Vehicle warning method, system, electronic device, and medium

Abstract

This invention provides a vehicle early warning method, system, electronic device, and medium, belonging to the field of vehicle technology. The method includes: acquiring a driver's facial image and driver's height data; extracting features from the driver's facial image to obtain a driver's age prediction result; performing auxiliary verification on the driver's age prediction result based on the driver's height data to obtain a driver's age judgment result; and comparing the driver's age judgment result with a preset threshold to determine whether to trigger an early warning process. This invention optimizes recognition technology and improves recognition accuracy by combining facial image features with height-assisted verification, achieving accurate driver age identification and timely early warning, thereby reducing the risk of accidents.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a vehicle warning method, system, electronic device, and medium. Background Technology

[0002] With the increasing prevalence of vehicles, there is a possibility that minors may drive on the road, engage in dangerous driving, and cause traffic accidents. However, relevant technologies lack reliable identification and early warning solutions for this scenario. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art, and proposes a vehicle warning method, system, electronic device and medium.

[0004] In a first aspect, embodiments of the present invention provide a vehicle warning method, comprising:

[0005] Acquire driver's facial image and driver's height data;

[0006] Feature extraction is performed on the driver's facial image to obtain the driver's age prediction result;

[0007] The driver's height data is used to assist in verifying the driver's age prediction result, and the driver's age judgment result is obtained.

[0008] The driver's age determination result is compared with a preset threshold to determine whether to trigger the warning process.

[0009] In some embodiments, acquiring the driver's facial image and driver's height data includes:

[0010] When the vehicle is started, the multi-source acquisition unit is activated; wherein, the multi-source acquisition unit includes a dual-mode camera and a seat position sensor;

[0011] Based on the original facial image of the driver acquired by the dual-mode camera, the original facial image of the driver is filtered to obtain the driver's facial image;

[0012] The driver's seat height and backrest angle data are collected based on the seat position sensor.

[0013] The driver's height data is obtained based on the seat height data and backrest angle data.

[0014] In some embodiments, the method further includes:

[0015] During vehicle operation, driver facial images are automatically collected at preset intervals.

[0016] When a preset dangerous operation is detected, the driver's facial image is captured and the current driving behavior is recorded.

[0017] In some embodiments, the step of extracting features from the driver's facial image to obtain a driver's age prediction result includes:

[0018] Feature extraction was performed on the driver's facial image based on the AgeNet model to obtain facial bone proportion features and skin texture features.

[0019] Based on the analysis of the facial bone proportion features and skin texture features, the driver's age prediction result is output.

[0020] In some embodiments, the step of assisting in verifying the driver's age prediction result based on the driver's height data to obtain the driver's age judgment result includes:

[0021] Obtain the deviation between the driver's height data and a preset height threshold;

[0022] The confidence weighting factor is determined based on the aforementioned deviation;

[0023] The driver's age is determined based on the confidence weighting factor and the driver's age prediction result.

[0024] In some embodiments, comparing the driver's age determination result with a preset threshold to determine whether to trigger a warning process includes:

[0025] The driver's age determination result is compared with a preset threshold;

[0026] If the driver's age determination result is less than the preset threshold, an early warning process is triggered;

[0027] If the driver's age determination result is greater than or equal to the preset threshold, then the system enters a low-power monitoring state.

[0028] In some embodiments, the step of triggering an early warning process if the driver's age determination result is less than the preset threshold includes:

[0029] If the driver's age determination result meets the first age range and the driving is stable, the first-level warning process is triggered, the warning is displayed on the vehicle display, a warning sound is issued and the warning information is pushed to the preset personnel;

[0030] If the driver's age determination result meets the second age range and a preset dangerous operation is detected, a level two warning process is triggered, a warning is displayed, a warning sound is issued, a warning message is pushed, and vehicle safety restriction operations are initiated; wherein, the second age range is less than the first age range.

[0031] Secondly, embodiments of the present invention provide a vehicle warning system, including:

[0032] The acquisition module is used to obtain driver facial images and driver height data;

[0033] The prediction module is used to extract features from the driver's facial image to obtain the driver's age prediction result;

[0034] The auxiliary verification module is used to assist in verifying the driver's age prediction result based on the driver's height data, and to obtain the driver's age judgment result.

[0035] The warning module is used to compare the driver's age determination result with a preset threshold to determine whether to trigger the warning process.

[0036] Thirdly, embodiments of the present invention provide an electronic device, including:

[0037] One or more processors;

[0038] Memory, used to store one or more programs;

[0039] When the one or more programs are executed by the one or more processors, the one or more processors implement any of the methods described above.

[0040] Fourthly, embodiments of the present invention provide a computer-readable medium on which a computer program is stored, the computer program being executed by a processor to implement the steps of any of the methods described above.

[0041] The vehicle early warning method provided by this invention includes: acquiring a driver's facial image and driver's height data; extracting features from the driver's facial image to obtain a driver's age prediction result; performing auxiliary verification on the driver's age prediction result based on the driver's height data to obtain a driver's age judgment result; and comparing the driver's age judgment result with a preset threshold to determine whether to trigger an early warning process. This invention optimizes recognition technology and improves recognition accuracy by combining facial image features with height-assisted verification, enabling accurate driver age identification and timely early warning, thereby reducing the risk of accidents. Attached Figure Description

[0042] Figure 1 This is a flowchart illustrating a vehicle early warning method provided in an embodiment of the present invention;

[0043] Figure 2 This is a schematic diagram illustrating specific optional implementation processes involved in the embodiments of the present invention;

[0044] Figure 3 This is a structural block diagram of a vehicle warning system provided in an embodiment of the present invention;

[0045] Figure 4 This is another structural block diagram of a vehicle warning system provided in an embodiment of the present invention;

[0046] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0047] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0048] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0049] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0050] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0051] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0052] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0053] The key terms involved in this invention are defined as follows:

[0054] AgeNet: A deep learning network model for age recognition (extracting features from facial images and predicting age);

[0055] Multimodal fusion: refers to a comprehensive judgment method that integrates facial image features and biometric features (such as height and driving behavior);

[0056] Dynamic acquisition: refers to the periodic / event-based image acquisition mechanism triggered according to the scenario from the start of vehicle ignition and during driving.

[0057] The relevant technologies suffer from drawbacks such as low accuracy in age recognition and limited intervention measures, making it difficult to accurately identify and control the risks associated with underage driving. For example, facial recognition relies on a single image and algorithm, making it susceptible to occlusion and lighting conditions that can lead to misjudgments of age, and it also lacks effective intervention methods after issuing warnings.

[0058] To address at least one of the technical problems existing in the aforementioned related technologies, the present invention provides a vehicle warning method. Figure 1 This is a flowchart illustrating a vehicle early warning method provided in an embodiment of the present invention;

[0059] As one embodiment of the present invention, such as Figure 1 As shown, the vehicle warning method includes:

[0060] Step S1: Obtain the driver's facial image and driver's height data;

[0061] Step S2: Extract features from the driver's facial image to obtain the driver's age prediction result;

[0062] Step S3: Assist in verifying the driver's age prediction result based on the driver's height data to obtain the driver's age judgment result;

[0063] Step S4: Compare the driver's age determination result with a preset threshold to determine whether to trigger the warning process.

[0064] It should be noted that the execution subject in this embodiment can be an electronic device, which can be a computer device with data processing function, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment, the execution subject is a computer device as an example for explanation.

[0065] Specifically, the vehicle warning method in this embodiment, by optimizing recognition technology, increasing dynamic data collection, and implementing tiered intervention, achieves accurate identification and timely prevention of underage driving behavior, thereby reducing the risk of traffic accidents. The following describes the specific steps.

[0066] In some embodiments, acquiring driver facial images and driver height data includes: activating a multi-source acquisition unit when the vehicle is started; wherein the multi-source acquisition unit includes a dual-mode camera and a seat position sensor; acquiring a driver's original facial image based on the dual-mode camera, filtering the driver's original facial image to obtain a driver facial image; acquiring driver's seat height data and backrest angle data based on the seat position sensor; and obtaining driver height data based on the seat height data and backrest angle data.

[0067] Specifically, such as Figure 2 As shown, dynamic data acquisition: After the vehicle is ignited, the multi-source acquisition unit starts immediately. For example, it acquires driver facial images through a dual-mode camera (visible light combined with infrared), such as acquiring 5 consecutive frames, filtering for clear images, and automatically switching to infrared mode in backlight / low light environments; the seat position sensor can estimate the driver's height by combining the seat height with the backrest angle to help determine age.

[0068] For example, after the vehicle is started, the multi-source acquisition unit is activated. The dual-mode camera acquires images of the driver's face in visible light mode, specifically in front of the driver and to the side of the A-pillar (e.g., 5 consecutive frames). If backlight or low light conditions are detected, it automatically switches to infrared mode and filters for clear images to obtain the driver's facial image for subsequent analysis.

[0069] For example, driver height is estimated using seat position sensors based on ergonomics and geometric mapping relationships. It is assumed that when the driver adjusts the seat to achieve a comfortable driving view, there is a quantifiable correlation between their posture and height. The vertical height of the seat rail relative to the vehicle's reference plane is measured using a seat height sensor, such as a linear displacement sensor or a Hall effect sensor. The angle between the seat back and the vertical direction is measured using a backrest angle sensor, such as a rotary potentiometer or a gyroscope. A linear regression model is used as the height estimation model, and the height is estimated based on the vertical height, angle, seat height coefficient, backrest angle coefficient, and compensation constant.

[0070] Specifically, in this embodiment, the driver's height data can also be estimated by measuring the distance between the head and the roof, replacing the seat position sensor to achieve the same auxiliary verification effect. For example, a dual-mode camera (installed directly in front of the driver's seat and on the A-pillar) is used to directly measure the vertical distance between the top of the driver's head and the top of the vehicle's interior lining using computer vision technology. This distance is negatively correlated with the driver's height and can serve as an independent input source for height estimation. Based on geometric relationships, an inverse proportional model for height estimation is established for use in height estimation.

[0071] In some embodiments, the method further includes: automatically acquiring driver facial images at preset intervals during vehicle operation; and acquiring driver facial images and recording current driving behavior when a preset dangerous operation is detected.

[0072] Specifically, supplementary data collection is triggered during driving. For example, timed collection: facial images are automatically collected at preset intervals, such as every 10 minutes, to prevent drivers from changing midway; abnormal triggering: when preset dangerous operations such as rapid acceleration or continuous lane changes are detected, facial images are immediately collected and driving behavior is recorded.

[0073] In this embodiment, the dynamic acquisition mechanism (timed + abnormal trigger) covers the entire ignition and driving scenario, which can avoid missed detection when switching drivers midway.

[0074] In some embodiments, feature extraction is performed on the driver's facial image to obtain a driver's age prediction result, including: extracting features from the driver's facial image based on the AgeNet model to obtain facial bone ratio features and skin texture features; analyzing the facial bone ratio features and skin texture features; and outputting a driver's age prediction result.

[0075] In some embodiments, the driver's age prediction result is verified by the driver's height data to obtain the driver's age judgment result, including: obtaining the deviation between the driver's height data and a preset height threshold; determining a confidence weight factor based on the deviation; and obtaining the driver's age judgment result based on the confidence weight factor and the driver's age prediction result.

[0076] In some embodiments, the driver's age determination result is compared with a preset threshold to determine whether to trigger an early warning process, including: comparing the driver's age determination result with the preset threshold; if the driver's age determination result is less than the preset threshold, then triggering an early warning process; if the driver's age determination result is greater than or equal to the preset threshold, then entering a low-power monitoring state.

[0077] Specifically, such as Figure 2As shown, age recognition and judgment are achieved through the fusion and analysis of collected data by an intelligent processing unit. Core recognition: The AgeNet model is used to extract features from clear facial images (driver's facial images), such as facial bone proportions and skin texture. Minors have more rounded facial bones and finer skin texture to predict the driver's age. Auxiliary verification: Combining height data, for example, when height is <1.6 meters, improves the confidence level of the judgment for minors. Result output: If the overall judged age (driver's age judgment result) is <18 years old, an early warning is triggered; if the driver's age judgment result is ≥18 years old, a low-power monitoring state is entered.

[0078] For example, the intelligent processing unit receives a clear driver facial image (driver facial image) selected by the multi-source acquisition unit and uses a pre-trained AgeNet model to extract features from the driver facial image. For instance, the AgeNet model analyzes key biometric features in the facial image using a convolutional neural network (CNN), mainly including facial bone proportions such as the jawline angle and cheekbone prominence, and skin texture such as pore density and skin smoothness. Based on these features (facial bone proportion features and skin texture features), the model outputs an age prediction value (driver age prediction result).

[0079] For example, the intelligent processing unit also receives driver height data calculated by the seat position sensor, which is used to construct a confidence weighting factor for auxiliary verification. When the height is below a preset threshold (e.g., height < 1.6 meters), the probability of the driver being a minor increases, so a weighting factor greater than 1 is assigned to improve the confidence of the "minor" judgment; otherwise, the weighting factor is 1.

[0080] In one example, the intelligent processing unit can use a weighted formula to calculate a comprehensive age determination value (driver's age determination result). Since the calculated comprehensive age determination value is, for example, 21 years old, which is greater than the legal driving age threshold of 18 years old, the driver is determined to meet the driving conditions. Therefore, no warning is triggered, but instead, a low-power monitoring state is entered, and the data acquisition and recognition process is only reactivated under timed or abnormal triggering conditions.

[0081] Understandably, if a driver's AgeNet model predicts their age to be 16 years old and their height to be 1.58 meters, the weighted age assessment result is 19.2. Although the weighted result is greater than 18 years old, this embodiment prioritizes the unweighted result of the core identification, i.e., the predicted age of 16 years old, as the primary criterion. Because the predicted age of 16 years old is less than 18 years old, an alert is still triggered.

[0082] It should be noted that age recognition can be replaced by a fusion of facial key features and behavioral features, such as using the "eye distance / face width ratio" and "steering wheel operation frequency" to assist in age determination. For example, the intelligent processing unit can utilize clear facial images captured by dual-mode cameras to locate a series of key points using facial landmark detection algorithms such as Dlib or MTCNN. Based on these key points, the following geometric proportion features are calculated: the eye distance / face width ratio, which is the ratio of the distance between the inner corners of the eyes to the distance between the left and right cheekbone points, is relatively large in adolescence and gradually decreases and stabilizes as facial bones develop; the facial width-to-height ratio, which is the ratio of facial width (distance between cheekbones) to lower face length (distance from the subnasal point to the chin point), is typically more rounded in adolescence, resulting in a larger width-to-height ratio. Driving behavior characteristics are collected and quantified within a specific time window, such as 60 seconds, using the vehicle control module and steering wheel angle sensor. Steering wheel operation frequency, i.e., the number of times the steering wheel angle changes beyond a preset threshold per unit time, is analyzed. Studies show that younger or less experienced drivers tend to make more frequent and larger steering corrections, resulting in a higher operation frequency. Accelerator pedal change rate, i.e., the rate of change in accelerator pedal depth, is also analyzed; rapid acceleration and deceleration are associated with high values ​​for this indicator, commonly seen in drivers with less experience. A multi-dimensional feature vector is constructed and input into a fusion prediction model, such as Gradient Boosting Decision Tree (GBDT) or Support Vector Machine (SVM), to output the final age classification result, such as minor or adult.

[0083] In this embodiment, facial age recognition using the AgeNet model combined with height-assisted verification improves recognition accuracy, increasing the accuracy rate to over 90% and reducing false positives. By fusing core facial image recognition features with height-assisted verification data, recognition accuracy is enhanced, effectively reducing the risk of false positives caused by a single data source, such as relying solely on facial images under extreme lighting conditions or individual developmental differences. For example, even when facial features are blurred, the confidence level for determining a minor can still be improved through auxiliary weights for drivers shorter than 1.6 meters. This embodiment employs weighted calculation and hierarchical judgment logic, prioritizing facial recognition results in most scenarios and adjusting confidence levels with height data to ensure the rationality of the decision. When the overall driver age (driver age judgment result) is ≥18 years, the system automatically switches to a low-power monitoring state, only collecting data periodically or reactivating the processing unit when necessary, such as during scheduled data collection or abnormal triggering, thereby reducing the overall vehicle system's energy consumption.

[0084] In some embodiments, if the driver's age determination result is less than the preset threshold, a warning process is triggered, including: if the driver's age determination result meets a first age range and the driving is stable, a first-level warning process is triggered, a warning is displayed on the vehicle display, a warning sound is emitted, and a warning message is pushed to a preset person; if the driver's age determination result meets a second age range and a preset dangerous operation is detected, a second-level warning process is triggered, a warning is displayed, a warning sound is emitted, a warning message is pushed, and a vehicle safety restriction operation is initiated; wherein, the second age range is less than the first age range.

[0085] Specifically, such as Figure 2 As shown, a tiered warning and intervention system is implemented, with the actuator unit taking corresponding measures based on the identification results. The first age range can be 16-17 years old, with a Level 1 warning (age 16-17 years old and driving steadily):

[0086] The in-vehicle display (instrument panel + central control screen) displays "HMI Warning: Driver's age does not meet driving requirements," and the buzzer sounds three times. The cloud management platform sends a text message (including vehicle location) to the vehicle owner to confirm the driver. A second age range is <16 years old. For a Level 2 warning (age <16 years or dangerous driving behavior): the in-vehicle display continuously displays the warning information, and the buzzer sounds once every 30 seconds. The cloud management platform simultaneously notifies traffic safety management departments, such as pushing vehicle model, license plate number, and real-time location. The vehicle control module activates safety restrictions, such as a maximum speed limit of 30 km / h, and prohibits entry onto highways.

[0087] In this embodiment, by combining tiered early warning with vehicle restrictions, timely reminders can be provided while proactively controlling the risks of dangerous driving. The linkage between tiered early warning and vehicle restrictions achieves a closed loop of "early warning-intervention".

[0088] In some embodiments, such as Figure 2 As shown, information is synchronized. All warning information, including facial images, recognition results, and vehicle locations, is uploaded to the cloud management platform in real time. Vehicle owners can view details through the app, and traffic management departments can quickly intervene based on location information.

[0089] Specifically, all warning information, including facial images, age recognition results, vehicle location, and driving behavior data, is uploaded to the cloud management platform in real time. Vehicle owners can view details such as the warning time and location, and driver images through the app; traffic management departments can quickly intervene by dispatching law enforcement resources based on location information.

[0090] In this embodiment, the efficiency of intervention is improved by synchronizing information from multiple parties (vehicle owner + traffic management department), effectively preventing minors from driving vehicles.

[0091] In this embodiment, a fusion logic combining facial image feature extraction and height-assisted verification is used to accurately identify the age of a car driver. A dynamic data acquisition mechanism is set up, combining timed data acquisition with anomaly triggering to achieve age monitoring throughout the driving process. A tiered intervention approach for underage driving is implemented through in-vehicle warnings, vehicle restrictions, and multi-party information push notifications. This embodiment, through multimodal feature fusion, dynamic data acquisition, and tiered intervention, addresses the shortcomings of related technologies, such as low age recognition accuracy, limited intervention measures, and the inability to accurately identify and control the risks associated with underage driving behavior.

[0092] The vehicle early warning method provided in this embodiment includes: acquiring a driver's facial image and driver's height data; extracting features from the driver's facial image to obtain a driver's age prediction result; performing auxiliary verification on the driver's age prediction result based on the driver's height data to obtain a driver's age judgment result; and comparing the driver's age judgment result with a preset threshold to determine whether to trigger an early warning process. This embodiment optimizes the recognition technology and improves recognition accuracy by combining facial image features with height-assisted verification, enabling accurate driver age identification and timely early warning, thereby reducing the risk of accidents.

[0093] Reference Figure 3 , Figure 3 This is a structural block diagram of an embodiment of the vehicle warning system of the present invention. Figure 3 As shown, the vehicle warning system includes:

[0094] The acquisition module 10 is used to acquire driver facial images and driver height data;

[0095] Prediction module 20 is used to extract features from the driver's facial image to obtain the driver's age prediction result;

[0096] The auxiliary verification module 30 is used to perform auxiliary verification on the driver's age prediction result based on the driver's height data, and obtain the driver's age judgment result.

[0097] The early warning module 40 is used to compare the driver's age determination result with a preset threshold to determine whether to trigger the early warning process.

[0098] Specifically, the vehicle warning system in this embodiment is used for driver age recognition and warning. Through multimodal feature fusion, dynamic acquisition and hierarchical intervention, it solves the defects of low age recognition accuracy, single intervention measures and other problems in related technologies, such as the inability to accurately identify the driving behavior of minors and control risks.

[0099] For example, such as Figure 4As shown, the vehicle warning system may include a multi-source acquisition unit, an intelligent processing unit, an actuator unit, a display module, and a cloud management platform. The multi-source acquisition unit includes a dual-mode camera (front of the driver's seat + side of the A-pillar) and a seat position sensor. The actuator unit may include a buzzer, an in-vehicle display, and a vehicle control module.

[0100] The vehicle warning system provided in this embodiment optimizes the recognition technology and improves the recognition accuracy by combining facial image features with height-assisted verification. This enables accurate identification and timely warning of the driver's age, thereby reducing the risk of accidents.

[0101] In addition, for technical details not described in detail in this vehicle warning system embodiment, please refer to the vehicle warning method provided in any embodiment of the present invention, which will not be repeated here.

[0102] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement any of the vehicle warning methods described in the above embodiments; the one or more I / O interfaces 103 are connected between the processors and the memory, configured to enable information interaction between the processors and the memory.

[0103] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0104] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0105] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0106] This invention also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps of any of the vehicle warning methods described in the above embodiments. The computer-readable storage medium may be volatile or non-volatile.

[0107] This invention also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the above-described vehicle warning method.

[0108] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0109] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0110] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0111] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0112] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0113] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0114] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0115] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0116] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0117] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A vehicle early warning method, characterized in that, include: Acquire driver's facial image and driver's height data; Feature extraction is performed on the driver's facial image to obtain the driver's age prediction result; The driver's height data is used to assist in verifying the driver's age prediction result, and the driver's age judgment result is obtained. The driver's age determination result is compared with a preset threshold to determine whether to trigger the warning process.

2. The method according to claim 1, characterized in that, The acquisition of the driver's facial image and driver's height data includes: When the vehicle is started, the multi-source acquisition unit is activated; wherein, the multi-source acquisition unit includes a dual-mode camera and a seat position sensor; Based on the original facial image of the driver acquired by the dual-mode camera, the original facial image of the driver is filtered to obtain the driver's facial image; The driver's seat height and backrest angle data are collected based on the seat position sensor. The driver's height data is obtained based on the seat height data and backrest angle data.

3. The method according to claim 2, characterized in that, The method further includes: During vehicle operation, driver facial images are automatically collected at preset intervals. When a preset dangerous operation is detected, the driver's facial image is captured and the current driving behavior is recorded.

4. The method according to claim 1, characterized in that, The step of extracting features from the driver's facial image to obtain the driver's age prediction result includes: Feature extraction was performed on the driver's facial image based on the AgeNet model to obtain facial bone proportion features and skin texture features. Based on the analysis of the facial bone proportion features and skin texture features, the driver's age prediction result is output.

5. The method according to claim 1, characterized in that, The step of assisting in verifying the driver's age prediction result based on the driver's height data to obtain the driver's age judgment result includes: Obtain the deviation between the driver's height data and a preset height threshold; The confidence weighting factor is determined based on the aforementioned deviation; The driver's age is determined based on the confidence weighting factor and the driver's age prediction result.

6. The method according to any one of claims 1 to 5, characterized in that, The step of comparing the driver's age determination result with a preset threshold to determine whether to trigger the warning process includes: The driver's age determination result is compared with a preset threshold; If the driver's age determination result is less than the preset threshold, an early warning process is triggered; If the driver's age determination result is greater than or equal to the preset threshold, then the system enters a low-power monitoring state.

7. The method according to claim 6, characterized in that, If the driver's age determination result is less than the preset threshold, an early warning process is triggered, including: If the driver's age determination result meets the first age range and the driving is stable, the first-level warning process is triggered, the warning is displayed on the vehicle display, a warning sound is issued and the warning information is pushed to the preset personnel; If the driver's age determination result meets the second age range and a preset dangerous operation is detected, a level two warning process is triggered, a warning is displayed, a warning sound is issued, a warning message is pushed, and vehicle safety restriction operations are initiated; wherein, the second age range is less than the first age range.

8. A vehicle warning system, characterized in that, include: The acquisition module is used to obtain driver facial images and driver height data; The prediction module is used to extract features from the driver's facial image to obtain the driver's age prediction result; The auxiliary verification module is used to assist in verifying the driver's age prediction result based on the driver's height data, and to obtain the driver's age judgment result. The warning module is used to compare the driver's age determination result with a preset threshold to determine whether to trigger the warning process.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images