[0088] In some example embodiments, the determination of the state monitoring result of the driver based on the pressure distribution feature difference comprises: in response to determining that the pressure distribution feature difference is higher than a first threshold, determining that the state monitoring result is serious distraction; in response to determining that the pressure distribution feature difference is lower than the first threshold but higher than a second threshold, determining that the state monitoring result is slight distraction; in response to determining that the pressure distribution feature difference is lower than the second threshold, determining that the state monitoring result is not distracted; wherein the first threshold is greater than the second threshold.

[0089] Through the above example embodiment, by setting multiple thresholds, the driver state is finely divided into not distracted, slight distraction, serious distraction and multiple levels, making the monitoring result more hierarchical and informative. At the same time, in subsequent embodiments, different subsequent processing strategies (such as only recording, mild reminding, and strong warning) are matched for different levels of state, realizing the precision and humanization of early warning and improving the acceptance of the driver.

[0090] In some example embodiments, the determination of the state monitoring result of the driver based on the pressure distribution feature difference comprises: determining auxiliary scene information, encoding the auxiliary scene information to obtain auxiliary scene features; The pressure distribution feature difference is taken as a query, and the auxiliary scene feature is taken as a key and a value. A focus weight of the auxiliary scene feature on the pressure distribution feature difference is calculated to generate an adjusted pressure distribution feature difference. The auxiliary scene feature is taken as a query, and the pressure distribution feature difference is taken as a key and a value. A focus weight of the pressure distribution feature difference on the auxiliary scene feature is calculated to generate an adjusted auxiliary scene feature. The pressure distribution feature difference, the auxiliary scene feature, the adjusted pressure distribution feature difference, and the adjusted auxiliary scene feature are fused to obtain a fusion feature. A prediction is performed based on the fusion feature to obtain the state monitoring result.

[0091] In specific implementation, the auxiliary scene information is determined, and the auxiliary scene information is encoded to obtain an auxiliary scene feature, including: The driving behavior information, the driving environment information, and the driving vehicle information are determined. The driving behavior information is linearly mapped and encoded to obtain a driving behavior feature. The driving environment information and the driving vehicle information are embedded and encoded to obtain a driving environment feature and a driving vehicle feature.

[0092] In specific implementation, the pressure distribution feature difference and the received auxiliary scene information are input into a pre-trained state monitoring model to obtain the state monitoring result output by the state monitoring model.

[0093] As an example, a state monitoring model is constructed based on a neural network model framework. Training pressure distribution feature differences, training auxiliary scene information, and training state monitoring results corresponding to the training pressure distribution feature differences and the training auxiliary scene information are taken as training samples. The training samples are input into a state monitoring model to be trained for iteration to obtain a performance index of a current model training. When the performance index does not continuously improve in the iteration process, model parameters of the current model are saved to obtain a trained state monitoring model.

[0094] In this way, the same body sway feature in different driving scenes (such as a straight highway and a winding mountain road) may represent different risk levels. A judgment based only on the pressure feature difference may deviate from the actual risk. Moreover, a simple value judgment cannot handle complex decision-making problems of multi-source heterogeneous information fusion.

[0095] Through the above exemplary embodiments, the pressure feature difference is input into the model together with the real-time scene information, so that the decision result fully considers the objective risk of the current driving environment, thereby making a judgment that is more in line with the actual safety needs. Meanwhile, through the pre-trained state monitoring model, the complex nonlinear relationship between the multi-source information and the distraction state is automatically learned, so that better discrimination performance and generalization ability can be obtained.

[0096] In some exemplary embodiments, after determining the state monitoring result of the driver based on the pressure distribution feature difference, the method further includes: in response to determining that the state monitoring result is serious distraction, controlling the vehicle to which the driver's seat belongs to perform a warning action; in response to determining that the state monitoring result is slight distraction, sending prompt information to a preset terminal device; in response to determining that the state monitoring result is not distracted, recording the pressure distribution feature difference.

[0097] As an example, controlling the vehicle to which the driver's seat belongs to perform a warning action includes: tactile warning (e.g., steering wheel vibration) and / or auditory warning (e.g., prompt sound to remind the driver to concentrate).

[0098] In specific implementation, the monitoring result is directly and automatically converted into a graded vehicle control instruction or information prompt, forming a complete safety closed loop of "perception-analysis-decision-execution". For serious distraction, a strong warning (such as steering wheel vibration) is immediately taken to quickly correct the dangerous state; for slight distraction, a non-intrusive prompt (such as sending information) is used to remind and educate; for the not distracted state, data is recorded for model optimization and long-term driving behavior analysis, achieving the maximization of resources and benefits.

[0099] Through the above exemplary embodiments, even if only slight distraction occurs, as long as a deviation occurs in the pressure distribution feature, it can be sensitively captured by comparison, so that predictive prompting and warning can be achieved, overcoming the lag of the DMS system which can only be discovered after the problem is obvious.

[0100] Through the above exemplary embodiments, the present disclosure uses the pressure information of the driver's seat as the data source, which is different from the visual sensor. The pressure sensor is less affected by the environment, and the signal acquisition is not affected by factors such as strong light, weak light, the driver wearing sunglasses or a mask, etc., improving the stability and accuracy. At the same time, the pressure information of the driver's seat is a non-identity-recognized physical quantity, and the privacy is weaker than visual information, protecting the user privacy.

[0101] It should be noted that the method of the embodiments of the present disclosure can be executed by a single device, such as a computer or a server, etc. The method of the embodiments can also be applied to a distributed scenario, and be completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only execute one or more steps in the method of the embodiments of the present disclosure, and the multiple devices can interact with each other to complete the method.

[0102] It should be noted that some embodiments of the present disclosure have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0103] Based on the same inventive concept, the present disclosure also provides a driver state monitoring device corresponding to the method of any of the above embodiments.

[0104] Reference Figure 3 is a device schematic diagram of a driver state monitoring device provided by an exemplary embodiment of the present disclosure.

[0105] The driver state monitoring device 300 comprises the following modules: The real-time pressure distribution feature determination module 310 is configured to perform feature extraction on real-time pressure information of a driver seat to obtain a real-time pressure distribution feature of the driver seat; The pressure distribution feature difference determination module 320 is configured to compare the real-time pressure distribution feature with a reference pressure distribution feature of a driver on the driver seat to obtain a pressure distribution feature difference; The state monitoring result determination module 330 is configured to determine a state monitoring result of the driver based on the pressure distribution feature difference.

[0106] In some exemplary embodiments, the real-time pressure distribution feature determination module 310 is specifically configured to: In response to a real-time vehicle speed of a vehicle to which the driver seat belongs being greater than a preset vehicle speed threshold, collecting the real-time pressure information based on a pressure sensor arranged on the driver seat; Or, In response to receiving at least one of auxiliary scene information, collecting the real-time pressure information based on a pressure sensor arranged on the driver seat, wherein the auxiliary scene information comprises at least one of the following: driving behavior information, driving environment information, and driving vehicle information.

[0107] In some example embodiments, the real-time pressure information comprises a time-series pressure distribution data stream, each frame of data in the time-series pressure distribution data stream being a pressure distribution matrix; The real-time pressure distribution feature determination module 310 is specifically configured to: For each pressure distribution matrix, based on a preset pressure sensor position coordinate, determine a pressure center coordinate of the pressure distribution matrix to obtain a pressure center coordinate sequence; In a preset length of sliding time window, perform moving trajectory analysis on the pressure center coordinate sequence in the sliding time window to obtain the real-time pressure distribution feature.

[0108] In some example embodiments, the real-time pressure distribution feature determination module 310 is specifically configured to: extract at least one of the following trajectory features of the pressure center coordinate sequence within the sliding time window to constitute the real-time pressure distribution feature: trajectory space feature, trajectory motion feature, and trajectory frequency domain feature.

[0109] In some example embodiments, the pressure distribution feature difference determination module 320 is specifically configured to: In response to real-time driving information of a vehicle to which the driver seat belongs satisfying a preset driving condition, collect reference pressure information based on a pressure sensor arranged on the driver seat; perform feature extraction on the reference pressure information to obtain a reference pressure distribution feature.

[0110] In some example embodiments, the pressure distribution feature difference determination module 320 is specifically configured to: determine a mean value and a standard deviation of the reference pressure distribution feature, and based on the mean value and the standard deviation, construct a reference pressure distribution model of the driver; compare the real-time pressure distribution feature with the reference pressure distribution model to obtain the pressure distribution feature difference.

[0111] In some example embodiments, the state monitoring result determination module 330 is specifically configured to: In response to determining that the pressure distribution feature difference is higher than a first threshold value, determine that the state monitoring result is serious distraction; In response to determining that the pressure distribution feature difference is lower than the first threshold value but higher than a second threshold value, determine that the state monitoring result is slight distraction; In response to determining that the pressure distribution feature difference is lower than the second threshold value, determine that the state monitoring result is no distraction. wherein the first threshold is greater than the second threshold.

[0112] In some example embodiments, the state monitoring result determination module 330 is specifically configured to: determine auxiliary scene information, encode the auxiliary scene information to obtain auxiliary scene features; calculate attention weights of the auxiliary scene features to the pressure distribution feature difference by taking the pressure distribution feature difference as a query and the auxiliary scene features as keys and values, and generate adjusted pressure distribution feature difference; calculate attention weights of the pressure distribution feature difference to the auxiliary scene features by taking the auxiliary scene features as a query and the pressure distribution feature difference as keys and values, and generate adjusted auxiliary scene features; fuse the pressure distribution feature difference, the auxiliary scene features, the adjusted pressure distribution feature difference and the adjusted auxiliary scene features to obtain fused features; perform prediction based on the fused features to obtain the state monitoring result.

[0113] In some example embodiments, the state monitoring result determination module 330 is further configured to: in response to determining that the state monitoring result is serious distraction, control the vehicle to which the driver seat belongs to perform a warning action; in response to determining that the state monitoring result is slight distraction, send prompt information to a preset terminal device; in response to determining that the state monitoring result is no distraction, record the pressure distribution feature difference.

[0114] For the convenience of description, the above apparatus is described in various modules respectively in terms of functions. Of course, the functions of each module can be implemented in one or more software and / or hardware when implementing the present disclosure.

[0115] It should be noted that, Figure 3 The driver state monitoring apparatus 300 shown can perform each step in the above method embodiments, and achieve each process and effect in the above method embodiments, which will not be described here.

[0116] Based on the same inventive concept, the present disclosure also provides an electronic device corresponding to any of the above method embodiments.

[0117] Figure 4 is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure.

[0118] In the embodiments of the present disclosure, Figure 4The electronic device shown can be a server or a terminal, where the terminal specifically includes a vehicle-mounted terminal, and the like, without limitation.

[0119] As shown in Figure 4 The electronic device can include a processor 410 and a memory 420 storing computer program instructions.

[0120] Specifically, the processor 410 described above can include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or can be configured as one or more integrated circuits that implement embodiments of the present disclosure.

[0121] The memory 420 can include a mass storage for information or instructions. By way of example, and not limitation, the memory 420 can include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 420 can include removable or non-removable (or fixed) media. Where appropriate, the memory 420 can be internal or external to the integrated gateway device. In certain embodiments, the memory 420 is non-volatile solid-state memory. In certain embodiments, the memory 420 includes read-only memory (ROM). Where appropriate, this ROM can be mask-programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0122] The processor 410 performs the steps of the driver state monitoring method provided by the embodiments of the present disclosure by reading and executing the computer program instructions stored in the memory 420.

[0123] In one example, the electronic device can further include a transceiver 430 and a bus 440. As shown in Figure 4 The processor 410, the memory 420, and the transceiver 430 are connected through the bus 440 and complete communication among each other.

[0124] Bus 440 includes a hardware, software, or both that couples components of computer system 400 to each other. As an example without limitation, bus 440 can include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side BUS (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand (IB) interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or another suitable bus or a combination of two or more of these. Where appropriate, bus 440 can include one or more buses of the same type or buses of different types.

[0125] The embodiment of the present disclosure further provides a computer readable storage medium, which can store a computer program. When the computer program is executed by a processor, the processor implements the driver state monitoring method provided by the embodiment of the present disclosure.

[0126] The storage medium described above may, for example, include a memory 420 of computer program instructions, which can be executed by the processor 410 to complete the driver state monitoring method provided by the embodiments of the present disclosure. Optionally, the storage medium can be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium can be a Read-Only Memory (ROM), a Random Access Memory (RAM), an external cache memory, a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, a flash memory and an optical data storage device, etc. As an illustration but not limitation, RAM is available in various forms, such as Static Random Access Memory (SRAM) and Dynamic Random Access Memory (DRAM), etc.

[0127] Reference Figure 5 The embodiments of the present disclosure also provide a vehicle 500, which includes one or more processors 510 and one or more memories 520.

[0128] The processor 510 can include one or more processing cores, such as a 4-core processor, a 10-core processor, etc. The processor 510 can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), a PLA (Programmable Logic Array). The processor 510 can also include a main processor and a coprocessor, the main processor is a processor for processing data in the wake-up state, also known as a CPU (Central Processing Unit), and the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 510 can be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed by the display screen. In some embodiments, the processor 510 can also include an AI (Artificial Intelligence) processor, which is used to process machine learning-related computing operations.

[0129] The memory 520 can include one or more computer-readable storage media. The computer-readable storage media can be non-transitory. The memory 520 can also include high-speed random access memory and can include non-volatile memory, such as one or more magnetic disk storage devices, optical storage devices, flash memory devices, or other non-volatile solid-state storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 520 is used for storing the at least one computer program for being executed by the processor 510 to implement the method of identifying a passable lane provided by the method embodiments in the present disclosure.

[0130] Those skilled in the art can understand that, Figure 5 The structure shown in the figure is not a limitation of the vehicle 500, and can include more or fewer components than shown, or combine certain components, or adopt a different arrangement of components.

[0131] Based on the same inventive concept, the present disclosure also provides a computer program product corresponding to the driver state monitoring method described in any of the above embodiments, which includes computer program instructions. In some embodiments, the computer program instructions can be executed by one or more processors of a computer to cause the computer and / or the processor to perform the driver state monitoring method. Corresponding to the execution subject of each step in each embodiment of the driver state monitoring method, the processor performing the corresponding step can belong to the corresponding execution subject.

[0132] The computer program product of the above embodiments is used to cause the computer and / or the processor to perform the driver state monitoring method as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not repeated here.

[0133] Those skilled in the art know that the embodiments of the present disclosure can be implemented as a system, a method, or a computer program product. Therefore, the present disclosure can be embodied in the form of entire hardware, entire software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, which is generally referred to as "circuitry", "module" or "system" herein. In addition, in some embodiments, the present disclosure can also be embodied in the form of a computer program product in one or more computer-readable media, which includes computer-readable program code.

[0134] Any combination of one or more computer readable medium can be utilized. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include 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 context of this document, a computer readable storage medium can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0135] A computer readable signal medium can include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal can take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium can be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0136] Program code embodied on a computer readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0137] Computer program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can 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 can 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 can be made to an external computer (for example, through the Internet using an Internet Service Provider). In an embodiment, the present disclosure is directed to computer program code embodied in a computer readable medium for execution by, or to control the operation of, a computer.

[0138] It should be understood that each block of the flowchart and / or block diagram illustrations, and combinations of blocks in the flowchart and / or block diagram illustrations, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0139] These computer program instructions can also be stored in a computer- readable medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable medium produce an article of manufacture including instructions which implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0140] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0141] Further, while a particular order of the operations of the methods of the present disclosure are shown in the attached figures, this is not meant to be limiting, and the operations could be performed in other orders, or even at the same time. Additionally or alternatively, certain steps can be omitted, combined, or further divided into additional steps.

[0142] The flowchart and block diagrams in the drawings 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 and block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical functions ("instructions"). It should also be noted that in some alternative implementations, the functions noted in the blocks can 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 can 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 illustrations, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0143] It should be noted that while several modules or units of the devices for action execution are mentioned in the above detailed description, such division is not mandatory. Indeed, according to an embodiment of the application, the features and functionalities of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functionalities of one module or unit described above can be further divided into embodied by a plurality of modules or units.

[0144] It should be understood by those of ordinary skill in the art that the above discussion of any embodiment is merely exemplary in nature and is not intended to imply limitations on the scope of the application, including the claims. Indeed, variations on the above embodiments can be made and steps can be implemented in any order, and many other changes and modifications can be made to the embodiments of the application described and illustrated above, all of which fall within the scope of the application as defined by the appended claims. Such embodiments of the inventive subject matter may, for example, be combined in any way.

[0145] In addition, for simplicity and clarity of illustration, power / ground connections to some of the circuitry illustrated are not shown in the provided figures. Further, as is conventional in the art, some of the components in the figures are shown in block diagram form to simplify the figures. In addition, details involving circuit elements which are well known to those skilled in the art have been left out in order not to obscure the concepts of the application. For example, specific details regarding the implementation of the various circuits have been left out in order not to obscure the concepts of the application. In other instances, well-known circuits, structures, devices, and software have been shown in block diagram form in order to avoid obscuring the concepts of the application.

[0146] Although the application has been described in conjunction with specific embodiments thereof, numerous alternatives, modifications, and variations will be readily apparent to those of ordinary skill in the art. For example, other memory architectures (e.g., dynamic RAM (DRAM)) can use the embodiments discussed.

[0147] It is therefore intended that the application be covered by all such alternatives, modifications and variations that fall within the broad scope of the appended claims. Accordingly, any and all departures from the above described implementations that are within the skill and understanding of those skilled in the art are to be considered as being within the scope of the present application.

[0148] While the spirit and principles of the present disclosure have been described with reference to several specific embodiments, it is to be understood that the disclosure is not limited to the specific embodiments disclosed and that the division into aspects is not meant to be limiting in that features from one aspect can be combined with features from another aspect to benefit from, for example, the disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. The scope of the appended claims covers all such modifications and arrangements.

Claims

1. A driver state monitoring method characterized by, The method comprises: feature extraction is performed on real-time pressure information of a driver seat to obtain real-time pressure distribution features of the driver seat; a pressure distribution feature difference is obtained by comparing the real-time pressure distribution features with reference pressure distribution features of a driver on the driver seat; a state monitoring result of the driver is determined based on the pressure distribution feature difference.

2. The method of claim 1, wherein, The determination manner of the real-time pressure information comprises: in response to real-time vehicle speed of a vehicle to which the driver seat belongs being greater than a preset vehicle speed threshold, collecting the real-time pressure information based on a pressure sensor arranged on the driver seat; or, in response to receiving at least one of auxiliary scene information, collecting the real-time pressure information based on the pressure sensor arranged on the driver seat, wherein the auxiliary scene information comprises at least one of driving behavior information, driving environment information, and driving vehicle information.

3. The method of claim 1, wherein, The real-time pressure information comprises a time-series pressure distribution data stream, and each frame of data in the time-series pressure distribution data stream is a pressure distribution matrix. The feature extraction is performed on the real-time pressure information of the driver seat to obtain the real-time pressure distribution features of the driver seat, which comprises: for each pressure distribution matrix, a pressure center coordinate of the pressure distribution matrix is determined based on a preset pressure sensor position coordinate to obtain a pressure center coordinate sequence; in a preset time length sliding time window, a moving trajectory of the pressure center coordinate sequence in the sliding time window is analyzed to obtain the real-time pressure distribution features.

4. The method of claim 3, wherein, The moving trajectory of the pressure center coordinate sequence in the sliding time window is analyzed to obtain the real-time pressure distribution features, which comprises: at least one of the following trajectory features of the pressure center coordinate sequence in the sliding time window is extracted to constitute the real-time pressure distribution features: trajectory space features, trajectory motion features, and trajectory frequency domain features.

5. The method of claim 1, wherein, The determination manner of the reference pressure distribution features comprises: in response to real-time driving information of a vehicle to which the driver seat belongs satisfying a preset driving condition, collecting reference pressure information based on the pressure sensor arranged on the driver seat; feature extraction is performed on the reference pressure information to obtain the reference pressure distribution features.

6. The method of claim 1, wherein, The comparison of the real-time pressure distribution features with the reference pressure distribution features of the driver on the driver seat to obtain the pressure distribution feature difference comprises: an average value and a standard deviation of the reference pressure distribution features are determined, and a reference pressure distribution model of the driver is constructed based on the average value and the standard deviation; the real-time pressure distribution features are compared with the reference pressure distribution model to obtain the pressure distribution feature difference.

7. The method of claim 1, wherein, The determination of the state monitoring result of the driver based on the pressure distribution feature difference comprises: in response to determining that the pressure distribution feature difference is higher than a first threshold, determining that the state monitoring result is serious distraction; in response to determining that the pressure distribution feature difference is lower than the first threshold but higher than a second threshold, determining that the state monitoring result is slight distraction; In response to determining that the pressure distribution feature difference is lower than the second threshold, determining that the state monitoring result is not distracted; The first threshold is greater than the second threshold.

8. The method of claim 1, wherein, The determining of the state monitoring result of the driver based on the pressure distribution feature difference comprises: determining auxiliary scene information, encoding the auxiliary scene information to obtain auxiliary scene features; taking the pressure distribution feature difference as a query and the auxiliary scene features as keys and values, calculating attention weights of the auxiliary scene features to the pressure distribution feature difference to generate adjusted pressure distribution feature differences; taking the auxiliary scene features as a query and the pressure distribution feature difference as keys and values, calculating attention weights of the pressure distribution feature difference to the auxiliary scene features to generate adjusted auxiliary scene features; fusing the pressure distribution feature difference, the auxiliary scene features, the adjusted pressure distribution feature difference and the adjusted auxiliary scene features to obtain fused features; performing prediction based on the fused features to obtain the state monitoring result.

9. The method of claim 1, wherein, After the determining of the state monitoring result of the driver based on the pressure distribution feature difference, the method further comprises: in response to determining that the state monitoring result is serious distraction, controlling the vehicle to which the driver's seat belongs to perform a warning action; in response to determining that the state monitoring result is slight distraction, sending prompt information to a preset terminal device; in response to determining that the state monitoring result is not distracted, recording the pressure distribution feature difference.

10. A vehicle characterized by comprising: The computer program is stored in the memory and executed by the processor to realize the steps of the method of any one of claims 1 to 9. In response to determining that the pressure distribution feature difference is lower than the second threshold, determining that the state monitoring result is not distracted; The first threshold is greater than the second threshold. The determining of the state monitoring result of the driver based on the pressure distribution feature difference comprises: determining auxiliary scene information, encoding the auxiliary scene information to obtain auxiliary scene features; taking the pressure distribution feature difference as a query and the auxiliary scene features as keys and values, calculating attention weights of the auxiliary scene features to the pressure distribution feature difference to generate adjusted pressure distribution feature differences; taking the auxiliary scene features as a query and the pressure distribution feature difference as keys and values, calculating attention weights of the pressure distribution feature difference to the auxiliary scene features to generate adjusted auxiliary scene features; fusing the pressure distribution feature difference, the auxiliary scene features, the adjusted pressure distribution feature difference and the adjusted auxiliary scene features to obtain fused features; performing prediction based on the fused features to obtain the state monitoring result. After the determining of the state monitoring result of the driver based on the pressure distribution feature difference, the method further comprises: in response to determining that the state monitoring result is serious distraction, controlling the vehicle to which the driver's seat belongs to perform a warning action; in response to determining that the state monitoring result is slight distraction, sending prompt information to a preset terminal device; in response to determining that the state monitoring result is not distracted, recording the pressure distribution feature difference. The computer program is stored in the memory and executed by the processor to realize the steps of the method of any one of claims 1 to 9.

Images