Driving ability evaluation system and method based on eye movement analysis

Abstract

The invention discloses a driving ability evaluation system and method based on eye movement analysis, and relates to the technical field of driving ability quantitative evaluation, and the method comprises the steps: obtaining driving parameter data and eye movement data when a tested person completes a simulation driving task on a simulation driving platform; performing data alignment and preprocessing on the driving parameter data and the eye movement data on a time axis; based on the preprocessed eye movement data, respectively calculating a fixation point percentage in each region of interest, a unit time glancing amplitude of the tested person, and a visual entropy value, a fixation frequency and a nearest neighbor index corresponding to the simulated driving task of the tested person in each stage; and the visual information search efficiency and the cognitive condition change of the tested person in the driving process are evaluated. The technical problem that in the prior art, due to subjective deviation and single data dimension, the attention level and the response speed of a driver in the actual driving process cannot be comprehensively and accurately reflected is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of quantitative evaluation of driving ability, and particularly to a driving ability evaluation system and method based on eye movement analysis. Background Art

[0002] Currently, the evaluation systems for aviation and automotive driving ability mainly rely on two dimensions: task performance indicators and instructor subjective evaluation. Among them, the task performance quantitative indicators measure the basic skills of drivers through structured indicators such as the completion degree of preset operation processes (such as flight checklists, standard takeoff and landing procedures) and action errors. The instructor experience-based evaluation system relies on manual observation and subjective scoring. For example, the instructor grades the driver on dimensions such as the rationality of complex scenario decision-making and communication efficiency. In addition, traditional driving ability evaluations also include theoretical exam question banks and high-fidelity simulator test methods to verify the driver's theoretical knowledge reserve and specific scenario operation ability.

[0003] Although traditional methods are widely used in driving ability evaluation, they have the following technical bottlenecks:

[0004] Subjective evaluation deviation: The instructor's scoring is limited by individual experience differences and lacks quantitative basis for implicit indicators such as the driver's mental load and micro-expression changes, resulting in insufficient consistency of evaluation results;

[0005] Single data dimension: Existing systems only collect basic operation data and do not integrate physiological signals and environmental interaction data, making it difficult to comprehensively reflect the driver's attention level and reaction speed during actual driving. Summary of the Invention

[0006] The purpose of the present invention is to provide a driving ability evaluation system and method based on eye movement analysis to solve at least one of the above technical problems.

[0007] In a first aspect, an embodiment of the present invention provides a driving ability evaluation method based on eye movement analysis, including: obtaining driving parameter data and eye movement data of a person to be tested when completing a simulated driving task on a simulated driving platform; the eye movement data includes fixation point data of the person to be tested in multiple regions of interest on the simulated platform; performing data alignment and preprocessing on the driving parameter data and the eye movement data on the time axis to obtain preprocessed driving parameter data and preprocessed eye movement data; based on the preprocessed eye movement data, calculating the fixation point percentage in each region of interest, the saccade amplitude per unit time of the person to be tested, the visual entropy value corresponding to each stage of the simulated driving task of the person to be tested, the fixation frequency, and the nearest neighbor index; evaluating the visual information search efficiency of the person to be tested during driving based on the fixation point percentage, the saccade amplitude per unit time, and the visual entropy value; evaluating the change in the cognitive situation of the person to be tested during driving based on the fixation frequency, the nearest neighbor index, and the visual entropy value.

[0008] Further, performing data alignment and preprocessing on the driving parameter data and the eye movement data on the time axis includes: performing data alignment on the driving parameter data and the eye movement data on the time axis; taking multiple anchor points set on the simulated driving platform as a reference, mapping the eye movement data with the static global map of the person to be tested when completing the simulated driving task to obtain an eye movement data mapping effect diagram; the eye movement data mapping effect diagram includes fixation point data in each region of interest.

[0009] Further, the calculation formula for the fixation point percentage in each region of interest includes:

[0010]

[0011] In the formula, P i is the fixation point percentage in the i-th region of interest, and A i is the number of fixation points in the i-th region of interest.

[0012] Further, the calculation formula for the saccade amplitude per unit time of the person to be tested includes:

[0013]

[0014] In the formula, S is the saccade amplitude per unit time, S total is the total saccade amplitude of the person to be tested, and N is the number of fixation points.

[0015] Further, the calculation formula for the visual entropy value includes:

[0016]

[0017] where H is the visual entropy value, and π i is the ratio of the fixation frequency in the i-th region of interest to the sum of the fixation numbers in all regions of interest, m is the number of regions of interest, and p ij is the probability that the fixation point transfers from the i-th region of interest to the j-th region of interest.

[0018] Furthermore, the calculation formula of the nearest neighbor index includes:

[0019]

[0020] where NNI is the nearest neighbor index, min(d ij ) represents the distance between the two nearest fixation points, A represents the area of the fixation point distribution region, and N is the number of fixation points.

[0021] Furthermore, the visual information search efficiency includes attention preference, attention span, and attention stability; based on the fixation percentage, the saccade amplitude per unit time, and the visual entropy value, the visual information search efficiency of the tested person during driving is evaluated, including: based on the fixation percentage, the attention preference of the tested person during driving is evaluated; based on the saccade amplitude per unit time, the attention span of the tested person during driving is evaluated; based on the visual entropy value, the attention stability of the tested person during driving is evaluated.

[0022] In a second aspect, an embodiment of the present invention further provides a driving ability evaluation system based on eye movement analysis, including: an acquisition module, a preprocessing module, a calculation module, a first evaluation module, and a second evaluation module; wherein, the acquisition module is used to acquire driving parameter data and eye movement data of a tested person when completing a simulated driving task on a simulated driving platform; the eye movement data includes fixation point data of the tested person in multiple regions of interest on the simulated platform; the preprocessing module is used to perform data alignment and preprocessing on the driving parameter data and the eye movement data on the time axis to obtain the preprocessed driving parameter data and the preprocessed eye movement data; the calculation module is used to calculate, based on the preprocessed eye movement data, the fixation percentage in each region of interest, the saccade amplitude per unit time of the tested person, the visual entropy value corresponding to the tested person in each stage of the simulated driving task, the fixation frequency, and the nearest neighbor index; the first evaluation module is used to evaluate the visual information search efficiency of the tested person during driving based on the fixation percentage, the saccade amplitude per unit time, and the visual entropy value; the second evaluation module is used to evaluate the change in the cognitive situation of the tested person during driving based on the fixation frequency, the nearest neighbor index, and the visual entropy value.

[0023] In a third aspect, an embodiment of the present invention further provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the method provided by the embodiment of the present invention is implemented.

[0024] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method provided by the embodiment of the present invention is implemented.

[0025] The present invention provides a driving ability evaluation system and method based on eye movement analysis. By analyzing eye movement data, it is possible to more accurately evaluate factors affecting safe driving, such as drivers' attention allocation and visual search patterns, provide support for driving training, safety assessment, and the formulation of personalized driving assistance programs, and alleviate the technical problems in the prior art that cannot comprehensively and accurately reflect drivers' attention levels and reaction speeds due to subjective biases and single data dimensions. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for the specific embodiments or the description of the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0027] Figure 1 It is a flowchart of a driving ability evaluation method based on eye movement analysis provided by an embodiment of the present invention;

[0028] Figure 2 It is a schematic diagram of the cabin area of a flight simulation driving platform provided by an embodiment of the present invention;

[0029] Figure 3 It is a schematic diagram of the relationship between eye movement data and cognitive characteristics provided by an embodiment of the present invention;

[0030] Figure 4 It is a schematic diagram of a driving ability evaluation system based on eye movement analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0032] Embodiment 1

[0033] Figure 1 is a flowchart of a driving ability evaluation method based on eye movement analysis according to an embodiment of the present invention. As Figure 1 shown, the method specifically includes the following steps:

[0034] Step S102, obtain the driving parameter data and eye movement data of the person to be tested when completing the simulated driving task on the simulated driving platform; the eye movement data includes the fixation point data of multiple regions of interest of the person to be tested on the simulated platform.

[0035] Step S104, perform data alignment and preprocessing on the driving parameter data and eye movement data on the time axis to obtain the preprocessed driving parameter data and the preprocessed eye movement data.

[0036] Step S106, based on the preprocessed eye movement data, calculate the fixation percentage in each region of interest, the saccade amplitude per unit time of the person to be tested, the visual entropy value corresponding to each stage of the simulated driving task of the person to be tested, the fixation frequency, and the nearest neighbor index respectively.

[0037] Step S108, evaluate the visual information search efficiency of the person to be tested during driving based on the fixation percentage, the saccade amplitude per unit time, and the visual entropy value.

[0038] Step S110, evaluate the change in the cognitive situation of the person to be tested during driving based on the fixation frequency, the nearest neighbor index, and the visual entropy value.

[0039] Optionally, the simulated driving tasks in the embodiments of the present invention include automobile simulated driving tasks and aviation simulated driving tasks. The simulated driving platform includes an automobile simulated driving platform or a flight simulation driving platform.

[0040] Figure 2 is a schematic diagram of the cabin area of a flight simulation driving platform according to an embodiment of the present invention. Among them, the software used for the flight simulation driving platform is DCSworld. As Figure 2 shown, first, the flight simulation driving platform is set up and tested, specifically including:

[0041] Software part:

[0042] (1) Open the Simapp software and set the screen resolution of the overall environment to ensure consistency with the content of DCSworld;

[0043] (2) Open the DCSworld program, enter the "Mission Editor", load the saved mission scenario, and wait for the scenario data to be loaded online;

[0044] (3) Press the simulation flight start button to start the flight mission.

[0045] Hardware part:

[0046] (1) Check the normal working conditions of the joystick, throttle, and pedals to ensure there is no looseness or damage;

[0047] (2) Record the socket positions of all interfaces to ensure consistency during subsequent analysis;

[0048] (3) Paste the specified QR codes at multiple preset positions on the flight simulation platform as anchor points and place them in fixed positions for subsequent mapping of eye movement data.

[0049] After that, the test subject wears the eye tracker and starts the flight mission. The test subject enters the DCSworld simulation environment and completes the flight mission. Each person repeats the flight mission at least 6 times to reduce errors caused by abnormal environments. During the flight, the test subject needs to observe and process multiple information sources, including the information on the left DDI, right DDI, UFC, other areas inside the cabin, and areas outside the cabin, and adjust the pitch, roll, speed, and heading of the aircraft by manually controlling the flight devices (joystick, throttle lever, rudder pedals) to ensure that the aircraft flies along the predetermined flight path.

[0050] After the experiment, export the flight parameter data and eye movement data of the test subject. The data file naming format is "Test subject code - Test time - Dataset name".

[0051] Specifically, step S104 further includes the following steps:

[0052] Step S1041, align the driving parameter data and eye movement data on the time axis.

[0053] Step S1042, based on multiple anchor points set on the simulation driving platform, map the eye movement data to the static global map of the test subject when completing the simulation driving task to obtain the eye movement data mapping effect diagram; the eye movement data mapping effect diagram includes the fixation point data in each region of interest.

[0054] Specifically, taking Figure 2 the shown QR code as the anchor point, map the eye movement data in the dynamic first-person view to the static global map.

[0055] Preprocessing of eye movement data includes: when the sampling frequency is N Hz, on the premise that the given minimum fixation duration t is 100 milliseconds, the data of the same target object needs to be continuously recorded N / 10 times to reach the minimum duration. That is, for the selected fixation point data, it is stipulated that the same fixation target object is recorded continuously for more than N / 10 frames to be recorded as one fixation data.

[0056] The main elements of driver ability assessment include various types. Their perception of the environment mainly relies on vision to collect various information such as flight status, sea surface status, flight signal lights, and flight instrument panels. This invention mainly selects evaluation indicators for the perception link of the driver from the perspective of vision; the decision-making process of the driver is actually a series of thinking activities in the brain, and the activities of the nervous system are difficult to measure with a certain indicator. Therefore, this invention corresponds the driver's decision-making result to the driving behavior to examine the driver's reaction to achieve the task goal. As a very important part in the process of constructing a comprehensive assessment, when selecting evaluation indicators, the principles of scientificity, availability, and comprehensiveness should be followed to evaluate as objectively and accurately as possible.

[0057] An excellent driver must master an efficient fixation / attention switching strategy. The evaluation of the driver's visual performance is to evaluate the situation of occupying the visual channel to process information during the cognitive process, including the evaluation of visual information search and visual information encoding. According to the relationship between eye movement and cognitive processing and attention transfer, and the two pathways of visual information processing in human-computer interaction, the measured indicators are based on the characteristics of eye movement behavior and reflect the attention and cognitive situation characteristics of the driver in the task. Figure 3 It is a schematic diagram of the relationship between eye movement data and cognitive characteristics provided by an embodiment of the present invention.

[0058] The driver's visual information search refers to the movement from one viewpoint to the next after completing information encoding at a certain viewpoint, and attention transfer occurs between two visual encodings. The driver quickly searches through the saccade behavior of the eyes among a large amount of information in the field of vision to determine a new area of interest.

[0059] Specifically, the visual information search effectiveness includes attention preference, attention span, and attention stability; step S108 further includes the following steps:

[0060] Step S1081, based on the percentage of fixation points, evaluate the attention preference of the person being tested during driving;

[0061] Step S1082, based on the saccade amplitude per unit time, evaluate the attention span of the person being tested during driving;

[0062] Step S1083, based on the visual entropy value, evaluate the attention stability of the person being tested during driving.

[0063] Specifically, the present invention selects the percentage of fixation points in the area of interest (AOIPercentage) to characterize the attention preference. The difference in the number of fixation points in each area of interest indicates the relative importance of each target information to the perceiver. When performing a flight task, the order of saccade is affected by the requirements of the flight manual. The monitoring of flight parameters restricts the driver's visual point, and the selection of the area of interest is the result of the selective allocation of the driver's attention. In different task environments, the driver's attention preference is different, and there are differences in the degree of attention to the instrument. The percentage of fixation points p in the i-th area of interest i is related to the number of fixation points A in the i-th area of interest i . The calculation formula for the percentage of fixation points in each area of interest includes:

[0064]

[0065] In the formula, P i is the percentage of fixation points in the i-th area of interest, and A i is the number of fixation points in the i-th area of interest.

[0066] Specifically, the present invention selects the saccade amplitude to characterize the attention span. There is a certain correlation between the task difficulty and the attention span. Increasing the task difficulty is accompanied by an increase in the amount of information. At this time, the cone angle of the visual area decreases, the effective visual threshold of attention decreases, and the tunnel vision phenomenon occurs, resulting in a decrease in the saccade amplitude. The total saccade amplitude S total is related to the number of fixation points N and the center of gravity CoG of the fixation points:

[0067]

[0068] Then the calculation of the saccade amplitude S per minute is as follows:

[0069]

[0070] Specifically, the calculation formula for the visual entropy value includes:

[0071]

[0072] In the formula, H is the visual entropy value, π i is the ratio of the frequency of fixation points in the i-th area of interest to the sum of the number of fixation points in all areas of interest, m is the number of areas of interest, and p ij is the probability that the fixation point transfers from the i-th area of interest to the j-th area of interest.

[0073] Specifically, the present invention selects the Visual Entropy to characterize the attention stability. Its magnitude depends on the randomness of the fixation point transfer and is related to the transfer probabilities in each region of interest. The maximum entropy is obtained when the transfer probabilities in each region of interest are the same. Generally, the relative entropy value is used to describe the regularity of the transfer. The visual entropy H is related to the transfer probability p of the viewpoint state space, and its general calculation expression is: i related, and its general calculation expression is:

[0074] Entrophy = H = Σp i log2(1 / p i )

[0075] The analysis of the visual entropy value in the present invention is based on the premise of dividing the regions of interest, and studies the stability of the attention transfer mode of the driver in each region of interest. First, it is necessary to analyze the transfer law of the driver's fixation points between the regions of interest. In the embodiment of the present invention, taking 7 regions of interest as an example, the fixation point transfer matrix under the given experimental conditions is calculated.

[0076] Let the fixation point sequence x = (x0, x1,... x n ) satisfy the Markov property. The region of interest where the previous fixation point is located and the region of interest where the adjacent subsequent fixation point is located, and the region of interest where the next fixation point is located is only affected by the region of interest where the previous fixation point is located, which is a statistical method for fixation point transfer. Let n ij be the frequency of the fixation point transferring from region of interest i to region of interest j. Then the matrix N composed of the frequencies of fixation transfers between the 7 regions of interest is as follows:

[0077]

[0078] Let p ij be the probability that the fixation point transfers from region of interest i to region of interest j, which is calculated by dividing n in the fixation point transfer frequency matrix ij by the total transfer frequency of the corresponding row, that is:

[0079]

[0080] And the matrix composed of p ij is the one-step transfer probability matrix of the driver's fixation points in the 7 regions of interest, that is:

[0081]

[0082] Let π i be the ratio of the fixation point frequency n i in region of interest i to the sum of the fixation point numbers in all regions of interest and n, that is:

[0083]

[0084] Using the transition probability p ij and the stationary distribution π determined by the convergence of all processes i to represent the attention transfer pattern in the 7 regions of interest, that is:

[0085]

[0086] From this, the visual entropy value of the driver under various flight stages and visibility conditions can be calculated.

[0087] Preferably, the present invention calculates the fixation frequency, the nearest neighbor index value, and the visual entropy value, and outputs the change in the driver's cognitive situation during the task execution. Among them, the fixation frequency is an eye movement index that can effectively reflect the cognitive situation in the task, which is the average fixation time or the number of fixations per unit time.

[0088] Specifically, the present invention selects the visual coding frequency to characterize the cognitive situation, and uses the measurable fixation frequency to reflect the coding frequency of visual information. Higher cognitive load is often accompanied by longer fixation time and lower fixation frequency. During the processing of the driver's visual information, the amount of information obtained, that is, the number of coded information, can be characterized by the total number of fixations n, and the time to obtain information, that is, the coding information efficiency, can be characterized by the total fixation time T fixaction (unit: s), and the coding frequency f of visual information v The expression is as follows:

[0089] f = f v = n / T fixation

[0090] Specifically, the Nearest Neighbor Index (NNI) can characterize the cognitive situation in the task by judging the randomness of the driver's fixation point distribution. An NNI value equal to 1 indicates that the fixation points are randomly distributed, an NNI value less than 1 indicates that the fixation points are more dispersed, and an NNI value greater than 1 indicates that the fixation points are regularly distributed. The NNI value can better reflect the change in the psychological situation during flight, and a higher NNI value of the fixation points reflects a high cognitive situation. Specifically, the calculation formula of the nearest neighbor index includes:

[0091]

[0092] In the formula, NNI is the nearest neighbor index, min(d ij ) represents the distance between the two nearest fixation points, A represents the area of the fixation point distribution region, and N is the number of fixation points.

[0093] Specifically, the method provided by the embodiments of the present invention further includes: based on the index system, combined with other indexes such as operation behaviors, a task portrait of the person to be tested observed under certain conditions is constructed. The instructor can accurately locate the problems of the driver in each flight stage according to this portrait and conduct targeted enhancement exercises. For example, if the fixation percentage of a certain driver in a specific area of interest is relatively low, it indicates that there are problems with their attention preference and relevant area observation training is needed.

[0094] As can be seen from the above description, the embodiments of the present invention provide a driving ability evaluation method based on eye movement analysis. By analyzing eye movement data, it can more accurately evaluate factors affecting safe driving such as the driver's attention allocation and visual search pattern, provide support for driving training, safety assessment, and the formulation of personalized driving assistance programs, and alleviate the technical problems in the prior art that cannot comprehensively and accurately reflect the driver's attention level and reaction speed during actual driving due to subjective deviation and single data dimension.

[0095] Embodiment 2

[0096] Figure 4 is a schematic diagram of a driving ability evaluation system based on eye movement analysis provided by the embodiments of the present invention. As Figure 4 shown, the system includes: an acquisition module 10, a preprocessing module 20, a calculation module 30, a first evaluation module 40, and a second evaluation module 50.

[0097] Specifically, the acquisition module 10 is used to acquire the driving parameter data and eye movement data of the person to be tested when completing the simulated driving task on the simulated driving platform; the eye movement data includes the fixation point data of the person to be tested in multiple areas of interest on the simulated platform.

[0098] The preprocessing module 20 is used to perform data alignment and preprocessing on the driving parameter data and eye movement data on the time axis to obtain the preprocessed driving parameter data and the preprocessed eye movement data.

[0099] The calculation module 30 is used to calculate the fixation percentage in each area of interest, the saccade amplitude per unit time of the person to be tested, the visual entropy value corresponding to the person to be tested in each stage of the simulated driving task, the fixation frequency, and the nearest neighbor index based on the preprocessed eye movement data.

[0100] The first evaluation module 40 is used to evaluate the visual information search efficiency of the person to be tested during driving based on the fixation percentage, the saccade amplitude per unit time, and the visual entropy value.

[0101] The second evaluation module 50 is used to evaluate the change in the cognitive situation of the person to be tested during driving based on the fixation frequency, the nearest neighbor index, and the visual entropy value.

[0102] Specifically, the visual information search efficiency includes attention preference, attention span, and attention stability; the first evaluation module 40 is further configured to:

[0103] Evaluate the attention preference of the tested person during driving based on the fixation percentage;

[0104] Evaluate the attention span of the tested person during driving based on the saccade amplitude per unit time;

[0105] Evaluate the attention stability of the tested person during driving based on the visual entropy value.

[0106] The present invention also provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the method provided by the embodiment of the present invention is implemented.

[0107] The present invention also provides a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by the processor, the method provided by the embodiment of the present invention is implemented.

[0108] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, in any regard, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be encompassed by the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

[0109] In addition, it should be understood that although this specification is described according to embodiments, not every embodiment only contains an independent technical solution. This narrative manner of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A driving ability assessment method based on eye movement analysis, characterized in that: include: Acquiring driving parameter data and eye movement data of the tested person when completing a simulated driving task on the simulated driving platform; the eye movement data includes gaze point data of the tested person in multiple interest areas of the simulated platform; Performing data alignment and preprocessing on the driving parameter data and the eye movement data on a time axis to obtain preprocessed driving parameter data and preprocessed eye movement data; Based on the pre-processed eye movement data, respectively calculating the percentage of fixation points in each region of interest, the scanning amplitude per unit time of the tested person, the visual entropy value, fixation frequency and nearest neighbor index corresponding to the simulated driving task of the tested person at each stage; Based on the percentage of fixation points, the scanning amplitude per unit time and the visual entropy value, evaluating the visual information search efficiency of the tested person during driving; Based on the gaze frequency, the nearest neighbor index and the visual entropy value, the changes in the cognitive status of the test person during the driving process are evaluated.

2. The method according to claim 1, characterized in that: Performing data alignment and preprocessing on the driving parameter data and the eye movement data on a time axis includes: Performing data alignment on the driving parameter data and the eye movement data on a time axis; Based on the multiple anchor points set on the simulated driving platform, the eye movement data is mapped with the static global map of the person being tested when completing the simulated driving task to obtain an eye movement data mapping effect map; the eye movement data mapping effect map includes the gaze point data in each area of ​​interest.

3. The method according to claim 1, characterized in that: The calculation formula for the percentage of fixations in each region of interest includes: Where P i is the percentage of fixations in the i-th region of interest, A i is the number of fixations in the i-th region of interest.

4. The method according to claim 1, characterized in that: The calculation formula of the scanning amplitude per unit time of the measured person includes: Where S is the sweep amplitude per unit time, S total is the total scanning amplitude of the person being measured, and N is the number of fixation points.

5. The method according to claim 1, characterized in that: The calculation formula of the visual entropy value includes: Where H is the visual entropy value, π i is the ratio of the frequency of fixations in the ith region of interest to the sum of the number of fixations in all regions of interest, m is the number of regions of interest, p ij is the probability that the gaze point shifts from the i-th region of interest to the j-th region of interest.

6. The method according to claim 1, characterized in that: The calculation formula of the nearest neighbor index includes: Where NNI is the nearest neighbor index, min(d ij ) represents the distance between the two nearest fixation points, A represents the area of ​​the fixation point distribution region, and N is the number of fixation points.

7. The method according to claim 1, characterized in that: The visual information search efficiency includes attention preference, attention span and attention stability; Based on the percentage of fixation points, the scanning amplitude per unit time and the visual entropy value, the visual information search efficiency of the tested person during driving is evaluated, including: Based on the percentage of fixation points, evaluating the attention preference of the tested person during driving; Based on the scanning amplitude per unit time, evaluating the attention span of the tested person during driving; Based on the visual entropy value, the attention stability of the person under test during driving is evaluated.

8. A driving ability assessment system based on eye movement analysis, characterized in that: include: An acquisition module, a preprocessing module, a calculation module, a first evaluation module and a second evaluation module; wherein, The acquisition module is used to acquire driving parameter data and eye movement data of the tested person when the tested person completes a simulated driving task on the simulated driving platform; the eye movement data includes gaze point data of the tested person in multiple interest areas of the simulated platform; The preprocessing module is used to align and preprocess the driving parameter data and the eye movement data on a time axis to obtain the preprocessed driving parameter data and the preprocessed eye movement data; The calculation module is used to calculate the percentage of fixation points in each area of ​​interest, the scanning amplitude per unit time of the measured person, the visual entropy value, fixation frequency and nearest neighbor index corresponding to the simulated driving task of the measured person at each stage, based on the eye movement data after preprocessing; The first evaluation module is used to evaluate the visual information search efficiency of the tested person during driving based on the percentage of fixation points, the scanning amplitude per unit time and the visual entropy value; The second evaluation module is used to evaluate changes in the cognitive status of the test subject during driving based on the gaze frequency, the nearest neighbor index and the visual entropy value.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images