Driver examination evaluation method, device, system and medium

Abstract

The invention discloses a driver examination evaluation method, device and system and a medium, and relates to the technical field of computer vision. The method comprises the following steps: acquiring a sight track of a driver, a vehicle motion state of a vehicle driven by the driver and an external environment image of the vehicle; determining a standard driving behavior of at least one actual driving scene corresponding to the external environment image; for any actual driving scene, according to the sight track corresponding to the actual driving scene and the corresponding vehicle motion state, determining the actual driving behavior of the driver in the actual driving scene; and according to the standard driving behavior corresponding to each actual driving scene and the actual driving behavior corresponding to each actual driving scene, evaluating an examination result of the driver examination. The method is a new driver examination evaluation method.

Description

Technical Field

[0001] This application relates to the field of computer vision technology, and more specifically, to an assessment method, apparatus, system, and medium for driver's license examinations. Background Technology

[0002] Currently, driver's license examinations mainly rely on two methods: manual assessment by examiners or automatic assessment based on vehicle sensors.

[0003] However, manual assessment methods are highly subjective. Automated assessment methods based on vehicle sensors cannot incorporate driver eye movements. Therefore, a new driver testing and assessment method is urgently needed. Summary of the Invention

[0004] One objective of this application is to provide a new technological solution for driver's license examination assessment.

[0005] According to a first aspect of this application, a method for assessing a driver's license examination is provided, the method comprising: Acquire the driver's line of sight, the vehicle's motion state, and the external environment image of the vehicle; Determine the standard driving behavior for at least one actual driving scenario corresponding to the external environment image; For any of the aforementioned actual driving scenarios, the driver's actual driving behavior in the actual driving scenario is determined based on the line-of-sight trajectory and the corresponding vehicle movement state. The driver's test results are evaluated based on the standard driving behavior corresponding to each actual driving scenario and the actual driving behavior corresponding to each actual driving scenario.

[0006] Optionally, evaluating the driver's license test results based on the standard driving behavior corresponding to each actual driving scenario and the actual driving behavior corresponding to each actual driving scenario includes: For any actual driving action in any actual driving behavior corresponding to any actual driving scenario, determine whether the actual driving action matches the standard driving action in the corresponding order in the standard driving behavior, and obtain the matching result of the actual driving action, the matching result including matching and non-matching; The driver's test score is determined based on the matching results of each actual driving action in each actual driving behavior corresponding to each actual driving scenario.

[0007] Optionally, after determining the driver's actual driving behavior for any given actual driving scenario based on the corresponding line-of-sight trajectory and vehicle motion state, the method further includes: For any actual driving scenario, if the standard driving behavior corresponding to the actual driving scenario includes a target standard driving action, and for any target standard driving action, if the actual driving action in the corresponding order of the actual driving behavior in the actual driving scenario does not match the target standard driving action, an alarm message will be output.

[0008] Optionally, the method further includes: For any of the aforementioned real-world driving scenarios, a driving analysis report for the driver is output based on the standard driving behavior corresponding to the real-world driving scenario and the actual driving behavior under the real-world driving scenario.

[0009] Optionally, obtaining the driver's line-of-sight trajectory includes: Acquire the driver's head movement data, the driver's eye movement data, and the relative positional relationship between the driver and the vehicle; Based on the head movement data, the driver's head rotation trajectory is determined; Based on the eye-tracking data, the trajectory of the driver's pupil movement is determined; The driver's line of sight is determined based on the head rotation trajectory, the pupil movement trajectory, and the relative positional relationship.

[0010] Optionally, the standard driving behavior for determining at least one actual driving scenario corresponding to the external environment image includes: The external environment image is input into a preset scene recognition model, and the preset scene recognition model outputs at least one actual driving scene. For any real-world driving scenario, the standard driving behavior corresponding to the real-world driving scenario is determined based on the real-world driving scenario and the preset mapping relationship. The preset mapping relationship is used to reflect the correspondence between different actual driving scenarios and standard driving behaviors. The preset scenario recognition model is trained by a training sample set, which includes multiple training samples. Each training sample includes a set of environmental images and the corresponding actual driving scenario in the driver's test.

[0011] According to a second aspect of this application, a driver's license examination assessment device is provided, the device comprising: The acquisition module is used to acquire the driver's line of sight, the vehicle's motion state, and the external environment image of the vehicle. The first determining module is used to determine the standard driving behavior of at least one actual driving scenario corresponding to the external environment image; The second determining module is used to determine the driver's actual driving behavior in any given actual driving scenario based on the line-of-sight trajectory and the corresponding vehicle movement state. The evaluation module is used to evaluate the driver's test results based on the standard driving behavior corresponding to each actual driving scenario and the actual driving behavior corresponding to each actual driving scenario.

[0012] According to a third aspect of this application, a driver's license examination assessment system is provided, the system comprising: An eye-tracking module is used to acquire the driver's eye movement trajectory; An environmental image sensor is used to acquire images of the external environment of the vehicle driven by the driver; Memory, used to store computer instructions; A processor for retrieving computer instructions from the memory to perform the method as described in any one of the first aspects.

[0013] Optionally, the eye-tracking module is located at the center console or A-pillar of the vehicle. The environmental image sensor includes a front-view camera, a left-view camera, a right-view camera, and a rear-view camera. The front-view camera is located at the front of the vehicle, the left-view camera is located at the left rearview mirror, the right rearview mirror, and the rear-view camera is located at the rear of the vehicle.

[0014] According to a fourth aspect of this application, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method according to any one of the first aspects.

[0015] Based on the above, this application provides a driver's license examination evaluation method. The method includes: acquiring the driver's eye trajectory, the vehicle's motion state, and an image of the vehicle's external environment; determining standard driving behavior for at least one actual driving scenario corresponding to the external environment image; for any actual driving scenario, determining the driver's actual driving behavior based on the eye trajectory and vehicle motion state corresponding to the actual driving scenario; and evaluating the driver's license examination results based on the standard driving behavior and the actual driving behavior for each actual driving scenario. In this method, actual driving behavior reflects not only the driver's hand and foot movements but also their eye movements. Therefore, evaluating driver's license examination results based on actual driving behavior can incorporate an assessment of the driver's eye responses. Furthermore, this method is a fully automated driver's license examination result evaluation method, avoiding the subjectivity inherent in manual evaluation. Therefore, this application provides a novel driver's license examination evaluation method.

[0016] Other features and advantages of this application will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of the present application and, together with their description, serve to explain the principles of the present application.

[0018] Figure 1 This is a flowchart illustrating an assessment method for a driver's license examination provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a driver's license examination assessment device provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a driver's license examination assessment system provided in an embodiment of this application. Detailed Implementation

[0019] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present application.

[0020] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the scope of this application and its application or use.

[0021] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0022] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0023] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0024] This application provides a method for evaluating driver's license examinations, which is applied to a driver's license examination evaluation system. The method is triggered when a driver takes a driver's license examination to evaluate the examination results. The driver's license examination can be a formal driver's license examination or a simulated driver's license examination.

[0025] like Figure 1 As shown, the driver's license examination assessment method provided in this application includes the following steps S1100 to S1400.

[0026] Step S1100: Acquire the driver's line of sight, the vehicle's motion state, and the vehicle's external environment image.

[0027] Among them, the driver's eye trajectory describes the trajectory of the driver's eye observation, that is, eye movements, which can reflect the driver's eye reaction during the driver's test. This reaction can reflect the driver's attention allocation, fatigue state and quick decision-making ability.

[0028] In one example, the driver's line of sight is as follows: looking at the left rearview mirror, then the right rearview mirror, then the headlight control area, and finally the seatbelt buckle area.

[0029] In this embodiment, the driver's license examination assessment system includes an eye-tracking module, which is used to acquire the driver's eye trajectory. Furthermore, in one embodiment of this application, the eye-tracking module can be positioned in front of, to the left of, or to the right of the driver. Alternatively, the eye-tracking module can be positioned at the center console or the A-pillar of the vehicle. Of course, the eye-tracking module can also be integrated into a head-mounted device worn by the driver.

[0030] The vehicle motion state described by the driver is used to describe how the vehicle moves under the driver's hand and foot movements. In one example, the vehicle motion state is a left turn followed by a right turn.

[0031] In one embodiment of this application, the driver's examination assessment system instructs the vehicle to report its motion status. Under the instruction of the driver's examination assessment system, the vehicle detects its motion status and reports it to the driver's examination assessment system.

[0032] The vehicle's external environment image is used to describe the environment outside the vehicle during driving. In this embodiment, the driver's license examination assessment system includes an environmental image sensor, which acquires images of the vehicle's external environment. The environmental image sensor may include multiple cameras. In one embodiment of this application, the environmental image sensor includes four cameras, which are respectively located at the front of the vehicle, the left rearview mirror, the right rearview mirror, and the rear of the vehicle. This allows the environmental image sensor to achieve comprehensive, blind-spot-free acquisition of images of the vehicle's surrounding environment. It should be noted that the environmental image sensor can reuse cameras within the vehicle, which can reduce the hardware cost of the driver's license examination assessment system.

[0033] In one embodiment of this application, obtaining the driver's line of sight trajectory in step S1100 is specifically achieved through the following steps S1110 to S1113.

[0034] Step S1110: Obtain the driver's head movement data, the driver's eye movement data, and the relative positional relationship between the driver and the vehicle.

[0035] In one embodiment of this application, when the eye-tracking module is installed on a head-mounted device, an IMU is also installed on the head-mounted device. The driver's head movement data is acquired through the IMU on the head-mounted device.

[0036] In another embodiment of this application, when the eye-tracking module is installed in a vehicle, the driver's head movement data can be obtained from the infrared images captured by the infrared camera in the eye-tracking module.

[0037] Eye-tracking data is collected directly by the eye-tracking module. Specifically, the relative positional relationship between the driver and the vehicle includes the relative positional relationship between the driver and various parts of the vehicle in a standard driving posture, such as the relative positional relationship between the driver's eyes and the left rearview mirror. This relative positional relationship between the driver and the vehicle is pre-calibrated and pre-stored in the driver's license examination assessment system.

[0038] Step S1111: Determine the driver's head rotation trajectory based on head movement data.

[0039] In this embodiment, the driver's head posture is determined based on head motion data, and the sequential head postures constitute the driver's head rotation trajectory.

[0040] Step S1112: Determine the driver's pupil movement trajectory based on eye-tracking data.

[0041] In this embodiment, the center of the driver's pupil is determined based on eye-tracking data, and the sequential pupil centers constitute the driver's pupil movement trajectory.

[0042] Step S1113: Determine the driver's line of sight trajectory based on the head rotation trajectory, pupil movement trajectory, and relative positional relationship.

[0043] In this embodiment, the driver's gaze direction is determined based on the head rotation trajectory and pupil movement trajectory. Combining the gaze direction with the relative positional relationship between the driver and the vehicle, the driver's gaze trajectory can then be determined.

[0044] Of course, other methods different from steps S1110 to S1113 above can also be used to obtain the driver's line of sight trajectory.

[0045] Step S1200: Determine the standard driving behavior for at least one actual driving scenario corresponding to the external environment image.

[0046] It is understandable that the external environment image is strongly correlated with the actual driving scenario; therefore, at least one actual driving scenario can be obtained from the external environment image.

[0047] Real-world driving scenarios can include scenarios from multiple dimensions. For example, real-world driving scenarios include at least one of the following: test scenarios, natural scenarios, emergency scenarios, and special road areas.

[0048] The test scenarios include: vehicle preparation, reversing into a parking space, parallel parking, curved driving, direct turning, passing through a width-restricted gate, passing through a single-sided bridge, hill start, regular start, regular driving, lane change, parking at the side of the road, intersection, meeting oncoming traffic, overtaking, and U-turn. Natural scenes include: daytime, nighttime, cloudy, rainy, and snowy days; Emergency scenarios include: sudden braking of the vehicle in front, vehicles on the left, right, or behind being too close, acceleration, and deceleration; Special areas include: near sidewalks, school zones, bus stops, sharp bends in mountain roads, and tunnels.

[0049] In one embodiment of this application, the above step S1200 is specifically implemented through the following steps S1210 and S1211.

[0050] Step S1210: Input the external environment image into the preset scene recognition model, and output at least one actual driving scene from the preset scene recognition model.

[0051] The preset scene recognition model is trained from a training sample set, which includes multiple training samples. Each training sample includes a set of environmental images and the corresponding actual driving scenarios in the driver's test.

[0052] In this embodiment, the preset scene recognition model is a pre-trained customized neural network model or a large AI model. The specific training process is as follows: a training sample set consisting of multiple training samples is input into the preset neural network or large AI model. One of the training samples includes a set of environmental images and the actual driving scene in the driver's test, which serves as the label for the set of environmental images. The preset neural network or large AI model learns from the training samples in the training sample set to generate the preset scene recognition model.

[0053] It is understandable that there are usually multiple actual driving scenarios during a single driver's license test. Therefore, at least one actual driving scenario can be obtained through the above step S1210.

[0054] Step S1211: For any actual driving scenario, determine the standard driving behavior corresponding to the actual driving scenario based on the actual driving scenario and the preset mapping relationship.

[0055] Among them, the preset mapping relationship is used to reflect the correspondence between different actual driving scenarios and standard driving behaviors.

[0056] In one example, the preset mapping relationship is shown in Table 1 below.

[0057] Table 1

[0058] Step S1300: For any actual driving scenario, determine the driver's actual driving behavior in the actual driving scenario based on the line-of-sight trajectory and the corresponding vehicle movement state.

[0059] In this embodiment, for any actual driving scenario, the vehicle movement state and line-of-sight trajectory within the corresponding time period of the driving scenario are determined as the line-of-sight trajectory and the corresponding vehicle movement state of the actual driving scenario.

[0060] Furthermore, the driver aligns the eye trajectory and vehicle motion state corresponding to the actual driving scenario in time to obtain the actual driving behavior, which is a combination of the driver's eye movements and hand and foot movements in time. That is, actual driving behavior includes eye movements and hand and foot movements. Based on this, it can be understood that a driver's actual driving behavior usually consists of at least one actual driving action, which is either an eye movement or a hand and foot movement. In one example, the driver's actual driving behavior is: sequentially observing the left rearview mirror, turning left, observing the right rearview mirror, and turning right, where observing the left rearview mirror, turning left, and observing the right rearview mirror are each an actual driving action.

[0061] As can be seen from the above step S1300, the actual driving behavior in this embodiment can reflect not only the driver's hand and foot movements, but also the driver's eye movements. Therefore, based on the actual driving behavior obtained in step S1300, the evaluation of the driver's test results can be combined with the driver's eye reaction.

[0062] Step S1400: Evaluate the driver's test results based on the standard driving behavior corresponding to each actual driving scenario and the actual driving behavior corresponding to each actual driving scenario.

[0063] In this embodiment, for any real-world driving scenario, the actual driving behavior is the driver's input answer in the driver's license exam, while the standard driving behavior is the correct answer in the driver's license exam. Therefore, the standard driving behavior is compared with the actual driving behavior to obtain the deviation between the two. Furthermore, based on the deviation between the standard driving behavior and the actual driving behavior, the corresponding sub-result of the exam in the real-world driving scenario is obtained. Even further, based on the sub-results of the exams in all real-world driving scenarios, the final exam result for the driver's license exam can be obtained.

[0064] In one embodiment of this application, step S1400 is specifically implemented through the following steps S1410 and S1411.

[0065] Step S1410: For any actual driving action in any actual driving behavior corresponding to any actual driving scenario, determine whether the actual driving action matches the standard driving action in the corresponding order in the standard driving behavior, and obtain the matching result of the actual driving action.

[0066] The matching results include both matches and non-matches.

[0067] In this embodiment, for any actual driving action in any actual driving behavior corresponding to any actual driving scenario, firstly, the standard action in the corresponding order is found from the standard driving behavior corresponding to that actual driving scenario, and then the actual driving action is compared with the corresponding standard action. If the two are the same or similar actions, the matching result of the actual driving action is determined to be a match; otherwise, it is a mismatch.

[0068] Step S1411: Determine the driver's test score based on the matching results of each actual driving action in each actual driving behavior corresponding to each actual driving scenario.

[0069] In one embodiment of this application, for any given actual driving scenario, each standard driving action in the corresponding standard driving behavior corresponds to a deduction score. Based on this, the specific implementation of step S1411 above can be as follows: for any actual driving scenario, select the non-matching matching results from the matching results corresponding to each actual driving action in the actual driving behavior; sum the deduction scores of the standard driving actions corresponding to the non-matching matching results to obtain the total deduction score for that actual driving scenario; sum the deduction scores of all actual driving scenarios to obtain the total deduction score; subtract the aforementioned total deduction score from the full score of the driver's license test to obtain the driver's license test score.

[0070] Based on the above, this application provides a driver's license examination evaluation method. The method includes: acquiring the driver's eye trajectory, the vehicle's motion state, and an image of the vehicle's external environment; determining standard driving behavior for at least one actual driving scenario corresponding to the external environment image; for any actual driving scenario, determining the driver's actual driving behavior based on the eye trajectory and vehicle motion state corresponding to the actual driving scenario; and evaluating the driver's license examination results based on the standard driving behavior and the actual driving behavior for each actual driving scenario. In this method, actual driving behavior reflects not only the driver's hand and foot movements but also their eye movements. Therefore, evaluating driver's license examination results based on actual driving behavior can incorporate an assessment of the driver's eye responses. Furthermore, this method is a fully automated driver's license examination result evaluation method, avoiding the subjectivity inherent in manual evaluation. Therefore, this application provides a novel driver's license examination evaluation method.

[0071] In one embodiment of this application, the driver's license examination assessment method provided in this application further includes the following step S1500 after the above step S1300.

[0072] Step S1500: For any actual driving scenario, if the standard driving behavior corresponding to the actual driving scenario includes the target standard driving action, and if the actual driving action in the corresponding order of the actual driving behavior in the actual driving scenario does not match the target standard driving action, output an alarm message.

[0073] In this embodiment, standard driving actions that would lead to dangerous driving if they do not conform to standard driving procedures are recorded as target driving actions. Therefore, if, for any target standard driving action in standard driving behavior, the corresponding sequence of actual driving actions in a real-world driving scenario does not match the target standard driving action, it indicates that the driver is engaging in dangerous driving. In this case, a warning message is output, such as playing a voice message saying "Danger," or displaying an exclamation mark (!") on the vehicle's central control screen.

[0074] Through the above step S1500, the driver examination assessment method provided in this application can also monitor whether actual driving actions will lead to dangerous driving, thereby improving the driver's driving safety.

[0075] Based on any of the above embodiments, the driver examination assessment method provided in this application further includes the following step S1600 after step S1300.

[0076] Step S1600: For any actual driving scenario, output a driving analysis report for the driver based on the standard driving behavior corresponding to the actual driving scenario and the actual driving behavior under the actual driving scenario.

[0077] In one embodiment of this application, standard driving behavior corresponding to the actual driving scenario, actual driving behavior in the actual driving scenario, and analysis instructions are input into the AI ​​big data model, which then outputs a driving analysis report. The analysis instructions are at least used to instruct the AI ​​big data model to analyze the driver's erroneous driving habits and provide driving suggestions to promote the improvement of the driver's driving skills.

[0078] Furthermore, the method of outputting the driver's driving analysis report in step S1600 can be specifically to output the driver's driving analysis report to the target terminal device. The target terminal device is the driver's terminal device, and / or the target terminal device is the instructor's or driving school's terminal device.

[0079] like Figure 2 As shown, this application also provides a driver's license examination assessment device 200, the device 200 comprising: The acquisition module 210 is used to acquire the driver's line of sight trajectory, the vehicle's motion state while the driver is driving the vehicle, and the external environment image of the vehicle. The first determining module 220 is used to determine the standard driving behavior of at least one actual driving scenario corresponding to the external environment image; The second determining module 230 is used to determine the driver's actual driving behavior in any of the actual driving scenarios based on the line-of-sight trajectory and the corresponding vehicle movement state. The evaluation module 240 is used to evaluate the test results of the driver's examination based on the standard driving behavior corresponding to each actual driving scenario and the actual driving behavior corresponding to each actual driving scenario.

[0080] In one embodiment of this application, the evaluation module 240 is specifically used to determine whether the actual driving action matches the standard driving action in the corresponding order in the standard driving behavior for any actual driving action in any actual driving behavior corresponding to any actual driving scenario, and to obtain a matching result of the actual driving action, wherein the matching result includes matching and non-matching. The driver's test score is determined based on the matching results of each actual driving action in each actual driving behavior corresponding to each actual driving scenario.

[0081] In one embodiment of this application, the driver's license examination assessment device 300 provided in this application further includes: The first output module is used to output an alarm message for any actual driving scenario, where the standard driving behavior corresponding to the actual driving scenario includes a target standard driving action, and for any target standard driving action, if the actual driving action in the corresponding order of the actual driving behavior in the actual driving scenario does not match the target standard driving action.

[0082] In one embodiment of this application, the driver's license examination assessment device 400 provided in this application further includes: The second output module is used to output a driving analysis report of the driver for any of the actual driving scenarios, based on the standard driving behavior corresponding to the actual driving scenario and the actual driving behavior in the actual driving scenario.

[0083] In one embodiment of this application, the acquisition module 210 is specifically used to acquire the driver's head movement data, the driver's eye movement data, and the relative positional relationship between the driver and the vehicle; Based on the head movement data, the driver's head rotation trajectory is determined; Based on the eye-tracking data, the trajectory of the driver's pupil movement is determined; The driver's line of sight is determined based on the head rotation trajectory, the pupil movement trajectory, and the relative positional relationship.

[0084] In one embodiment of this application, the first determining module 220 is specifically used to input the external environment image into a preset scene recognition model, and the preset scene recognition model outputs at least one actual driving scene; For any real-world driving scenario, the standard driving behavior corresponding to the real-world driving scenario is determined based on the real-world driving scenario and the preset mapping relationship. The preset mapping relationship is used to reflect the correspondence between different actual driving scenarios and standard driving behaviors. The preset scenario recognition model is trained by a training sample set, which includes multiple training samples. Each training sample includes a set of environmental images and the corresponding actual driving scenario in the driver's test.

[0085] like Figure 3 As shown, this application also provides a driver's license examination assessment system 500, the system 300 comprising: Eye-tracking module 310 is used to acquire the driver's gaze trajectory; An environmental image sensor 320 is used to acquire images of the external environment of the vehicle driven by the driver. Memory 330 is used to store computer instructions; Processor 340 is configured to retrieve computer instructions from the memory to perform the method as described in any of the above method embodiments.

[0086] In one embodiment of this application, the eye-tracking module is disposed at the center console or A-pillar of the vehicle, and the environmental image sensor includes a front-view camera, a left-view camera, a right-view camera, and a rear-view camera, wherein the front-view camera is disposed at the front of the vehicle, the left-view camera is disposed at the left rearview mirror, the right rearview mirror, and the rear-view camera is disposed at the rear of the vehicle.

[0087] In one embodiment of this application, the driver's license examination assessment system 300 may be integrated into the vehicle. Alternatively, it may be independent of the vehicle.

[0088] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the methods described in the above-described method embodiments.

[0089] This application may be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this application.

[0090] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0091] 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.

[0092] The computer program instructions used to perform the operations of this application may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status 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 circuits, such as programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), are personalized by utilizing the status information of the computer-readable program instructions. These electronic circuits can execute the computer-readable program instructions to implement various aspects of this application.

[0093] Various aspects of this application are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. 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.

[0094] 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.

[0095] 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.

[0096] 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 this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing 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 marked 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, can 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. It will be well known to those skilled in the art that implementation in hardware, implementation in software, and implementation using a combination of software and hardware are equivalent.

[0097] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical applications, or technical improvements to the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of this application is defined by the appended claims.

Claims

1. A method of evaluating a driver's test, characterized in that The method comprises: acquiring a line-of-sight trajectory of a driver, a vehicle motion state of the driver driving a vehicle, and an external environment image of the vehicle; determining a standard driving behavior of at least one actual driving scene corresponding to the external environment image; for any actual driving scene, determining an actual driving behavior of the driver under the actual driving scene according to the line-of-sight trajectory corresponding to the actual driving scene and the vehicle motion state corresponding to the actual driving scene; evaluating an examination result of a driver examination according to the standard driving behavior corresponding to each actual driving scene and the actual driving behavior corresponding to each actual driving scene.

2. The method of claim 1, wherein, The evaluation of the examination result of the driver examination according to the standard driving behavior corresponding to each actual driving scene and the actual driving behavior corresponding to each actual driving scene comprises: for any actual driving action in the actual driving behavior corresponding to any actual driving scene, determining whether the actual driving action matches a standard driving action in a corresponding order in the standard driving behavior, to obtain a matching result of the actual driving action, the matching result comprising matching and not matching; determining a score of the driver examination according to the matching result corresponding to each actual driving action in the actual driving behavior corresponding to each actual driving scene.

3. The method of claim 1, wherein, After the determination of the actual driving behavior of the driver under the actual driving scene according to the line-of-sight trajectory corresponding to the actual driving scene and the vehicle motion state corresponding to the actual driving scene for any actual driving scene, the method further comprises: for any actual driving scene, if the standard driving behavior corresponding to the actual driving scene comprises a target standard driving action, and if an actual driving action in a corresponding order in the actual driving behavior under the actual driving scene does not match the target standard driving action for any target standard driving action, outputting an alarm prompt information.

4. The method of claim 1, wherein, The method further comprises: for any actual driving scene, outputting a driving analysis report of the driver according to the standard driving behavior corresponding to the actual driving scene and the actual driving behavior under the actual driving scene.

5. The method of claim 1, wherein, The acquisition of the line-of-sight trajectory of the driver comprises: acquiring head motion data of the driver, eye movement data of the driver, and a relative position relationship between the driver and the vehicle; determining a head rotation trajectory of the driver according to the head motion data; determining a pupil movement trajectory of the driver according to the eye movement data; determining the line-of-sight trajectory of the driver according to the head rotation trajectory, the pupil movement trajectory, and the relative position relationship.

6. The method of claim 1, wherein, The determination of the standard driving behavior of at least one actual driving scene corresponding to the external environment image comprises: inputting the external environment image into a preset scene recognition model, and outputting at least one actual driving scene by the preset scene recognition model; for any actual driving scene, determining the standard driving behavior corresponding to the actual driving scene according to a preset mapping relationship between the actual driving scene and the standard driving behavior. The preset mapping relationship is used to reflect a corresponding relationship between different actual driving scenes and standard driving behaviors, the preset scene recognition model is obtained by training a training sample set, the training sample set includes a plurality of training samples, and one training sample includes a group of environment images and a corresponding actual driving scene in the driver test.

7. An evaluation device for a driver's test, characterized in that The device comprises: An acquisition module is configured to acquire a line-of-sight trajectory of a driver, a vehicle motion state of a vehicle driven by the driver, and an external environment image of the vehicle. A first determination module is configured to determine a standard driving behavior of at least one actual driving scene corresponding to the external environment image. A second determination module is configured to, for any actual driving scene, determine an actual driving behavior of the driver for the actual driving scene according to a line-of-sight trajectory corresponding to the actual driving scene and a corresponding vehicle motion state. An evaluation module is configured to evaluate a test result of a driver test according to the standard driving behavior corresponding to each actual driving scene and the actual driving behavior corresponding to each actual driving scene.

8. An evaluation system for a driver's examination, characterized in that The system comprises: An eye tracking module is configured to acquire a line-of-sight trajectory of a driver. An environment image sensor is configured to acquire an external environment image of a vehicle driven by the driver. A memory is configured to store computer instructions. A processor is configured to call the computer instructions from the memory to execute the method according to any one of claims 1-6.

9. The system of claim 8, wherein, The eye tracking module is arranged at a central control position or an A-pillar position of the vehicle, and the environment image sensor comprises a front-view camera, a left-view camera, a right-view camera, and a rear-view camera, wherein the front-view camera is arranged at the front of the vehicle, the left-view camera is arranged at a left side-view mirror, the right-view camera is arranged at a right side-view mirror, and the rear-view camera is arranged at the tail of the vehicle.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer program, and the computer program is executed by the processor to implement the method according to any one of claims 1-6. A computer program is stored on the computer program, and the computer program is executed by the processor to implement the method according to any one of claims 1-6.

Images