Icon test threshold value generation method and device, equipment and storage medium

Abstract

This invention belongs to the field of vehicle testing technology and discloses a method, apparatus, device, and storage medium for generating icon test thresholds. The invention acquires video image data corresponding to the vehicle icon to be tested; divides the video image data into initial image data, first image data, and second image data; performs threshold prediction based on the first image data and the initial image data to obtain a first test threshold; performs threshold prediction based on the second image data and the initial image data to obtain a second test threshold; and generates an icon test threshold based on the first and second test thresholds. Because threshold prediction can be performed by acquiring video image data, automatically generating icon test thresholds requires no manual intervention, is simple to set, and involves multiple threshold predictions, generating the icon test threshold based on the test thresholds obtained from multiple predictions, thus avoiding prediction errors that may occur in a single prediction and ensuring the rationality of the generated threshold.

Description

Technical Field

[0001] This invention relates to the field of vehicle testing technology, and in particular to a method, apparatus, device, and storage medium for generating icon test thresholds. Background Technology

[0002] Nowadays, testing the icons in a car dashboard is generally done by using a single camera to automate the testing. The determination of whether the icon display is correct is mainly done by capturing a certain number of frames of images, comparing the number of images containing the icon to be tested to the total number of images, and then comparing it with a pre-set threshold.

[0003] The thresholds set in advance are usually estimated manually through repeated tests in the early stages. However, for instruments with increasingly complex and diverse designs, the frequencies of different intermittent icons are often different, and the threshold settings are also different. The method of manual estimation is often not accurate enough. Moreover, when the hardware (camera, instrument) changes, the camera frame rate (how many pictures are displayed per second) and the flashing frequency of the intermittent icons (the icons to be detected on the instrument) also change, and the threshold often needs to be recalculated.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a method, apparatus, device, and storage medium for generating icon test thresholds, aiming to solve the technical problem that the thresholds for testing images in car dashboards require manual estimation, resulting in poor practical performance.

[0006] To achieve the above objectives, the present invention provides a method for generating an icon test threshold, the method comprising the following steps:

[0007] Obtain the video image data corresponding to the vehicle icon to be tested;

[0008] The video image data is divided into initial image data, first image data, and second image data;

[0009] Based on the first image data and the initial image data, a threshold prediction is performed to obtain a first test threshold.

[0010] Based on the second image data and the initial image data, a threshold prediction is performed to obtain a second test threshold.

[0011] An icon test threshold is generated based on the first test threshold and the second test threshold.

[0012] Optionally, the step of performing threshold prediction based on the first image data and the initial image data to obtain a first test threshold includes:

[0013] The image frame rate and icon blinking frequency are determined based on the initial image data.

[0014] Construct icon statistics based on the first image data;

[0015] A first test threshold is obtained by using a preset threshold prediction model to predict the threshold based on the image frame rate, the icon blinking frequency, and the icon statistics.

[0016] Optionally, the step of determining the image frame rate and icon blinking frequency based on the initial image data includes:

[0017] The initial image data is decomposed to obtain an initial image set;

[0018] The initial image set is statistically analyzed to obtain the total number of images and the number of images with lit icons.

[0019] The image frame rate is determined based on the total number of images and the image duration of the initial image data, and the icon flashing frequency is determined based on the number of images where the icon is lit up and the total number of images.

[0020] Optionally, the step of constructing icon statistics based on the first image data includes:

[0021] The first image data is split into multiple sets of image data by splitting it into sub-second segments;

[0022] Perform data statistics on the images contained in each group of image data to obtain the number of images with lit icons and the total number of images for each group of image data;

[0023] The number of lit-up icons and the total number of images corresponding to each group of image data are aggregated to obtain icon statistics.

[0024] Optionally, the step of generating an icon test threshold based on the first test threshold and the second test threshold includes:

[0025] Obtain the absolute value of the difference between the first test threshold and the second test threshold;

[0026] Obtain the icon test severity level corresponding to the vehicle icon to be tested;

[0027] Find the difference threshold corresponding to the stringency level of the icon test;

[0028] If the absolute value of the difference is greater than the difference limit threshold, then the average value of the first test threshold and the second test threshold is calculated to obtain the icon test threshold.

[0029] Optionally, after the step of finding the difference limit threshold corresponding to the stringency level of the icon test, the method further includes:

[0030] If the absolute value of the difference is less than or equal to the difference limit threshold, then the threshold selection rule corresponding to the stringency level of the icon test is searched.

[0031] Based on the threshold selection rules, an icon test threshold is selected from the first test threshold and the second test threshold.

[0032] Optionally, the step of dividing the video image data into initial image data, first image data, and second image data includes:

[0033] Extract image frames of a preset duration from the video image data to obtain initial image data;

[0034] The extracted video image data is divided into first image data and second image data according to the image duration.

[0035] Furthermore, to achieve the above objectives, the present invention also proposes an icon testing threshold generation device, which includes the following modules:

[0036] The acquisition module is used to acquire the video image data corresponding to the vehicle icon under test;

[0037] The segmentation module is used to divide the video image data into initial image data, first image data, and second image data;

[0038] The prediction module is used to perform threshold prediction based on the first image data and the initial image data to obtain a first test threshold.

[0039] The prediction module is also used to perform threshold prediction based on the second image data and the initial image data to obtain a second test threshold.

[0040] The generation module is used to generate an icon test threshold based on the first test threshold and the second test threshold.

[0041] Furthermore, to achieve the above objectives, the present invention also proposes an icon test threshold generation device, which includes: a processor, a memory, and an icon test threshold generation program stored in the memory and executable on the processor. When the icon test threshold generation program is executed by the processor, it implements the steps of the icon test threshold generation method as described above.

[0042] Furthermore, to achieve the above objectives, the present invention also proposes a computer-readable storage medium storing an icon test threshold generation program, wherein the icon test threshold generation program, when executed, implements the steps of the icon test threshold generation method as described above.

[0043] This invention acquires video image data corresponding to the vehicle icon under test; divides the video image data into initial image data, first image data, and second image data; performs threshold prediction based on the first image data and the initial image data to obtain a first test threshold; performs threshold prediction based on the second image data and the initial image data to obtain a second test threshold; and generates an icon test threshold based on the first and second test thresholds. Since threshold prediction can be performed by acquiring video image data, and the icon test threshold is automatically generated without manual intervention, the setup method is simple. Furthermore, it performs multiple threshold predictions and generates the icon test threshold based on the test thresholds obtained from these multiple predictions, thus avoiding prediction errors that may occur in a single prediction and ensuring the rationality of the generated threshold. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of the structure of an electronic device in the hardware operating environment involved in the embodiments of the present invention;

[0045] Figure 2 This is a flowchart illustrating the first embodiment of the icon test threshold generation method of the present invention;

[0046] Figure 3 This is a flowchart illustrating the second embodiment of the icon test threshold generation method of the present invention;

[0047] Figure 4 This is a flowchart illustrating the third embodiment of the icon test threshold generation method of the present invention;

[0048] Figure 5 This is a schematic diagram of the threshold generation execution process according to an embodiment of the present invention;

[0049] Figure 6 This is a structural block diagram of the first embodiment of the icon test threshold generation device of the present invention.

[0050] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0051] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0052] Reference Figure 1 , Figure 1This is a schematic diagram of the icon test threshold generation device structure for the hardware operating environment involved in the embodiments of the present invention.

[0053] like Figure 1 As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0054] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0055] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and an icon test threshold generation program.

[0056] exist Figure 1 In the electronic device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in the icon test threshold generation device. The electronic device calls the icon test threshold generation program stored in the memory 1005 through the processor 1001 and executes the icon test threshold generation method provided in the embodiment of the present invention.

[0057] This invention provides a method for generating icon test thresholds, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of an icon test threshold generation method according to the present invention.

[0058] In this embodiment, the icon test threshold generation method includes the following steps:

[0059] Step S10: Obtain the video image data corresponding to the vehicle icon to be tested.

[0060] It should be noted that the execution subject of this embodiment can be the icon test threshold generation device (hereinafter referred to as the threshold generation device) or the vehicle itself. The threshold generation device can be a controller in the vehicle, such as an ECU controller, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment and the following embodiments, the threshold generation device is used as an example to describe the icon test threshold generation method of the present invention.

[0061] It should be noted that the vehicle icon to be tested can be a vehicle dashboard icon whose correct display needs to be checked. The vehicle icon to be tested can be preset by the administrator of the threshold generation device according to actual needs. The administrator can pre-specify multiple vehicle dashboard icons as vehicle icons to be tested. When there are multiple vehicle icons to be tested, the generation of their icon test thresholds is independent and does not affect each other. That is, for each vehicle icon to be tested, the icon test threshold generation method provided by this invention will be executed once to generate the icon test threshold corresponding to the vehicle icon to be tested.

[0062] In practical use, the video image data corresponding to the vehicle icon under test can be obtained by reading the video image data corresponding to the vehicle icon under test from the image acquisition device used during the test. The image acquisition device can be a pre-set device such as a camera that can perform image acquisition, and the video image data corresponding to the vehicle icon under test can be video image data containing the vehicle icon under test in the video frame.

[0063] In practice, since the threshold prediction can be completed by acquiring video image data of sufficient duration, when acquiring video image data corresponding to the vehicle icon to be tested, the administrator of the threshold generation device can pre-set a test duration (e.g., set the test duration to 35 seconds), and then read the video image data corresponding to the vehicle icon to be tested with the same duration as the test duration from the image acquisition device used during the test.

[0064] Step S20: Divide the video image data into initial image data, first image data, and second image data.

[0065] It should be noted that dividing video image data into initial image data, first image data, and second image data can be done based on video segmentation rules preset by the administrator of the threshold generation device.

[0066] Furthermore, in order to ensure the reasonable division of video image data, step S20 in this embodiment may include:

[0067] Extract image frames of a preset duration from the video image data to obtain initial image data;

[0068] The extracted video image data is divided into first image data and second image data according to the image duration.

[0069] It should be noted that the preset duration can be set by the administrator of the threshold generation device according to actual needs. The initial image data is generally used to count the image frame rate and icon blinking frequency. In order to ensure the accuracy of the icon blinking frequency statistics, the preset duration can be set to N times the normal blinking frequency of the vehicle icon under test. N can be preset by the administrator of the threshold generation device. For example, if the normal blinking frequency of the vehicle icon under test is once per second and N is set to 5, then the preset duration is 5 seconds.

[0070] In the specific implementation, since a threshold prediction is performed based on the first image data and the second image data respectively, in order to minimize the error in the prediction and ensure the rationality of the final generated icon test threshold, it is necessary to ensure that the length of the image data used for threshold prediction is consistent. Therefore, the extracted video image data can be divided into the first image data and the second image data according to the image duration.

[0071] Step S30: Based on the first image data and the initial image data, perform threshold prediction to obtain the first test threshold.

[0072] It should be noted that the threshold prediction based on the first image data and the initial image data to obtain the first test threshold can be achieved by using a pre-set threshold prediction model to predict the threshold based on the first image data and the initial image data. The threshold prediction model can be a pre-trained deep learning model, such as an RNN model or other similar models.

[0073] Step S40: Based on the second image data and the initial image data, perform threshold prediction to obtain a second test threshold.

[0074] It should be noted that the method for obtaining the second test threshold based on the second image data and the initial image data is the same as the method for obtaining the first test threshold, and will not be repeated here. The threshold prediction model used for both threshold predictions can be the same deep learning model, or it can be two different models built based on the same algorithm but trained separately; this embodiment does not impose any restrictions on this.

[0075] Of course, in the actual implementation process, longer video image data can also be obtained to perform more threshold predictions, and this embodiment does not limit this.

[0076] Step S50: Generate an icon test threshold based on the first test threshold and the second test threshold.

[0077] It should be noted that the icon test threshold generated based on the first test threshold and the second test threshold can be calculated by averaging the first test threshold and the second test threshold, and the average value is used as the icon test threshold corresponding to the vehicle icon under test (i.e., the threshold for determining whether the vehicle icon under test can be displayed normally when testing it).

[0078] This embodiment acquires video image data corresponding to the vehicle icon to be tested; divides the video image data into initial image data, first image data, and second image data; performs threshold prediction based on the first image data and the initial image data to obtain a first test threshold; performs threshold prediction based on the second image data and the initial image data to obtain a second test threshold; and generates an icon test threshold based on the first and second test thresholds. Since threshold prediction can be performed by acquiring video image data, and the icon test threshold is automatically generated without manual intervention, the setup method is simple. Furthermore, multiple threshold predictions are performed, and the icon test threshold is generated based on the test thresholds obtained from these multiple predictions, thus avoiding prediction errors that may occur in a single prediction and ensuring the rationality of the generated threshold.

[0079] refer to Figure 3 , Figure 3 This is a flowchart illustrating a second embodiment of an icon test threshold generation method according to the present invention.

[0080] Based on the first embodiment described above, step S30 of the icon test threshold generation method in this embodiment includes:

[0081] Step S301: Determine the image frame rate and icon blinking frequency based on the initial image data.

[0082] It should be noted that the image frame rate can be the frame rate of the video image data, that is, the number of images contained in each second of the video image data. The icon blinking frequency can be the frequency at which the vehicle icon under test lights up during image capture.

[0083] Furthermore, in order to accurately obtain the image frame rate and icon blinking frequency, step S301 in this embodiment may include:

[0084] The initial image data is decomposed to obtain an initial image set;

[0085] The initial image set is statistically analyzed to obtain the total number of images and the number of images with lit icons.

[0086] The image frame rate is determined based on the total number of images and the image duration of the initial image data, and the icon flashing frequency is determined based on the number of images where the icon is lit up and the total number of images.

[0087] It should be noted that obtaining an initial image set by image decomposition of the initial image data can be achieved by breaking down the initial image data into individual images and then aggregating these images into a collection. However, since existing video data generally employs compression techniques, directly decomposing the images may result in the loss of certain features. Therefore, specialized video decomposition tools can be used when decomposing the initial image data.

[0088] In practical use, the initial image set is statistically analyzed to obtain the total number of images and the number of images with lit icons. This can be achieved by counting the number of images in the initial image set to obtain the total number of images, and by counting the number of images in the initial image set that contain lit vehicle icons to be tested to obtain the number of lit icons.

[0089] In practical implementation, determining the image frame rate based on the total number of images and the image duration of the initial image data can be achieved by dividing the total number of images by the image duration of the initial image data. Similarly, determining the icon blinking frequency based on the number of icon-lit images and the total number of images can be achieved by dividing the number of icon-lit images by the total number of images.

[0090] Step S302: Construct icon statistics based on the first image data.

[0091] It should be noted that the icon statistics can include the number of images contained in the image data corresponding to each second in the first image data and the number of images where the icon is lit up.

[0092] In a specific implementation, in order to accurately obtain icon statistics data, step S302 in this embodiment may include:

[0093] The first image data is split into multiple sets of image data by splitting it into sub-second segments;

[0094] Perform data statistics on the images contained in each group of image data to obtain the number of images with lit icons and the total number of images for each group of image data;

[0095] The number of lit-up icons and the total number of images corresponding to each group of image data are aggregated to obtain icon statistics.

[0096] It should be noted that splitting the first image data into multiple sets of image data by second can be achieved by splitting the first image data into multiple sets of image data in one second. For example, if the first image data is a 15-second video image data, it can be split into 15 sets of image data.

[0097] It should be noted that to obtain the number of lit-up icon images and the total number of images corresponding to the image data, the image data can be decomposed to obtain the corresponding image set. Then, the total number of images in the image set is obtained to get the total number of images. Finally, the number of images in the image set that contain the lit-up vehicle icon under test is counted to obtain the number of lit-up icon images.

[0098] In practical use, the number of lit icons and the total number of images corresponding to each group of image data are aggregated to obtain icon statistics. This can be achieved by aggregating the number of lit icons and the total number of images corresponding to each group of image data into data in a preset format. The preset format is related to the input format of the preset threshold prediction model.

[0099] Step S303: The first test threshold is obtained by performing threshold prediction based on the image frame rate, the icon blinking frequency and the icon statistics using a preset threshold prediction model.

[0100] In practical use, the first test threshold can be obtained by using a preset threshold prediction model to predict the threshold based on the image frame rate, icon blinking frequency, and icon statistics. This can be achieved by generating model input parameters based on the image frame rate, icon blinking frequency, and icon statistics, inputting the model input parameters into the preset threshold prediction model, and obtaining the prediction result output by the preset threshold prediction model.

[0101] This embodiment determines the image frame rate and icon blinking frequency based on the initial image data; constructs icon statistics based on the first image data; and obtains a first test threshold by performing threshold prediction using a preset threshold prediction model based on the image frame rate, the icon blinking frequency, and the icon statistics. Because the data is statistically processed before being input into the model, this avoids the need for the model to perform similar statistics, thus reducing the structural complexity of the model.

[0102] refer to Figure 4 , Figure 4 This is a flowchart illustrating a third embodiment of an icon test threshold generation method according to the present invention.

[0103] Based on the first embodiment described above, step S50 of the icon test threshold generation method in this embodiment includes:

[0104] Step S501: Obtain the absolute value of the difference between the first test threshold and the second test threshold.

[0105] It should be noted that obtaining the absolute value of the difference between the first test threshold and the second test threshold can be done by subtracting the second test threshold from the first test threshold, obtaining the difference, and then taking the absolute value of the difference.

[0106] Step S502: Obtain the icon test severity level corresponding to the vehicle icon to be tested.

[0107] It should be noted that the icon test strictness level can be a quantitative data used to represent the strictness of the vehicle icon under test. The higher the icon test strictness level, the stronger the strictness of the test on the vehicle icon.

[0108] In a specific implementation, obtaining the icon test severity level corresponding to the vehicle icon to be tested can be done by looking up the icon test severity level corresponding to the vehicle icon to be tested in a preset icon level mapping table. The preset icon level mapping table can include the mapping relationship between the vehicle icon to be tested and the icon test severity level, and this mapping relationship can be preset by the administrator of the threshold generation device.

[0109] Step S503: Find the difference limit threshold corresponding to the strictness level of the icon test.

[0110] It should be noted that finding the difference limit threshold corresponding to the strictness level of the icon test can be done by looking up the difference limit threshold corresponding to the strictness level of the icon test in a preset level difference mapping table. The preset level difference mapping table can include the mapping relationship between the strictness level of the icon test and the difference limit threshold. This mapping relationship can be preset by the administrator of the threshold generation device.

[0111] In practical use, the higher the stringency level of the icon test, the more stringent the test is, and the smaller the corresponding tolerance for error. Therefore, the stringency level of the icon test is inversely proportional to the difference limit threshold.

[0112] Step S504: If the absolute value of the difference is greater than the difference limit threshold, calculate the average of the first test threshold and the second test threshold to obtain the icon test threshold.

[0113] It should be noted that if the absolute value of the difference is greater than the difference limit threshold, it means that the predicted values ​​obtained from the two threshold predictions are significantly different. In this case, in order to minimize the error of the generated icon test threshold and ensure the rationality of the final icon test threshold, the average of the first test threshold and the second test threshold can be used as the icon test threshold.

[0114] In practical use, to ensure that the generated threshold meets actual usage requirements when the difference between the two predictions is small, this embodiment may further include the following after step S503:

[0115] If the absolute value of the difference is less than or equal to the difference limit threshold, then the threshold selection rule corresponding to the stringency level of the icon test is searched.

[0116] Based on the threshold selection rules, an icon test threshold is selected from the first test threshold and the second test threshold.

[0117] It should be noted that if the absolute value of the difference is less than or equal to the difference limit threshold, it indicates that the predicted values ​​obtained from the two threshold predictions are relatively similar. In this case, either threshold can be used to ensure reasonableness. The icon test threshold can then be generated based on the threshold selection requirements in the actual test. Therefore, the threshold selection rules corresponding to the icon test strictness level can be found. The threshold selection rules corresponding to each icon test strictness level can be preset by the administrator of the threshold generation device.

[0118] In practical implementation, the threshold selection rules include at least two types: taking the maximum value and taking the minimum value. If the threshold selection rule is to take the maximum value, then selecting the icon test threshold from the first test threshold and the second test threshold based on the threshold selection rule can be done by selecting the maximum value of the first test threshold and the second test threshold as the icon test threshold;

[0119] If the threshold selection rule is to take the minimum value, then selecting the icon test threshold from the first test threshold and the second test threshold based on the threshold selection rule can be done by selecting the minimum value of the first test threshold and the second test threshold as the icon test threshold.

[0120] To facilitate understanding, we will now combine... Figure 5 This explanation is provided, but it does not limit the scope of this solution. Figure 5 This is a schematic diagram of the threshold generation execution process in this embodiment, as shown below. Figure 5As shown, at the beginning, the threshold generation device performs new icon detection, that is, it checks whether there are still any vehicle icons to be tested that have not yet had their icon test thresholds generated. If so, it reads in a 35-second video stream, that is, it reads the video image data corresponding to the vehicle icon to be tested for a duration of 35 seconds. Then, it uses the images contained in the first 5 seconds of the 35-second video stream as the initial image data, scans and counts them to obtain the current frame rate FPS (i.e., the image frame rate mentioned above) and icon frequency FV (i.e., the icon blinking frequency mentioned above). Then, it extracts the first 15 seconds of image frames from the 35-second video stream after removing the first 5 seconds (i.e., the remaining 30 seconds of video stream after removing the first 5 seconds of video stream), groups them in sets of 1 second each (time T), and counts the total number of images Bi contained in each group, as well as the number of bright images. The system generates 15 sets of data (A1, B1)...(A15, B15) for the vehicle icon to be tested, Ai, and then inputs the obtained image frame rate, icon blinking frequency, and icon statistics into the deep learning module M1 for threshold prediction to obtain the current optimal threshold S1 (the first test threshold). Similarly, it performs threshold prediction based on the last 15 seconds of image frames extracted from a 35-second video stream (excluding the first 5 seconds) to obtain the current optimal threshold S2 (the second test threshold). The reliability verification module then generates the optimal threshold S based on S1 and S2, and associates S with the current vehicle icon to be tested. Finally, it checks whether there are any vehicle icons to be tested that do not have an icon test threshold set (i.e.,...). Figure 5 (The process ends after detecting all frequency icons in the middle). If yes, the process ends; otherwise, it returns. Figure 5 The steps to start new icon detection in the middle.

[0121] This embodiment obtains the absolute value of the difference between the first test threshold and the second test threshold; obtains the icon test severity level corresponding to the vehicle icon to be tested; finds the difference limit threshold corresponding to the icon test severity level; if the absolute value of the difference is greater than the difference limit threshold, the average of the first test threshold and the second test threshold is calculated to obtain the icon test threshold. Because the difference between the first test threshold and the second test threshold is detected based on the difference limit threshold corresponding to the icon test severity level of the vehicle icon to be tested, different methods are selected to generate the icon test threshold based on the first test threshold and the second test threshold, ensuring the rationality of the finally generated icon test threshold.

[0122] Furthermore, this embodiment of the invention also proposes a storage medium storing an icon test threshold generation program, which, when executed by a processor, implements the steps of the icon test threshold generation method described above.

[0123] Reference Figure 6 , Figure 6This is a structural block diagram of the first embodiment of the icon test threshold generation device of the present invention.

[0124] like Figure 6 As shown, the icon test threshold generation device proposed in this embodiment of the invention includes:

[0125] The acquisition module 10 is used to acquire the video image data corresponding to the vehicle icon to be tested;

[0126] The segmentation module 20 is used to divide the video image data into initial image data, first image data, and second image data;

[0127] Prediction module 30 is used to perform threshold prediction based on the first image data and the initial image data to obtain a first test threshold;

[0128] The prediction module 30 is further configured to perform threshold prediction based on the second image data and the initial image data to obtain a second test threshold.

[0129] The generation module 40 is used to generate an icon test threshold based on the first test threshold and the second test threshold.

[0130] This embodiment acquires video image data corresponding to the vehicle icon to be tested; divides the video image data into initial image data, first image data, and second image data; performs threshold prediction based on the first image data and the initial image data to obtain a first test threshold; performs threshold prediction based on the second image data and the initial image data to obtain a second test threshold; and generates an icon test threshold based on the first and second test thresholds. Since threshold prediction can be performed by acquiring video image data, and the icon test threshold is automatically generated without manual intervention, the setup method is simple. Furthermore, multiple threshold predictions are performed, and the icon test threshold is generated based on the test thresholds obtained from these multiple predictions, thus avoiding prediction errors that may occur in a single prediction and ensuring the rationality of the generated threshold.

[0131] Furthermore, the prediction module 30 is also used to determine the image frame rate and icon blinking frequency based on the initial image data; construct icon statistics data based on the first image data; and perform threshold prediction based on the image frame rate, the icon blinking frequency, and the icon statistics data using a preset threshold prediction model to obtain a first test threshold.

[0132] Furthermore, the prediction module 30 is also used to decompose the initial image data to obtain an initial image set; to count the initial image set to obtain the total number of images and the number of images with icons lit up; to determine the image frame rate based on the total number of images and the image duration of the initial image data; and to determine the icon flashing frequency based on the number of images with icons lit up and the total number of images.

[0133] Furthermore, the prediction module 30 is also used to split the first image data into multiple sets of image data in seconds; to perform data statistics on the images contained in each set of image data to obtain the number of icons lit up and the total number of images corresponding to each set of image data; and to aggregate the number of icons lit up and the total number of images corresponding to each set of image data to obtain icon statistics data.

[0134] Furthermore, the generation module 40 is also used to obtain the absolute value of the difference between the first test threshold and the second test threshold; obtain the icon test strictness level corresponding to the vehicle icon to be tested; find the difference limit threshold corresponding to the icon test strictness level; if the absolute value of the difference is greater than the difference limit threshold, calculate the average value of the first test threshold and the second test threshold to obtain the icon test threshold.

[0135] Furthermore, the generation module 40 is also used to find the threshold selection rule corresponding to the strictness level of the icon test if the absolute value of the difference is less than or equal to the difference limit threshold; and select the icon test threshold from the first test threshold and the second test threshold based on the threshold selection rule.

[0136] Furthermore, the segmentation module 20 is also used to extract image frames of a preset duration from the video image data to obtain initial image data; and to divide the extracted video image data into first image data and second image data according to the image duration.

[0137] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0138] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0139] In addition, for technical details not described in detail in this embodiment, please refer to the icon test threshold generation method provided in any embodiment of the present invention, which will not be repeated here.

[0140] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0141] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0142] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0143] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. An icon test threshold generation method, characterized by, The method for generating the icon test threshold includes the following steps: Obtain the video image data corresponding to the vehicle icon to be tested; The video image data is divided into initial image data, first image data, and second image data; Based on the first image data and the initial image data, a threshold prediction is performed to obtain a first test threshold. Based on the second image data and the initial image data, a threshold prediction is performed to obtain a second test threshold. Generate icon test thresholds based on the first test threshold and the second test threshold; The step of performing threshold prediction based on the first image data and the initial image data to obtain the first test threshold includes: The image frame rate and icon blinking frequency are determined based on the initial image data. Construct icon statistics based on the first image data; A first test threshold is obtained by using a preset threshold prediction model to predict the threshold based on the image frame rate, the icon blinking frequency, and the icon statistics. The step of constructing icon statistics based on the first image data includes: The first image data is split into groups of one second each to generate multiple groups of image data; The image data is decomposed to generate image sets corresponding to each set of image data; Count the total number of images in the image set and generate the total number of images corresponding to each group of image data; The number of images in the image set containing the lit-up vehicle icon to be tested is counted, and the number of lit-up icon images corresponding to each group of images is generated; The number of lit-up icons and the total number of images corresponding to each group of image data are aggregated to obtain icon statistics. The step of dividing the video image data into initial image data, first image data, and second image data includes: Extract image frames of a preset duration from the video image data to obtain initial image data; The extracted video image data is divided into first image data and second image data according to the image duration.

2. The icon test threshold generation method of claim 1, wherein, The step of determining the image frame rate and icon blinking frequency based on the initial image data includes: The initial image data is decomposed to obtain an initial image set; The initial image set is statistically analyzed to obtain the total number of images and the number of images with lit icons. The image frame rate is determined based on the total number of images and the image duration of the initial image data, and the icon flashing frequency is determined based on the number of images where the icon is lit up and the total number of images.

3. The icon test threshold generation method of claim 1, wherein, The step of generating an icon test threshold based on the first test threshold and the second test threshold includes: Obtain the absolute value of the difference between the first test threshold and the second test threshold; Obtain the icon test severity level corresponding to the vehicle icon to be tested; Find the difference threshold corresponding to the stringency level of the icon test; If the absolute value of the difference is greater than the difference limit threshold, then the average value of the first test threshold and the second test threshold is calculated to obtain the icon test threshold.

4. The icon test threshold generation method of claim 3, wherein, After the step of finding the difference threshold corresponding to the stringency level of the icon test, the method further includes: If the absolute value of the difference is less than or equal to the difference limit threshold, then the threshold selection rule corresponding to the stringency level of the icon test is searched. Based on the threshold selection rules, an icon test threshold is selected from the first test threshold and the second test threshold.

5. An icon test threshold generation apparatus characterized by comprising: The icon test threshold generation device includes the following modules: The acquisition module is used to acquire the video image data corresponding to the vehicle icon under test; The segmentation module is used to divide the video image data into initial image data, first image data, and second image data; The prediction module is used to perform threshold prediction based on the first image data and the initial image data to obtain a first test threshold. The prediction module is also used to perform threshold prediction based on the second image data and the initial image data to obtain a second test threshold. The generation module is used to generate an icon test threshold based on the first test threshold and the second test threshold; The prediction module is further configured to determine the image frame rate and icon blinking frequency based on the initial image data; construct icon statistics data based on the first image data; and perform threshold prediction using a preset threshold prediction model based on the image frame rate, the icon blinking frequency, and the icon statistics data to obtain a first test threshold. The prediction module is further configured to: split the first image data into multiple sets of image data by dividing it into groups of one second each; decompose the image data into images to generate image sets corresponding to each set of image data; count the total number of images in the image sets to generate the total number of images corresponding to each set of image data; count the number of images in the image sets that contain lit-up vehicle icons to be tested to generate the number of lit-up icon images corresponding to each set of image data; and aggregate the number of lit-up icon images corresponding to each set of image data and the total number of images to obtain icon statistics data. The segmentation module is further configured to extract image frames of a preset duration from the video image data to obtain initial image data; and to divide the extracted video image data into first image data and second image data according to the image duration.

6. An icon test threshold generation device characterized by comprising: The icon test threshold generation device includes: a processor, a memory, and an icon test threshold generation program stored in the memory and executable on the processor. When the icon test threshold generation program is executed by the processor, it implements the steps of the icon test threshold generation method as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an icon test threshold generation program, which, when executed, implements the steps of the icon test threshold generation method as described in any one of claims 1-4.

Images