A vehicle-mounted touch interaction evaluation method and device

Abstract

The present invention relates to the technical field of vehicle interactive screen testing, and more specifically, to a vehicle-mounted touch interaction evaluation method and device. In the device, a head-mounted eye tracker module is used to collect the driver's eye movement data; the rear camera module is fixed on the roof, and the front camera module is fixed on the instrument panel to collect images of the driver's operation on the vehicle screen; the host is used to parse the display content of the vehicle screen to determine the urgency of the interaction in the current driving scenario; the visual distraction data is determined according to the eye movement data and the urgency of the interaction, and the operational distraction data is determined according to the driver's operation data on the vehicle screen and the urgency of the interaction; the vehicle-mounted touch interaction evaluation results are obtained according to the visual distraction data and the operational distraction data. The present invention conducts touch interaction testing based on the comprehensive sight-off-road and operation data to improve the accuracy and success rate of the test.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle interactive screen testing, and in particular to a vehicle-mounted touch interaction evaluation method and device. Background Art

[0002] With the rapid development of intelligent connected vehicle technology, cars are transforming from a simple means of transportation to an intelligent mobile space that integrates transportation, information, entertainment and other functions. This transformation not only improves the user's driving experience, but also puts forward higher requirements for the convenience and safety of smart cockpit interaction. How to make the interaction between people and vehicles more efficient and convenient and reduce the distraction of users when driving has become an important consideration in the design of human-computer interaction in smart cockpits.

[0003] In recent years, the installation rate of central control screens in smart cockpits has risen rapidly, and touch interaction, which uses screen clicks / slides in conjunction with buttons / knobs, has become one of the main ways of human-computer interaction in smart cockpits. Touch interaction provides users with a more intuitive and rich interface experience, but it also brings some safety hazards. With the continuous integration of automotive central control screen functions and the partial replacement of physical buttons with touch screen buttons, some cockpit products have too many operating steps and too long sight away from the road when performing common operations such as air conditioning settings during driving, posing a driving safety hazard due to reasons such as overly complex screen logic menu design.

[0004] At present, the main indicator for evaluating touch interaction safety in the industry is eye movement data. The industry generally uses the single gaze away from the road time and the total gaze away from the road time to represent eye movement data, and the number of operation steps to represent operation behavior.

[0005] At present, the industry mainly uses head-mounted eye trackers for touch safety testing. Head-mounted eye trackers are widely used in colleges, research institutions, eye movement laboratories, and corporate test platforms, with a high market share. However, the core idea of ​​the current head-mounted eye tracker is to establish a mapping relationship between the human eye and the gaze point, which means that it is only applicable to a certain range in front of the subject in actual application, and it is impossible to obtain the operation behavior and eye movement data at the same time. For example, when blindly operating hard buttons such as turning on the assisted driving function, turning on the air conditioner, lighting control, and window control, the operation within the field of view can be obtained at the same time. Moreover, the clarity of the eye tracker (the head-mounted eye tracker currently commonly used in the industry is 2 million pixels) is not enough to support the judgment of whether the central control screen has executed the command and achieved the expected result, and it cannot support the judgment of the specific functions of the actual operation of the hand in the central control screen. Finally, the existing eye tracker is severely exposed in the case of strong light, and it is impossible to clearly capture the picture of the central control and see the actual performance of the central control.

[0006] At the same time, the existing testing methods are interfered by human factors. The time that different personnel spend away from the road during a single operation varies greatly, and the time that the same person spends away from the road in different test conditions also varies greatly, resulting in large differences in the number of operating steps and the total time that the eyes are away from the road, which causes large fluctuations in the data and unstable test results. In addition, the existing test result analysis method is to conduct multiple tests before the test and eliminate extreme values ​​through data analysis after the test, which greatly increases the test time and the test results cannot be guaranteed, increasing the risk of repeated testing.

[0007] In view of this, the present invention is proposed. Summary of the invention

[0008] The purpose of the present invention is to provide a vehicle-mounted touch interaction evaluation method and device, which can perform touch interaction testing by integrating sight-off-road and operation data to improve the accuracy and success rate of the test.

[0009] In order to achieve the above object, the present invention adopts the following technical solutions:

[0010] In a first aspect, the present invention provides an in-vehicle touch interaction evaluation device, which is installed in a car cabin, and comprises: a host, and a head-mounted eye tracker module, a rear camera module, and a front camera module connected to the host;

[0011] The head-mounted eye tracker module is used to collect the driver's eye movement data;

[0012] The rear camera module is fixed on the roof of the vehicle, and the front camera module is fixed on the instrument panel, and is used to collect images of the driver's operation on the vehicle screen;

[0013] The host is used to obtain the driver's eye movement data and images of operations on the vehicle screen during vehicle driving; analyze the display content of the vehicle screen to determine the interaction urgency in the current driving scenario; determine visual distraction data based on the eye movement data and the interaction urgency, and determine operational distraction data based on the driver's operation data on the vehicle screen and the interaction urgency; obtain vehicle touch interaction evaluation results based on the visual distraction data and the operational distraction data; the operation data includes blind operation square control operation data, physical button operation data, and hand movements when operating the central control screen.

[0014] In a second aspect, the present invention provides a vehicle-mounted touch interaction evaluation method, comprising:

[0015] S110, during vehicle driving, obtaining eye movement data of the driver and images of the operation on the vehicle screen;

[0016] S120, analyzing the display content of the vehicle-mounted screen to determine the urgency of interaction in the current driving scenario;

[0017] S130, determining visual distraction data according to the eye movement data and the interaction urgency, and determining operational distraction data according to the driver's operation data on the vehicle-mounted screen and the interaction urgency;

[0018] S140. Obtaining an in-vehicle touch interaction evaluation result according to the visual distraction data and the operation distraction data; the operation data includes physical button operation data and hand movements when operating the central control screen.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] (1) The present invention arranges a head-mounted eye tracker module, a rear camera module, and a front camera module in the car cockpit, and then transmits the eye movement data transmitted by the head-mounted eye tracker and the operation behavior data obtained by the rear camera module and the front camera module to the host, thereby ensuring that the driver's eye movement data and images can be obtained simultaneously during the entire test process. At the same time, through the high pixel, anti-exposure and complementary field of view characteristics of the rear camera module and the front camera module, the clarity of the image is improved and the problem of overexposure of the central control caused by excessive light is solved.

[0021] (2) The time interval is set by a fixed timer, which ensures the stability of the driver's single operation duration and single eye-off-the-road time, thereby ensuring the stability of the total eye-off-the-road time and operation steps, eliminating human factors. At the same time, by stabilizing the single operation duration, it reduces the risk of invalid operation tests and repeated tests, improves work efficiency, and solves the problem of individual differences between different testers and different states of the same tester affecting the test results in the current eye tracker, as well as the risk of repeated tests and low test efficiency.

[0022] (3) The present invention monitors the driver's touch interaction operations in the whole vehicle driving scenario in real time by time-aligning the eye movement data and the image, ensuring that the driver's eye movement data and the image can be obtained simultaneously during the entire test process.

[0023] (4) The present invention fixes the rear camera together by using a fixing fixture on the roof and a tripod, thereby improving the stability of the shooting picture in dynamic bumpy scenes.

[0024] (5) The present invention determines the degree of interaction urgency in the current driving scenario by analyzing the image of the vehicle-mounted screen, and calculates visual distraction data and operational distraction data according to the degree of interaction urgency. First, the interactive performance of the screen is evaluated from two dimensions, namely, vision and operation. Then, the evaluation result is obtained by combining the influence of the degree of interaction urgency. The influence of the current driving scenario on the driver is fully considered, so that the evaluation result is scientific and reasonable and can reflect the driving environment at that time. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 It is a structural schematic diagram of a vehicle-mounted touch interaction evaluation device provided by an embodiment of the present invention;

[0027] Figure 2 is a schematic structural diagram of a rear camera module provided by an embodiment of the present invention;

[0028] Figure 3 is a schematic diagram of a touch interaction test software display provided by an embodiment of the present invention;

[0029] Figure 4 is a schematic diagram of a driver touching a screen captured by a front camera module provided by an embodiment of the present invention;

[0030] Figure 5 is a schematic diagram of a driver touching a screen captured by a rear camera module provided by an embodiment of the present invention;

[0031] Figure 6 is a flow chart of a vehicle-mounted touch interaction evaluation method provided by an embodiment of the present invention;

[0032] Among them, 1-host; 2-1-head-mounted eye tracker module; 2-2-first dedicated connection harness; 3-1-rear camera fixing fixture; 3-2-rear camera; 3-3-tripod; 3-4-second dedicated connection harness; 4-1-front camera; 4-2-front camera fixing fixture; 4-3-industrial grade tape; 4-4-third dedicated connection harness; 1-1-eye movement data; 1-2 images taken by the rear camera module; 1-3-images taken by the front camera module; 1-4 timeline. DETAILED DESCRIPTION

[0033] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0034] This embodiment is applicable to scenarios where the driver interacts with the vehicle screen while driving, such as touching the screen and pressing buttons around the screen, and the interaction behavior is evaluated. This embodiment provides an in-vehicle touch interaction evaluation device, which is installed in the car cabin and is used to achieve real-time monitoring of touch interaction tasks performed in the car cabin. Figure 1 , including: a host 1, and a head-mounted eye tracker module 2-1, a rear camera module and a front camera module connected to the host 1 through a wiring harness.

[0035] The head-mounted eye tracker module 2-1 is worn on the head of the driver (or tester) to collect the driver's eye movement data. Specifically, the head-mounted eye tracker module includes a head-mounted eye tracker and a first dedicated connection harness. A head-mounted eye tracker is a device that can record the movement trajectory of human eyes. It captures eye movement data through a high-precision camera to achieve high-precision eye tracking, thereby obtaining eye movement data trajectories and calculating eye movement data. The head-mounted eye tracker is connected to the host through the first dedicated connection harness, and the eye movement data collected by the head-mounted eye tracker is transmitted to the touch interaction test software through the host. The touch interaction test software is installed in the host.

[0036] The rear camera module is fixed on the roof. For details, see Figure 2 , the rear camera module includes a rear camera 3-2, a rear camera fixing fixture 3-1, a tripod 3-3 and a second dedicated connection harness 3-4. The upper end of the rear camera 3-2 is fixed to the roof through the rear camera fixing fixture 3-1, for example, adsorbed on the sunroof. The rear camera 3-2 can achieve 360-degree rotation and can be used for adjusting the camera field of view in different scenes. The lower end of the rear camera 3-2 is fixed to the bottom of the cockpit by a tripod 3-3, which is suitable for the stability of the shooting picture in dynamic bumpy scenes. The rear camera 3-2 is connected to the host 1 through the second dedicated connection harness 3-4, and the collected image of the driver's operation on the vehicle screen is transmitted to the touch interaction test software through the host 1. The rear camera 3-2 is ≥5 million pixels, which can clearly capture the driver's physical button operations and hand movements when operating the central control screen.

[0037] The front camera module is fixed on the instrument panel and is used to collect images of the driver's operation on the vehicle screen. Specifically, the front camera module includes a plurality of front cameras 4-1 with ≥5 million pixels. The number of the front cameras 4-1 is determined according to the test range, for example, including a first camera and a second camera, the first camera is located on the left side of the driver, and the second camera is located on the right side of the driver. The front camera module also includes a front camera fixing fixture 4-2, an industrial-grade tape 4-3, and a third dedicated connection harness 4-4, which are used to assist in obtaining the blind spot image of the rear camera module, that is, the front camera module and the shooting field of view are complementary to the shooting field of view of the rear camera module. The front camera 4-1 is fixed on the front camera fixing fixture 4-2, and the front camera fixing fixture 4-2 is fixed on the instrument panel by a professional industrial-grade tape 4-3. The front camera 4-1 is connected to the host 1 through the third dedicated connection harness 4-4, and the collected image of the driver's operation on the vehicle screen is transmitted to the touch interaction test software through the host 1.

[0038] The touch interaction test software in the host 1 receives the eye movement data and the image of the driver's operation on the vehicle screen, and displays it in real time on the screen of the host 1. Since the eye tracker, the front camera module and the rear camera module are different devices, they have different timing. The eye movement data and the image need to be time-aligned. Specifically, the host sends a message carrying the standard time to the head-mounted eye tracker module, the rear camera module and the front camera module; the head-mounted eye tracker module, the rear camera module and the front camera module correct the eye movement data and the image according to the message, and send the corrected eye movement data and the image to the host. See Figure 3 The eye movement data and images received by the host have been time-aligned, thereby achieving synchronization of eye movements and hand movements and data synchronization of the entire system. The eye movement data 1-1, the image 1-2 taken by the rear camera module, and the image 1-3 taken by the front camera module are synchronously displayed on a time axis 1-4 and displayed on the host screen through the touch interaction test software.

[0039] The touch interaction test software in the host mainly performs the following operations, see Figure 6 .

[0040] S110. During vehicle driving, obtaining the driver's eye movement data and images of the operation on the vehicle screen.

[0041] According to the test requirements, when the vehicle speed reaches 50km / h, the driver is prompted to perform specified operations. The head-mounted eye tracker module, rear camera module and front camera module begin to collect the driver's eye movement data and images in real time, and transmit them to the host through the wiring harness. The host displays the time-aligned eye movement data and images on the host screen. Eye movement data includes gaze position and time.

[0042] Optionally, both the rear camera module and the front camera module can capture images of the driver's operation on the vehicle screen. Figure 4 and Figure 5 , both can capture the complete vehicle screen, but the rear camera module can capture more driver operations due to its high field of view, but the vehicle screen area accounts for a small proportion and is less affected by light. The front camera module can capture the driver's hand movements, and the vehicle screen area accounts for a large proportion and is greatly affected by light. If the screen is reflective, it will be difficult to recognize the displayed image. In order to combine the advantages of the front and rear images, overcome the defects, improve the image clarity and solve the problem of overexposure of the central control due to excessive light, the host in this embodiment determines the image quality of the first image captured by the front camera module in the operation area and the image quality in the screen area before parsing the display content of the vehicle screen and determining the urgency of the interaction in the current driving scenario, and determines the image quality of the second image captured by the rear camera module in the operation area and the image quality in the screen area; the image quality includes clarity and exposure; the first image and the second image are taken at the same time; the operation area and the screen area where the image quality meets the requirements are identified to obtain the display content and operation data.

[0043] Since the positions of the screen and the camera are fixed, the screen area in the first image (i.e., the area displayed on the in-vehicle screen) is fixed and known. The operating area is the active area when a person touches / presses the in-vehicle screen. This can also be determined based on experience, and generally includes part of the screen area near the driver's position and the surrounding area. Assume Figure 4 is the first image, Figure 5 The second image has a screen area as shown in a red frame and an operation area as shown in a green frame. Since the driver needs to reach his hand from the left side of the screen to the right side to operate the screen, and only the images of the driver just reaching out to operate and retracting his hand (at this time, the hand is on the left side of the screen) need to be detected, the right side of the screen can be ignored as the operation area, and the driver's hand movements can be captured only in the left area and the surrounding area shown in the green frame. If the ambient light is strong or the aperture of a camera is not adjusted properly, the screen exposure will affect the display content and make it unrecognizable, and even affect the recognition of the driver's operation. Therefore, firstly, the operation area and the screen area are segmented on the first image and the second image to determine the clarity and exposure. For example, the clarity is evaluated by analyzing the pixel gradient, variance, etc. of the operation area / screen area, and the exposure is evaluated by the pixel brightness histogram. If the clarity is greater than the clarity threshold and the exposure is greater than the exposure threshold, the image quality meets the requirements. If there is at least one screen area and at least one image area that meet the requirements, the two areas are identified separately. If there are two screen areas or two image areas that meet the requirements (such as Figure 4and Figure 5 If all image areas in the image region meet the requirements), you can select one of the two image regions / operation regions for recognition. Figure 4 The screen area meets the requirements, Figure 5 If the operation area meets the requirements, the two areas are identified. If there is only a screen area that meets the requirements or only an operation area that meets the requirements, the first image and the second image are discarded. Specifically, the display content of the vehicle screen is identified in the screen area, including but not limited to text, icons, numbers and picture types, and the time t_1 is marked. The driver's hand movements are identified in the operation area. If the finger points to or touches the screen or the buttons around the screen, it is considered that the driver's action of operating the screen is recognized, and operation data (1, t_2) is generated, 1 indicates operation, and t_2 indicates time. This embodiment can identify display content and operation data in a clear area without high exposure, thereby improving the success rate of the test.

[0044] S120: Analyze the display content of the vehicle screen to determine the urgency of interaction in the current driving scenario.

[0045] Specifically, the display content of the vehicle screen is parsed to obtain the display type, which includes driving safety alarm type, navigation type, electronic appliance type and entertainment type. For example, if the display content is a map, it is a navigation type; if the display content is a music player and lyrics, it is an entertainment type; if the display content is an air conditioning adjustment interface and temperature, it is an electronic appliance type; if the display content is an overspeed alarm, a fuel consumption or low power consumption alarm, etc., it is a driving safety alarm type. Then, the interaction urgency interval is determined according to the display type. This can be determined according to business needs. Assuming that the interaction urgency is expressed by 1 to 100 to indicate the urgency of the driver to see or operate the screen, the larger the value, the more urgent it is. The driving safety alarm type is 90 to 100, and a value can be determined for each screen image; the navigation type is 70 to 90, the electronic appliance type is 50 to 70, and the entertainment type is less than 50, and a value can be determined for each screen image. For the navigation type, the current interaction urgency within the interaction urgency interval (such as the above 70 to 90) is determined according to the navigation type and the current driving road conditions. If the current driving condition is a fork in the road or a road section with dense traffic lights, you need to look at the navigation on the screen frequently, then select a larger value in the interaction urgency interval; if the current driving condition is a one-way road and there is no fork in the set distance (such as Highway 5), then select a smaller value in the interaction urgency interval. For the type of electronic appliances, the current interaction urgency in the interaction urgency interval (such as 50~70 above) is determined according to the type of electronic appliances and the current in-car environment and out-of-car environment. If the current in-car temperature is greater than the high temperature threshold (such as 35 degrees) or lower than the low temperature threshold (such as 15 degrees), it is not suitable for the driver to drive, and it is urgent to turn on the air conditioner through the car screen, then select a larger value in the interaction urgency interval; otherwise, select a smaller value in the interaction urgency interval; if there is bad weather outside the car, such as rain, cloudy or foggy, it is urgent to turn on the wipers and lights through the car screen (this embodiment assumes that only the electronic appliances can be controlled through the car screen), then select a larger value in the interaction urgency interval; otherwise, select a smaller value in the interaction urgency interval.

[0046] S130: Determine visual distraction data according to the eye movement data and the interaction urgency, and determine operational distraction data according to the driver's operation data on the vehicle-mounted screen and the interaction urgency.

[0047] The host calculates the duration of a single time when the eyes are away from the road based on the eye movement data obtained in real time. Specifically, the time when the eyes return to the road is subtracted from the time when the eyes leave the road in retrospect to obtain the duration of a single time when the eyes are away from the road. The host calculates the duration of a single operation based on the operation data obtained in real time. Specifically, the time when the operation switches from operation to non-operation is subtracted from the time when the operation switches from non-operation to operation in retrospect to obtain the duration of a single operation.

[0048] Optionally, if the duration of a single sight-off-the-road (i.e., the duration of a single sight-off-the-road) or a single operation (i.e., the duration of a single touch or key press on the vehicle screen) exceeds 2 seconds, it will bring great danger to driving. Therefore, the duration of a single sight-off-the-road during the test should not exceed 2 seconds, and driving safety should be guaranteed first before evaluating the touch interaction. Based on this, the device also includes a fixed time timer for sending signals at intervals of a set duration (such as 2 seconds or 1.9 seconds); not limited to sound and light signals, to prompt the driver to return his sight and hold the steering wheel with both hands. Furthermore, before the host determines the visual distraction data based on the eye movement data and the urgency of the interaction, if the duration of a single sight-off-the-road or a single operation exceeds the set duration, the eye movement data or operation data is discarded. By limiting the set duration, the stability of the total sight-off-the-road time and the operation steps can be guaranteed, thereby eliminating the impact of factors such as individual differences between different test personnel and different states of the same test personnel on the test results. At the same time, by stabilizing the duration of a single operation and the time the eyes are off the road, the risk of invalid operation tests and repeated tests is reduced, and work efficiency is improved.

[0049] Through the above statistics on the duration of single sight-off-road and the duration of single operation, the number of sight-off-road times and the number of single operations are obtained.

[0050] In S130, the duration of a single gaze away from the road and the number of times the gaze is away from the road are determined according to the eye movement data; a first coefficient of a single gaze away from the road is determined according to the current interaction urgency and the first set weight; visual distraction data is obtained according to the first coefficient, the number of times the gaze is away from the road, and the duration of a single gaze away from the road. The number of operations and the duration of a single operation are determined according to the operation data; a second coefficient of a single operation is determined according to the interaction urgency and the second set weight; operation distraction data is obtained according to the second coefficient, the number of operations, and the duration of a single operation.

[0051] Specifically, the current interaction urgency is multiplied by the first set weight to obtain the first coefficient, and the current interaction urgency is multiplied by the second set weight to obtain the second coefficient. During driving, it is more dangerous to look away from the road than to operate the screen, so the first set weight is greater than the second set weight. Refer to the following formula to obtain visual distraction data and operational distraction data .

[0052] ;

[0053] ;

[0054] Among them, w1 is the first set weight, w2 is the second set weight, N1 is the number of times the sight is off the road, and N2 is the number of operations. is the urgency of interaction when the i-th sight is off the road, is the duration of the i-th sight-off-road time, is the interaction urgency at the jth operation, is the operation duration of the jth operation.

[0055] S140: Obtain an in-vehicle touch interaction evaluation result according to the visual distraction data and the operational distraction data.

[0056] Add the visual distraction data and the operational distraction data. The larger the sum, the more frequently the driver is distracted and the worse the evaluation result. Based on this, multiple evaluation results can be set, such as 1 star, 2 stars, 3 stars, 4 stars, and 5 stars. Each evaluation result corresponds to a different sum value, for example, a sum of 50 or more is 1 star, a sum of 30-50 is 2 stars, a sum of 20-30 is 3 stars, a sum of 10-20 is 4 stars, and a sum of less than 10 is 5 stars. You can also use a fixed value (such as 100) to subtract the sum of the visual distraction data and the operational distraction data, and use the difference to get the in-vehicle touch interaction evaluation result. The larger the difference, the better the evaluation result. You can set a threshold value. When the difference is greater than or equal to the threshold, the evaluation passes, and when it is less than the threshold, the evaluation fails.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] (1) The present invention arranges a head-mounted eye tracker module, a rear camera module, and a front camera module in the car cockpit, and then transmits the eye movement data transmitted by the head-mounted eye tracker and the operation behavior data obtained by the rear camera module and the front camera module to the host, thereby ensuring that the driver's eye movement data and images can be obtained simultaneously during the entire test process. At the same time, through the high pixel, anti-exposure and complementary field of view characteristics of the rear camera module and the front camera module, the clarity of the image is improved and the problem of overexposure of the central control caused by excessive light is solved.

[0059] (2) The time interval is set by a fixed timer, which ensures the stability of the driver's single operation duration and single eye-off-the-road time, thereby ensuring the stability of the total eye-off-the-road time and operation steps, eliminating human factors. At the same time, by stabilizing the single operation duration, it reduces the risk of invalid operation tests and repeated tests, improves work efficiency, and solves the problem of individual differences between different testers and different states of the same tester affecting the test results in the current eye tracker, as well as the risk of repeated tests and low test efficiency.

[0060] (3) The present invention monitors the driver's touch interaction operations in the whole vehicle driving scenario in real time by time-aligning the eye movement data and the image, ensuring that the driver's eye movement data and the image can be obtained simultaneously during the entire test process.

[0061] (4) The present invention fixes the rear camera together by using a fixing fixture on the roof and a tripod, thereby improving the stability of the shooting picture in dynamic bumpy scenes.

[0062] (5) The present invention determines the degree of interaction urgency in the current driving scenario by analyzing the image of the vehicle-mounted screen, and calculates visual distraction data and operational distraction data according to the degree of interaction urgency. First, the interactive performance of the screen is evaluated from two dimensions, namely, vision and operation. Then, the evaluation result is obtained by combining the influence of the degree of interaction urgency. The influence of the current driving scenario on the driver is fully considered, so that the evaluation result is scientific and reasonable and can reflect the driving environment at that time.

[0063] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and this document does not limit this.

[0064] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A vehicle-mounted touch interaction evaluation device, characterized in that: The device is installed in a car cabin, and comprises: a host, and a head-mounted eye tracker module, a rear camera module and a front camera module connected to the host; The head-mounted eye tracker module is used to collect the driver's eye movement data; The rear camera module is fixed on the roof of the vehicle, and the front camera module is fixed on the instrument panel, and is used to collect images of the driver's operation on the vehicle screen; The host is used to obtain the driver's eye movement data and images of the vehicle screen operation during vehicle driving; analyze the display content of the vehicle screen to determine the interaction urgency in the current driving scenario; determine the visual distraction data according to the eye movement data and the interaction urgency, and determine the operation distraction data according to the driver's operation data on the vehicle screen and the interaction urgency; obtain the vehicle touch interaction evaluation result according to the visual distraction data and the operation distraction data, specifically, add the visual distraction data and the operation distraction data, the larger the sum value is, the more frequently the driver is distracted, and the worse the evaluation result is; the operation data includes the physical button operation data, and the hand movements when operating the central control screen; Parsing the display content of the vehicle-mounted screen to determine the interaction urgency in the current driving scenario, including: the interaction urgency is expressed as 1 to 100, and the larger the value, the more urgent it is; Parsing the display content of the vehicle-mounted screen to obtain a display type, wherein the display type includes a driving safety alarm type, a navigation type, an electronic appliance type, and an entertainment type; Determining an interaction urgency interval according to the display type; the interaction urgency interval of the driving safety warning type is 90-100, and determining a value from the interval as the current interaction urgency; The interaction urgency level of navigation type is between 70 and 90. The current interaction urgency level within the interaction urgency level range is determined based on the navigation type and the current driving conditions. The interaction urgency level of electronic and electrical appliances is in the range of 50 to 70. The current interaction urgency level within the interaction urgency level range is determined based on the electronic and electrical appliance type and the current in-vehicle and out-of-vehicle environments. The entertainment type interaction urgency interval is lower than 50, and a value is determined from the interval as the current interaction urgency; Determining visual distraction data according to the eye movement data and the interaction urgency, including: Determine the duration of a single gaze-away time and the number of times the gaze is away from the road based on the eye movement data; Determine a first coefficient of a single sight-off-road according to the current interaction urgency and a first set weight; Obtain visual distraction data according to the first coefficient, the number of times the eyes are away from the road, and the duration of a single time the eyes are away from the road; The visual distraction data The formula is: ； Among them, w1 is the first set weight, N1 is the number of times the sight is off the road, is the urgency of interaction when the i-th sight is off the road, is the duration of the i-th sight-off-road time; The operation distraction data is determined according to the driver's operation data on the vehicle screen and the urgency of the interaction, including: Determine the number of operations and the duration of a single operation according to the operation data; Determining a second coefficient of a single operation according to the interaction urgency and a second set weight; The operation distraction data is obtained according to the second coefficient, the number of operations and the duration of a single operation; the operation distraction data The formula is: ； Wherein, w2 is the second set weight, N2 is the number of operations, is the interaction urgency at the jth operation, is the operation duration of the jth operation.

2. The device according to claim 1, characterized in that Before parsing the display content of the vehicle-mounted screen and determining the urgency of interaction in the current driving scenario, the host is further used to: Determine the image quality of the first image captured by the front camera module in the operation area and the image quality in the screen area, and determine the image quality of the second image captured by the rear camera module in the operation area and the image quality in the screen area; the image quality includes clarity and exposure; the first image and the second image are captured at the same time; The operation area and screen area whose image quality meets the requirements are identified to obtain the display content and operation data.

3. The device according to claim 1 or 2, characterized in that: It also includes a fixed time timer for sending a signal at set time intervals; Before determining the visual distraction data based on the eye movement data and the interaction urgency, the host is also used to discard the eye movement data or operation data if a single sight-away-from-the-road duration or a single operation duration exceeds the set duration.

4. The device according to claim 1, characterized in that Before parsing the displayed content to determine the interaction urgency in the current driving scenario, the host is further configured to: Sending a message carrying the standard time to the head-mounted eye tracker module, the rear camera module and the front camera module; The head-mounted eye tracker module, the rear camera module and the front camera module correct the eye movement data and the image according to the message, and send the eye movement data and the image after the correction time to the host.

5. The device according to claim 1, characterized in that The front camera module includes a first camera and a second camera; The first camera is located on the left side of the driver, and the second camera is located on the right side of the driver.

6. The device according to claim 1, characterized in that The rear camera module includes a rear camera, a rear camera fixing fixture, a tripod and a dedicated connection harness; The upper end of the rear camera is fixed to the roof of the vehicle through the rear camera fixing fixture, and the rear camera can rotate 360 ​​degrees; the lower end of the rear camera is fixed to the bottom of the cabin through a tripod; The front camera module and the shooting field of view are complementary to the shooting field of view of the rear camera module.

7. A vehicle-mounted touch interaction evaluation method, characterized in that: include: S110, during vehicle driving, obtaining the driver's eye movement data and images of the vehicle screen operation; S120, analyzing the display content of the vehicle-mounted screen to determine the interaction urgency in the current driving scenario; specifically, the interaction urgency is represented by 1 to 100, and the larger the value, the more urgent it is; Parsing the display content of the vehicle-mounted screen to obtain a display type, wherein the display type includes a driving safety alarm type, a navigation type, an electronic appliance type, and an entertainment type; Determining an interaction urgency interval according to the display type; The interaction urgency level of the driving safety warning type is in the range of 90 to 100, and a value is determined from the range as the current interaction urgency level; The interaction urgency level of navigation type is between 70 and 90. The current interaction urgency level within the interaction urgency level range is determined based on the navigation type and the current driving conditions. The interaction urgency level of electronic and electrical appliances is in the range of 50 to 70. The current interaction urgency level within the interaction urgency level range is determined based on the electronic and electrical appliance type and the current in-vehicle and out-of-vehicle environments. The entertainment type interaction urgency interval is lower than 50, and a value is determined from the interval as the current interaction urgency; S130, determining visual distraction data according to the eye movement data and the interaction urgency, and determining operational distraction data according to the driver's operation data on the vehicle-mounted screen and the interaction urgency; The determining of visual distraction data according to the eye movement data and the interaction urgency comprises: Determine the duration of a single gaze-away time and the number of times the gaze is away from the road based on the eye movement data; Determine a first coefficient of a single sight-off-road according to the current interaction urgency and a first set weight; Obtain visual distraction data according to the first coefficient, the number of times the eyes are away from the road, and the duration of a single time the eyes are away from the road; The visual distraction data The formula is: ； Among them, w1 is the first set weight, N1 is the number of times the sight is off the road, is the urgency of interaction when the i-th sight is off the road, is the duration of the i-th sight-off-road time; The determining of the operation distraction data according to the driver's operation data on the vehicle-mounted screen and the interaction urgency degree includes: Determine the number of operations and the duration of a single operation according to the operation data; Determining a second coefficient of a single operation according to the interaction urgency and a second set weight; The operation distraction data is obtained according to the second coefficient, the number of operations and the duration of a single operation; the operation distraction data The formula is: ； Wherein, w2 is the second set weight, N2 is the number of operations, is the interaction urgency at the jth operation, is the operation duration of the jth operation; S140. Obtaining an in-vehicle touch interaction evaluation result according to the visual distraction data and the operational distraction data, specifically, adding the visual distraction data to the operational distraction data. The larger the sum value is, the more frequently the driver is distracted, and the worse the evaluation result is. The operational data includes physical button operation data and hand movements when operating the central control screen.

Images