Human eye state detection method and device

Abstract

The invention relates to a human eye state detection method and device, and belongs to the technical field of intelligent cabin perception, and the detection method comprises the steps: obtaining an eye opening degree value of a driver through the eye opening feature information of the driver, obtaining a standard eye opening degree value according to the eye opening feature information of a standard human face, obtaining a threshold value adjustment factor through the driver eye opening degree value and the standard eye opening degree value, obtaining a target opening degree threshold value according to the threshold value adjustment factor and a preset standard opening degree threshold value, and obtaining a real-time opening degree value based on the real-time eye feature information of the driver. The eye state of the driver is determined according to the real-time opening degree value and the target opening degree threshold value; according to the method, the eye feature information of the driver and the eye feature information of the standard face are combined, the target opening degree threshold value is adjusted, the eye state is judged based on the target opening degree threshold value, the situations of missing detection and error detection caused by the size of the eyes can be effectively avoided, and therefore the detection accuracy of the eye state is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent cockpit perception technology, and in particular to a method and device for detecting human eye status. Background Art

[0002] At present, the proportion of traffic accidents caused by fatigue driving or distracted driving during long-distance driving remains high. Strengthening the monitoring of the driver's status and reminding the driver to maintain a safe driving state has become an effective means to reduce traffic accidents. In recent years, the intelligent cockpit has developed rapidly, among which the driver status monitoring system is a popular development direction. The system mainly monitors the driver's status in real time and promptly reminds the driver when an abnormal state is detected to ensure the life and property safety of the driver and passengers. Human eye status detection is one of the important technologies of the driver status monitoring system. This technology provides basic information for driver status judgment through real-time monitoring of the human eye status. Therefore, the accuracy of human eye status detection is one of the important indicators to measure the performance of the entire driver status monitoring system.

[0003] Most of the human eye state detection in the prior art is based on a fixed threshold, which can be one or a set of values. The main problem with the prior art is that since drivers have different sizes of eyes, using a fixed threshold to determine the eye states of different drivers will cause inaccurate detection. Summary of the invention

[0004] To this end, the present invention provides a method and device for detecting the state of a human eye, so as to solve the problem of inaccurate detection caused by setting a threshold value as a fixed value in the existing human eye state detection and judging the eye states of different drivers based on the fixed threshold value.

[0005] In a first aspect, a method for detecting a human eye state is provided, the method comprising:

[0006] Obtaining the driver's eye opening degree value according to the driver's eye opening characteristic information; the eye opening characteristic information includes: the maximum height between the upper and lower eyelids and the length from the inner canthus to the outer canthus when the human eye is opened to the maximum state;

[0007] Obtaining a standard eye opening degree value based on eye opening feature information of a standard face; the standard face is facial feature information fitted based on a preset number of face data;

[0008] Obtaining a threshold adjustment factor according to the driver's eye opening degree value and the standard eye opening degree value;

[0009] A target opening degree threshold is obtained according to the threshold adjustment factor and a preset standard opening degree threshold; the preset standard opening degree threshold is a threshold set according to the eye opening degree of the standard human face, and is used to determine the eye state of the standard human face;

[0010] A real-time eye opening value is obtained based on the real-time eye feature information of the driver, and the driver's eye state is determined based on the real-time eye opening value and the target eye opening threshold; the eye state includes an open eye state and a closed eye state.

[0011] Furthermore, obtaining the driver's eye opening degree value based on the driver's eye opening characteristic information includes:

[0012] Based on the maximum height between the upper and lower eyelids and the length from the inner canthus to the outer canthus when the driver's eyes are opened to the maximum, the opening and closing value of the driver's eyes is obtained by the opening and closing value calculation formula, and the opening and closing value calculation formula is:

[0013] EAR=H / W;

[0014] Among them, EAR is the opening value; H is the maximum height between the upper and lower eyelids; W is the length from the inner canthus to the outer canthus.

[0015] Furthermore, obtaining a standard eye opening degree value based on the eye opening feature information of a standard face includes:

[0016] Based on the maximum height between the upper and lower eyelids and the length from the inner canthus to the outer canthus when the eyes are opened to the maximum in the standard human face, the standard eye opening degree value is obtained by the opening degree value calculation formula.

[0017] Furthermore, obtaining a threshold adjustment factor according to the driver's eye opening degree value and the standard eye opening degree value includes:

[0018] Based on the driver's eye opening degree value and the standard eye opening degree value, a threshold adjustment factor is obtained by an adjustment formula, and the adjustment formula is:

[0019] R = EAR2 / EAR1;

[0020] Among them, R is the threshold adjustment factor; EAR2 is the driver's eye opening degree value; EAR1 is the standard eye opening degree value.

[0021] Furthermore, obtaining the target opening degree threshold value according to the threshold adjustment factor and the preset standard opening degree threshold value includes:

[0022] Based on the threshold adjustment factor and the preset standard opening degree threshold, the target opening degree threshold is obtained by a target threshold formula, and the target threshold formula is:

[0023] T = T0 × R;

[0024] Among them, T is the target opening and closing degree threshold; T0 is the preset standard opening and closing degree threshold; R is the threshold adjustment factor.

[0025] Furthermore, obtaining a real-time eye opening value according to the real-time eye feature information of the driver, and determining the eye state of the driver according to the real-time eye opening value and the target eye opening threshold, includes:

[0026] Acquire the height between the upper and lower eyelids and the length from the inner canthus to the outer canthus of the driver's eyes in real time, and obtain the real-time opening and closing value of the driver through the opening and closing value calculation formula;

[0027] If the real-time opening degree value is greater than or equal to the target opening degree threshold, the driver's eyes are in an open state;

[0028] If the real-time opening degree value is less than the target opening degree threshold, the driver's eyes are in a closed state.

[0029] Furthermore, the real-time acquisition of the height between the upper and lower eyelids and the length from the inner canthus to the outer canthus of the driver's eyes, and the real-time opening and closing value of the driver obtained by the opening and closing value calculation formula include:

[0030] Acquire in real time the height between the upper and lower eyelids of the left and right eyes of the driver and the length from the inner canthus to the outer canthus;

[0031] The real-time opening and closing value of the left eye and the real-time opening and closing value of the right eye of the driver are obtained respectively by the opening and closing value calculation formula;

[0032] The real-time opening and closing degree value of the left eye and the real-time opening and closing degree value of the right eye are averaged to obtain the real-time opening and closing degree value.

[0033] Furthermore, the real-time acquisition of the height between the upper and lower eyelids and the length from the inner canthus to the outer canthus of the driver's eyes, and the real-time opening and closing value of the driver obtained by the opening and closing value calculation formula include:

[0034] Acquire in real time the height between the upper and lower eyelids of the left and right eyes of the driver and the length from the inner canthus to the outer canthus;

[0035] The real-time opening and closing value of the left eye and the real-time opening and closing value of the right eye of the driver are obtained respectively by the opening and closing value calculation formula;

[0036] The smaller value between the left eye real-time opening and closing degree value and the right eye real-time opening and closing degree value is taken as the real-time opening and closing degree value.

[0037] Furthermore, it also includes:

[0038] The driver is monitored by video in real time, and one frame of the video is extracted at every preset time interval to detect the eye state. If the eye state is detected to be closed for a preset number of consecutive times, it is determined to be fatigue driving.

[0039] In a second aspect, a device for detecting a human eye state is provided, the device comprising:

[0040] The driver's eye opening degree module is used to obtain the driver's eye opening degree value according to the driver's eye opening characteristic information; the eye opening characteristic information includes: the maximum height between the upper and lower eyelids when the human eye is opened to the maximum state and the length from the inner canthus to the outer canthus;

[0041] A standard eye opening degree module is used to obtain a standard eye opening degree value based on the eye opening feature information of a standard human face; the standard human face is facial feature information fitted based on a preset number of human face data;

[0042] An adjustment factor module, used for obtaining a threshold adjustment factor according to the driver's eye opening degree value and the standard eye opening degree value;

[0043] A target threshold module, used to obtain a target opening degree threshold according to the threshold adjustment factor and a preset standard opening degree threshold; the preset standard opening degree threshold is a threshold set according to the eye opening degree of the standard human face, and is used to determine the eye state of the standard human face;

[0044] The detection module is used to obtain a real-time opening and closing value based on the real-time eye feature information of the driver, and determine the driver's eye state based on the real-time opening and closing value and the target opening and closing threshold; the eye state includes an open eye state and a closed eye state.

[0045] The present invention adopts the above technical solution and has at least the following beneficial effects:

[0046] Provided are a method and device for detecting the state of human eyes. The method comprises obtaining the eye opening degree value of the driver through the eye opening characteristic information of the driver, obtaining the standard eye opening degree value according to the eye opening characteristic information of a standard human face, obtaining a threshold adjustment factor through the eye opening degree value of the driver and the standard eye opening degree value, obtaining a target opening degree threshold according to the threshold adjustment factor and a preset standard opening degree threshold, obtaining a real-time opening degree value based on the real-time eye characteristic information of the driver, and determining the eye state of the driver according to the real-time opening degree value and the target opening degree threshold. In the present invention, the eye characteristic information of the driver and the eye characteristic information of the standard human face are combined to adjust the target opening degree threshold, and the eye state is determined based on the target opening degree threshold, which can effectively avoid missed detection and wrong detection due to the size of the eyes, thereby improving the detection accuracy of the human eye state.

[0047] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 is a flow chart of a method for detecting a human eye state shown in an exemplary embodiment of the present invention;

[0050] Figure 2 It is a schematic block diagram of a device for detecting a human eye state shown in an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] Problems with existing technologies: Currently, most of the eye state detection in driver state monitoring systems is based on fixed threshold judgments. The threshold cannot be changed according to the eye information of each driver. Using a fixed threshold to judge the eye state of different drivers often results in missed detections or false detections due to differences in eye shapes and sizes. For example, if the driver has small eyes, using a fixed threshold to judge will result in a closed state even if the driver opens his eyes as wide as possible.

[0053] The embodiment of the present application provides a method and device for detecting the state of a human eye, wherein the driver's eye opening degree value is obtained through the driver's eye opening feature information, the standard eye opening degree value is obtained according to the eye opening feature information of a standard human face, the threshold adjustment factor is obtained through the driver's eye opening degree value and the standard eye opening degree value, the target opening degree threshold is obtained according to the threshold adjustment factor and a preset standard opening degree threshold, the real-time opening degree value is obtained based on the driver's real-time eye feature information, and the driver's eye state is determined according to the real-time opening degree value and the target opening degree threshold; in the present invention, the driver's eye feature information and the standard human face's eye feature information are combined to adjust the target opening degree threshold, and the eye state is determined based on the target opening degree threshold, so that the detection is targeted and the detection accuracy of the human eye state can be effectively improved.

[0054] See also Figure 1 , Figure 1 is a flow chart of a method for detecting the state of human eyes shown in an exemplary embodiment of the present invention, see Figure 1 , the method comprising:

[0055] Step S11, obtaining the driver's eye opening degree value according to the driver's eye opening characteristic information; the eye opening characteristic information includes: the maximum height between the upper and lower eyelids when the human eye is opened to the maximum state and the length from the inner canthus to the outer canthus;

[0056] Step S12, obtaining a standard eye opening degree value according to the eye opening characteristic information of a standard face; the standard face is facial characteristic information fitted according to a preset number of face data;

[0057] Step S13, obtaining a threshold adjustment factor according to the driver's eye opening degree value and a standard eye opening degree value;

[0058] Step S14, obtaining a target eye opening threshold value according to the threshold adjustment factor and the preset standard eye opening threshold value; the preset standard eye opening threshold value is a threshold value set according to the eye opening degree of a standard human face, and is used to determine the eye state of the standard human face;

[0059] Step S15, obtaining a real-time eye opening value based on the real-time eye feature information of the driver, and determining the driver's eye state based on the real-time eye opening value and a target eye opening threshold; the eye state includes an open eye state and a closed eye state.

[0060] It should be noted that the technical solution provided in this embodiment can be loaded into the driver status detection system in the form of a small program in specific practice, or can be used as an independent application to realize human eye status detection. Applicable scenarios include but are not limited to: automobile smart cockpit perception, ship smart cockpit perception and other functional scenarios that require human eye status detection.

[0061] Specifically, the preset amount of facial data can be set according to the accuracy of eye state detection, or can be set according to business requirements. For example, the higher the eye state detection accuracy requirement, the greater the preset amount of facial data.

[0062] It should be noted that the preset standard opening and closing degree threshold can be set by human experience; it can also be obtained through model learning.

[0063] It can be understood that the detection method provided in this embodiment obtains the driver's eye opening degree value through the driver's eye opening feature information, obtains the standard eye opening degree value based on the eye opening feature information of a standard human face, obtains the threshold adjustment factor through the driver's eye opening degree value and the standard eye opening degree value, obtains the target opening degree threshold based on the threshold adjustment factor and the preset standard opening degree threshold, obtains the real-time opening degree value based on the driver's real-time eye feature information, and determines the driver's eye state based on the real-time opening degree value and the target opening degree threshold; in the present invention, the target opening degree threshold is adjusted based on the driver's eye feature information and the eye feature information of a standard human face, and the eye state is determined based on the target opening degree threshold, which can effectively avoid missed detection and false detection due to eye size, thereby improving the detection accuracy of the human eye state.

[0064] In specific practice, step S11 "obtaining the driver's eye opening degree value based on the driver's eye opening characteristic information" includes: based on the maximum height between the upper and lower eyelids and the length from the inner canthus to the outer canthus when the driver's eyes are open to the maximum state, obtaining the driver's eye opening degree value through the opening degree value calculation formula, and the opening degree value calculation formula is:

[0065] EAR=H / W;

[0066] Among them, EAR is the opening value; H is the maximum height between the upper and lower eyelids; W is the length from the inner canthus to the outer canthus.

[0067] It should be noted that the driver's driving status is detected through video, the facial area is identified, and the height between the upper and lower eyelids and the length from the inner canthus to the outer canthus of the driver's eyes are compared frame by frame. After several blinking cycles of comparison, the maximum height between the upper and lower eyelids and the length from the inner canthus to the outer canthus when the driver's eyes are open to the maximum are obtained.

[0068] In specific practice, step S12 "obtaining a standard eye opening degree value based on the eye opening feature information of a standard human face" includes: based on the maximum height between the upper and lower eyelids and the length from the inner canthus to the outer canthus when the eyes of the standard human face are opened to the maximum state, obtaining the standard eye opening degree value through the opening degree value calculation formula.

[0069] In specific practice, step S13 "obtaining a threshold adjustment factor based on the driver's eye opening degree value and the standard eye opening degree value" includes: based on the driver's eye opening degree value and the standard eye opening degree value, obtaining the threshold adjustment factor through an adjustment formula, the adjustment formula is:

[0070] R = EAR2 / EAR1;

[0071] Among them, R is the threshold adjustment factor; EAR2 is the driver's eye opening degree value; EAR1 is the standard eye opening degree value.

[0072] It can be understood that the detection method provided in this embodiment combines the driver's eye feature information and the eye feature information of a standard face, adjusts the target opening and closing degree threshold, and determines the eye state based on the target opening and closing degree threshold, which can effectively improve the detection accuracy of the human eye state.

[0073] In specific practice, step S14 "obtaining a target opening degree threshold according to a threshold adjustment factor and a preset standard opening degree threshold" includes: obtaining a target opening degree threshold by a target threshold formula based on the threshold adjustment factor and the preset standard opening degree threshold, and the target threshold formula is:

[0074] T = T0 × R;

[0075] Among them, T is the target opening and closing degree threshold; T0 is the preset standard opening and closing degree threshold; R is the threshold adjustment factor.

[0076] In specific practice, step S15 "obtaining a real-time opening and closing value based on the real-time eye feature information of the driver, and determining the driver's eye state based on the real-time opening and closing value and the target opening and closing threshold" includes: obtaining the height between the upper and lower eyelids and the length from the inner canthus to the outer canthus of the driver's eyes in real time, and obtaining the driver's real-time opening and closing value through the opening and closing value calculation formula; if the real-time opening and closing value is greater than or equal to the target opening and closing threshold, the driver's eye state is open; if the real-time opening and closing value is less than the target opening and closing threshold, the driver's eye state is closed.

[0077] Specifically, the height between the upper and lower eyelids of the driver's left and right eyes and the length from the inner canthus to the outer canthus are obtained in real time; the real-time opening and closing value of the driver's left eye and the real-time opening and closing value of the right eye are obtained respectively through the opening and closing value calculation formula; the real-time opening and closing value of the left eye and the real-time opening and closing value of the right eye are averaged to obtain the real-time opening and closing value, or the smaller value of the real-time opening and closing value of the left eye and the real-time opening and closing value of the right eye is taken as the real-time opening and closing value.

[0078] In specific practice, it also includes: real-time video monitoring of the driver, extracting a frame from the video at every preset time interval to detect the eye state, and if it is detected that the eyes are closed for a preset number of consecutive times, it is determined to be fatigue driving.

[0079] It should be noted that the preset time interval and the preset number of times can be specifically set according to the accuracy of human eye state detection.

[0080] In a specific embodiment, face recognition is performed to determine the number and position information of faces in an image, and then key point detection is performed on each face region to obtain key point information of the eye region. Then, a logical judgment of the eye state is performed. The complete process is as follows:

[0081] Step S21, identifying the face area.

[0082] Step S22: Detect key point information of the face area.

[0083] Step S23, determine whether the driver has been recorded based on the key point information. If not, use the driver's facial feature information (eyes open) when the vehicle is just started and driving in a straight line as the standard facial feature information of the driver's normal driving, and record and save it (what is saved is the n-dimensional vector, not the facial image) and perform the following steps. If it has been recorded, jump directly to the step S26 each frame human eye state judgment process.

[0084] Step S24: compare the standard facial feature information of the driver with the feature information of the default standard face (the standard face fitted by big data, in a normal open-eye state) to determine the difference between the driver's eye size and the standard face. The specific comparison method is as follows:

[0085] Step S241, using the eye opening degree calculation formula to calculate the eye opening degree values ​​of the left and right eyes in the standard face image respectively, and then taking the average value to obtain the standard eye opening degree value.

[0086] Step S242: Calculate the eye opening and closing values ​​of the driver's left and right eyes respectively using the eye opening and closing value calculation formula, and then take the average value to obtain the eye opening and closing value of the driver.

[0087] Step S243: Based on the standard eye opening degree value and the driver's eye opening degree value, a threshold adjustment factor is calculated using an adjustment formula.

[0088] Step S25: multiply the preset standard opening / closing degree threshold by the threshold adjustment factor to obtain the target opening / closing degree threshold.

[0089] Step S26: Save the target opening and closing degree threshold as the inherent attribute of the driver, which is used for judging the human eye state of the driver in each subsequent frame. The specific human eye state judgment process is as follows:

[0090] Step S261, respectively calculating the opening and closing values ​​of the left and right eyes in a frame of image acquired in real time, and then taking the average value to obtain the real-time opening and closing value.

[0091] Step S262: If the real-time opening degree value is greater than or equal to the target opening degree threshold, the driver's eyes are in an open state; if the real-time opening degree value is less than the target opening degree threshold, the driver's eyes are in a closed state.

[0092] See also Figure 2 , Figure 2 is a schematic block diagram of a device for detecting the state of human eyes according to an exemplary embodiment of the present invention, see Figure 2 , the human eye state detection device 100 comprises:

[0093] The driver's eye opening degree module 101 is used to obtain the driver's eye opening degree value according to the driver's eye opening characteristic information; the eye opening characteristic information includes: the maximum height between the upper and lower eyelids when the human eye is opened to the maximum state and the length from the inner canthus to the outer canthus;

[0094] The standard eye opening degree module 102 is used to obtain the standard eye opening degree value according to the eye opening characteristic information of the standard face; the standard face is the facial characteristic information fitted according to the preset number of face data;

[0095] An adjustment factor module 103 is used to obtain a threshold adjustment factor according to the driver's eye opening degree value and a standard eye opening degree value;

[0096] The adjustment factor module 104 is used to obtain a target eye opening threshold according to the threshold adjustment factor and a preset standard eye opening threshold; the preset standard eye opening threshold is a threshold set according to the eye opening degree of a standard human face, and is used to determine the eye state of the standard human face;

[0097] The adjustment factor module 105 is used to obtain a real-time eye opening value according to the real-time eye feature information of the driver, and determine the driver's eye state according to the real-time eye opening value and the target eye opening threshold; the eye state includes an open eye state and a closed eye state.

[0098] It should be noted that the technical solution provided in this embodiment can be applied in specific practice to scenarios including but not limited to: automobile intelligent cockpit perception, ship intelligent cockpit perception and other functional scenarios that require human eye status detection.

[0099] Specifically, the preset amount of facial data can be set according to the accuracy of eye state detection, or can be set according to business requirements. For example, the higher the eye state detection accuracy requirement, the greater the preset amount of facial data.

[0100] It should be noted that the preset standard opening and closing degree threshold can be set by human experience; it can also be obtained through model learning.

[0101] It can be understood that the detection device provided in the present embodiment obtains the eye opening degree value of the driver through the eye opening feature information of the driver, obtains the standard eye opening degree value according to the eye opening feature information of a standard human face, obtains the threshold adjustment factor through the eye opening degree value of the driver and the standard eye opening degree value, obtains the target opening degree threshold according to the threshold adjustment factor and the preset standard opening degree threshold, obtains the real-time opening degree value based on the real-time eye feature information of the driver, and determines the driver's eye state according to the real-time opening degree value and the target opening degree threshold; in the present invention, the target opening degree threshold is adjusted based on the driver's eye feature information and the eye feature information of a standard human face, and the eye state is determined based on the target opening degree threshold, which can effectively avoid missed detection and false detection due to eye size, thereby improving the detection accuracy of the human eye state.

[0102] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

[0103] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0104] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0105] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for detecting human eye status, characterized in that: The method comprises: Obtaining the driver's eye opening degree value according to the driver's eye opening characteristic information; the eye opening characteristic information includes: the maximum height between the upper and lower eyelids and the length from the inner canthus to the outer canthus when the human eye is opened to the maximum state; Obtaining a standard eye opening degree value based on eye opening feature information of a standard face; the standard face is facial feature information fitted based on a preset number of face data; Obtaining a threshold adjustment factor according to the driver's eye opening degree value and the standard eye opening degree value; A target opening degree threshold is obtained according to the threshold adjustment factor and a preset standard opening degree threshold; the preset standard opening degree threshold is a threshold set according to the eye opening degree of the standard human face, and is used to determine the eye state of the standard human face; A real-time eye opening value is obtained based on the real-time eye feature information of the driver, and the driver's eye state is determined based on the real-time eye opening value and the target eye opening threshold; the eye state includes an open eye state and a closed eye state.

2. The detection method according to claim 1, characterized in that: The method of obtaining the driver's eye opening degree value according to the driver's eye opening characteristic information includes: Based on the maximum height between the upper and lower eyelids and the length from the inner canthus to the outer canthus when the driver's eyes are opened to the maximum, the opening and closing value of the driver's eyes is obtained by the opening and closing value calculation formula, and the opening and closing value calculation formula is: EAR=H / W; Among them, EAR is the opening value; H is the maximum height between the upper and lower eyelids; W is the length from the inner canthus to the outer canthus.

3. The detection method according to claim 2, characterized in that: The method of obtaining the standard eye opening degree value based on the eye opening feature information of the standard face includes: Based on the maximum height between the upper and lower eyelids and the length from the inner canthus to the outer canthus when the eyes are opened to the maximum in the standard human face, the standard eye opening degree value is obtained by the opening degree value calculation formula.

4. The detection method according to claim 1, characterized in that: The threshold adjustment factor is obtained according to the driver's eye opening degree value and the standard eye opening degree value, including: Based on the driver's eye opening degree value and the standard eye opening degree value, a threshold adjustment factor is obtained by an adjustment formula, and the adjustment formula is: R = EAR2 / EAR1; Among them, R is the threshold adjustment factor; EAR2 is the driver's eye opening degree value; EAR1 is the standard eye opening degree value.

5. The detection method according to claim 1, characterized in that: Obtaining the target opening degree threshold value according to the threshold adjustment factor and the preset standard opening degree threshold value includes: Based on the threshold adjustment factor and the preset standard opening degree threshold, the target opening degree threshold is obtained by a target threshold formula, and the target threshold formula is: T = T0 × R; Among them, T is the target opening and closing degree threshold; T0 is the preset standard opening and closing degree threshold; R is the threshold adjustment factor.

6. The detection method according to claim 2, characterized in that: The step of obtaining a real-time eye opening value according to the real-time eye feature information of the driver, and determining the eye state of the driver according to the real-time eye opening value and the target eye opening threshold comprises: Acquire the height between the upper and lower eyelids and the length from the inner canthus to the outer canthus of the driver's eyes in real time, and obtain the real-time opening and closing value of the driver through the opening and closing value calculation formula; If the real-time opening degree value is greater than or equal to the target opening degree threshold, the driver's eyes are in an open state; If the real-time opening degree value is less than the target opening degree threshold, the driver's eyes are in a closed state.

7. The detection method according to claim 6, characterized in that: The real-time acquisition of the height between the upper and lower eyelids and the length from the inner canthus to the outer canthus of the driver's eyes, and the real-time opening and closing value of the driver obtained by the opening and closing value calculation formula, includes: Acquire in real time the height between the upper and lower eyelids of the left and right eyes of the driver and the length from the inner canthus to the outer canthus; The real-time opening and closing value of the left eye and the real-time opening and closing value of the right eye of the driver are obtained respectively by the opening and closing value calculation formula; The real-time opening and closing degree value of the left eye and the real-time opening and closing degree value of the right eye are averaged to obtain the real-time opening and closing degree value.

8. The detection method according to claim 6, characterized in that: The real-time acquisition of the height between the upper and lower eyelids and the length from the inner canthus to the outer canthus of the driver's eyes, and the real-time opening and closing value of the driver obtained by the opening and closing value calculation formula, includes: Acquire in real time the height between the upper and lower eyelids of the left and right eyes of the driver and the length from the inner canthus to the outer canthus; The real-time opening and closing value of the left eye and the real-time opening and closing value of the right eye of the driver are obtained respectively by the opening and closing value calculation formula; The smaller value between the left eye real-time opening and closing degree value and the right eye real-time opening and closing degree value is taken as the real-time opening and closing degree value.

9. The detection method according to claim 1, characterized in that: Also includes: The driver is monitored by video in real time, and one frame of the video is extracted at every preset time interval to detect the eye state. If it is detected that the eyes are closed for a preset number of consecutive times, it is determined to be fatigue driving.

10. A device for detecting human eye status, characterized in that: The device comprises: The driver's eye opening degree module is used to obtain the driver's eye opening degree value according to the driver's eye opening characteristic information; the eye opening characteristic information includes: the maximum height between the upper and lower eyelids when the human eye is opened to the maximum state and the length from the inner canthus to the outer canthus; A standard eye opening degree module is used to obtain a standard eye opening degree value based on the eye opening feature information of a standard face; the standard face is facial feature information fitted based on a preset number of face data; An adjustment factor module, used for obtaining a threshold adjustment factor according to the driver's eye opening degree value and the standard eye opening degree value; a target threshold module, used to obtain a target opening degree threshold according to the threshold adjustment factor and a preset standard opening degree threshold; the preset standard opening degree threshold is a threshold set according to the eye opening degree of the standard human face, and is used to determine the eye state of the standard human face; The detection module is used to obtain a real-time opening and closing value based on the real-time eye feature information of the driver, and determine the driver's eye state based on the real-time opening and closing value and the target opening and closing threshold; the eye state includes an open eye state and a closed eye state.

Images