Motherboard detection method and motherboard detection device

Abstract

The application provides a mainboard detection method and a mainboard detection device. The method comprises the following steps: determining a first image in an original video input by a mainboard and a second image in a to-be-detected video output by the mainboard; wherein the comparison results of all pixels of the first image and the second image are consistent; obtaining a to-be-detected image in the to-be-detected video and a standard image in the original video; wherein the interval frame numbers between the standard image and the first image and between the to-be-detected image and the second image are the same; performing image comparison on all pixels of the to-be-detected image and the standard image; and if the comparison result is consistent, it is determined that the detection is passed. Thus, the application compares all pixels of the whole image, thereby avoiding the problem of low detection accuracy when only local images are detected in the related art.

Description

Motherboard testing methods and devices Technical Field

[0001] This application relates to testing technology, and more particularly to a motherboard testing method and a motherboard testing device. Background Technology

[0002] Currently, display devices typically include a motherboard, which processes external video signals input to the display device to enable the display to show the image. The accuracy of the final displayed image is directly affected by the motherboard's ability to correctly process the input video signals.

[0003] In related technologies, when detecting the input and output video of a motherboard, before the original video is input to the motherboard, the same marker is added to a fixed position in each frame of the video. Then, the marked video is input to the motherboard. Afterward, the frame images output by the motherboard are acquired. If the position and image information of the frame images match the fixed position and the marker before input, it indicates that the motherboard can process the video normally.

[0004] However, the above techniques only detect information at the markers in the output frame image, and the remaining parts of the frame image may still have problems, which may lead to inaccurate detection results. Summary of the Invention

[0005] This application provides a motherboard testing method and a motherboard testing device to solve the problem of inaccurate test results for motherboard output video in related technologies.

[0006] Firstly, this application provides a motherboard detection method, the method comprising:

[0007] Determine a first image in the original video input from the motherboard and a second image in the video to be detected output from the motherboard; wherein the pixel comparison results of the first image and the second image are consistent;

[0008] Obtain the image to be detected from the video to be detected and the standard image from the original video; wherein the positional interval between the standard image and the first image is the same as the positional interval between the image to be detected and the second image;

[0009] A pixel-by-pixel comparison is performed between the image to be detected and the standard image; if the comparison results are consistent, the detection is deemed successful.

[0010] In some embodiments, determining a first image in the original video input from the motherboard and a second image in the video to be detected output from the motherboard includes:

[0011] The original video is divided into multiple video segments, each video segment corresponding to an identification feature, which is a common feature of all frame images in the corresponding video segment.

[0012] Acquire a second image from the video to be detected, perform image comparison on the second image and multiple identification features, and determine the identification features corresponding to the second image;

[0013] The second image is compared with each frame of the video segment corresponding to the identification feature by performing a full pixel image comparison to determine the second image in the video to be detected output by the motherboard.

[0014] In some embodiments, dividing the original video into multiple video segments includes:

[0015] Image recognition is performed on each frame of the original video to determine the key image corresponding to each frame.

[0016] The original video is divided into multiple video segments based on the key images corresponding to each frame, wherein the similarity between the key images corresponding to each frame in the video segment is greater than or equal to a preset threshold.

[0017] For each video segment, the key image corresponding to any frame in that video segment is used as the identification feature of that video segment.

[0018] In some embodiments, acquiring the image to be detected in the video to be detected and the standard image in the original video includes:

[0019] Obtain the image to be detected from the video to be detected;

[0020] Based on the time interval between the image to be detected and the second image, determine the number of frames between the image to be detected and the second image in the video to be detected;

[0021] Based on the interval frame number and the first image, a standard image in the original video is determined.

[0022] In some embodiments, the original video input from the motherboard is input in a loop; acquiring the image to be detected in the video to be detected and the standard image in the original video includes:

[0023] Obtain the image to be detected from the video to be detected;

[0024] Based on the time interval between the image to be detected and the second image, determine the number of frames between the image to be detected and the second image in the video to be detected;

[0025] Based on the interval frame count and the total number of frames in the original video, determine the number of loops and the remaining frame count of the original video;

[0026] Based on the first image and the remaining number of frames, the standard image corresponding to the image to be detected is determined.

[0027] In some embodiments, after performing a full-pixel image comparison between the image to be detected and the standard image, the method further includes:

[0028] If the comparison results are inconsistent, then the frame image adjacent to the standard image is obtained in the original video. If at least one frame image is consistent with all the pixels of the image to be detected, then the detection is deemed to have passed.

[0029] In some embodiments, determining a first image in the original video input from the motherboard and a second image in the video to be detected output from the motherboard includes:

[0030] The image to be detected that passes the test is used as the first image, and the standard image that passes the test is used as the second image.

[0031] Secondly, this application provides a motherboard testing device, comprising: a controller and a motherboard; the controller is connected to the motherboard;

[0032] The controller is used to determine a first image in the original video input from the motherboard and a second image in the video to be detected output from the motherboard; wherein, the pixel comparison results of the first image and the second image are consistent;

[0033] The controller is used to acquire the image to be detected in the video to be detected and the standard image in the original video; wherein the number of frames between the standard image and the first image is the same as the number of frames between the image to be detected and the second image;

[0034] The controller is used to perform a full pixel comparison between the image to be detected and the standard image; if the comparison results are consistent, the detection is deemed successful.

[0035] In some embodiments, the controller is specifically used to divide the original video into multiple video segments, wherein each video segment corresponds to an identification feature, and different video segments have different identification features. The identification feature is a common feature of all frame images in the corresponding video segment.

[0036] The controller is specifically used to acquire a second image in the video to be detected, perform image comparison on the second image and multiple identification features, and determine the identification features corresponding to the second image.

[0037] The controller is specifically used to perform a full pixel image comparison between the second image and each frame of the video segment corresponding to the identification feature, and to determine the second image in the video to be detected output by the motherboard.

[0038] In some embodiments, the controller is specifically used to perform image recognition on each frame of the original video to determine the key image corresponding to each frame.

[0039] The controller is specifically used to divide the original video into multiple video segments based on the key images corresponding to each frame image, wherein the similarity between the key images corresponding to each frame image in the video segment is greater than or equal to a preset threshold.

[0040] Specifically, the controller is used to, for each video segment, use the key image corresponding to any frame in the video segment as the identification feature of the video segment.

[0041] In some embodiments, the controller is specifically configured to acquire the image to be detected in the video to be detected;

[0042] The controller is specifically used to determine the number of frames between the image to be detected and the second image in the video to be detected, based on the time interval between the image to be detected and the second image.

[0043] The controller is specifically used to determine the standard image in the original video based on the interval frame number and the first image.

[0044] In some embodiments, the controller is specifically configured to: input the original video from the motherboard in a loop; and acquire the image to be detected in the video to be detected and the standard image in the original video, including:

[0045] The controller is specifically used to acquire the image to be detected in the video to be detected;

[0046] The controller is specifically used to determine the number of frames between the image to be detected and the second image in the video to be detected, based on the time interval between the image to be detected and the second image.

[0047] The controller is specifically used to determine the number of loops and the number of remaining frames of the original video based on the interval frame number and the total number of frames of the original video;

[0048] The controller is specifically used to determine the standard image corresponding to the image to be detected based on the first image and the remaining number of frames.

[0049] In some embodiments, the controller is further configured to: if the comparison results are inconsistent, acquire a frame image adjacent to the standard image in the original video; if at least one frame image is consistent with the pixel comparison results of the image to be detected, then determine that the detection is successful.

[0050] In some embodiments, the controller is specifically configured to use the detected image to be detected as the first image and the detected standard image as the second image.

[0051] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0052] The memory stores computer-executed instructions;

[0053] The processor executes computer execution instructions stored in the memory to implement the method as described in any of the first aspects.

[0054] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method described in any of the first aspects.

[0055] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the first aspects.

[0056] The motherboard detection method and apparatus provided in this application include: determining a first image in the original video input to the motherboard and a second image in the video to be detected output by the motherboard; wherein the pixel comparison results of the first image and the second image are consistent; acquiring the image to be detected in the video to be detected and a standard image in the original video; wherein the number of frames between the standard image and the first image is the same as the number of frames between the image to be detected and the second image; performing a pixel comparison of the image to be detected and the standard image; if the comparison results are consistent, the detection is deemed to have passed. Thus, this application avoids the problem of low detection accuracy when only local images are detected in related technologies by comparing all pixels of the entire image. Attached Figure Description

[0057] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0058] Figure 1 is a schematic diagram of an application scenario provided by this application;

[0059] Figure 2 is a flowchart illustrating a motherboard testing method provided in an embodiment of this application;

[0060] Figure 3 is a flowchart illustrating an image determination method provided in an embodiment of this application;

[0061] Figure 4 is a schematic diagram of a scenario provided by an embodiment of this application;

[0062] Figure 5 is a schematic diagram of a video segmentation scenario provided in an embodiment of this application;

[0063] Figure 6 is a flowchart illustrating a video segmentation method provided in an embodiment of this application;

[0064] Figure 7 is a schematic diagram of another scenario provided by an embodiment of this application;

[0065] Figure 8 is a flowchart illustrating a method for obtaining an image to be detected and a standard image according to an embodiment of this application;

[0066] Figure 9 is a flowchart illustrating another method for obtaining an image to be detected and a standard image provided in an embodiment of this application;

[0067] Figure 10 is a schematic diagram of another scenario provided by an embodiment of this application;

[0068] Figure 11 is a flowchart illustrating another motherboard detection method provided in an embodiment of this application;

[0069] Figure 12 is a schematic diagram of the structure of a motherboard detection device provided in an embodiment of the application.

[0070] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0071] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application.

[0072] Currently, display devices typically include a motherboard, which processes external video signals input to the display device to enable the display to show the processed image. Therefore, the motherboard's ability to correctly process the input video signal is crucial for the display device. When the motherboard's image processing function malfunctions, it can lead to inaccurate displayed images, thus affecting the user experience. Therefore, after the motherboard is manufactured, it is usually tested using a motherboard testing device.

[0073] When inputting raw video to the motherboard, the controller in the motherboard detection device can be equipped with a storage unit, and the pre-stored raw video can be input to the motherboard through its input terminal. Alternatively, in some embodiments, the input interfaces of the motherboard and the controller can respectively receive raw video input from external sources. Furthermore, the controller can also connect to the output interface of the motherboard to acquire frames from the video to be detected output by the motherboard, allowing the controller to confirm the detection results by detecting the output video images.

[0074] In some embodiments, the detection device further includes a power supply unit for providing power signals to the motherboard and the controller when the motherboard is being detected.

[0075] In some embodiments, the detection device may also be equipped with a wireless communication module for receiving externally input video images via wireless transmission, such as Wi-Fi or Bluetooth.

[0076] In some embodiments, the detection device may also include a display module for displaying the current results to the user in real time. The display module may also include devices such as a buzzer and indicator lights, which can alert the user by sound or light when the detection fails.

[0077] In some embodiments, the controller is provided with an instruction receiving interface, allowing the user to input user commands (e.g., start, stop, or pause detection commands) through the graphical user interface in the display module. The controller can then receive the user input commands through the graphical user interface. Alternatively, the user can input user commands by entering specific sounds or gestures, and the controller can recognize the sounds or gestures through sound or image sensors to receive the user input commands.

[0078] Figure 1 is a schematic diagram of an application scenario provided by this application. In the figure, the motherboard receives externally input video signals, processes the video signals, and then outputs the processed video signals. In related technologies, when detecting the input and output video of the motherboard, before the original video is input to the motherboard, the same marker is added to a fixed position in each frame of the video. Then, the marked video is input to the motherboard. Afterwards, the frame images output by the motherboard are obtained. If the position and image information in the frame images are consistent with the fixed positions and the markers before input, it indicates that the motherboard can process the video normally.

[0079] For example, in Figure 1, each frame of the original video input to the motherboard has a marker area at its upper right corner, and a predetermined marker pattern is set in the marker area (the grid line area in the figure is the marker area). When the marker pattern that is consistent with the one in the original video is also detected in the marker area at the upper right corner of the video image output by the motherboard, it indicates that the detection is successful.

[0080] However, the above techniques only detect information at the markers in the output frame image, and the remaining parts of the frame image may still have problems, which may lead to inaccurate detection results.

[0081] The motherboard testing method and motherboard testing device provided in this application are intended to solve the above-mentioned technical problems in related technologies.

[0082] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0083] Figure 2 is a flowchart illustrating a motherboard detection method provided in an embodiment of this application. As shown in Figure 1, the method includes the following steps:

[0084] S101. Determine the first image in the original video input from the motherboard and the second image in the video to be detected output from the motherboard; wherein the pixel comparison results of the first image and the second image are consistent.

[0085] For example, in this embodiment, when testing the motherboard, it is first necessary to confirm that the first image and the second image in which the original video input by the motherboard and the output video to be tested have the same pixel comparison results, so as to confirm the correspondence between the image frames in the video to be tested and the original video.

[0086] In one example, when determining the first image in the original video and the second image in the video to be detected, a frame can be randomly selected from the video to be detected output by the motherboard as the second image. The first image corresponding to the second image is then determined by comparing all pixels of the second image with each frame in the original video.

[0087] S102. Obtain the image to be detected in the video to be detected and the standard image in the original video; wherein the positional interval between the standard image and the first image is the same as the positional interval between the image to be detected and the second image.

[0088] For example, after determining the first image and the second image, the next image to be detected is extracted from the video to be detected. Specifically, multiple frames of the images to be detected can be extracted, and the detection result is determined by detecting these multiple frames. Furthermore, the multiple frames can be extracted randomly or at predetermined time intervals; no specific limitation is made here. Then, a standard image can be determined using the first image, the second image, and the extracted images to be detected. The positional interval between the standard image and the first image is the same as the positional interval between the images to be detected and the second image. That is, based on the same positional interval, the standard image and the images to be detected can be considered as two corresponding frames before the input to the motherboard and after the output to the motherboard.

[0089] After extracting the image to be detected, the number of frames between the image to be detected and the determined second image is determined. The number of frames can be used as the position interval. After determining the number of frames, the standard image in the original video corresponding to the image to be detected can be determined based on the number of frames and the first image.

[0090] In one example, the ratio of the difference between the time when the image to be detected is extracted and the time when the first image is extracted to the total duration of the video to be detected can be used as the positional interval. This interval can then be combined with the total duration of the original video and the duration of the first image to determine the first image. There are no specific restrictions on the positional interval here.

[0091] S103. Perform a full pixel comparison between the image to be detected and the standard image; if the comparison results are consistent, the detection is deemed successful.

[0092] For example, after determining the image to be detected and the standard image, all pixels in the two images can be compared. When the comparison results are consistent, the two images are confirmed to be the same, and the motherboard detection passes.

[0093] Specifically, when comparing all pixels, a conventional pixel similarity detection algorithm can be used to determine the similarity value between two frames. When the similarity is greater than a preset value, the two images are considered to be the same and the detection passes.

[0094] In this embodiment, the first image in the original video input by the motherboard and the second image in the video to be detected output by the motherboard are first determined to establish the correspondence between the image frames in the original video and the video to be detected. Then, when the image to be detected is acquired, a standard image can be determined based on the determined first and second images and the positional interval between the second image and the image to be detected. The image to be detected is then compared with the standard image for all pixels to determine the detection result, thus avoiding the problem of inaccurate detection results when only a local area of ​​the image is detected.

[0095] In some embodiments, when determining the first image in the original video input from the motherboard and the second image in the video to be detected output from the motherboard, i.e. when performing step S101 corresponding to FIG2, the determination can be made by the method shown in FIG3.

[0096] Figure 3 is a flowchart illustrating an image determination method provided in an embodiment of this application. As shown in Figure 3, the method includes:

[0097] S201. Divide the original video into multiple video segments, where each video segment corresponds to an identifier feature, which is the common feature of all frame images in the corresponding video segment.

[0098] For example, when determining the first image and the second image, the acquired original video can first be divided into multiple video segments. Each video segment can be assigned a corresponding identifier feature, and the identifier feature is a common feature of each frame image in the corresponding video segment, thereby establishing the correspondence between the identifier feature and the video segments.

[0099] Specifically, the correspondence can be seen in the example in Figure 4. Figure 4 is a schematic diagram of a scenario provided by an embodiment of this application. The original video in the figure includes frame image 1 to frame image n, n frame images. And the n frame images correspond to m first video segments, where m is less than n. And the m video segments correspond to m identification features. It should be noted that the relationship between video segments and identification features here is one-to-one, but in other examples it can also be many-to-one, which is not limited here.

[0100] In one example, when splitting the original video segment, the following method can be used to segment each frame of the original video to determine the object corresponding to each frame. When the similarity between the types of objects included in adjacent frames is high, they can be regarded as the same video segment.

[0101] For example, as shown in Figure 5, which is a schematic diagram of a video segmentation scenario provided by an embodiment of this application. When frame image 1 includes sky, tree, passerby 1, and passerby 2; frame image 2 includes sky, tree, passerby 1, passerby 2, and passerby 3; frame image 3 includes sky, tree, rabbit 1, and rabbit 2; and frame image 4 includes sky, tree, rabbit 1, and rabbit 2; since the objects included in frame image 1 are highly similar to those in frame image 2, they can be segmented into the same video segment 1. While the objects contained in frame image 3 and frame image 4 are identical, they differ significantly from those in frame image 2; therefore, frame image 3 and frame image 4 can be segmented into the same video segment 2. Furthermore, in video segment 1, the features extracted from the common part of passerby 1 in frame image 1 and frame image 2 can be selected as the common features of video segment 1, i.e., the identifying features of video segment 1. Similarly, for video segment 2, the features of rabbit 1 can be selected as the common features of that video segment, i.e., the identifying features of video segment 2.

[0102] S202. Obtain the second image in the video to be detected, perform image comparison on the second image and multiple identification features, and determine the identification features corresponding to the second image.

[0103] For example, in the video to be detected output by the motherboard, a second image is obtained, and the second image is compared with the identification features corresponding to each video segment determined in step S201, thereby determining the identification features with high consistency with the second image.

[0104] Specifically, the features extracted from the second image can be compared with the similarity of each identifier feature. Based on the similarity comparison results, the identifier feature with the highest similarity can be determined as the identifier feature corresponding to the second image.

[0105] S203. Perform a full pixel comparison between the second image and each frame image in the video segment corresponding to the identification feature to determine the second image in the video to be detected output by the motherboard.

[0106] For example, after determining the identification features corresponding to the second image, the second image is further compared pixel by pixel with each frame of the video segment corresponding to the identification features to determine the first image that matches the pixel comparison result of the second image. Matching results here can be defined as the error between the pixels of the two frames being less than a preset value.

[0107] In this embodiment, during the detection process, the original video is first divided into multiple video segments, with each video segment corresponding to a unique identifier feature. When establishing the correspondence between the original video and the video to be detected, the identifier feature corresponding to the second image in the video to be detected is selected from among the multiple identifier features. After determining the corresponding identifier feature, since there is a correspondence between the identifier feature and the video segment, the video segment corresponding to the second image is determined. Then, a full pixel comparison is performed between the second image and each frame in the video segment, thus mapping the second image to a specific frame in the first video segment, i.e., the first image. Since the identifier feature itself is a common feature across all video segments and cannot represent all the features of any frame in any video segment, the identifier feature only preliminarily determines the frame range corresponding to the first image. Then, a comparison is performed between the first image and all pixels of each frame in the first video segment to obtain the first image and the second image. This method of determining the first and second images reduces the number of comparisons between the second image and all pixels of each frame in the original video, shortening the determination time. This also helps to eliminate the tedious process of pixel comparison when determining the standard image corresponding to the image to be detected. Instead, the standard image can be obtained directly based on the determined first image, second image, and the positional interval between the second image and the image to be detected.

[0108] In some embodiments, FIG6 is a schematic flowchart of a video segmentation method provided by an embodiment of this application. Specifically, when performing step S201, it can be executed through the steps shown in FIG6:

[0109] S301. Perform image recognition on each frame of the original video to determine the key image corresponding to each frame.

[0110] For example, by performing image recognition on each frame of the original video, the corresponding key image in each frame is determined.

[0111] Specifically, in practical applications, a pre-trained algorithm model can be used to identify objects in each frame of an image, and then select the key images corresponding to each frame from the identified objects.

[0112] In one example, the key image could be the object that occupies the largest area among the identified objects.

[0113] In one example, a pre-trained algorithm model can be implemented using a convolutional neural network (CNN). The CNN identifies objects in each frame and selects the image with the highest confidence score as the key image for that frame. For instance, if an image contains a cat, a table, a rabbit, a butterfly, and a person, with corresponding confidence scores of 0.55, 0.2, 0.05, 0.12, and 0.08, the cat with the highest confidence score can be used as the key image.

[0114] S302. Divide the original video into multiple video segments based on the key images corresponding to each frame, wherein the similarity between the key images corresponding to each frame in the video segment is greater than or equal to a preset threshold.

[0115] S303. For each video segment, the key image corresponding to any frame in the video segment is used as the identification feature of the video segment.

[0116] For example, after determining the key images of each frame, a similarity comparison is performed on the key images corresponding to each frame to segment the original video.

[0117] Specifically, based on the temporal order of the frames in the original video, the similarity of key images corresponding to adjacent frames can be calculated. When the similarity between key images is greater than or equal to a preset threshold, these images can be divided into the same video segment; otherwise, they are different video segments.

[0118] After the video segments are divided, since the similarity between the frames in the same video segment is high, a key image corresponding to a frame in a video segment can be randomly selected as the identification feature of that video segment, thereby establishing the correspondence between each video segment and the identification feature in the original video.

[0119] For example, Figure 7 is a schematic diagram of another scenario provided by an embodiment of this application. Currently, there are frame images 1, 2, 3, and 4. After image recognition and key image filtering are performed on the four frames, the key images corresponding to each frame are determined to be triangles, triangles, triangles, and circles, respectively. By comparing the above key images, it is determined that the triangles corresponding to frame images 1-3 have a high similarity, therefore these three frames belong to video segment 1. However, the key image corresponding to frame image 4 has a large difference, therefore frame image 4 is assigned to video segment 2.

[0120] In this embodiment, by segmenting the original video, key images can be identified in each frame. Then, by detecting the interactions between these key images, the various video segments of the original video are identified. Using this method, after recognizing each frame, the image corresponding to one of the identified objects is selected as the key image from among multiple identified objects. This avoids the tedious process of comparing each identified object in each frame when comparing images in the original video. When determining the key image, objects occupying a larger area can be identified as key objects in that frame, or objects with higher confidence (i.e., those with more reliable identification results) can be selected as key images to improve detection efficiency.

[0121] In some embodiments, when performing the step S102 in the above embodiments to obtain the image to be detected in the video to be detected and the standard image in the original video, two cases can be considered: one case is that the original video received by the motherboard is a video played only once, and the other case is that the video received by the motherboard is a video in which the original video is input in a loop.

[0122] Specifically, for case one, step S102 can be performed through the following steps. Figure 8 is a flowchart illustrating a method for obtaining an image to be detected and a standard image according to an embodiment of this application, as shown, including the following steps:

[0123] S401. Obtain the image to be detected from the video to be detected;

[0124] S402. Based on the time interval between the image to be detected and the second image, determine the number of frames between the image to be detected and the second image in the video to be detected;

[0125] S403. Based on the interval frame number and the first image, determine the standard image in the original video.

[0126] For example, when acquiring the image to be detected in the video to be detected, it can be randomly selected or selected according to a preset time interval; no specific limitation is made here. After acquiring the image to be detected, the number of interval frames between the two images in the time interval can be determined based on the time interval between the image to be detected and the second image in the video to be detected. Specifically, the number of interval frames in the time interval can be calculated directly based on the time interval and the frame rate of the image to be detected.

[0127] After determining the interval frame number, since the second image and the first image in the original video corresponding to the second image have already been determined, in order to determine the image corresponding to the image to be detected in the original video, it is only necessary to use the determined interval frame number and the first image, and the frame image that is at a distance of the interval frame number from the first image as the standard image in the original video.

[0128] Specifically, for case two, step S102 can be performed through the following steps. Figure 9 is a flowchart illustrating another method for obtaining an image to be detected and a standard image provided by an embodiment of this application, as shown, including the following steps:

[0129] S501. Obtain the image to be detected from the video to be detected;

[0130] S502. Based on the time interval between the image to be detected and the second image, determine the number of frames between the image to be detected and the second image in the video to be detected.

[0131] For example, the specific principles of steps S501 and S502 can be found in steps S401 and S402 shown in Figure 8, and will not be repeated here.

[0132] S503. Based on the interval frame number and the total number of frames in the original video, determine the number of loops and the remaining number of frames in the original video;

[0133] S504. Based on the first image and the remaining number of frames, determine the standard image corresponding to the image to be detected.

[0134] For example, in some cases, when the original video is long, the time spent on processing the first and second images, or on segmenting the original video, is considerable. Furthermore, when the segmentation results and the corresponding identifiers for each video segment are pre-stored in the motherboard detection device, a long original video can also result in a large storage space requirement. Therefore, in such cases, it is advisable to input the original video into the motherboard using a cyclic input method, thereby reducing the processing time and storage space required.

[0135] For example, Figure 10 is a schematic diagram of another scenario provided by an embodiment of this application. In the figure, when inputting the original video to the motherboard, a loop input method can be used to input the video.

[0136] When the original video is input in a loop, in order to determine the image to be detected and the standard image, after determining the number of frames between the image to be detected and the second image, it is necessary to divide the total number of frames in the original video by the number of frames between the two intervals. The quotient is the number of loops in the original video, and the remainder is the number of remaining frames. Then, based on the first image and the number of remaining frames, the standard image is determined, that is, the image with the remaining frame interval from the first image is used as the standard image.

[0137] In some embodiments, FIG11 is a schematic flowchart of another motherboard detection method provided in this application. The method includes the following steps:

[0138] S601. Determine the first image in the original video input from the motherboard and the second image in the video to be detected output from the motherboard; wherein the pixel comparison results of the first image and the second image are consistent.

[0139] S602. Obtain the image to be detected in the video to be detected and the standard image in the original video; wherein the positional interval between the standard image and the first image is the same as the positional interval between the image to be detected and the second image.

[0140] S603. Perform a full pixel comparison between the image to be detected and the standard image.

[0141] S604. If the comparison results are consistent, the test is deemed to have passed.

[0142] For example, the specific principles of steps S601-S604 can be found in steps S101-S103 shown in Figure 2, and will not be repeated here.

[0143] S605. If the comparison results are inconsistent, obtain the frame image adjacent to the standard image in the original video. If at least one frame image is consistent with all pixels of the image to be detected, the detection is deemed to have passed.

[0144] For example, in this embodiment, during the detection process, if the similarity between a certain image to be detected and its corresponding standard image does not reach the second preset value, since the time interval between each frame of the video is short, in order to avoid the problem of inaccurate determination of the standard image caused by time detection error, at least one frame image can be selected near the frame where the standard image is located, and the similarity comparison between the frame image and the image to be detected can be further performed. If there is an image in the frame image that matches the comparison result of the image to be detected, then the detection is determined to be passed.

[0145] In this embodiment, to avoid the error caused by time detection affecting the accuracy of the final detection result of the image to be detected, when the pixel comparison results between the image to be detected and the standard image are inconsistent, at least one image can be selected near the third image, and then the image to be detected can be compared with the selected image again to improve the detection accuracy of the image to be detected.

[0146] In some embodiments, when determining the first image in the original video input from the motherboard and the second image in the video to be detected output from the motherboard, i.e., when executing step S101 in FIG2, if the current detection is the first detection, the determination can be made according to the methods provided in the above embodiments. If the current detection is not the first detection, the following steps can be used when determining the first image and the second image: the image to be detected that has passed the detection is taken as the first image, and the standard image that has passed the detection is taken as the second image. That is, the image to be detected that passed the previous detection and the standard image that passed the detection can be updated as the first image and the second image. Here, it should be noted that in the embodiment shown in FIG11, after the determination is passed in step S605, when updating the second image, the image that matches the comparison result of the image to be detected is taken as the standard image and updated as the second image.

[0147] After redefining the first and second images, the image to be detected and the standard image can be determined based on the updated first and second images when selecting the image to be detected.

[0148] In this embodiment, the first image and the second image can be updated each time an image to be detected passes detection. Since the error between adjacent frames is small when the video frame rate is high, that is, the similarity between adjacent frames is high, there may be some errors when initially determining the first image and the second image. In order to avoid the cumulative error becoming large as the time between the second image and subsequent images to be detected becomes longer, the first image and the second image can be updated each time detection passes, thereby improving the detection accuracy.

[0149] Figure 12 is a schematic diagram of a motherboard detection device provided in an embodiment of this application. The detection device includes: a controller and a motherboard; the controller is connected to the motherboard.

[0150] The controller is used to determine a first image in the original video input from the motherboard and a second image in the video to be detected output from the motherboard; wherein the pixel comparison results of the first image and the second image are consistent;

[0151] The controller is used to acquire the image to be detected in the video to be detected and the standard image in the original video; wherein the number of frames between the standard image and the first image is the same as the number of frames between the image to be detected and the second image;

[0152] The controller is used to perform a full pixel comparison between the image to be detected and the standard image; if the comparison results are consistent, the detection is deemed successful.

[0153] In some embodiments, the controller is specifically used to divide the original video into multiple video segments, wherein each video segment corresponds to an identification feature, and the identification features of different video segments are different. The identification feature is a common feature of all frame images in the corresponding video segment.

[0154] Specifically, the controller is used to acquire a second image in the video to be detected, perform image comparison on the second image and multiple identification features, and determine the identification features corresponding to the second image.

[0155] Specifically, the controller is used to perform a full pixel image comparison between the second image and each frame of the video segment corresponding to the identification features, and to determine the second image in the video to be detected output by the motherboard.

[0156] In some embodiments, the controller is specifically used to perform image recognition on each frame of the original video to determine the key image corresponding to each frame.

[0157] Specifically, the controller is used to divide the original video into multiple video segments based on the key images corresponding to each frame, wherein the similarity between the key images corresponding to each frame in the video segment is greater than or equal to a preset threshold.

[0158] Specifically, the controller is used to, for each video segment, use the key image corresponding to any frame in that video segment as the identification feature of that video segment.

[0159] In some embodiments, the controller is specifically configured to acquire the image to be detected in the video to be detected;

[0160] Specifically, the controller is used to determine the number of frames between the image to be detected and the second image in the video to be detected, based on the time interval between the image to be detected and the second image.

[0161] Specifically, the controller is used to determine the standard image in the original video based on the interval frame number and the first image.

[0162] In some embodiments, the controller is specifically configured to: input the original video from the motherboard in a loop; acquire the image to be detected in the video to be detected and the standard image in the original video; including:

[0163] Specifically, the controller is used to acquire the image to be detected in the video to be detected;

[0164] Specifically, the controller is used to determine the number of frames between the image to be detected and the second image in the video to be detected, based on the time interval between the image to be detected and the second image.

[0165] Specifically, the controller is used to determine the number of loops and the number of remaining frames of the original video based on the interval frame number and the total number of frames of the original video.

[0166] Specifically, the controller is used to determine the standard image corresponding to the image to be detected based on the first image and the remaining number of frames.

[0167] In some embodiments, the controller is further configured to, if the comparison results are inconsistent, acquire a frame image adjacent to the standard image in the original video, and if at least one frame image is consistent with all pixels of the image to be detected, determine that the detection is successful.

[0168] In some embodiments, the controller is specifically configured to use the detected image to be detected as the first image and the detected standard image as the second image.

[0169] For example, the principle and implementation effect of the motherboard detection device provided in the above embodiments can be found in the embodiments of the motherboard detection method, and will not be repeated here.

[0170] This application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0171] The memory stores the instructions that the computer executes;

[0172] The processor executes computer execution instructions stored in memory to implement the method as in any embodiment of the motherboard detection method.

[0173] This application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method of any embodiment of the motherboard detection method.

[0174] This application discloses a computer program product, which includes a computer program that, when executed by a processor, implements the method as described in any embodiment of the motherboard detection method.

[0175] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0176] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A motherboard testing method, characterized in that, The method includes: dividing the original video input from the motherboard into multiple video segments, wherein each video segment corresponds to an identifier feature, the identifier feature being a common feature of all frame images in the corresponding video segment; acquiring a second image from the video to be detected output from the motherboard, performing image comparison between the second image and the multiple identifier features to determine the identifier feature corresponding to the second image; performing a full pixel comparison between the second image and each frame image in the video segment corresponding to the identifier feature to determine a first image in the original video that matches the full pixel comparison result of the second image; acquiring the image to be detected in the video to be detected; determining the number of frames between the image to be detected and the second image in the video to be detected based on the time interval between the image to be detected and the second image; determining a standard image in the original video based on the number of frames between the frames and the first image; wherein the positional interval between the standard image and the first image is the same as the positional interval between the image to be detected and the second image; performing a full pixel comparison between the image to be detected and the standard image; if the comparison result is consistent, the detection is deemed successful.

2. The method according to claim 1, characterized in that, The step of dividing the original video into multiple video segments includes: performing image recognition on each frame of the original video to determine the key image corresponding to each frame; dividing the original video into multiple video segments based on the key image corresponding to each frame, wherein the similarity between the key images corresponding to each frame in the video segment is greater than or equal to a preset threshold; and for each video segment, using the key image corresponding to any frame in the video segment as the identification feature of the video segment.

3. The method according to claim 1, characterized in that, The original video input from the motherboard is input in a loop. The process of acquiring the image to be detected in the video to be detected and the standard image in the original video includes: acquiring the image to be detected in the video to be detected; determining the interval frame number between the image to be detected and the second image in the video to be detected based on the time interval between the image to be detected and the second image; determining the loop count and remaining frame number of the original video based on the interval frame number and the total number of frames in the original video; and determining the standard image corresponding to the image to be detected based on the first image and the remaining frame number.

4. The method according to claim 1, characterized in that, After performing a full pixel comparison between the image to be detected and the standard image, the method further includes: if the comparison results are inconsistent, obtaining a frame image adjacent to the standard image in the original video; if at least one frame image is consistent with the full pixel comparison results of the image to be detected, then the detection is deemed successful.

5. The method according to claim 1, characterized in that, The process of determining the first image in the original video input from the motherboard and the second image in the video to be tested output from the motherboard includes: using the image to be tested that has passed detection as the first image and using the standard image that has passed detection as the second image.

6. A motherboard testing device, characterized in that, include: Controller and motherboard; The controller is connected to the motherboard; The controller is used to divide the original video input from the motherboard into multiple video segments, each video segment corresponding to an identifier feature, the identifier feature being a common feature of all frame images in the corresponding video segment; acquire a second image from the video to be detected output from the motherboard, perform image comparison between the second image and the multiple identifier features to determine the identifier feature corresponding to the second image; perform a full pixel comparison between the second image and each frame image in the video segment corresponding to the identifier feature to determine a first image in the original video that matches the full pixel comparison result of the second image; the controller is used to acquire the image to be detected in the video to be detected and, based on the time interval between the image to be detected and the second image, determine the number of frames between the image to be detected and the second image in the video to be detected; determine a standard image in the original video based on the number of frames between the frames between the frames between the frames between the frames between the frames between the frames between the frames between the frames between the frames between the frames between the frames; wherein the positional interval between the standard image and the first image is the same as the positional interval between the image to be detected and the second image; the controller is used to perform a full pixel comparison between the image to be detected and the standard image; if the comparison result is consistent, the detection is deemed successful.

7. The motherboard testing device according to claim 6, characterized in that, The controller is specifically used to perform image recognition on each frame of the original video to determine the key image corresponding to each frame; the controller is specifically used to divide the original video into multiple video segments based on the key image corresponding to each frame, wherein the similarity between the key images corresponding to each frame in the video segment is greater than or equal to a preset threshold; the controller is specifically used to use the key image corresponding to any frame in each video segment as the identification feature of the video segment.

Images