CN118115978A

CN118115978A - Driver trust degree detection method and device, electronic equipment and storage medium

Info

Publication number: CN118115978A
Application number: CN202410254306.3A
Authority: CN
Inventors: 黄浩; 李清坤; 陈诚; 马翠霞; 王宏安
Original assignee: Chongqing Zhongke Automobile Software Innovation Center
Current assignee: Chongqing Zhongke Automobile Software Innovation Center
Priority date: 2024-03-06
Filing date: 2024-03-06
Publication date: 2024-05-31

Abstract

The embodiment of the invention relates to a driver trust detection method, a device, electronic equipment and a storage medium, wherein a video clip of a first preset duration is acquired based on a vehicle-mounted camera, and the video clip comprises a plurality of face images of a driver; extracting face key points on each face image, and determining the face area corresponding to each face image based on the face key points; if the number of the face images with the face area not smaller than the preset area exceeds the first preset number, determining the eye key point of each face image, and determining the eye aspect ratio corresponding to each face image according to the eye key point; outputting reminding information of the driver over-trust automatic driving system if the duration corresponding to the continuous face images with the eye aspect ratio smaller than the preset threshold value exceeds the second preset duration; and estimating the trust degree of the driver in the CAD scene in real time through the face key points and the eye key points in the acquired face image of the driver.

Description

Driver trust degree detection method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of automatic driving, and in particular, to a method and apparatus for detecting driver confidence, an electronic device, and a storage medium.

Background

In the driving scenario of a conditional automatic driving (Conditionally Automated Driving, abbreviated as CAD) system, in order to prevent the driver from over-trust of the CAD system, it is necessary to detect the driver's confidence level in real time.

In the related art, the detection mode of the driver's trust degree is mainly divided into a detection mode based on a subjective scale and a detection mode based on a physiological signal, but the former has strong invasiveness to the driver due to the adoption of a questionnaire mode, is bad in real-time performance and is unfavorable for real-time detection, and the latter needs the driver to be provided with a corresponding physiological signal detector to influence driving experience, and the acquired signal has large deviation and lacks stability, so that false detection or omission detection of the driver's trust degree is easy to cause.

Disclosure of Invention

The invention provides a driver trust degree detection method, a device, electronic equipment and a storage medium, which are used for solving the technical problem that false detection or omission of driver trust degree is easy to occur in real-time detection in an automatic driving process.

In a first aspect, the present invention provides a driver confidence level detection method, including: acquiring a video clip with a first preset duration based on a vehicle-mounted camera, wherein the video clip comprises a plurality of face images of a driver; extracting face key points on each face image, and determining the face area corresponding to each face image based on the face key points; if the number of the face images with the face area not smaller than the preset area exceeds the first preset number, determining the eye key point of each face image, and determining the eye aspect ratio corresponding to each face image according to the eye key point; and if the duration corresponding to the continuous face images with the eye aspect ratio smaller than the preset threshold value exceeds the second preset duration, outputting the reminding information of the driver over-trust automatic driving system.

In some embodiments, the method further comprises: if the number of the face images with the face area smaller than the preset area exceeds the first preset number, determining the face rotation angle of each face image; and if the face rotation angle is larger than the preset angle, outputting reminding information of the driver over-trust automatic driving system.

In some embodiments, the determining the face area corresponding to each face image based on the face keypoints includes: determining the maximum abscissa, the minimum abscissa, the maximum ordinate and the minimum ordinate of each face key point in each face image; and determining the face area of the corresponding face image based on the maximum abscissa, the minimum abscissa, the maximum ordinate and the minimum ordinate.

In some embodiments, the face area is calculated as follows:

S₁＝|X_min-X_max|×|Y_min-Y_max|

wherein S ₁ represents the face area, X _min represents the minimum abscissa, X _max represents the maximum abscissa, Y _min represents the minimum ordinate, and Y _max represents the maximum ordinate.

In some embodiments, the method further comprises: acquiring a front face image of a driver based on a vehicle-mounted camera; and recognizing a frontal face area in the frontal face image, and determining the minimum circumscribed rectangular area of the frontal face area as the preset area.

In some embodiments, the capturing, based on the vehicle-mounted camera, a video clip of a first preset duration, where the video clip includes a plurality of face images of the driver, and then further includes: screening a plurality of face images of the driver according to a preset screening rule; and if the number of the face images after screening exceeds the second preset number, executing the step of extracting the face key points on each face image.

In a second aspect, an embodiment of the present invention provides a driver confidence level detection device, including: the image acquisition module is used for acquiring video clips of a first preset duration based on the vehicle-mounted camera, wherein the video clips comprise a plurality of face images of a driver; the face area calculation module is used for extracting face key points on each face image and determining the face area corresponding to each face image based on the face key points; the trust degree detection module is used for determining the eye key point of each face image if the number of the face images with the face area not smaller than the preset area exceeds the first preset number, and determining the eye aspect ratio corresponding to each face image according to the eye key point; the confidence level output module is used for outputting reminding information of the driver over-confidence automatic driving system if the duration time corresponding to the continuous face images with the eye aspect ratio smaller than the preset threshold value exceeds the second preset duration time.

In some embodiments, the confidence detection module is further configured to determine a face rotation angle of each face image if the number of face images with a face area smaller than the preset area exceeds the first preset number; the trust degree output module is further used for outputting reminding information of the driver over-trust automatic driving system if the face rotation angle is larger than a preset angle.

In a third aspect, the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus; a memory for storing a computer program; and a processor for implementing the steps of the driver confidence level detection method according to any one of the first aspect when executing the program stored in the memory.

In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the driver confidence detection method according to any of the first aspects.

The driver trust degree detection method, the device, the electronic equipment and the storage medium provided by the embodiment of the invention acquire video clips of a first preset duration based on a vehicle-mounted camera, wherein the video clips comprise a plurality of face images of a driver; extracting face key points on each face image, and determining the face area corresponding to each face image based on the face key points; if the number of the face images with the face area not smaller than the preset area exceeds the first preset number, determining the eye key point of each face image, and determining the eye aspect ratio corresponding to each face image according to the eye key point; outputting reminding information of the driver over-trust automatic driving system if the duration corresponding to the continuous face images with the eye aspect ratio smaller than the preset threshold value exceeds the second preset duration; the embodiment of the invention estimates the trust degree of the driver in real time through the face key points and the eye key points in the collected face images of the driver, is not easy to miss detection and misdetection, completes the face image collection by utilizing the vehicle-mounted camera, has a simple collection mode, does not need any equipment to be worn by the driver, and improves the driving experience.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to a person skilled in the art that other drawings can be obtained from these drawings without inventive effort.

Fig. 1 is a schematic flow chart of a driver confidence level detection method according to an embodiment of the present invention;

Fig. 2 is a flow chart of another driver confidence level detection method according to an embodiment of the present invention;

Fig. 3 is a schematic flow chart of another driver confidence level detection method according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of a driver confidence level detection device according to an embodiment of the present invention;

Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

First, the terms involved in the present invention will be explained:

eye aspect ratio (EYE ASPECT Radio, EAR for short): refers to the ratio between the eye height and width. The corresponding EAR values are different when the eye is open and closed.

Conditional automatic driving (Conditionally automated driving, CAD) system: refers to a system that is capable of implementing an autopilot function under certain conditions, but still requires the driver to take over control of the vehicle when needed. The confidence level is an important index of the CAD system, including the trust of the driver on the CAD system and the trust of the CAD system on the driver. The driver believes that the CAD system can effectively control the vehicle under specific conditions and can respond to different traffic conditions and road conditions in time, and if the driver lacks trust on the CAD, the driver may excessively intervene or be unwilling to use an automatic driving function, so that the performance and benefit of the CAD system are affected; the latter means that CAD needs to trust the driver's ability and willingness and take over control when needed, i.e. the CAD system must be confident that the driver is properly skilled and alert in order to effectively control the vehicle in case of an emergency in the automatic driving mode, if the CAD system lacks trust in the driver's ability, transitional control may not be smoothly performed, resulting in a safety risk.

In the related art, measurement modes aiming at the trust degree of a driver mainly comprise a measurement mode based on a subjective scale and a measurement mode based on a physiological signal. The method is characterized in that a specific question and a scale are designed, the trust level of an individual or a group to a specific object or entity is measured by adopting a questionnaire manner, the questionnaire generally comprises a statement about trust, a researched person needs to express the agreement degree of the statement on the scale, obviously, the measurement manner based on the subjective scale is strong in invasiveness and poor in instantaneity, real-time detection is difficult in the driving process, and extra workload of a driver is increased, so that unnecessary interference is caused in the driving process. The latter can infer people's trust level in specific circumstances through measuring physiological reactions such as rhythm of the heart, skin conductance or electroencephalogram, but this kind of measurement mode based on physiological signals is not enough in that gather physiological signals mode is loaded down with trivial details, needs the driver to be equipped with physiological signal detector (such as head-mounted device, wrist-watch etc.), influences driving experience, and the signal deviation of gathering is big, lacks stability, and the driver also receives the surrounding environment influence easily to lead to the signal of gathering to appear the error, causes the false detection or the omission of trust to the driver.

Aiming at the technical problems, the technical conception of the invention is as follows: the measurement mode based on the gesture is provided, the trust degree of the driver at the current moment can be intuitively detected based on the face area, the EAR value, the face rotation angle and the like, and whether the trust degree of the driver at the current moment is in a trusted interval value is judged.

Fig. 1 is a schematic flow chart of a driver confidence level detection method provided by an embodiment of the present invention, where an execution subject is a driver confidence level detection device, or an electronic device with the driver confidence level detection device disposed. As shown in fig. 1, the driver confidence level detection method includes:

step S101, acquiring video clips of a first preset duration based on a vehicle-mounted camera, wherein the video clips comprise a plurality of face images of a driver.

Specifically, a camera is installed in the vehicle, which is aligned to the driver seat, and the frame rate of the camera can be more than 30fps (namely, more than 30 images are acquired per second), so that effective, stable and clear acquisition of video clips containing the faces of the driver is realized. In this step, when the confidence level of the driver in the CAD system scene needs to be monitored, a video clip of at least 5s and at most 8s may be collected based on the vehicle-mounted camera, where the video clip is a sequential image set with timing information. The first preset time period may be set according to experience of those skilled in the art, and the present invention is not limited thereto.

Step S102, extracting face key points on each face image, and determining the face area corresponding to each face image based on the face key points.

Specifically, each face image may be sequentially input into the MEDIAPIPE model, and face feature points are extracted to obtain a plurality of face key points, for example 468 face key points, which may be denoted as t= { P ₁,P₂,P₃,...P₄₆₈ }; then, the face outline can be determined according to the face key points, so that the face area in each face image can be calculated.

In some embodiments, the determining, in the step S102, a face area corresponding to each face image based on the face keypoints includes: determining the maximum abscissa, the minimum abscissa, the maximum ordinate and the minimum ordinate of each face key point in each face image; and determining the face area of the corresponding face image based on the maximum abscissa, the minimum abscissa, the maximum ordinate and the minimum ordinate.

Specifically, the position of each face key point is composed of (X, Y, Z) coordinates, the maximum abscissa and the minimum abscissa of all face key points on each face image are selected, and the face area on each face image is calculated according to the maximum abscissa and the minimum abscissa.

In some embodiments, the face area is calculated as follows:

S₁＝|X_min -X_max | × | Y_min - Y_max| (1)

Wherein S ₁ represents the face area, X _min represents the minimum abscissa, X _max represents the maximum abscissa, Y _min represents the minimum ordinate, and Y _max represents the maximum ordinate. It can be seen that the face area calculated in this embodiment can be understood as the minimum circumscribed rectangular area of the face area.

Step S103, if the number of face images with the face area not smaller than the preset area exceeds the first preset number, determining the eye key point of each face image, and determining the eye aspect ratio corresponding to each face image according to the eye key point.

Specifically, the first preset number may be understood as a certain proportion value, for example, 1/2, of the total number of the face images after screening, that is, if more than half of the face areas of the face images are larger than or equal to the preset area, it is indicated that the driver is always facing the front of the driver in the current first preset duration for a long time, at this time, the eye key points in each face image may be continuously extracted, and the corresponding EAR value may be calculated according to the eye key points.

Step S104, if the duration corresponding to the continuous face images with the eye aspect ratio smaller than the preset threshold exceeds the second preset duration, outputting reminding information of the driver over-trust automatic driving system.

Specifically, the preset threshold may be a value close to 0, after the EAR value of each face image is obtained in step S103, the EAR value is compared with the preset threshold, if the EAR value is greater than the preset threshold, it indicates that the eyes of the driver are open, if the EAR value is less than the preset threshold, that is, the EAR value is close to 0, it indicates that the eyes of the driver are closed at this time, if the EAR value for a long time fluctuates around 0, it indicates that the confidence of the driver on the CAD system is too high in the current time period, and prompt information of the driver over-confidence the CAD system can be sent out by using voice equipment or the like; if the EAR value does not continuously fluctuate around 0 for a long time, the driver is provided with a certain alertness in the current time period, and the driver can take over control of the vehicle in time when an emergency occurs in the automatic driving mode at any time.

Specifically, before step S103, a preset area is required to be predetermined, that is, a video clip (e.g., 5-8S) in front of the driver' S front view is collected in advance based on the vehicle-mounted camera, the video clip includes a front face image of the driver, a front face area in the front face image is identified based on the face recognition model, and the front face area S ₀ is calculated according to the minimum circumscribed rectangular area of the front face area, that is, the preset area _.

In some embodiments, after the step S101, the method further includes: screening a plurality of face images of the driver according to a preset screening rule; and if the number of the face images after screening exceeds the second preset number, executing the step of extracting the face key points on each face image.

In particular, the second preset number may be understood as a minimum image number threshold. After obtaining the video clips of 5-8s, extracting a time sequence image set from the video clips, and screening out qualified images (namely images containing faces and clear images of drivers) according to preset screening rules, wherein the number of the left images is N ₀, and if N ₀ is larger than a minimum picture number threshold value, the subsequent steps can be continued, otherwise, the video clips are omitted. Through image screening, the detection efficiency and accuracy of the trust degree can be improved.

According to the driver trust detection method provided by the embodiment of the invention, the video clips of the first preset duration are collected based on the vehicle-mounted camera, and the video clips comprise a plurality of face images of the driver; extracting face key points on each face image, and determining the face area corresponding to each face image based on the face key points; if the number of the face images with the face area not smaller than the preset area exceeds the first preset number, determining the eye key point of each face image, and determining the eye aspect ratio corresponding to each face image according to the eye key point; outputting reminding information of the driver over-trust automatic driving system if the duration corresponding to the continuous face images with the eye aspect ratio smaller than the preset threshold value exceeds the second preset duration; the trust degree of the driver is estimated in real time through the face key points and the eye key points in the collected face images of the driver, detection omission and false detection are not easy to occur, the face image collection is completed by utilizing the vehicle-mounted camera, the collection mode is simple, the driver does not need to wear any equipment, and driving experience is improved.

On the basis of the above embodiment, fig. 2 is a schematic flow chart of another driver confidence detection method according to the embodiment of the present invention. As shown in fig. 2, the driver confidence level detection method includes:

step S201, acquiring video clips of a first preset duration based on a vehicle-mounted camera, wherein the video clips comprise a plurality of face images of a driver.

Step S202, extracting face key points on each face image, and determining the face area corresponding to each face image based on the face key points.

Step 203, if the number of face images with the face area smaller than the preset area exceeds the first preset number, determining a face rotation angle of each face image.

And step S204, outputting reminding information of the driver over-trust automatic driving system if the face rotation angle is larger than the preset angle.

Steps S201 and S202 in this embodiment are similar to the implementation manner of steps S101 and S102 in the foregoing embodiment, and will not be described here again.

The difference from the foregoing embodiment is that if the number of face images whose face area is smaller than the preset area exceeds the first preset number, the face rotation angle of each face image is determined; and if the face rotation angle is larger than the preset angle, outputting reminding information of the driver over-trust automatic driving system.

Specifically, after the face area corresponding to each face image is calculated, comparing the face area with a preset area, if more than half of the face areas of the face images are smaller than the preset area, indicating that most of the time of a driver in the current time period is not right ahead of the driver, continuously calculating the face rotation angle of the driver at the moment, if the face rotation angle is larger than the preset angle, judging that the confidence of the driver to the CAD system is too high, and timely utilizing voice equipment and the like to send reminding information of the driver to overtrust the CAD system.

On the basis of the foregoing embodiment, if the number of face images with the face area smaller than the preset area exceeds the first preset number, determining a face rotation angle of each face image; if the face rotation angle is larger than the preset angle, the reminding information of the automatic driving system is output, and the trust degree of the driver to the CAD system is detected in real time according to the face area and the face rotation angle.

On the basis of the above embodiment, fig. 3 is a schematic flow chart of another driver confidence detection method according to an embodiment of the present invention. As shown in fig. 3, the driver confidence level detection method includes:

step S301, acquiring a front face image of a driver based on a vehicle-mounted camera.

Step S302, a frontal face area in the frontal face image is identified, and the minimum circumscribed rectangular area of the frontal face area is determined to be the preset area.

Step S303, acquiring video clips of a first preset duration based on a vehicle-mounted camera, wherein the video clips comprise a plurality of face images of a driver.

And S304, screening a plurality of face images of the driver according to a preset screening rule.

Step S305, determining whether the number of the face images after screening exceeds a second preset number.

If yes, go to step S306; if not, returning to step S303 to re-acquire the video clip.

Step S306, extracting face key points on each face image, and determining the face area corresponding to each face image based on the face key points.

According to the comparison result of the face area and the preset area and the corresponding face image number, steps S307 and S308 or steps S309 and S310 are executed.

Step S307, if the number of face images with the face area not smaller than the preset area exceeds the first preset number, determining the eye key point of each face image, and determining the eye aspect ratio corresponding to each face image according to the eye key point.

Step 308, if the duration corresponding to the continuous face images with the eye aspect ratio smaller than the preset threshold exceeds the second preset duration, outputting a reminding message of the driver over-trust automatic driving system.

Step 309, if the number of face images with the face area smaller than the preset area exceeds the first preset number, determining a face rotation angle of each face image.

Step S310, if the face rotation angle is larger than the preset angle, outputting reminding information of the driver over-trust automatic driving system.

In this embodiment, the preset area S ₀ is calculated by steps S301 and S302, and the specific process is as follows: the method comprises the steps of pre-collecting 5-8S of video clips in front of driver front vision based on a vehicle-mounted camera, extracting face key points based on a face recognition model, determining a face contour according to the face key points, and calculating a preset area S by using a minimum circumscribed rectangle based on the face contour _0.

Secondly, face image acquisition and image screening are completed through steps S303-S305, and the specific process is as follows: and acquiring 5-8 seconds of video clips containing the faces of the driver in real time based on the vehicle-mounted camera, extracting frames from the video clips to extract a time sequence image set, removing overexposure, overdrising and blurring face images, ensuring that the number of the remaining images is larger than a minimum picture number threshold value, and finally obtaining a qualified face image set N with time sequence information.

The face area calculation is completed again through step S306, and the specific process is as follows: and sequentially inputting the acquired N qualified face image sets into MEDIAPIPE models to extract 468 face key points, selecting X _min,X_max,Y_min,Y_max in all face key points, and calculating a face area S ₁ through a formula (1).

The trust level detection is completed again through the steps S07-S310, and the specific process is as follows: if the qualified face image set N is judged to have more than N/2 of pictures S ₁<S₀, calculating the face rotation angle of the driver, and if the face rotation angle is larger than a preset angle, judging that the driver has high trust degree on the CAD system; if the qualified face image set N is judged to have more than N/2 of the pictures S ₁>S₀, human eye key points (such as 32 key points are selected) of the driver are further extracted, EAR is calculated, and if the EAR value with a long duration fluctuates around 0, the driver in the current time period is judged to have high trust degree on the CAD system. When the driver is found to have too high confidence, the voice reminding device is started immediately to remind.

In conclusion, the face information of the driver is collected in real time, the trust degree of the driver can be estimated in real time by utilizing the face area, the eye aspect ratio and the face rotation angle, the detection omission and the false detection are not easy, and the real-time trust degree measurement based on the face information of the driver under the conditional automatic driving scene can be realized; and adopt on-vehicle camera to gather the face image, its collection mode is indirect, does not have any direct contact to the driver, need not to wear any equipment, under the prerequisite of not influencing the driving, promotes the driving experience.

Fig. 4 is a schematic structural diagram of a driver confidence level detection device according to an embodiment of the present invention, and as shown in fig. 4, the driver confidence level detection device includes an image acquisition module 401, a face area calculation module 402, a confidence level detection module 403, and a confidence level output module 404;

The image acquisition module 401 is configured to acquire a video clip of a first preset duration based on a vehicle-mounted camera, where the video clip includes a plurality of face images of a driver; a face area calculation module 402, configured to extract face key points on each face image, and determine a face area corresponding to each face image based on the face key points; the confidence detection module 403 is configured to determine an eye key point of each face image if the number of face images with a face area not smaller than a preset area exceeds a first preset number, and determine an eye aspect ratio corresponding to each face image according to the eye key point; and the confidence level output module 404 is configured to output a reminder that the driver excessively trusts the autopilot system if a duration corresponding to the continuous face images with the eye aspect ratio smaller than the preset threshold exceeds a second preset duration.

In some embodiments, the confidence detection module 403 is further configured to determine a face rotation angle of each face image if the number of face images with the face area smaller than the preset area exceeds the first preset number; the confidence level output module 404 is further configured to output a reminder for the driver to trust the autopilot system excessively if the face rotation angle is greater than a preset angle.

In some embodiments, the face area calculation module 402 is specifically configured to: determining the maximum abscissa, the minimum abscissa, the maximum ordinate and the minimum ordinate of each face key point in each face image; and determining the face area of the corresponding face image based on the maximum abscissa, the minimum abscissa, the maximum ordinate and the minimum ordinate.

In some embodiments, the face area is calculated as follows:

S₁＝|X_min-X_max|×|Y_min-Y_max|

In some embodiments, the face area calculation module 402 is further configured to: acquiring a front face image of a driver based on a vehicle-mounted camera; and recognizing a frontal face area in the frontal face image, and determining the minimum circumscribed rectangular area of the frontal face area as the preset area.

In some embodiments, the image acquisition module 401 is further configured to screen a plurality of face images of the driver according to a preset screening rule; if the number of the face images after the filtering exceeds the second preset number, the face area calculation module 402 performs the step of extracting the face key points on each face image.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process and corresponding beneficial effects of the driver confidence level detection device described above may refer to the corresponding process in the foregoing method example, and will not be described herein again.

As shown in fig. 5, an embodiment of the present invention provides an electronic device, which includes a processor 501, a communication interface 502, a memory 503, and a communication bus 504, wherein the processor 501, the communication interface 502, and the memory 503 perform communication with each other through the communication bus 504,

A memory 503 for storing a computer program;

in one embodiment of the present invention, the processor 501 is configured to implement the steps of the driver confidence detection method provided in any one of the foregoing method embodiments when executing the program stored in the memory 503.

The implementation principle and technical effects of the electronic device provided by the embodiment of the invention are similar to those of the above embodiment, and are not repeated here.

The memory 503 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 503 has a storage space for program code for performing any of the method steps described above. For example, the memory space for the program code may include individual program code for implementing individual steps in the above method, respectively. The program code can be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, compact Disk (CD), memory card or floppy disk. Such computer program products are typically portable or fixed storage units. The storage unit may have a memory segment or a memory space or the like arranged similarly to the memory 503 in the above-described electronic device. The program code may be compressed, for example, in a suitable form. In general, the storage unit comprises a program for performing the method steps according to an embodiment of the invention, i.e. code that can be read by a processor, such as 501 for example, which when run by an electronic device causes the electronic device to perform the various steps in the method described above.

Embodiments of the present invention also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program which, when executed by a processor, implements the steps of the driver confidence detection method described above.

The computer-readable storage medium may be embodied in the apparatus/means described in the above embodiments; or may exist alone without being assembled into the apparatus/device. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present invention.

According to embodiments of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The driver trust degree detection method is characterized by comprising the following steps of:

Acquiring a video clip with a first preset duration based on a vehicle-mounted camera, wherein the video clip comprises a plurality of face images of a driver;

extracting face key points on each face image, and determining the face area corresponding to each face image based on the face key points;

If the number of the face images with the face area not smaller than the preset area exceeds the first preset number, determining the eye key point of each face image, and determining the eye aspect ratio corresponding to each face image according to the eye key point;

And if the duration corresponding to the continuous face images with the eye aspect ratio smaller than the preset threshold value exceeds the second preset duration, outputting the reminding information of the driver over-trust automatic driving system.

2. The method according to claim 1, wherein the method further comprises:

If the number of the face images with the face area smaller than the preset area exceeds the first preset number, determining the face rotation angle of each face image;

And if the face rotation angle is larger than the preset angle, outputting reminding information of the driver over-trust automatic driving system.

3. The method according to claim 1 or 2, wherein the determining a face area corresponding to each face image based on the face keypoints comprises:

Determining the maximum abscissa, the minimum abscissa, the maximum ordinate and the minimum ordinate of each face key point in each face image;

And determining the face area of the corresponding face image based on the maximum abscissa, the minimum abscissa, the maximum ordinate and the minimum ordinate.

4. A method according to claim 3, wherein the face area is calculated as:

S₁＝|X_min-X_max|×|Y_min-Y_max|

5. A method according to claim 3, characterized in that the method further comprises:

acquiring a front face image of a driver based on a vehicle-mounted camera;

and recognizing a frontal face area in the frontal face image, and determining the minimum circumscribed rectangular area of the frontal face area as the preset area.

6. The method according to claim 1 or 2, wherein the capturing, based on the vehicle-mounted camera, a video clip for a first preset duration, the video clip including a plurality of face images of the driver, further includes:

screening a plurality of face images of the driver according to a preset screening rule;

And if the number of the face images after screening exceeds the second preset number, executing the step of extracting the face key points on each face image.

7. The driver trust degree detection device is characterized by comprising:

The image acquisition module is used for acquiring video clips of a first preset duration based on the vehicle-mounted camera, wherein the video clips comprise a plurality of face images of a driver;

The face area calculation module is used for extracting face key points on each face image and determining the face area corresponding to each face image based on the face key points;

The trust degree detection module is used for determining the eye key point of each face image if the number of the face images with the face area not smaller than the preset area exceeds the first preset number, and determining the eye aspect ratio corresponding to each face image according to the eye key point;

The confidence level output module is used for outputting reminding information of the driver over-confidence automatic driving system if the duration time corresponding to the continuous face images with the eye aspect ratio smaller than the preset threshold value exceeds the second preset duration time.

8. The apparatus of claim 7, wherein the confidence level detection module is further configured to determine a face rotation angle of each face image if the number of face images having a face area smaller than the preset area exceeds the first preset number;

The trust degree output module is further used for outputting reminding information of the driver over-trust automatic driving system if the face rotation angle is larger than a preset angle.

9. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

a memory for storing a computer program;

A processor for implementing the steps of the driver confidence level detection method according to any one of claims 1 to 6 when executing a program stored on a memory.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the driver confidence detection method according to any one of claims 1-6.