Fatigue driving detection method, intelligent glasses and detection platform

Abstract

This application relates to the field of intelligent device technology, and discloses a fatigue driving detection method, smart glasses, and a detection platform. The method is applied to smart glasses connected to a vehicle's infotainment system. The method includes: illuminating the driver's eyes using an infrared module; acquiring images of the illuminated driver's eyes and obtaining the driver's current eye gaze information based on the image acquisition results; and sending the current eye gaze information to the vehicle's infotainment system, enabling the system to detect driver fatigue based on a preset detection model. The preset detection model is trained using sample eye gaze information. Since driver fatigue manifests as abnormal eye movements, the smart glasses in this application can acquire images of the driver's eyes to determine their current eye gaze information, and then transmit this information to the vehicle's infotainment system, allowing the system to detect the driver's fatigue state.

Description

Technical Field

[0001] This application relates to the field of intelligent device technology, and in particular to a fatigue driving detection method, intelligent glasses and detection platform. Background Technology

[0002] With the rapid development of technology, driving safety has received increasing attention. In busy traffic environments, driver fatigue is a significant factor contributing to traffic accidents. Statistics show that a considerable proportion of traffic accidents each year are caused by fatigued driving, resulting in substantial personal injury and property damage. Therefore, how to detect driver fatigue is a pressing technical problem that needs to be solved. Summary of the Invention

[0003] The main purpose of this application is to provide a fatigue driving detection method, smart glasses, and detection platform, aiming to solve the existing technical problems of how to detect driver fatigue.

[0004] To achieve the above objectives, this application provides a fatigue driving detection method, which is applied to smart glasses connected to a vehicle's infotainment system. The smart glasses are equipped with an infrared module, and the method includes:

[0005] The infrared module is used to illuminate the driver's eyes;

[0006] Images of the driver's eyes after illumination are captured, and the driver's current eye gaze information is obtained based on the image capture results;

[0007] The current eye gaze information is sent to the vehicle system so that the vehicle system can perform fatigue driving detection on the driver based on the current eye gaze information and a preset detection model. The preset detection model is obtained by training with sample eye gaze information.

[0008] In one embodiment, the step of obtaining the driver's current eye gaze information based on the image acquisition results includes:

[0009] The current gaze direction and the current gaze point position of the eyeball are determined based on the image acquisition results.

[0010] The driver's current eye gaze information is obtained based on the current gaze point position and the current gaze direction.

[0011] In one embodiment, the step of determining the current gaze direction and the current gaze point position of the eyeball based on the image acquisition result includes:

[0012] The pupil coordinates of the eyeball and the coordinates of the reflection point of the preset reflection point in the eyeball are determined based on the image acquisition results.

[0013] Based on the coordinates of the reflection point, the corneal curvature center of the eyeball is determined using a preset eyeball geometric model, and the current gaze direction of the eyeball is determined based on the pupil coordinates and the corneal curvature center.

[0014] The size data of the image acquisition result is obtained, and the current gaze point position of the eyeball is determined based on the size data and the current gaze direction.

[0015] In one embodiment, the step of determining the current gaze point position of the eyeball based on the size data and the current gaze direction includes:

[0016] The width and height data of the image acquisition result are based on the size data;

[0017] The horizontal coordinate of the current gaze point of the eyeball is determined based on the preset maximum optical axis vector, the current gaze direction, and the width data.

[0018] The current gaze point ordinate of the eyeball is determined based on the preset maximum optical axis vector, the current gaze direction, and the height data.

[0019] The current gaze point position of the eyeball is obtained based on the horizontal coordinate of the current gaze point and the vertical coordinate of the current gaze point.

[0020] In one embodiment, prior to the step of illuminating the driver's eyes using the infrared module, the method further includes:

[0021] The eyeballs of the driver who is looking at the preset calibration point are collected to obtain calibration collection results, and the current optical axis direction vector of the eyeball is obtained based on the calibration collection results;

[0022] Obtain the preset optical axis direction vector corresponding to the preset calibration point, and obtain the offset of the eyeball at the preset calibration point based on the current optical axis direction vector and the preset optical axis direction vector;

[0023] The offset at the preset calibration point is interpolated according to a preset polynomial.

[0024] The step of determining the current gaze direction of the eyeball based on the pupil coordinates and the corneal curvature center includes:

[0025] The initial gaze direction of the eyeball is determined based on the pupil coordinates and the corneal curvature center, and the visual axis is corrected by interpolation to obtain the current gaze direction of the eyeball.

[0026] In one embodiment, after the step of collecting data from the driver's eyeballs fixed on the preset calibration point and obtaining the calibration data collection results, the method further includes:

[0027] Based on the calibration acquisition results, determine the driver's eye gaze information at the preset calibration point;

[0028] Stability analysis was performed on the calibrated eye gaze information;

[0029] If the stability analysis results do not meet the preset stability requirements, the preset calibration point is adjusted, and the process returns to the step of collecting data on the driver's eyeballs focused on the preset calibration point.

[0030] In one embodiment, the smart glasses are equipped with a detection component, and the step of illuminating the driver's eyes using the infrared module includes:

[0031] The current wearing status of the smart glasses is detected using the detection component;

[0032] When the current wearing state is "wearing", the infrared module is used to illuminate the driver's eyes.

[0033] Furthermore, to achieve the above objectives, this application also provides a fatigue driving detection method, which is applied to a vehicle infotainment system connected to smart glasses, and the method includes:

[0034] The system receives the driver's current eye gaze information, which is then used to illuminate the driver's eyes via the infrared module of the smart glasses. An image of the illuminated driver's eyes is then captured, and the results are obtained based on the image capture.

[0035] Based on the current eye gaze information, fatigue driving detection is performed on the driver using a preset detection model, which is obtained by training with sample eye gaze information.

[0036] Furthermore, to achieve the above objectives, embodiments of this application also provide smart glasses, the smart glasses comprising:

[0037] An infrared module is used to illuminate the driver's eyes;

[0038] The information acquisition module is used to acquire images of the driver's eyes after illumination and to obtain the driver's current eye gaze information based on the image acquisition results.

[0039] The information sending module is used to send the current eye gaze information to the vehicle system, so that the vehicle system can perform fatigue driving detection on the driver based on the current eye gaze information and a preset detection model. The preset detection model is obtained by training with sample eye gaze information.

[0040] In addition, to achieve the above objectives, this application embodiment also provides a detection platform, which includes: smart glasses and a car equipped with a vehicle-mounted system, wherein the smart glasses are connected to the vehicle-mounted system;

[0041] The smart glasses are used to illuminate the driver's eyes using an infrared module; to capture images of the illuminated driver's eyes and obtain the driver's current eye gaze information based on the image capture results; and to send the current eye gaze information to the vehicle's infotainment system.

[0042] The vehicle system is used to detect driver fatigue based on the current eye gaze information using a preset detection model, which is obtained by training with sample eye gaze information.

[0043] This application provides a fatigue driving detection method, smart glasses, and a detection platform. The method is applied to smart glasses connected to a vehicle infotainment system. The smart glasses are equipped with an infrared module. The method includes: illuminating the driver's eyes with the infrared module; acquiring images of the driver's eyes after illumination and obtaining the driver's current eye gaze information based on the image acquisition results; and sending the current eye gaze information to the vehicle infotainment system, so that the vehicle infotainment system can perform fatigue driving detection on the driver based on the current eye gaze information using a preset detection model. The preset detection model is obtained by training with sample eye gaze information.

[0044] Since drivers' eyes may become abnormal when they are fatigued, in this application, the driver can wear the smart glasses described in this application to capture images of the driver's eyes, determine the driver's current eye gaze information based on the image capture results, and then transmit the current eye gaze information to the vehicle's infotainment system. The infotainment system is equipped with a preset detection model trained using sample eye gaze information, which can detect the driver's fatigue state based on the current eye gaze information. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0046] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a schematic diagram of the smart glasses structure of the hardware operating environment involved in the embodiments of this application;

[0048] Figure 2 This is a flowchart illustrating the first embodiment of the fatigue driving detection method of this application;

[0049] Figure 3 This is a flowchart illustrating the second embodiment of the fatigue driving detection method of this application;

[0050] Figure 4 This is a flowchart of the current gaze point position acquisition process in the second embodiment of the fatigue driving detection method of this application;

[0051] Figure 5 This is a flowchart illustrating the third embodiment of the fatigue driving detection method of this application;

[0052] Figure 6 This is a schematic diagram of the area division in the third embodiment of the fatigue driving detection method of this application;

[0053] Figure 7 This is a flowchart illustrating the fourth embodiment of the fatigue driving detection method of this application.

[0054] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0055] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0056] Reference Figure 1 , Figure 1 This is a schematic diagram of the smart glasses structure of the hardware operating environment involved in the embodiments of this application.

[0057] like Figure 1As shown, the smart glasses may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may be connected to a display screen; optionally, the user interface 1003 may include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or non-volatile memory (NVM), such as a disk drive. Alternatively, the memory 1005 may be a storage device independent of the aforementioned processor 1001.

[0058] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0059] like Figure 1 As shown, the memory 1005, which is identified as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a boot program.

[0060] exist Figure 1 In the electronic device shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the user equipment; the electronic device calls the fatigue driving detection program stored in the memory 1005 through the processor 1001 and executes the steps of the fatigue driving detection method provided in the embodiments of this application.

[0061] It should be noted that with the rapid development of technology, driving safety has received increasing attention. In busy traffic environments, driver fatigue is a significant factor contributing to traffic accidents. Statistics show that a considerable proportion of traffic accidents each year are caused by fatigued driving, resulting in substantial personal injury and property damage. Therefore, how to detect driver fatigue is a pressing technical problem that needs to be solved.

[0062] Therefore, in order to solve the above-mentioned defects, this embodiment provides a fatigue driving detection method. Since the driver's eyes will be abnormal when the driver is fatigued, in this embodiment, the driver can wear the smart glasses in this embodiment to collect images of the driver's eyes, and determine the driver's current eye gaze information based on the image collection results. Then, the current eye gaze information is transmitted to the vehicle's system. The vehicle's system is equipped with a preset detection model obtained by training with sample eye gaze information. The driver's fatigue state can be detected based on the current eye gaze information through the preset detection model.

[0063] For ease of understanding, the following is combined with Figures 2 to 7 The fatigue driving detection method provided in the embodiments of this application will be described in detail.

[0064] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the fatigue driving detection method of this application. The first embodiment of the fatigue driving detection method of this application is presented as follows: Figure 2 As shown, in this embodiment, the specific method includes:

[0065] Step S10: Illuminate the driver's eyes using the infrared module;

[0066] Step S20: Acquire an image of the driver's eyeballs after illumination, and obtain the driver's current eye gaze information based on the image acquisition results.

[0067] It is understood that the method in this embodiment can be applied to smart glasses connected to the vehicle's infotainment system. These smart glasses can be glasses equipped with an infrared module, such as augmented reality (AR) glasses, artificial intelligence (AI) smart glasses, etc., and this embodiment does not impose any limitations on them. However, for ease of understanding, this embodiment uses AI smart glasses as an example of the aforementioned smart glasses. The aforementioned vehicle infotainment system can be any infotainment system installed in a car, and this embodiment does not impose any limitations on it.

[0068] It should be noted that the aforementioned infrared module can be any module that emits infrared light, such as an infrared emitter, and this embodiment is not limited thereto. Furthermore, in this embodiment, the aforementioned infrared module can be mounted on smart glasses and can illuminate the driver's eyes with the generated infrared light; the specific configuration can be tailored to the actual situation.

[0069] It is also understood that, in order to capture the driver's eye movements, this embodiment may include an image acquisition component, such as a camera, on the aforementioned smart glasses. This acquisition component can then capture images of the driver's eyes, obtaining the aforementioned image acquisition results.

[0070] It should be understood that the aforementioned current eye gaze information may be the information on what the driver's eyes are currently looking at, which may include the current gaze point position and the current gaze direction. The current gaze point position may be the specific location where the eyes are currently looking at, and the current gaze direction may be the direction in which the eyes are looking.

[0071] In practical use, when the driver is driving a car and is wearing the aforementioned smart glasses, the infrared module can emit infrared light that shines onto the driver's eyes. The sensor can also capture images of the driver's eyes and obtain the driver's current gaze information based on the image capture results.

[0072] Step S30: Send the current eye gaze information to the vehicle system so that the vehicle system can perform fatigue driving detection on the driver based on the current eye gaze information and a preset detection model. The preset detection model is obtained by training with sample eye gaze information.

[0073] It should be noted that, in this embodiment, the aforementioned preset detection model can be installed within the vehicle's infotainment system. The preset detection module can obtain the model by training the initial detection model using sample eye gaze information. This sample eye gaze information can include the driver's eye gaze direction and the position of the sample gaze point. This sample eye gaze information and the corresponding detection results are transmitted to the initial detection model for training, thereby obtaining the aforementioned preset detection model, which is then deployed within the infotainment system of the vehicle driven by the driver.

[0074] In practical use, smart glasses can connect to the vehicle's infotainment system via wired or wireless connections. Since driver fatigue can cause eye abnormalities, the smart glasses, after obtaining the driver's current gaze information, can transmit this information to the vehicle's infotainment system. The system can then transmit this information to a pre-set detection model for identification, obtaining the driver's fatigue detection result.

[0075] It is important to emphasize that after the vehicle's infotainment system receives the aforementioned current eye gaze information, it can preprocess this information to ensure the accuracy of subsequent recognition. This preprocessing includes, but is not limited to, noise reduction and filtering. Then, a preset detection model can be used to extract features from the preprocessed current eye gaze information, specifically extracting features from the preprocessed current gaze point position and the preprocessed current gaze direction. Based on the feature extraction results, driver fatigue detection can then be performed.

[0076] It should also be emphasized that the initial detection model mentioned above can be any model used to implement the above-mentioned fatigue driving detection function. The specific model can be set according to the actual situation, and this embodiment does not impose any restrictions on it.

[0077] Furthermore, in order to enable the vehicle system to accurately detect driver fatigue, in this embodiment, the aforementioned preset detection model can also combine and analyze the current eye gaze information with the current driving state of the vehicle and the driver's physiological state. That is, after obtaining the current eye gaze information, the vehicle system can obtain the current driving state of the vehicle and collect the driver's physiological state through smart glasses. This physiological state may include the driver's heart rate, respiratory rate, etc. Then, based on the current eye gaze information, the current driving state, and the driver's physiological state, the preset detection model is used to detect driver fatigue.

[0078] It should be noted that the aforementioned current driving state can be the state of the car's driving, such as driving speed and driving direction. This is because when the driver is fatigued, the car's driving speed and driving direction may be inconsistent with normal driving conditions. Therefore, this embodiment can combine the current eye gaze information with the car's current driving state for analysis.

[0079] The aforementioned driver's physiological state can be related to the driver's physical condition, such as heart rate and respiratory rate. This is because when a driver is fatigued, their physiological state differs from a normal state. Therefore, this embodiment can combine and analyze the current eye gaze information, the vehicle's current driving status, and the driver's physiological state. Furthermore, the smart glasses can also have a physiological state acquisition function, transmitting the acquired physiological state data to the vehicle's infotainment system.

[0080] Furthermore, during the initial detection model training, this embodiment can also transmit the sample's eye gaze information, driving status, physiological status, and corresponding detection results to the initial detection model for model training, thereby obtaining the aforementioned preset detection model.

[0081] Furthermore, considering that when driver fatigue is detected, in order to remind the driver, in this embodiment, after the step of sending the current eye gaze information to the vehicle system so that the vehicle system can perform fatigue detection on the driver based on the current eye gaze information using a preset detection model, the method further includes:

[0082] Step S40: Upon receiving a device prompt instruction sent by the vehicle system, the vehicle system prompts the driver according to the corresponding first preset prompt method. The device prompt instruction is generated by the vehicle system when it determines that the driver is driving while fatigued.

[0083] It should be noted that the aforementioned device prompting command can be a command used to cause the smart glasses to provide prompts according to a first preset prompting method. The aforementioned first preset prompting method may include, but is not limited to, vibration prompts, voice prompts, etc. Furthermore, to enable the smart glasses to have a vibration prompting function, this embodiment may also include a vibration component, such as a vibration motor, within the smart glasses. When the smart glasses receive a device prompting command, they can provide a vibration prompt through this vibration component. Similarly, to enable the smart glasses to have a voice prompting function, this embodiment may also include a voice component, such as a speaker, within the smart glasses. When the smart glasses receive a device prompting command, they can provide a voice prompt through this voice component.

[0084] It should also be emphasized that, for the vehicle's infotainment system, when it determines that the driver is fatigued, it can also issue a warning, that is, it can warn the driver according to a corresponding second preset warning method. The aforementioned second warning method may include, but is not limited to, controlling vehicle speed, taking over steering, and voice prompts. That is, when the vehicle's infotainment system determines that the driver is fatigued, it can reduce vehicle speed, maintain steering, or issue voice prompts, etc., and the specific settings can be customized according to actual conditions; this embodiment does not impose any limitations on this.

[0085] Furthermore, to ensure that driver fatigue detection only begins after the driver wears the aforementioned smart glasses, in this embodiment, the smart glasses are equipped with a detection component, and the step of irradiating the driver's eyes using the infrared module includes:

[0086] Step S11: Detect the current wearing status of the smart glasses using the detection component;

[0087] Step S12: When the current wearing state is the worn state, the infrared module is used to illuminate the driver's eyes.

[0088] Understandably, the aforementioned detection components can be any component that detects whether the driver is wearing smart glasses, such as a distance sensor or a light sensor. The aforementioned "wearing" state can be determined by the corresponding detection component as a state in which smart glasses are being worn.

[0089] As one implementation, if the detection component is a distance sensor, the distance sensor can be placed on the temple or frame of the smart glasses. The step of detecting the current wearing status of the smart glasses using the detection component includes: detecting the relative distance between the smart glasses and the driver using the distance sensor.

[0090] Accordingly, the step of illuminating the driver's eyes with the infrared module when the current wearing state is the worn state includes:

[0091] When the relative distance reaches a preset relative distance threshold, the current wearing state is determined to be a worn state, and the infrared module is used to illuminate the driver's eyes.

[0092] In actual use, the distance sensor can collect the relative distance between itself and the driver in real time and determine whether the relative distance reaches the preset relative distance threshold. If the preset relative distance threshold is not reached, it means that the driver is not wearing the smart glasses and can prompt the driver to wear them. If the preset relative distance threshold is reached, it means that the driver is wearing them and can start fatigue driving detection, that is, start using the infrared module to irradiate the driver's eyes.

[0093] Since drivers' eyes may become abnormal when they are fatigued, in this embodiment, the driver can wear the smart glasses in this embodiment to capture images of the driver's eyes, determine the driver's current eye gaze information based on the image capture results, and then transmit the current eye gaze information to the vehicle's infotainment system. The vehicle's infotainment system is equipped with a preset detection model trained with sample eye gaze information. The preset detection model can detect the driver's fatigue state based on the current eye gaze information.

[0094] It should also be noted that, since the aforementioned preset detection model is deployed on the vehicle's infotainment system in this embodiment, the smart glasses only collect the driver's current eye gaze information. Therefore, the smart glasses can be deployed in a lightweight manner, that is, a lightweight AI model is deployed on the AI ​​smart glasses. The process of determining the current eye gaze information based on the image acquisition results is completed through this lightweight AI model, so as to reduce the amount of data transmission and latency, improve the real-time performance of the system, and then the preset detection model in the vehicle's infotainment system can be used for detection.

[0095] Reference Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the fatigue driving detection method of this application. Based on the first embodiment described above, the second embodiment of the fatigue driving detection method of this application is proposed.

[0096] In order to obtain the driver's current eye gaze information, such as Figure 3 As shown, in this embodiment, the step of obtaining the driver's current eye gaze information based on the image acquisition results includes:

[0097] Step S21: Determine the current gaze direction of the eyeball and the current gaze point position of the eyeball based on the image acquisition results.

[0098] Understandably, after obtaining the image acquisition results, the driver's current gaze direction and current gaze point position can be obtained from the image acquisition results.

[0099] Specifically, the steps of determining the current gaze direction and the current gaze point position of the eyeball based on the image acquisition results include:

[0100] Step S211: Determine the pupil coordinates of the eyeball and the coordinates of the reflection point of the preset reflection point in the eyeball based on the image acquisition results.

[0101] It should be understood that the aforementioned pupil coordinates can be the coordinates of the center of the driver's pupil. The aforementioned preset reflection point can be a point used for eye tracking, such as a corneal reflection point, and the aforementioned reflection point coordinates can be the coordinates of that preset reflection point on the eyeball.

[0102] Due to the physiological structure and physical properties of the eyeball, the light spot formed by corneal reflection will not move if the relative positions of the light source and the head remain unchanged. Therefore, in this embodiment, after the smart glasses obtain the image acquisition results, the pupil coordinates of the driver's eyeball and the coordinates of the reflection point of the preset reflection point in the eyeball can be extracted from the image acquisition results.

[0103] It should be emphasized that the number of preset reflection points can be multiple. For example, points on the upper, lower, left, and right sides of the cornea of ​​the eye can be used as preset reflection points. Of course, other locations are also possible, and this embodiment does not limit this.

[0104] Step S212: Based on the coordinates of the reflection point, determine the corneal curvature center of the eyeball using a preset eyeball geometric model, and determine the current gaze direction of the eyeball based on the pupil coordinates and the corneal curvature center.

[0105] It is understood that the aforementioned preset eyeball geometry model can be a geometric model of the eyeball. The aforementioned corneal curvature center can refer to the geometric center corresponding to the curvature of the aforementioned preset reflection point on the surface of the eyeball.

[0106] In practical use, the aforementioned smart glasses can pre-store a geometric model of the eyeball as the preset eyeball geometric model. After the smart glasses obtain the coordinates of the reflection point and the pupil coordinates, the corneal curvature center of the eyeball can be determined based on the reflection point coordinates and the preset eyeball geometric model.

[0107] Specifically, one can first determine the normal direction of the preset reflection point on the corneal surface based on the coordinates of the reflection point and the preset eyeball geometry model, and then determine the incident angle and reflection angle of the preset reflection point based on the normal direction. Finally, the corneal curvature center can be determined based on the incident angle and reflection angle.

[0108] The line connecting the pupil center (corresponding to the pupil coordinates) to the corneal curvature center can then be used as the current gaze direction of the eyeball.

[0109] Step S213: Obtain the size data of the image acquisition result, and determine the current gaze point position of the eyeball based on the size data and the current gaze direction.

[0110] It should be noted that the aforementioned size data can be the width and height data of the image acquired. In this embodiment, after obtaining the current gaze direction of the eye, the width and height data of the image acquisition result can be obtained, and then the current gaze point position can be determined based on the width data, height data, and current gaze direction.

[0111] Step S22: Obtain the driver's current eye gaze information based on the current gaze point position and the current gaze direction.

[0112] Once the driver's current gaze point and gaze direction are obtained, these can be used as the driver's current eye gaze information.

[0113] Furthermore, in order to obtain the current gaze point position, refer to Figure 4 , Figure 4 This is a flowchart illustrating the process of obtaining the current gaze point position in the second embodiment of the fatigue driving detection method of this application. Figure 4 As shown, in this embodiment, the step of determining the current gaze point position of the eyeball based on the size data and the current gaze direction includes:

[0114] Step S2131: Based on the size data, obtain the width and height data of the image acquisition result.

[0115] It should be noted that the aforementioned width data can refer to the width of the image in the image acquisition result, and the aforementioned height data can refer to the height of the image in the image acquisition result. In practical use, after obtaining the image acquisition result, the width and height data of the image acquisition result can be obtained. For ease of subsequent explanation, in this embodiment, the aforementioned width data can be denoted as W, and the height data as H.

[0116] Step S2132: Determine the horizontal coordinate of the current gaze point of the eyeball based on the preset maximum optical axis vector, the current gaze direction, and the width data;

[0117] Step S2133: Determine the ordinate of the current gaze point of the eyeball based on the preset maximum optical axis vector, the current gaze direction, and the height data;

[0118] Understandably, the aforementioned preset maximum optical axis vector can be the angle between the line connecting the geometric center of the eyeball and the center of the pupil when the eyeball rotates to its extreme position, and the line connecting the geometric center of the eyeball and the center of corneal curvature. This can be obtained in advance through measurement. The aforementioned horizontal coordinate of the current fixation point can be the coordinate of the current fixation point position on the horizontal axis, and the aforementioned vertical coordinate of the current fixation point can be the coordinate of the current fixation point position on the vertical axis. If the current fixation direction is denoted as (x1, y1), and the preset maximum optical axis vector is denoted as (x2, y2), and the horizontal coordinate of the current fixation point is denoted as xg, then xg = x1 / x2 * W. If the horizontal coordinate of the current fixation point is denoted as yg, then yg = y1 / y2 * H.

[0119] Step S2134: Obtain the current gaze point position of the eyeball based on the horizontal coordinate of the current gaze point and the vertical coordinate of the current gaze point.

[0120] After obtaining the x-coordinate and y-coordinate of the current gaze point, the position of the current gaze point, i.e. (xg, yg), can be obtained.

[0121] In practical use, the smart glasses in this embodiment can first illuminate the driver's eyes through an infrared module and collect images of the driver's eyes after illumination to obtain image acquisition results. Based on the image acquisition results, the pupil coordinates and reflection point coordinates of the eyeball are determined. The corneal curvature center of the eyeball can be determined based on the reflection point coordinates using a preset eyeball geometric model. Then, the current gaze direction of the eyeball is determined based on the pupil coordinates and the corneal curvature center. The current gaze point position can be obtained by combining the width and height data of the image acquisition results with the current gaze direction.

[0122] Reference Figure 5 , Figure 5 This is a flowchart illustrating the third embodiment of the fatigue driving detection method of this application. Based on the above embodiments, the third embodiment of the fatigue driving detection method of this application is proposed.

[0123] Considering the potential physiological deviation between the optical axis and the visual axis, and in order to improve detection accuracy, such as... Figure 5 As shown, in this embodiment, before the step of illuminating the driver's eyes with the infrared module, the method further includes:

[0124] Step S01: Collect data on the driver's eyeballs that are focused on the preset calibration point, obtain calibration data collection results, and obtain the current optical axis direction vector of the eyeballs based on the calibration data collection results.

[0125] It should be noted that the aforementioned preset calibration points can be points used to determine the offset between the optical axis and the visual axis. In this embodiment, these points can be set on the display screen of the wearable device, for example, the four top corners and the center of the display screen can be used as the preset calibration points.

[0126] It should also be noted that the aforementioned current optical axis direction vector can be the line vector connecting the center of the driver's pupil and the center of corneal curvature when looking at the preset calibration point.

[0127] When in use, the smart glasses can prompt the user to look at each of the preset calibration points in sequence, and collect images of the user's eyeballs through the acquisition component to obtain the calibration acquisition results; then the calibration acquisition results are identified to determine the center of the driver's pupil and the center of corneal curvature when looking at the preset calibration point, and the current optical axis direction vector under the preset calibration point can be obtained based on the center of the pupil and the center of corneal curvature.

[0128] Step S02: Obtain the preset optical axis direction vector corresponding to the preset calibration point, and obtain the offset of the eyeball at the preset calibration point based on the current optical axis direction vector and the preset optical axis direction vector.

[0129] It is understood that the aforementioned preset optical axis direction vector can be the vector connecting the center of the pupil and the center of corneal curvature when the driver's eye is focused on the preset calibration point under ideal conditions. The aforementioned preset optical axis direction vector can be obtained in advance through testing or by other means, and this embodiment does not impose any limitations on this.

[0130] It is also understandable that if the current optical axis direction vector corresponding to a certain preset calibration point is denoted as v(x3, y3), the corresponding preset optical axis direction vector is denoted as v'(x3', y3'), and the corresponding offset is denoted as offset, then offset = (x3' - x3, y3' - y3).

[0131] In practical use, after obtaining the current optical axis direction vector corresponding to each preset calibration point, the preset optical axis direction vector corresponding to each preset calibration point can be obtained. Then, based on the preset optical axis direction vector and the current optical axis direction vector, the offset corresponding to each preset calibration point can be obtained.

[0132] Step S03: Interpolate the offset at the preset calibration point according to the preset polynomial.

[0133] It should be noted that the aforementioned preset polynomial can be a polynomial used for fitting, such as a quadratic polynomial, and this embodiment does not impose any restrictions on it.

[0134] After obtaining the offset corresponding to each preset calibration point, it can be substituted into the above preset polynomial and fitted by the least squares method. Then, the offset under the preset calibration point is interpolated according to the fitting result, so as to obtain the offset corresponding to all points on the display screen.

[0135] Accordingly, the step of determining the current gaze direction of the eyeball based on the pupil coordinates and the corneal curvature center includes:

[0136] Step S2121: Determine the initial gaze direction of the eyeball based on the pupil coordinates and the corneal curvature center, and perform visual axis correction on the initial gaze direction through interpolation processing results to obtain the current gaze direction of the eyeball.

[0137] It should be understood that the initial gaze direction mentioned above can be the gaze direction before visual axis correction using the offset. In actual use, after obtaining the offset corresponding to each preset calibration point in advance, when determining the current gaze direction of the eye based on the pupil coordinates and the corneal curvature center, the line connecting the pupil center corresponding to the pupil coordinates to the corneal curvature center can be used as the initial gaze direction of the eye. Then, the offset at the corresponding point is selected from the interpolation results, and the visual axis is calibrated based on the offset. That is, the offset is added to the initial gaze direction to obtain the current gaze direction of the eye.

[0138] Furthermore, considering that different drivers may have different wearing habits and different eye structures, in order to improve the accuracy of subsequent visual axis correction, in this embodiment, after the step of collecting data on the driver's eyes fixed on the preset calibration point and obtaining the calibration data collection results, the method further includes:

[0139] Step S011: Determine the calibration eye gaze information of the driver's eye gaze at the preset calibration point based on the calibration acquisition results;

[0140] Step S012: Perform stability analysis on the calibrated eye gaze information.

[0141] It should be noted that the aforementioned calibration eye gaze information can be the calibration gaze direction and calibration gaze point position of the eye during calibration. In this embodiment, the process of determining the calibration gaze direction and calibration gaze point position of the driver's eye based on the calibration acquisition results is consistent with the process of obtaining the current gaze point position and current gaze direction based on the image acquisition results, and will not be elaborated upon in this embodiment.

[0142] After obtaining eye fixation information, a stability analysis can be performed on this information. Specifically, this involves determining the standard deviation and consistency ratio between the calibrated eye fixation information and the preset standard eye fixation information. The preset standard eye fixation information can be the standard fixation direction and the standard fixation point position corresponding to each preset calibration point.

[0143] Step S013: If the stability analysis result does not meet the preset stability requirements, adjust the preset calibration point and return to the step of collecting data from the driver's eyes fixed on the preset calibration point.

[0144] After obtaining the standard deviation and consistency ratio, it can be determined whether the standard deviation and consistency ratio both meet the above-mentioned preset stability requirements. The preset stability requirements can be preset standard deviation thresholds and preset consistency ratio thresholds.

[0145] If the stability analysis results corresponding to each preset calibration point meet the preset stability requirements, it can be said that the calibration acquisition results meet the requirements, and then the step of obtaining the current optical axis direction vector of the eyeball based on the calibration acquisition results can be performed.

[0146] If the stability analysis results corresponding to a preset calibration point do not meet the preset stability requirements, it indicates that the calibration acquisition results do not meet the requirements. Therefore, the preset calibration points can be adjusted. Specifically, this can involve increasing the number of preset calibration points at the location of the one that did not meet the requirements. The specific number and location of the added preset calibration points can be set according to the actual situation; this embodiment does not impose any restrictions on this. After adding the points, the driver's eye is photographed again at the preset calibration points with the added focus to obtain new calibration acquisition results. This process continues until the gaze information of the calibrated eye in the new calibration acquisition results meets the stability requirements.

[0147] Furthermore, considering that when performing the interpolation process, since drivers generally maintain a slightly downward and forward gaze when fatigued, a higher accuracy requirement is needed for this direction, in this embodiment, the step of interpolating the offset at the preset calibration point according to a preset polynomial includes:

[0148] Step S031: Obtain the target center calibration point from each of the preset calibration points, and adjust the target center calibration point by a preset adjustment distance.

[0149] It should be noted that the aforementioned target center calibration point can be a point located at the center of the display screen from the preset calibration points. For ease of understanding, refer to... Figure 6 , Figure 6 This is a schematic diagram of the area division in the third embodiment of the fatigue driving detection method of this application. Figure 6 As shown, this embodiment uses 5 preset calibration points for illustration. The four preset calibration points at the vertices are denoted as a, b, c, and d, respectively, and the preset calibration point in the center is denoted as o.

[0150] After obtaining the target center calibration point o from each preset calibration point, the preset adjustment distance (i.e., Figure 6 The preset adjustment distance (k) is used to determine the center area obtained after adjustment, which is the area that the driver's eyes focus on when fatigued. This preset adjustment distance (k) allows you to adjust the target center calibration point to obtain the adjusted target center calibration point. Figure 6 (o' in the middle).

[0151] It is important to emphasize that the aforementioned preset adjustment distance can be obtained based on the area the driver's eyes focused on during historical fatigue states. That is, after obtaining the gaze point position of the driver's eyes during fatigue states from historical data, a circle is drawn based on this gaze point position with a preset radius. This preset radius can be set according to actual conditions, and this embodiment does not impose any restrictions on it. When drawing the circle, it is sufficient to ensure that all gaze point positions during historical fatigue driving are within this circle.

[0152] After drawing the circle, the corresponding center can be determined based on the circle drawing result. Then, the preset adjustment distance can be obtained based on the center and the target center calibration point o.

[0153] Step S032: Determine the central region based on the adjusted target center calibration point, and determine the edge region based on the central region.

[0154] like Figure 6 As shown, after determining the adjusted target center calibration point o', a circle can be drawn according to the preset radius, and the area inside the circle is taken as the center area, and the area outside the circle is taken as the edge area.

[0155] Step S033: Interpolate the central region using a first preset polynomial based on each preset calibration point, and interpolate the edge region using a second preset polynomial based on each preset calibration point.

[0156] It is understood that both the first and second preset polynomials are polynomials used for fitting. However, it should be noted that, in order to ensure the accuracy of the central region, the degree of the first preset polynomial in this embodiment may be higher than that of the second preset polynomial. For example, the first preset polynomial may be a cubic polynomial, and the second preset polynomial may be a quadratic polynomial, etc.

[0157] Therefore, in practical use, after obtaining the central and edge regions, a first preset polynomial can be used to fit the data within the central region based on each preset calibration point, and interpolation is performed based on the fitting results. Similarly, a second preset polynomial can be used to fit the data within the edge regions based on each preset calibration point, and interpolation is performed based on the fitting results. This ensures higher accuracy in detecting data slightly below and directly in front of the driver's line of sight.

[0158] Furthermore, considering that when the vehicle system determines that the driver is in a normal driving state, in order to improve the driver's driving experience, in this embodiment, after the vehicle system performs fatigue driving detection on the driver based on the current eye gaze information using a preset detection model, it further includes:

[0159] When the vehicle's infotainment system determines that the driver is not fatigued, the system obtains the vehicle's current interaction information.

[0160] The vehicle system adjusts the current interaction information based on the current eye gaze information, and interacts with the driver according to the adjusted current interaction information.

[0161] It should be noted that the aforementioned current interactive information can be any information on the vehicle that interacts with the driver, such as the vehicle's head-up display, instrument display, navigation display, and announcement prompts, etc. This embodiment does not impose any restrictions on this.

[0162] Specifically, as one implementation, when the aforementioned current interaction information is the car's head-up display, the vehicle-mounted system adjusts the current interaction information based on the current eye gaze information, and interacts with the driver according to the adjusted current interaction information, including the following steps:

[0163] The vehicle's infotainment system determines the current position of the head-up display based on the current interaction information, and determines the corresponding adjustment direction and distance based on the current eye gaze information;

[0164] The vehicle's infotainment system adjusts the current display position according to the adjustment direction and distance, and then displays a head-up display based on the adjusted current display position.

[0165] It is understandable that, since the current eye gaze information in this embodiment may include the driver's current gaze point position and current gaze direction, when the vehicle system determines that the driver is not driving while fatigued, it can first obtain the current display position of the head-up display on the car window as the aforementioned current display position.

[0166] It is also understood that this embodiment sets corresponding adjustment directions and distances for different current gaze point positions and current gaze directions. For example, when the driver's current gaze point position is biased to the left, the corresponding adjustment direction is also to the left; when the driver's current gaze point position is biased to the right, the corresponding adjustment direction is also to the right. Specifically, the adjustment direction and adjustment distance corresponding to the current gaze point position and current gaze direction can be set according to the actual situation, and this embodiment does not impose any restrictions on this.

[0167] Therefore, in actual use, when the vehicle's infotainment system determines that the driver is not fatigued, it can obtain the current display position of the head-up display based on the current interaction information, and determine the corresponding adjustment direction and distance based on the current eye gaze information. Then, it can adjust the current display position according to this adjustment direction and distance, and display the head-up display according to the adjusted position. This ensures that the adjusted head-up display position is better positioned within the driver's optimal field of vision, improving the driver's driving experience.

[0168] As another implementation, when the aforementioned current interaction information is the car's navigation display, the vehicle's infotainment system adjusts the current interaction information based on the current eye gaze information, and interacts with the driver according to the adjusted current interaction information, including:

[0169] The vehicle's infotainment system determines the navigation display information based on the current interaction information and determines the necessary display items based on the current eye gaze information;

[0170] The vehicle's infotainment system adjusts the navigation display information according to the necessary display items and then displays navigation information according to the adjusted information.

[0171] It should be understood that the navigation display information mentioned above can be content displayed during navigation, such as road information, driving direction, current vehicle speed, and current lane, etc., and this embodiment does not limit this. It should also be understood that the necessary display items mentioned above can be display items that, under the current eye gaze information, can be used for navigation and can reduce obstruction of the driver's line of sight.

[0172] Since the content displayed, whether on the head-up display or the vehicle's infotainment screen, can be overwhelming and distracting when the driver is not actively viewing the navigation, this embodiment addresses this issue. When the vehicle's infotainment system determines that the driver is not fatigued, it first determines the navigation information based on current interaction data. Then, it selects the necessary display items based on the driver's current gaze point and direction. Finally, it adjusts the navigation display information according to these necessary items and displays the navigation information accordingly.

[0173] For example, when the driver's current gaze point is in front of the road, it means that the driver already knows the navigation content. Therefore, the necessary display items can be to only retain the driving direction and the current speed. Then, the navigation display information on the head-up display (or the navigation display information on the vehicle screen) can only display the driving direction and the current speed, thereby reducing the amount of navigation information displayed and reducing obstruction to the driver's line of sight.

[0174] When the driver's current gaze is on the navigation information displayed on the head-up display (or the navigation information displayed on the vehicle's infotainment screen), it indicates that the driver is currently unaware of the navigation content and needs to check it. Therefore, the necessary display items can be detailed navigation content, such as road information, driving direction, current speed, and current lane. Then, the navigation information displayed on the head-up display (or the navigation information displayed on the vehicle's infotainment screen) can show the road information, driving direction, current speed, and current lane, thereby ensuring that the driver clearly understands the navigation and improving the driving experience.

[0175] Furthermore, to achieve the above objectives, this application also proposes a fatigue driving detection method, referring to... Figure 7 , Figure 7 This is a flowchart illustrating the fourth embodiment of the fatigue driving detection method of this application. The fourth embodiment of the fatigue driving detection method of this application is presented as follows: Figure 7 As shown, in this embodiment, the method is applied to a vehicle infotainment system connected to smart glasses, and the method includes:

[0176] Step S50: Receive the driver's current eye gaze information. The current eye gaze information is obtained by illuminating the driver's eyes through the infrared module of the smart glasses, capturing images of the driver's eyes after illumination, and obtaining the results based on the image capture.

[0177] Step S60: Based on the current eye gaze information, perform fatigue driving detection on the driver using a preset detection model, wherein the preset detection model is obtained by training with sample eye gaze information.

[0178] It should be emphasized that other embodiments or specific implementations of the fatigue driving detection method described in this application can refer to the embodiments of the first to third fatigue driving detection methods described above, and will not be repeated here.

[0179] Furthermore, in order for the vehicle system to accurately detect driver fatigue, the aforementioned step of detecting driver fatigue using a preset detection model based on the current eye gaze information, wherein the preset detection model is obtained through training with sample eye gaze information, includes:

[0180] Step S61: Obtain the current driving status of the vehicle, and perform fatigue driving detection on the driver based on the current eye gaze information and the current driving status using a preset detection model. The preset detection model is obtained by training with sample eye gaze information and sample driving status.

[0181] Furthermore, considering that when driver fatigue is detected, in order to remind the driver, this embodiment, after the step of detecting driver fatigue based on the current eye gaze information using a preset detection model, further includes:

[0182] Step S70: When it is determined that the driver is driving while fatigued, the driver is prompted according to the corresponding second preset prompt method.

[0183] Furthermore, after the above-mentioned step of detecting driver fatigue based on the current eye gaze information using a preset detection model, the method further includes:

[0184] Step S80: When it is determined that the driver is not driving while fatigued, the current interaction information of the vehicle is obtained; the current interaction information is adjusted according to the current eye gaze information, and the driver is interacted with according to the adjusted current interaction information.

[0185] Furthermore, when the aforementioned current interaction information is the car's head-up display, the steps of adjusting the current interaction information based on the current eye gaze information and interacting with the driver according to the adjusted current interaction information include:

[0186] The current display position of the head-up display is determined based on the current interaction information, and the corresponding adjustment direction and adjustment distance are determined based on the current eye gaze information; the current display position is adjusted according to the adjustment direction and adjustment distance, and the head-up display is displayed according to the adjusted current display position.

[0187] Furthermore, when the aforementioned current interaction information is the car's navigation display, the steps of adjusting the current interaction information based on the current eye gaze information and interacting with the driver according to the adjusted current interaction information include:

[0188] The navigation display information is determined based on the current interaction information, and the corresponding necessary display items are determined based on the current eye gaze information; the navigation display information is adjusted according to the necessary display items, and the navigation display is performed according to the adjusted navigation display information.

[0189] Furthermore, to achieve the above objectives, embodiments of this application also propose a smart glasses, the smart glasses comprising:

[0190] An infrared module is used to illuminate the driver's eyes;

[0191] The information acquisition module is used to acquire images of the driver's eyes after illumination and to obtain the driver's current eye gaze information based on the image acquisition results.

[0192] The information sending module is used to send the current eye gaze information to the vehicle system, so that the vehicle system can perform fatigue driving detection on the driver based on the current eye gaze information and a preset detection model. The preset detection model is obtained by training with sample eye gaze information.

[0193] It should be noted that the specific implementation of the smart glasses in this embodiment can also refer to the embodiments of the above method, and will not be repeated here.

[0194] In addition, to achieve the above objectives, this application also proposes a detection platform, which includes: smart glasses and a car equipped with a vehicle-mounted system, wherein the smart glasses are connected to the vehicle-mounted system;

[0195] The smart glasses are used to illuminate the driver's eyes using an infrared module; to capture images of the illuminated driver's eyes and obtain the driver's current eye gaze information based on the image capture results; and to send the current eye gaze information to the vehicle's infotainment system.

[0196] The vehicle system is used to detect driver fatigue based on the current eye gaze information using a preset detection model, which is obtained by training with sample eye gaze information.

[0197] It should be noted that the detection platform in this embodiment can be a platform composed of the aforementioned smart glasses and the vehicle's infotainment system. The specific implementation of the detection platform in this embodiment can also refer to the embodiments of the above method, which will not be repeated here.

[0198] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0199] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0200] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0201] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for detecting driver fatigue, characterized in that, The method is applied to smart glasses connected to a vehicle infotainment system, the smart glasses being equipped with an infrared module, the method comprising: The infrared module is used to illuminate the driver's eyes; Images of the driver's eyes after illumination are captured, and the driver's current eye gaze information is obtained based on the image capture results; The current eye gaze information is sent to the vehicle system so that the vehicle system can perform fatigue driving detection on the driver based on the current eye gaze information and a preset detection model. The preset detection model is obtained by training with sample eye gaze information.

2. The method as described in claim 1, characterized in that, The step of obtaining the driver's current eye gaze information based on the image acquisition results includes: The current gaze direction and the current gaze point position of the eyeball are determined based on the image acquisition results. The driver's current eye gaze information is obtained based on the current gaze point position and the current gaze direction.

3. The method as described in claim 2, characterized in that, The step of determining the current gaze direction and the current gaze point position of the eyeball based on the image acquisition results includes: The pupil coordinates of the eyeball and the coordinates of the reflection point of the preset reflection point in the eyeball are determined based on the image acquisition results. Based on the coordinates of the reflection point, the corneal curvature center of the eyeball is determined using a preset eyeball geometric model, and the current gaze direction of the eyeball is determined based on the pupil coordinates and the corneal curvature center. The size data of the image acquisition result is obtained, and the current gaze point position of the eyeball is determined based on the size data and the current gaze direction.

4. The method as described in claim 3, characterized in that, The step of determining the current gaze point position of the eyeball based on the size data and the current gaze direction includes: The width and height data of the image acquisition result are based on the size data; The horizontal coordinate of the current gaze point of the eyeball is determined based on the preset maximum optical axis vector, the current gaze direction, and the width data. The current gaze point ordinate of the eyeball is determined based on the preset maximum optical axis vector, the current gaze direction, and the height data. The current gaze point position of the eyeball is obtained based on the horizontal coordinate of the current gaze point and the vertical coordinate of the current gaze point.

5. The method as described in claim 3, characterized in that, Before the step of illuminating the driver's eyes using the infrared module, the method further includes: The eyeballs of the driver who is looking at the preset calibration point are collected to obtain calibration collection results, and the current optical axis direction vector of the eyeball is obtained based on the calibration collection results; Obtain the preset optical axis direction vector corresponding to the preset calibration point, and obtain the offset of the eyeball at the preset calibration point based on the current optical axis direction vector and the preset optical axis direction vector; The offset at the preset calibration point is interpolated according to a preset polynomial. The step of determining the current gaze direction of the eyeball based on the pupil coordinates and the corneal curvature center includes: The initial gaze direction of the eyeball is determined based on the pupil coordinates and the corneal curvature center, and the visual axis is corrected by interpolation to obtain the current gaze direction of the eyeball.

6. The method as described in claim 5, characterized in that, After the step of collecting data from the driver's eyes fixed on the preset calibration point and obtaining the calibration data acquisition results, the method further includes: Based on the calibration acquisition results, determine the driver's eye gaze information at the preset calibration point; Stability analysis was performed on the calibrated eye gaze information; If the stability analysis results do not meet the preset stability requirements, the preset calibration point is adjusted, and the process returns to the step of collecting data on the driver's eyeballs focused on the preset calibration point.

7. The method according to any one of claims 1 to 6, characterized in that, The smart glasses are equipped with a detection component, and the step of illuminating the driver's eyes using the infrared module includes: The current wearing status of the smart glasses is detected using the detection component; When the current wearing state is "wearing", the infrared module is used to illuminate the driver's eyes.

8. A method for detecting driver fatigue, characterized in that, The method is applied to an in-vehicle infotainment system connected to smart glasses, and the method includes: The system receives the driver's current eye gaze information, which is then used to illuminate the driver's eyes via the infrared module of the smart glasses. An image of the illuminated driver's eyes is then captured, and the results are obtained based on the image capture. Based on the current eye gaze information, fatigue driving detection is performed on the driver using a preset detection model, which is obtained by training with sample eye gaze information.

9. A type of smart glasses, characterized in that, The smart glasses include: An infrared module is used to illuminate the driver's eyes; The information acquisition module is used to acquire images of the driver's eyes after illumination and to obtain the driver's current eye gaze information based on the image acquisition results. The information sending module is used to send the current eye gaze information to the vehicle system, so that the vehicle system can perform fatigue driving detection on the driver based on the current eye gaze information and a preset detection model. The preset detection model is obtained by training with sample eye gaze information.

10. A detection platform, characterized in that, The detection platform includes: smart glasses and a car equipped with a vehicle-mounted infotainment system, wherein the smart glasses are connected to the vehicle-mounted infotainment system; The smart glasses are used to illuminate the driver's eyes using an infrared module; to capture images of the illuminated driver's eyes and obtain the driver's current eye gaze information based on the image capture results; and to send the current eye gaze information to the vehicle's infotainment system. The vehicle system is used to detect driver fatigue based on the current eye gaze information using a preset detection model, which is obtained by training with sample eye gaze information.

Images