Metadata detection method and apparatus

Abstract

Disclosed are a metadata detection method and apparatus, relating to the technical field of multimedia. A computing device acquires metadata of image data comprising one or more image frames, and processes the metadata of the image data on the basis of a detection strategy to obtain a detection result. The detection strategy is used for indicating: determining a similarity between metadata of two adjacent image frames in a plurality of image frames, and / or detecting geometric characteristics of a brightness mapping curve of the image data, wherein the brightness mapping curve of a first image is obtained on the basis of metadata of the first image, and the first image is any image frame in the image data.

Description

Metadata detection method and device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on November 2, 2023, with application number 202311452888.8 and application name “Metadata Detection Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of multimedia technology, and in particular to a metadata detection method and device. Background Art

[0003] Dynamic range mapping in the video field refers to the process of adapting the raw video data obtained by the front end to the display device. The aforementioned process relies on the metadata in the video data, which includes the parameters for adapting the image included in the raw video data to the display device. To ensure the accuracy of the aforementioned adaptation process, basic verification is often performed by checking whether the type of metadata meets the requirements and whether the metadata meets the corresponding specifications. However, the aforementioned basic verification can only evaluate the reliability of the metadata based on the format of the metadata. When the image is mapped to the display device for display based on the metadata, the picture quality of the image on the display device cannot be guaranteed.

[0004] Summary of the Invention

[0005] The present application provides a metadata detection method and apparatus to address the problem that basic verification can only evaluate the reliability of metadata based on the format of the metadata, but when the image is mapped to a display device for display based on the metadata, the picture quality of the image on the display device cannot be guaranteed.

[0006] In a first aspect, the present application provides a metadata detection method. The metadata detection method can be applied to a computer system or a computing device that implements the metadata detection method in the computer system. The computing device is, for example, a server or a terminal (encoding end). The metadata detection method includes: a computing device obtains metadata of image data including one or more frames of images, and processes the metadata of the image data according to a detection strategy to obtain a detection result. The detection strategy is used to indicate: determining the similarity of metadata of two adjacent frames of images in a plurality of frames of images, and / or detecting the geometric characteristics of the brightness mapping curve of the image data, wherein the brightness mapping curve of the first image is obtained based on the metadata of the first image, and the first image is any frame image in the image data.

[0007] Compared to simply verifying the type and specifications of metadata, in this application, the computing device detects the similarity of metadata between two adjacent frames of image data. This can determine that when the metadata difference between the two adjacent frames is too large, the image data will flicker when the image data is displayed. In other words, this application also considers the display effect factors caused by metadata, improves the depth of metadata detection, and ensures the image quality of the displayed image data. In addition, the computing device obtains a brightness mapping curve based on the metadata and detects the geometric characteristics of the brightness mapping curve, achieving multi-dimensional detection of metadata, further improving the depth of metadata detection and ensuring the image quality of the displayed image data.

[0008] Exemplarily, the brightness mapping curve of the first image represents: a correspondence between original brightness values ​​of pixels in the first image and displayed brightness values ​​of the pixels when the first image is displayed.

[0009] In one possible implementation, the computing device obtains metadata of the image data, including: the computing device receives a user triggering operation on a control component on a user interface, and then obtains the metadata of the image data in response to the user triggering operation on the control component.

[0010] In this application, the computing device interacts with the user through a user interface to confirm whether the user needs to perform quality detection of the metadata of the image data. While achieving visualization, it determines whether to perform quality detection of the metadata based on user needs, thereby improving processing freedom.

[0011] In one possible implementation, when the detection strategy is used to indicate: determining the similarity of metadata between two adjacent frames of images in a multi-frame image, the computing device processes the metadata of the image data according to the detection strategy, and the content of the detection result obtained can be the following two examples.

[0012] In Example 1, a computing device determines the similarity of at least one metadata between two adjacent image frames. If the similarity of the at least one metadata between the two adjacent image frames is greater than a first threshold, the detection result indicates that the metadata of one of the two adjacent image frames is normal. If the similarity of the at least one metadata between the two adjacent image frames is less than the first threshold, the detection result indicates that the metadata of one of the two adjacent image frames is abnormal. If the similarity of the at least one metadata between the two adjacent image frames is equal to the first threshold, the detection result indicates whether the metadata of one of the two adjacent image frames is abnormal or normal.

[0013] Example 2: A computing device determines the brightness mapping curves of the two adjacent image frames based on the metadata of the two adjacent image frames, and then determines the similarity of the brightness mapping curves of the two adjacent image frames. If the similarity of the brightness mapping curves of the two adjacent image frames is less than a first threshold, the detection result is used to indicate that the metadata of one of the two adjacent image frames is abnormal. If the similarity of the brightness mapping curves of the two adjacent image frames is greater than the first threshold, the detection result is used to indicate that the metadata of one of the two adjacent image frames is normal. If the similarity of the brightness mapping curves of the two adjacent image frames is equal to the first threshold, the detection result is used to indicate whether the metadata of one of the two adjacent image frames is normal or abnormal.

[0014] In the present application, since the brightness mapping curve indicates the correspondence between the original brightness value of the pixel points in the first image and the displayed brightness value of the pixel points when the first image is displayed, it shows the complete mapping relationship when the image is mapped to the display device. Therefore, the computing device detects the quality of the metadata of the image data based on the complete mapping relationship corresponding to the two adjacent frames of images, and can detect whether the screen flickers when the image data is displayed. This avoids verifying only the type or specification of the metadata, improves the depth of metadata quality detection, and in other words, the reliability of the metadata, and ensures the quality of the displayed image data.

[0015] In one possible implementation, when the detection strategy is used to indicate: detecting the geometric characteristics of the brightness mapping curve of the image data, the computing device processes the metadata of the image data according to the detection strategy, and the content of the obtained detection result can be the following three examples.

[0016] In Example 1, a brightness mapping curve corresponding to a second image includes multiple curve segments. The second image is any frame of image data. A computing device determines multiple displayed brightness values ​​corresponding to each of multiple original brightness values ​​of the multiple curve segments corresponding to the second image, and calculates the differences between these multiple displayed brightness values. If all of the differences are less than or equal to a second threshold, the detection result indicates that the metadata of the second image is normal. If at least one of the differences is greater than the second threshold, the detection result indicates that the metadata of the second image is abnormal.

[0017] In this application, the computing device detects the continuity of the brightness mapping curve to avoid discontinuity of the brightness mapping curve corresponding to the metadata, thereby preventing the problem of screen faults when displaying image data, thereby ensuring the quality of the screen when displaying image data.

[0018] In Example 2, a brightness mapping curve corresponding to a third image includes multiple curve segments, and the third image is any frame of image data. A computing device determines the monotonicity of the multiple curve segments corresponding to the third image. If the monotonicity of the multiple curve segments is not uniform, the detection result indicates that the metadata of the third image is abnormal. If the monotonicity of the multiple curve segments is uniform, the detection result indicates that the metadata of the third image is normal.

[0019] In this application, the computing device detects the monotonicity of the brightness mapping curve to avoid the problem of brightness flipping when the original brightness value is too large and the corresponding display brightness value is too small, or when the original brightness value is too small and the corresponding display brightness value is too large, thereby ensuring the quality of the picture when displaying image data.

[0020] In Example 3, a computing device determines the target original brightness value corresponding to the target display brightness value in the brightness mapping curve corresponding to the fourth image, and calculates the ratio of the number of pixels in the fourth image that are greater than or less than the target original brightness value to the total number of pixels in the fourth image. The fourth image is any frame image in the image data. If the ratio is greater than a third threshold, the detection result indicates that the metadata of the fourth image is abnormal. If the ratio is less than the third threshold, the detection result indicates that the metadata of the fourth image is normal. If the ratio is equal to the third threshold, the detection result indicates that the metadata of the fourth image is normal or abnormal.

[0021] In this application, the computing device avoids the problem of missing brightness of some pixels (i.e., not displayed) when displaying image data by detecting the rationality of the brightness mapping curve (brightness rationality), that is, detecting whether there is an original brightness value in the brightness mapping curve that does not correspond to the display brightness value, thereby ensuring the quality of the picture when displaying image data.

[0022] In one possible implementation, the multiple image frames are images between two scene-change frames, where the scene-change frame is the subsequent image in the multiple image frames whose metadata similarity is less than or equal to a fourth threshold. That is, when performing the quality check, the computing device only checks the metadata of the multiple image frames between the two scene-change frames, thereby reducing the amount of data computation and improving data efficiency.

[0023] In one possible implementation, the metadata detection method further includes: if the one or more frames of images with abnormal metadata indicated by the detection result are scene cut frames, updating the one or more frames of images with abnormal metadata indicated by the detection result to have normal metadata. The scene cut frame is a subsequent frame in the plurality of adjacent frames of images for which the metadata similarity is less than or equal to a fourth threshold.

[0024] In this application, because scene switching may occur in image data, sudden changes in brightness and other parameters during scene switching are considered normal. That is, when an image frame is a scene switching frame, the abnormal metadata of the scene switching frame is allowed and is considered normal. The computing device sets the detection result corresponding to the scene switching frame as normal, which conforms to the scene switching law.

[0025] Regarding the above-mentioned scene switching frame, two examples of determining the scene switching frame are provided below.

[0026] Example 1: The computing device obtains a scene switching identifier included in metadata of the fifth image, where the scene switching identifier is used to indicate that the fifth image is a scene switching frame and the fifth image is any frame image in the image data.

[0027] Example 2: A computing device determines the similarity of attributes of pixel points in a sixth image and a seventh image, and when the similarity of the attributes of pixel points in the sixth image and the seventh image is less than or equal to a fifth threshold, calculates the similarity between the metadata of the sixth image and the metadata of the seventh image, thereby determining that the sixth image is a scene switch frame. The sixth image and the seventh image are in the same sliding window, the seventh image is one or more frames of images adjacent to the sixth image, and the sixth image and the seventh image are any frame of images in the image data. The similarity between the metadata of the sixth image and the metadata of the seventh image is less than or equal to a sixth threshold, and the attributes include: one or more of a luminance value or a luminance-chrominance YUV.

[0028] In the present application, the computing device determines the scene switching frame from multiple frames of images based on the similarity of attributes and the similarity of metadata, and then refers to the scene switching frame when determining abnormal metadata. That is, when the monotonicity of the brightness mapping curve corresponding to the metadata of the scene switching frame is not uniform, the continuity is inconsistent, etc., the metadata of the scene switching frame is also normal, thereby improving the accuracy of determining abnormal metadata.

[0029] In a possible implementation, the metadata detection method further includes: the computing device outputting a detection result.

[0030] For example, the computing device outputs the detection result to a display device.

[0031] In a possible implementation, the metadata detection method further includes: when the detection result indicates that the metadata of one or more frames of images are abnormal, the computing device updates the metadata of the one or more frames of images with abnormal metadata.

[0032] In the present application, the computing device ensures the quality of image data displayed by the display device by updating the metadata of one or more frames of images with abnormal metadata.

[0033] In a second aspect, the present application provides a metadata detection method. The metadata detection method can be applied to a computer system or a computing device that implements the metadata detection method in the computer system. The computing device is, for example, a server or a terminal (decoding end). The metadata detection method includes: a computing device obtains metadata of image data including one or more frames of images, and processes the metadata of the image data according to a detection strategy to obtain a detection result. The detection strategy is used to indicate: determining the similarity of metadata of two adjacent frames of images in the multiple frames of images, and / or detecting the geometric characteristics of the brightness mapping curve of the image data, wherein the brightness mapping curve of the first image is obtained based on the metadata of the first image, and the first image is any frame image in the image data.

[0034] Exemplarily, the brightness mapping curve of the first image represents: a correspondence between original brightness values ​​of pixels in the first image and displayed brightness values ​​of the pixels when the first image is displayed.

[0035] In one possible implementation, the metadata detection method further includes: if the detection result indicates that the similarity of metadata between two adjacent frames of images in the multi-frame image is less than or equal to a first threshold, and / or the geometric characteristic detection of the brightness mapping curve of at least one frame of image in the image data is abnormal, then an alarm is issued according to the detection result.

[0036] In one possible implementation, the metadata detection method further includes: when the detection result indicates that the metadata of one or more frames of images is abnormal, the computing device maps the one or more frames of images according to preset metadata, and the one or more frames of images include images with abnormal metadata.

[0037] In the present application, when the metadata of one or more frames of an image are abnormal, the computing device uses preset metadata to map the image data to the display device to ensure the quality of the image data when the display device displays it.

[0038] For other possible implementations of the second aspect, reference may be made to any possible implementation of the first aspect described above, and details will not be repeated here.

[0039] In a third aspect, the present application provides a metadata detection device, which is applied to a computer system or a computing device that supports the computer system to implement the metadata detection method. The metadata detection device includes various modules for executing the metadata detection method in the first aspect or any optional implementation of the first aspect. For example, the metadata detection device includes: a first acquisition module and a first processing module.

[0040] The first acquisition module is configured to acquire metadata of image data, wherein the image data includes one or more frames of image.

[0041] The first processing module is configured to process the metadata of the image data according to a detection strategy to obtain a detection result. The detection strategy is configured to determine the similarity between metadata of two adjacent frames of the image data and / or to detect geometric characteristics of a brightness mapping curve of the image data. The brightness mapping curve of a first image is obtained based on the metadata of the first image, where the first image is any frame of the image data.

[0042] For more detailed implementation details of the metadata detection device, please refer to the description of any implementation method in the first aspect above, as well as the content of the following specific implementation methods, which will not be repeated here.

[0043] In a fourth aspect, the present application provides a metadata detection device, which is applied to a computer system or a computing device that supports the computer system to implement the metadata detection method. The metadata detection device includes various modules for executing the metadata detection method in the second aspect or any optional implementation of the second aspect. For example, the metadata detection device includes: a second acquisition module and a second processing module.

[0044] The second acquisition module is used to acquire metadata of image data, where the image data includes one or more frames of image.

[0045] The second processing module is configured to process the metadata of the image data according to a detection strategy to obtain a detection result. The detection strategy is configured to instruct: determining the similarity of metadata between two adjacent frames of the multiple images; and / or detecting geometric characteristics of a brightness mapping curve of the image data, where the brightness mapping curve of a first image is obtained based on the metadata of the first image, where the first image is any frame of the image data.

[0046] For more detailed implementation details of the metadata detection device, please refer to the description of any implementation method in the second aspect above, as well as the content of the following specific implementation methods, which will not be repeated here.

[0047] In a fifth aspect, the present application provides a chip comprising: a processor and a power supply circuit; the power supply circuit is used to power the processor, and the processor is used to execute the method in the above-mentioned first aspect or any possible implementation of the first aspect; and / or, the processor is used to execute the method in the above-mentioned second aspect or any possible implementation of the second aspect.

[0048] In a sixth aspect, the present application provides a decoder comprising a memory and a processor, wherein the memory is configured to store computer instructions; when the processor executes the computer instructions, the method of the first aspect or any possible implementation of the first aspect is implemented; and / or when the processor executes the computer instructions, the method of the second aspect or any possible implementation of the second aspect is implemented. The decoder may be an encoder or a decoder.

[0049] In a seventh aspect, the present application provides a computer-readable storage medium storing a computer program or instruction. When the computer program or instruction is executed by a processing device, the method in the above-mentioned first aspect or any possible implementation of the first aspect is implemented; and / or, when the computer program or instruction is executed by a processing device, the method in the above-mentioned second aspect or any possible implementation of the second aspect is implemented.

[0050] In an eighth aspect, the present application provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processing device, it implements the method in the above-mentioned first aspect or any possible implementation of the first aspect; and / or, when the computer program or instructions are executed by a processing device, it implements the method in the above-mentioned second aspect or any possible implementation of the second aspect.

[0051] The beneficial effects of the second to eighth aspects above can be referred to the first aspect or any possible implementation of the first aspect, and will not be described in detail here. Based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] FIG1 is an application scenario diagram of a computer system provided by this application;

[0053] FIG2 is a flowchart of the metadata detection method provided by this application;

[0054] FIG3 is a schematic diagram of a graphical user interface provided by this application;

[0055] FIG4 is a flow chart of the geometric characteristic detection method provided in this application;

[0056] FIG5 is a second flow chart of the geometric characteristic detection method provided by the present application;

[0057] FIG6 is a third flow chart of the geometric characteristic detection method provided by this application;

[0058] FIG7 is a schematic flow chart of a method for determining a scene switching frame provided by the present application;

[0059] FIG8 is a second flow chart of the metadata detection method provided by this application;

[0060] FIG9 is a first structural diagram of a metadata detection device provided by the present application;

[0061] FIG10 is a second structural diagram of a metadata detection device provided by the present application;

[0062] FIG11 is a third structural diagram of a metadata detection device provided by the present application;

[0063] FIG12 is a fourth structural diagram of a metadata detection device provided by the present application;

[0064] FIG13 is a schematic diagram of the structure of a computing device provided in this application. DETAILED DESCRIPTION

[0065] To facilitate understanding, the technical terms involved in this application are first introduced.

[0066] High dynamic range (HDR) refers to an image with a dynamic range between 0.001 nits and 10,000 nits, where nit is a unit of light.

[0067] Standard dynamic range (SDR) refers to images with a dynamic range of 1nit to 100nit.

[0068] Metadata, in this application, refers to the key feature information of each frame image in the video, such as the average brightness, maximum brightness or minimum brightness of the scene.

[0069] Static metadata refers to metadata that remains unchanged throughout the entire video or scene.

[0070] Dynamic metadata refers to metadata that changes dynamically based on the scene or each frame.

[0071] Tone mapping (TM) refers to the tone mapping technology between dynamic ranges, that is, the adjustment method between different dynamic ranges.

[0072] The following example shows how to adapt the original video obtained by the video production end to a display device. The original HDR video captured or produced by the video production end has a maximum brightness of 4000 nits, while the display device's SDR display capability is only 100 nits. Therefore, the 4000-nit original video needs to be mapped to 100 nits for display on the display device.

[0073] The above-mentioned mapping methods can include static mapping and dynamic mapping. Static mapping refers to the overall mapping of the same video or image content using a single static metadata. Dynamic mapping uses different data for each scene or frame based on the characteristics of each frame in the video, that is, mapping using dynamic metadata.

[0074] The advantage of the static mapping is that it carries less information and has a simple processing flow. The priority of the dynamic mapping is that in extremely dark or bright scenes, the details of the scene in the video are still preserved, and the display effect is better.

[0075] The mapping process relies on metadata containing key information or features of the video. A mapping curve derived from this metadata is used to adapt the original video to the display device. This mapping curve represents the correspondence between the original brightness of a pixel in an image in the video and the displayed brightness of that pixel when the image is displayed.

[0076] To ensure that the display device can display the original video content well, the metadata of the original video is often detected. The following provides two possible detection methods.

[0077] Detection method 1: After encoding the video to obtain a bitstream, detect whether the video metadata is correctly encapsulated in the bitstream.

[0078] Since the encapsulation location of metadata in a bitstream (media file) has corresponding specifications (such as supplemental enhancement information (SEI)), this solution can parse the bitstream and confirm whether the corresponding metadata can be found based on the metadata identifier.

[0079] The above solution can only confirm whether the metadata is correctly encapsulated, but does not test the quality of the metadata itself.

[0080] Detection method 2: After encoding the video and generating a bitstream, the metadata type in the bitstream can be detected to determine whether the metadata type meets the preset requirements. Furthermore, the corresponding metadata parameters meet the set specifications and threshold ranges. For example, the detection can be performed on Boolean metadata and fixed-point metadata.

[0081] When judging Boolean metadata, it is possible to determine whether the Boolean metadata has only two values: true and false. When judging fixed-point metadata, it is possible to determine whether the fixed-point metadata overflows the bit value range. The value range of N-bit non-negative fixed-point metadata is 0 to 2. N -1.

[0082] The above-mentioned detection method 2 only performs basic verification of the metadata, that is, it only determines whether different types of metadata meet the specification requirements, and does not evaluate the quality of the metadata. As a result, it is impossible to determine the quality of the original video when it is mapped to the display device according to the metadata, resulting in unstable display quality.

[0083] In summary, the above detection method can only evaluate the reliability of metadata based on the format of the metadata. When the original video data (one or more frames of images) is mapped to the display device for display based on the metadata, the picture quality of the image in the display device cannot be guaranteed.

[0084] Based on this, the present application provides a metadata detection method, which can be applied to a computing device, which can be an encoding end or a decoding end. The metadata detection method includes: the computing device obtains metadata of image data including one or more frames of images, and processes the metadata of the image data according to a detection strategy to obtain a detection result. The detection strategy is used to indicate: determining the similarity of metadata of two adjacent frames of images in the multiple frames, and / or detecting the geometric characteristics of the brightness mapping curve of the image data, the brightness mapping curve of the first image being obtained based on the metadata of the first image. The first image is any frame in the image data.

[0085] Compared to simply verifying the type and specifications of metadata, in this application, the computing device detects the similarity of metadata between two adjacent frames of image data. This can determine that when the metadata difference between the two adjacent frames is too large, the image data will flicker when the image data is displayed. In other words, this application also considers the display effect factors caused by metadata, improves the depth of metadata detection, and ensures the image quality of the displayed image data. In addition, the computing device obtains a brightness mapping curve based on the metadata and detects the geometric characteristics of the brightness mapping curve, achieving multi-dimensional detection of metadata, further improving the depth of metadata detection and ensuring the image quality of the displayed image data.

[0086] Exemplarily, the brightness mapping curve of the first image represents: a correspondence between original brightness values ​​of pixels in the first image and displayed brightness values ​​of the pixels when the first image is displayed.

[0087] When the computing device is an encoding end, the computing device may also output a detection result. When the computing device is a decoding end, the computing device may issue an alarm based on the detection result.

[0088] The metadata detection method provided by the present application can be applied to the computer system shown in Figure 1. As shown in Figure 1, Figure 1 is an application scenario diagram of a computer system provided by the present application.

[0089] A computer system includes an encoder 100 and a decoder 200. The encoder 100 generates encoded video (or a bitstream). Therefore, the encoder 100 can be referred to as a video encoder. The decoder 200 can decode the bitstream (e.g., image data containing one or more frames of images) generated by the encoder 100. Therefore, the decoder 200 can be referred to as a video decoder. Various implementations of the encoder 100, the decoder 200, or both can include one or more processors and a memory coupled to the processor(s). The memory can include, but is not limited to, random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or any other medium that can be used to store desired program code in the form of computer-accessible instructions or data structures.

[0090] In the example of FIG1 , encoding end 100 includes source video 110, video encoder 120, and output interface 130. In some examples, output interface 130 may include a modem and / or a transmitter. Source video 110 may be obtained from a video capture device (e.g., a camera), a video archive containing previously captured video, a video feed interface for receiving video from a video content provider, and / or a computer graphics system for generating video, such as an image rendering engine, or a combination of these video sources.

[0091] For example, the encoding terminal 100 may be equipped with (davinci resolve) tool, color grading system (baselight) tool.

[0092] Video encoder 120 can encode video (multiple source images) from source video 110. In some examples, encoding end 100 transmits the bitstream directly to decoding end 200 via output interface 130 via link 300. In other examples, the bitstream can also be stored on storage device 400 for later access by decoding end 200 for decoding and / or playback. The bitstream includes metadata for the image data.

[0093] The metadata for a frame of image may include: the maximum brightness value, minimum brightness value, and average brightness value corresponding to the frame of image, etc. The aforementioned metadata content is merely an example. In other embodiments of the present application, the metadata for a frame of image may also include: parameters of several specified functions (such as an exponential function, a logarithmic function, a quadratic function, a cubic spline function, etc.). The specified function and the parameters of the specified function are used to map the video to a display device (such as display device 210) for display.

[0094] In the example of FIG1 , the decoding end 200 includes an input interface 230, a video decoder 220, and a display device 210. In some examples, the input interface 230 includes a receiver and / or a modem. The input interface 230 can receive encoded video via a link 300 and / or from a storage device 400. The video decoder 220 decodes the received bitstream to obtain a video (a plurality of decoded images). The display device 210 can be integrated with the decoding end 200 or can be external to the decoding end 200. Generally speaking, the display device 210 displays the decoded video. The display device 210 can include a variety of display devices, such as a liquid crystal display (LCD), a plasma display, an organic light-emitting diode (OLED) display, or other types of display devices.

[0095] For example, after the encoding end 100 acquires the video, metadata corresponding to each frame image in the video may be generated. Then, when the video encoder 120 in the encoding end 100 encodes the video, the metadata is further encoded to obtain a bitstream.

[0096] Furthermore, after the decoding end 200 obtains the code stream, it processes the metadata corresponding to the image data carried in the code stream according to the detection strategy to obtain a detection result.

[0097] On the one hand, the present application provides a metadata detection method, which can be applied to the computer system shown in Figure 1. Figure 2 is a flowchart of the metadata detection method provided by the present application. The metadata detection method can be executed by a first computing device 310, which can be the encoding end 100 in Figure 1. The first computing device 310 is deployed with a metadata editing tool (such as As shown in FIG2 , the metadata detection method may include the following steps S210 and S220.

[0098] S210 : The first computing device 310 obtains metadata of the image data.

[0099] The image data includes one or more frames of images. When the image data includes multiple frames of images, the image data can be called a video.

[0100] In one possible implementation, the first computing device 310 obtains metadata of image data, including: the first computing device 310 generates metadata of each frame image in the video based on the obtained video.

[0101] For example, the first computing device 310 may obtain the video from a memory, or obtain the video by a video capture device (such as a camera) built into or connected to the first computing device 310. The aforementioned method of obtaining the video is merely an example of the present application. In other embodiments of the present application, a video rendered by an image rendering engine may also be obtained.

[0102] In a possible example, the first computing device 310 generates metadata for each frame of the video according to the acquired video, including: the first computing device 310 may generate metadata for each frame of the video according to the deployed The tool generates metadata for the video, and then obtains metadata corresponding to each frame image in the video.

[0103] For example, the first computing device 310 imports the video into tools, and in The tool defines the type of metadata to be generated and then outputs the metadata of the video. Or, The tool outputs the edited video along with the video's metadata.

[0104] In another possible example, the first computing device 310 generates metadata for each frame image in the video based on the acquired video, including: the first computing device 310 can generate metadata for the video based on the baselight tool deployed thereon, and thus obtain metadata for each frame image in the video.

[0105] Regarding the metadata content of the image data obtained by the first computing device 310, a possible embodiment is provided below, as shown in Figure 3, which is a schematic diagram of the image user interface provided by this application. S210 in Figure 2 may include the following steps S310 and S320.

[0106] S310: The first computing device 310 receives a user trigger operation on a control component on a user interface.

[0107] The user interface includes controls for metadata detection.

[0108] As shown in Figure 3, the metadata detection control component in the user interface can be in various forms, such as a square or a switch shape, which is not limited in this application. The control component is used to indicate whether to generate metadata for each frame image in the video.

[0109] In one possible example, the first computing device 310 may display a user interface on the front end. The front end here may refer to a display connected to the first computing device 310, or a display screen possessed by the first computing device 310, etc. This application is not limited to this.

[0110] In one possible implementation, the first computing device 310 receives the user's triggering operation on the control component, including: the first computing device 310 obtains the user's triggering operation on the control component on the user interface through various input devices (keyboard, mouse, touch screen, etc.).

[0111] Regarding the specific implementation of the trigger operation, three possible examples are provided below.

[0112] In example 1, the trigger operation may be a user confirming the control component of metadata detection through a keyboard, such as the trigger operation being a confirmation (enter) key triggered by the user.

[0113] Example 2: The triggering operation may be a user clicking a control component of metadata detection using a mouse.

[0114] Example 3: The trigger operation may be a user clicking or sliding a control component for metadata detection on a touch screen.

[0115] The above examples are only optional implementations provided in this embodiment and should not be understood as limiting the present application. In other embodiments of the present application, the trigger operation may also be air operation or voice control.

[0116] S320: The first computing device 310 obtains metadata of the image data in response to a user triggering operation on the control component.

[0117] The first computing device 310 determines to generate metadata for each frame image in the video in response to a user triggering operation on the control component through various input devices, and performs the metadata detection method shown in FIG2 .

[0118] Regarding the content of metadata generated by the first computing device 310 for each frame of image in the video, reference may be made to the description of S210 above, which will not be elaborated here.

[0119] In this application, the first computing device 310 interacts with the user through a user interface to confirm whether the user needs to perform metadata quality detection. While achieving visualization, it determines whether to perform metadata quality detection based on user needs, thereby improving processing freedom.

[0120] Continuing to refer to FIG. 2 , the metadata detection method provided in this embodiment further includes step S220 .

[0121] S220 : The first computing device 310 processes the metadata of the image data according to the detection strategy to obtain a detection result.

[0122] In a possible embodiment, the above detection strategy is used to indicate that the first computing device 310 determines the similarity of metadata between two adjacent frames of images in the multiple frames of images.

[0123] When the metadata similarity between two adjacent image frames is greater than a first threshold (this first threshold may also be referred to as threshold 1, which may be 0.85), the first computing device 310 determines that the detection results for the two adjacent image frames are normal. When the metadata similarity between the two adjacent image frames is less than threshold 1, the first computing device 310 determines that the detection results for the two adjacent image frames are abnormal. When the metadata similarity between the two adjacent image frames is equal to threshold 1, the first computing device 310 may determine whether the detection results for the two adjacent image frames are normal or abnormal based on user needs, which is not limited here.

[0124] The similarity of metadata between two adjacent image frames may be the similarity of at least one metadata element of the two adjacent image frames, or the similarity of brightness mapping curves corresponding to the two adjacent image frames. The brightness mapping curve of the first image is obtained based on the metadata of the first image, and the brightness mapping curve is used to indicate the correspondence between the original brightness value of the pixel point in the first image and the displayed brightness value of the pixel point when the first image is displayed. The device displaying the first image is a display device, which may be the decoding end in Figure 1. The first image is any frame image in the image data.

[0125] For example, the original brightness value represents the original brightness of the pixels in each frame of the video when the first computing device 310 acquires the video. The display brightness value represents the brightness of the pixels displayed by the display device when the video is mapped to the display device.

[0126] In a possible implementation, the first computing device 310 calculates the similarity of at least one metadata between two adjacent frames of images.

[0127] The first computing device 310 may calculate the similarity by calculating the distance between at least one metadata in two adjacent image frames. For example, the first computing device 310 may calculate the distance between at least one metadata in two adjacent image frames using Euclidean distance, Manhattan distance, Chebyshev distance, or the like.

[0128] If the distance between at least one metadata item in two adjacent image frames is greater than a preset distance, the detection results of the two adjacent image frames are determined to be abnormal. If the distance between at least one metadata item in two adjacent image frames is less than a preset distance, the detection results of the two adjacent image frames are determined to be normal. If the distance between at least one metadata item in two adjacent image frames is equal to the preset distance, the detection results of the two adjacent image frames are determined to be normal or abnormal based on user needs.

[0129] Exemplarily, the at least one metadata includes a maximum brightness value and a minimum brightness value. The maximum brightness value and the minimum brightness value of the first frame of the two adjacent image frames are 4000 and 500, respectively, and the maximum brightness value and the minimum brightness value of the second frame of the two adjacent image frames are 4200 and 520, respectively. The first computing device 310 determines the similarity of the metadata of the two adjacent image frames based on the maximum brightness value and the minimum brightness value of the two adjacent image frames, that is, determines the distance between (4000, 500) and (4200, 520).

[0130] In another possible implementation, the first computing device 310 calculates the similarity of brightness mapping curves determined according to metadata of two adjacent image frames.

[0131] The first calculation device 310 may use Fréchet distance, dynamic time warping (DTW), etc. to determine the similarity of brightness mapping curves corresponding to two adjacent image frames.

[0132] The Fréchet distance is defined as the maximum value obtained by selecting a point on one curve and a point on the other curve, then connecting the two points to form a connecting line segment. The position and length of the connecting line segment are constrained by the order of the points on the two curves. The Fréchet distance is the maximum value that minimizes the connecting line segment obtained by this process. The smaller the Fréchet distance, the more similar the two curves are.

[0133] The basic idea of ​​DTW is to align two time series (curves) to minimize the distance between them while satisfying strict monotonicity and smoothness constraints. Specifically, DTW calculates the distance matrix between the two series and uses dynamic programming to find the optimal path, providing a measure of the similarity between the two series.

[0134] In one possible scenario, when the similarity between the brightness mapping curves of two adjacent image frames is less than a threshold value of 1, the first computing device 310 determines that the metadata of one of the two adjacent image frames is abnormal. In other words, the detection result indicates that the metadata of one of the two adjacent image frames is abnormal. When the similarity between the brightness mapping curves of the two adjacent image frames is greater than the threshold value of 1, the first computing device 310 determines that the metadata of the two adjacent image frames is normal. In other words, the detection result indicates that the metadata of the two adjacent image frames is normal.

[0135] When the similarity of the brightness mapping curves of two adjacent image frames is equal to the threshold 1, the first computing device 310 confirms whether the metadata of the two adjacent image frames are normal or abnormal, which is not limited in this application.

[0136] In a possible example, one of the two adjacent image frames is used to indicate the latter of the two adjacent image frames.

[0137] In the present application, since the brightness mapping curve indicates the correspondence between the original brightness value of the pixel in the first image and the displayed brightness value of the pixel when the first image is displayed, it shows the complete mapping relationship when the image is mapped to the display device. Therefore, the first computing device 310 detects the quality of the metadata based on the complete mapping relationship corresponding to the two adjacent frames of images, and can detect whether the display device will experience screen flickering when displaying the two adjacent frames of images. This avoids verifying only the type or specification of the metadata, improves the depth of metadata quality detection, and in other words, the reliability of the metadata, and ensures the quality of the video when the display device displays the video.

[0138] In a possible scenario, three examples of obtaining corresponding brightness mapping curves according to metadata of each frame image are shown below.

[0139] In Example 1, the metadata includes only a number of brightness features of each frame, such as the maximum brightness value, the minimum brightness value, and the average brightness value. The first computing device 310 uses the brightness features of each frame as the horizontal axis, and the vertical axis corresponds to the brightness information of the display device (such as the maximum brightness value, the minimum brightness value, and the average brightness value). The first computing device 310 smoothly connects the aforementioned multiple points using a preset function to obtain a brightness mapping curve.

[0140] The preset curve may be a Catmull-Rom spline curve, a Bézier curve, or the like.

[0141] The Catmull-Rom spline is a curve used to interpolate control points. It can produce smooth and natural curves and is therefore widely used in computer graphics, animation, and other related fields.

[0142] A Bezier curve is a mathematical curve that describes a smooth curve. It describes the curve's shape by defining a starting point (such as the minimum brightness value mentioned above), an end point (such as the maximum brightness value mentioned above), and control points (such as the average brightness value mentioned above). The starting and end points are the endpoints of the curve, while the control points determine the curve's curvature and shape.

[0143] In Example 2, the metadata includes, in addition to the brightness feature described in Example 1, several specified function parameters (such as an exponential function, a logarithmic function, a quadratic function, a cubic spline function, etc.). The parameters of the specified function are used to adjust the brightness, chroma, etc. of the video. The first computing device 310 generates a brightness mapping curve based on the function parameters and the corresponding function.

[0144] For example, the metadata indicates an exponential function and parameters corresponding to the exponential function, and the first computing device 310 can accurately determine the brightness mapping curve according to the exponential function and the parameters corresponding to the exponential function.

[0145] Example 3 is a combination of the above examples 1 and 2, which will not be described in detail here.

[0146] The above content is merely an optional example provided in this embodiment and should not be construed as limiting the present application.

[0147] In a possible embodiment, the above detection strategy is further used to instruct the first computing device 310 to detect geometric characteristics of a brightness mapping curve of the image data.

[0148] In this embodiment, the first computing device 310 mainly detects at least one of continuity, monotonicity, and rationality of the geometric characteristics of the mapping curve.

[0149] Continuity refers to whether the multiple segments of the brightness mapping curve are continuous. Specifically, it refers to whether the difference between two adjacent segments at the same horizontal coordinate is less than a second threshold. The first computing device 310 detects the continuity of the brightness mapping curve, as described in FIG. 4 below, and is not further described here.

[0150] In a possible example, the abscissa of the brightness mapping curve is used to indicate an original brightness value, and the ordinate of the brightness mapping curve is used to indicate a displayed brightness value.

[0151] Monotonicity refers to whether the multiple segments of the brightness mapping curve are all increasing or decreasing. The first computing device 310 detects the monotonicity of the brightness mapping curve, as shown in FIG5 below, and is not described in detail here.

[0152] Reasonableness refers to whether there are brightness values ​​in the brightness mapping curve that are greater than or less than the target original brightness value corresponding to the target display brightness value. The first computing device 310 checks the reasonableness of the brightness mapping curve, as shown in FIG6 below, and is not further described here.

[0153] In the present application, the first computing device 310 detects at least one of the continuity, monotonicity, and rationality of the brightness mapping curves of multiple frames of images, thereby realizing multi-dimensional detection of metadata, improving the depth of metadata quality detection, and thereby ensuring the picture quality of the image when displayed.

[0154] In one possible embodiment, the first computing device 310 may output the detection result to the front end, which may then display the detection result. The front end here may refer to a display connected to the first computing device 310, or a display screen provided by the first computing device 310, etc., which is not limited in this application.

[0155] The detection result may include the metadata of each frame image in the video, such as whether the metadata of the first frame image is normal or the metadata of the second frame image is abnormal.

[0156] In a possible example, the above detection results may also include: the specific conditions of the metadata of each frame image, such as at least one abnormality in the continuity, monotonicity, and rationality of the brightness mapping curve corresponding to the first frame image, or the second frame image will have screen flickering, that is, the similarity between the metadata of the first frame image and the second frame image is less than or equal to the threshold 1.

[0157] In another possible example, the above detection result may further include: marking one or more frames of images with abnormal metadata, that is, the marked images are images with abnormal metadata.

[0158] In a possible embodiment, the first computing device 310 may determine, based on the content of the detection result, to update the metadata of one or more frames of images with abnormal metadata.

[0159] In a possible implementation, the first computing device 310 determines that one or more frames of images have abnormal metadata in the detection result, and then regenerates metadata based on the one or more frames of images with abnormal metadata.

[0160] Exemplarily, the first computing device 310 instructs the metadata editing tool to regenerate metadata based on one or more frames of images with abnormal metadata.

[0161] In another optional implementation, the first computing device 310 determines that the detection result indicates that there are one or more frames of images with metadata anomalies, and then instructs the metadata editing tool to regenerate metadata corresponding to each frame of the video based on the video.

[0162] The above-mentioned method of regenerating metadata may refer to the content of obtaining metadata in S210, which will not be described in detail here.

[0163] In this application, the first computing device 310 detects metadata quality from multiple dimensions by determining the similarity of metadata between two adjacent frames of multiple images and / or detecting the geometric characteristics of the brightness mapping curve of the image data. This improves the depth of metadata quality detection, that is, the reliability of the metadata, and ensures the quality of the image displayed on the display device. Furthermore, based on the detection results, abnormal metadata is regenerated, further ensuring the quality of the image displayed on the display device.

[0164] To test the continuity of the mapping curves for each frame of image, a possible implementation is provided below, as shown in Figure 4, which is a flow chart of the geometric property detection method provided in this application. The brightness mapping curve corresponding to the second image includes multiple segments. The second image is any frame of image data. The second threshold can be referred to as Threshold 2. S220 in Figure 2 may include the following steps S410 to S440.

[0165] S410 : The first computing device 310 determines a plurality of display brightness values ​​corresponding to each of a plurality of original brightness values ​​of a plurality of curve segments corresponding to the second image.

[0166] As shown in Figure 4, the brightness mapping curve of the second image has three segments. The first computing device 310 determines that the sets of horizontal coordinates corresponding to two adjacent segments have overlapping horizontal coordinates. These overlapping horizontal coordinates are the original brightness values ​​described above, such as the original brightness value a and the original brightness value b. The first computing device 310 determines the display brightness value c' on curve 1 and the display brightness value c'' on curve 2 corresponding to the original brightness value a.

[0167] Likewise, the first computing device 310 determines a display brightness value d′ corresponding to curve 2 and a display brightness value d″ corresponding to curve 3 at the original brightness value b.

[0168] S420: The first calculation device 310 calculates the difference between the multiple display brightness values.

[0169] Taking one of the multiple original brightness values ​​as an example, the brightness mapping curve corresponds to multiple display brightness values ​​at the original brightness value, and the first calculation device 310 determines the difference between the multiple display brightness values.

[0170] For example, the first computing device 310 determines a difference of 1 between the display brightness value c' and the display brightness value c'', and a difference of 2 between the display brightness value d' and the display brightness value d''.

[0171] S430: If the difference values ​​are all less than or equal to the threshold 2, the detection result is used to indicate that the metadata of the second image is normal.

[0172] The first computing device 310 compares the differences corresponding to the multiple original brightness values ​​with a threshold 2, and when the differences are all less than or equal to the threshold 2, determines that the detection result indicates that the metadata of the second image is normal.

[0173] Exemplarily, the difference 1 is compared with the threshold 2 (eg, 30 nits), and the difference 2 is compared with the threshold 2. If both the difference 1 and the difference 2 are less than or equal to the threshold 2, the detection result indicates that the metadata of the second image is normal.

[0174] S440: If there is at least one difference value greater than the threshold 2, the detection result is used to indicate that the metadata of the second image is abnormal.

[0175] The first computing device 310 compares the difference values ​​corresponding to the plurality of original brightness values ​​with a threshold 2, and when one of the difference values ​​is greater than the threshold 2, determines that the detection result indicates that the metadata of the second image is abnormal.

[0176] Exemplarily, if at least one difference between the difference 1 and the threshold 2, or the difference 2 and the threshold 2, is greater than the threshold 2, then it is determined that the detection result indicates that the metadata of the second image is abnormal.

[0177] In the present application, the first computing device 310 detects the continuity of the brightness mapping curve to avoid discontinuity of the brightness mapping curve corresponding to the metadata, thereby preventing the display device from displaying images with broken images, thereby ensuring the quality of the image when displaying the image.

[0178] To detect the monotonicity of the brightness mapping curve for each frame of image, a possible implementation is provided below, as shown in Figure 5, which is a second flow chart of the geometric property detection method provided in this application. The brightness mapping curve corresponding to the third image includes multiple curve segments, and the third image is any frame of image data. S220 in Figure 2 above may include the following steps S510 to S530.

[0179] S510 : The first computing device 310 determines the monotonicity of multiple curve segments corresponding to the third image.

[0180] As shown in FIG5 , the first computing device 310 may derive the three curve segments (curve 1, curve 2, and curve 3) corresponding to the third image to obtain a derivative result. If the derivative result may be a specific value or function, the first computing device 310 determines whether the specific value or function is greater than 0 or less than 0. If the derivative result is greater than 0, the curve segment is monotonically increasing; if the derivative result is less than 0, the curve segment is monotonically decreasing.

[0181] S520: If the first computing device 310 determines that the monotonicity corresponding to the multiple curve segments is not uniform, the detection result is used to indicate that the metadata of the third image is abnormal.

[0182] When the three curves shown in Figure 5 are not all monotonically decreasing (the derivative results are all less than 0) or monotonically increasing (the derivative results are all greater than 0), the first computing device 310 determines that the monotonicity of the brightness mapping curve corresponding to the third image is not uniform, and the detection result indicates that the metadata of the third image is abnormal.

[0183] S530: If the first computing device 310 determines that the monotonicity corresponding to the multiple curve segments is uniform, the detection result is used to indicate that the metadata of the third image is normal.

[0184] When the three curves shown in FIG. 5 are all monotonically decreasing or monotonically increasing, the first computing device 310 determines that the brightness mapping curve corresponding to the third image is monotonically uniform, and the detection result indicates that the metadata of the third image is normal.

[0185] In the present application, the first computing device 310 detects the monotonicity of the brightness mapping curve to avoid the problem of brightness flipping when the original brightness value is too large and the corresponding display brightness value is too small, or when the original brightness value is too small and the corresponding display brightness value is too large, thereby ensuring the quality of the picture when displaying the image.

[0186] To test the rationality of the brightness mapping curve for each frame of image, a possible implementation is provided below, as shown in Figure 6, which is a flowchart diagram of the third geometric property detection method provided in this application. The fourth image is any frame in the image data, and the third threshold can be referred to as Threshold 3. S220 in Figure 2 above may include the following steps S610 to S640.

[0187] S610: The first computing device 310 determines a target original brightness value corresponding to a target display brightness value in a brightness mapping curve corresponding to the fourth image.

[0188] Exemplarily, the target display brightness value may be a maximum display brightness value or a minimum display brightness value that can be displayed by the display device.

[0189] Taking the maximum display brightness value or the minimum display brightness value that can be displayed by the display device as the target display brightness value as an example, the first computing device 310 determines the first original brightness value (target original brightness value) corresponding to the maximum display brightness value in the brightness mapping curve corresponding to the fourth image.

[0190] S620: The first computing device 310 calculates the ratio of the number of pixels in the fourth image that are greater than or less than the target original brightness value to the total number of pixels in the fourth image.

[0191] If the target display brightness value is the maximum display brightness value, the first computing device 310 may determine a value a greater than the first original brightness value corresponding to the maximum display brightness value from the brightness mapping curve corresponding to the fourth image. The value a may include one or more values.

[0192] The first computing device 310 determines the number 1 of pixels having an original brightness value of value a from the fourth image, and then calculates the ratio of the number 1 to the total number of pixels corresponding to the fourth image, that is, the proportion.

[0193] As shown in FIG6 , the maximum display brightness value is 500 nits. The first computing device 310 determines that the first original brightness value corresponding to the maximum display brightness value in the brightness mapping curve is 5000 nits. Furthermore, the first computing device 310 determines that the brightness in the brightness mapping curve is greater than the first original brightness value, such as 5500 nits. The first computing device 310 determines that the number of pixels in the fourth image with a brightness value of 5500 nits is 300. The total number of pixels in the fourth image is 1920 * 1080 = 2073600. Therefore, the percentage of 300 / 2073600 is approximately 0.014%.

[0194] In a possible example, the first computing device 310 may directly determine, from the fourth image, the number of pixels whose original brightness values ​​are greater than the first original brightness value to obtain the number 1.

[0195] Similarly, if the target display brightness value is the minimum display brightness value, the first computing device 310 may determine a value b smaller than the second original brightness value corresponding to the minimum display brightness value from the brightness mapping curve corresponding to the fourth image. The value b may include one or more values.

[0196] The first computing device 310 determines the number 2 of pixels having an original brightness value of the value b from the fourth image, and then calculates the ratio of the number 2 to the total number of pixels corresponding to the fourth image, that is, the proportion.

[0197] As shown in FIG6 , the minimum display brightness value is 1 nit. First computing device 310 determines that the second original brightness value corresponding to the minimum display brightness value in the brightness mapping curve is 0.1 nit. Furthermore, it determines a brightness value in the brightness mapping curve that is smaller than the second original brightness value, such as 0.05 nit. First computing device 310 determines that the number of pixels in the fourth image with a brightness value of 0.05 nit is 300. The total number of pixels in the fourth image is 1920 * 1080 = 2073600. Therefore, the percentage is 300 / 2073600, which is approximately 0.014%.

[0198] In a possible example, when determining the number 2, the first computing device 310 may directly determine the number of pixels having a brightness value less than the second original brightness value from the fourth image to obtain the number 2.

[0199] In a possible embodiment, the target original brightness value may also be a maximum display brightness value preset by the user, or a minimum display brightness value preset by the user.

[0200] S630: If the first computing device 310 determines that the proportion is greater than the threshold value 3, the detection result is used to indicate that the metadata of the fourth image is abnormal.

[0201] Exemplarily, the first computing device 310 compares the calculated ratio with a threshold value 3 (eg, 0.02%). If the ratio is less than the third threshold value, the detection result indicates that the metadata of the fourth image is normal.

[0202] S640: If the first computing device 310 determines that the proportion is less than the threshold value 3, the detection result is used to indicate that the metadata of the fourth image is normal.

[0203] Exemplarily, if the above proportion is greater than a threshold value of 3, the detection result indicates that the metadata of the fourth image is abnormal.

[0204] In one possible example, when the ratio of the aforementioned quantity 1 to the total number of pixels corresponding to the fourth image, and the ratio of the aforementioned quantity 2 to the total number of pixels corresponding to the fourth image, are both less than a third threshold, the metadata of the fourth image is normal. Conversely, if at least one of the aforementioned two ratios is greater than the third threshold, the metadata of the fourth image is abnormal.

[0205] In one possible scenario, if the proportion is equal to the threshold 3, the detection result is used to indicate whether the metadata of the fourth image is normal or abnormal, which is not limited in this application.

[0206] In the present application, the first computing device 310 detects the rationality of the brightness mapping curve (brightness rationality), that is, detects whether there is an original brightness value in the brightness mapping curve that does not correspond to the display brightness value, thereby avoiding the problem of missing brightness of some pixels (i.e., not displayed) when the display device displays the video, and ensures the quality of the picture when displaying the image.

[0207] In one possible embodiment, the metadata also includes a scene change identifier, and the image whose metadata includes the scene change identifier is a scene change frame. If the detection result indicates that the one or more frames of images with abnormal metadata are scene change frames, the first computing device 310 updates the one or more frames of images with abnormal metadata indicated by the detection result to have normal metadata. The scene change frame is the next frame in the plurality of adjacent frames of images whose similarity is less than or equal to the fourth threshold.

[0208] In one possible example, when the first computing device 310 determines that one or more frames of images with abnormal metadata are scene switching frames, it only updates the detection result of the one or more frames of images with abnormal metadata to: the metadata of the one or more frames of images is normal.

[0209] In this application, since scenes may change in a video, sudden changes in brightness and other parameters during a scene change are considered normal. That is, when an image frame is a scene change frame, the metadata abnormality of the scene change frame is allowed and is considered normal. The first computing device 310 sets the detection result corresponding to the scene change frame as normal, which conforms to the scene change rule.

[0210] In one possible embodiment, in S210, the first computing device 310 obtains metadata of the image data between the two scene-cut frames. That is, when performing the quality detection, the first computing device 310 only detects metadata of the image data between the two scene-cut frames, thereby reducing the amount of data computation and improving data efficiency.

[0211] There are two possible ways to determine the scene switching frame.

[0212] In an optional implementation, the first computing device 310 may determine whether the metadata of each frame image includes a scene cut identifier. The first computing device 310 obtains the scene cut identifier included in the metadata of the fifth image, where the scene cut identifier indicates that the fifth image is a scene cut frame, and the fifth image is any frame image in the image data.

[0213] In another optional implementation, as shown in FIG7 , FIG7 is a flow chart of a method for determining a scene cut frame provided by this application. The sixth image and the seventh image are any frames of image data in the video. The fifth threshold value may also be referred to as Threshold 5, and the sixth threshold value may also be referred to as Threshold 6. The method may include the following steps S710 to S730.

[0214] S710: The first computing device 310 determines similarities between attributes of pixels in the sixth image and the seventh image.

[0215] The sixth image and the seventh image are in the same sliding window, and the seventh image is one or more frames of images adjacent to the sixth image.

[0216] The pixel attributes may include pixel brightness (nit), brightness-chrominance (YUV) and other data. In YUV, "Y" represents brightness (luminance or luma), while "U" and "V" represent chrominance (chroma).

[0217] The following provides several similarity calculation methods: Pearson correlation coefficient, Spearman correlation coefficient, and coefficient of determination.

[0218] The Pearson correlation coefficient is a statistic that measures the degree of linear correlation between two data.

[0219] Spearman correlation coefficient: It is a method to measure the correlation between data, but it does not require the data to be in a linear relationship.

[0220] Coefficient of determination: The coefficient of determination measures the degree to which one data explains another data by calculating the square of the Pearson correlation coefficient.

[0221] The similarity calculation method is described as the Pearson correlation coefficient, the Spearman correlation coefficient, and the Pearson correlation coefficient among the determination coefficients. The first computing device 310 determines the Pearson correlation coefficient of the attributes (e.g., brightness values) of the pixels in the sixth image and the image (seventh image) preceding the sixth image in the video, for example, using the following formula:

[0222] Among them, X i Indicates the brightness value of the i-th pixel in the sixth image, Y i Indicates the brightness value of the i-th pixel in the seventh image, X iThe position of the corresponding pixel in the sixth image and Y i The corresponding pixels are at the same position in the seventh image. It can represent the average brightness value of all pixels of the sixth image, It can represent the average brightness value of all pixels in the seventh image.

[0223] The above example illustrates a sliding window size of two frames. In other embodiments of the present application, the sliding window may be three or five frames, etc. The size of the sliding window can be set by the user as needed and is not limited by the present application. The multiple frames within the sliding window are adjacent multiple frames, which refer to multiple images that appear continuously when playing a video.

[0224] In another embodiment of the present application, the first computing device 310 determines similarities in brightness values ​​and YUV values ​​of pixels in the sixth image and the seventh image.

[0225] Regarding the determination by the first computing device 310 of the brightness values ​​and YUV similarities of the pixels of the sixth image and the seventh image, reference may be made to the above-described determination of the brightness values ​​of the pixels of the sixth image and the seventh image, which will not be elaborated herein.

[0226] When the brightness values ​​of the pixels of the sixth image and the seventh characteristic, and the YUV similarity of the pixels of the sixth image and the seventh characteristic are both less than or equal to the threshold 5, the similarity of the attributes of the pixels in the sixth image and the seventh image is less than or equal to the threshold 5.

[0227] S720: The first computing device 310 calculates the similarity between the metadata of the sixth image and the metadata of the seventh image.

[0228] When the similarity between the attributes of the pixel points in the sixth image and the seventh image is less than or equal to the threshold 5, the first computing device 310 calculates the similarity between the metadata of the sixth image and the metadata of the seventh image, that is, the change between the metadata of the sixth image and the metadata of the seventh image.

[0229] In one possible example, the first computing device 310 compares the similarity between the attributes of the pixels in the sixth image and the attributes of the pixels in the seventh image with a threshold value of 5 (e.g., 0.8). When the similarity is greater than the threshold value 5, it indicates that the sixth image in the sliding window is a non-scene cut frame. When the similarity is less than or equal to the threshold value 5, further evaluation of the sixth image is required, namely, calculating the similarity between the metadata of the sixth image and the metadata of the seventh image.

[0230] Regarding the calculation by the first computing device 310 of the similarity between the metadata of the sixth image and the metadata of one or more frames of images adjacent to the sixth image, reference may be made to the above-mentioned S220 , which will not be elaborated herein.

[0231] Exemplarily, the first computing device 310 calculates the similarity between the metadata of the sixth image and the metadata of each of the one or more frames of images indicated by the seventh image.

[0232] S730: The first computing device 310 determines that the sixth image is a scene switching frame.

[0233] The similarity between the metadata of the sixth image and the metadata of the seventh image is less than or equal to a threshold value of 6. In other words, the similarity between the metadata of the sixth image and the metadata of one or more frames of images adjacent to the sixth image is less than or equal to the threshold value of 6.

[0234] Exemplarily, if the similarity between the metadata of the sixth image and the metadata of one or more frames adjacent to the sixth image is less than or equal to a threshold value of 6 (eg, 0.8), the first computing device 310 determines that the sixth image is a scene switch frame.

[0235] If a similarity between the metadata of the sixth image and the metadata of one or more frames of images adjacent to the sixth image is greater than a threshold value 6, the first computing device 310 determines that the sixth image is a non-scene cut frame.

[0236] In the present application, the first computing device 310 determines the scene switching frame from multiple frames of the video based on the similarity of the attributes of the pixel points and the similarity of the metadata. Then, when determining abnormal metadata, the scene switching frame can be referred to. That is, when the monotonicity of the brightness mapping curve corresponding to the metadata of the scene switching frame is not uniform, the continuity is inconsistent, etc., the metadata of the scene switching frame is also normal, thereby improving the accuracy of determining abnormal metadata.

[0237] In a possible embodiment, before performing the above-mentioned processing shown in FIG. 7 , the first computing device 310 may downsample each frame image in the video to reduce the resolution and improve the processing efficiency.

[0238] Furthermore, to avoid metadata errors during bitstream transmission and video decoding, this application provides a metadata detection method that can be applied to the computer system shown in Figure 1. Figure 8 is a second flow diagram of the metadata detection method provided by this application. This metadata detection method can be executed by a second computing device 320, which can be the decoding end 200 in Figure 1. As shown in Figure 8, this metadata detection method can include the following steps S810 and S820.

[0239] S810: The second computing device 320 obtains metadata of the image data.

[0240] The second computing device 320 receives the code stream sent by the first computing device 310, or retrieves the stored code stream from the storage device 400. The code stream includes encoded image data and metadata corresponding to the image data. The second computing device 320 decodes the code stream to obtain the metadata of the image data. The image data includes one or more frames of images.

[0241] In a possible example, the second computing device 320 uses the video decoder 220 to decode the code stream to obtain metadata of multiple frames of images in the video.

[0242] S820: The second computing device 320 processes the metadata of the image data according to the detection strategy to obtain a detection result.

[0243] The detection strategy is configured to indicate: determining similarity between metadata of two adjacent frames of the multiple image frames, and / or detecting geometric characteristics of a brightness mapping curve of the image data. The brightness mapping curve of the first image is obtained based on the metadata of the first image, where the first image is any frame of the image data.

[0244] For the description of S820, reference can be made to the content of obtaining the detection result shown in S220 above, which will not be repeated here. For example, the content executed by the first computing device 310 shown in Figures 2 to 7 above can also be executed by the second computing device 320.

[0245] In the present application, the second computing device 320 (decoding end) further detects the metadata of the received image data to avoid metadata errors caused during the data transmission process or video decoding process, thereby ensuring the picture quality when displaying the image.

[0246] In a possible embodiment, the second computing device 320 issues an alarm based on the detection result.

[0247] In which, when the detection result indicates that the similarity of metadata of two adjacent frames of images in multiple frames is less than or equal to a first threshold, and / or the geometric characteristic detection of the brightness mapping curve of at least one frame of image in the image data is abnormal, the second computing device 320 issues an alarm based on the detection result.

[0248] In one possible implementation, the second computing device 320 may issue an alert by displaying an alert message on a front-end of the second computing device 320, or by sending the alert message to the user via a text message or email. The alert message indicates that: the similarity between metadata of two adjacent frames of images in the multiple frames is less than or equal to a first threshold, and / or that a geometric characteristic detection of a brightness mapping curve of at least one frame of image data is abnormal.

[0249] The front end here may refer to a display connected to the second computing device 320, or a display screen possessed by the second computing device 320, etc., which is not limited in this application.

[0250] In one possible example, the second computing device 200 will also save the above-mentioned alarm information.

[0251] In another possible implementation, the second computing device 320 alerts a processing unit based on the detection result. The processing unit is configured to map the decoded image to a front-end processor. The processing unit is disposed within the second computing device 320.

[0252] The alarm instructs the decoding end to perform mapping processing on one or more frames of images according to preset metadata, and the one or more frames of images include images with abnormal metadata.

[0253] The second computing device 320 may execute the following three examples of content according to the alarm indication.

[0254] In Example 1, the second computing device 320 deletes metadata of a subsequent image frame whose metadata similarity is less than or equal to a first threshold value based on an alarm indication. Furthermore, when mapping the subsequent image frame to the front end of the second computing device 320, the second computing device 320 performs mapping processing based on the preset metadata.

[0255] Example 2: The second computing device 320 deletes the metadata of at least one frame of image with abnormal geometric feature detection in the image data according to the alarm indication, and performs mapping processing according to the preset metadata when mapping the at least one frame of image with abnormal geometric feature detection to the front end of the second computing device 320.

[0256] In Example 3, when the second computing device 320 maps the video to the front-end according to the alarm indication, it processes the video according to the preset metadata. In other words, the second computing device 320 deletes the metadata decoded from the bitstream and maps the image decoded from the bitstream to the front-end for display according to the preset metadata.

[0257] The metadata detection method provided by the present application has been described in detail above with reference to Figures 1 to 7 . Now, the first metadata detection device provided by the present application will be described with reference to Figure 9 , which is a schematic diagram of the structure of a metadata detection device provided by the present application. First metadata detection device 900 can be used to implement the functions of first computing device 310 in the above-described method embodiment, thereby also achieving the beneficial effects of the above-described method embodiment.

[0258] As shown in FIG9 , the first metadata detection apparatus 900 includes a first acquisition module 910 and a first processing module 920. The first metadata detection apparatus 900 is configured to implement the functions of the first computing device 310 in the method embodiments corresponding to FIG1 through FIG7 . In one possible example, the specific process for implementing the metadata detection method described above by the first metadata detection apparatus 900 includes the following steps:

[0259] The first acquisition module 910 is configured to acquire metadata of image data, which includes one or more frames of image.

[0260] A first processing module 920 is configured to process the metadata of the image data according to a detection strategy to obtain a detection result. The detection strategy is configured to indicate: determining the similarity of metadata between two adjacent frames of the multi-frame image data; and / or detecting geometric characteristics of a brightness mapping curve of the image data; the brightness mapping curve of a first image is obtained based on the metadata of the first image, where the first image is any frame of the image data.

[0261] To further implement the functions of the method embodiments shown in Figures 1 to 7 above, the present application also provides a metadata detection device, as shown in Figure 10 . Figure 10 is a second structural schematic diagram of a metadata detection device provided by the present application. The first metadata detection device 900 further includes a first update module 930 and a second update module 940.

[0262] Among them, the first updating module 930 is used to update the one or more frames of images with abnormal metadata indicated by the detection result to normal metadata if the one or more frames of images with abnormal metadata indicated by the detection result are scene switching frames; the scene switching frame is the next frame image in the adjacent multiple frames whose metadata similarity is less than or equal to the fourth threshold.

[0263] The second updating module 940 is configured to update the metadata of the one or more frames of images with abnormal metadata if the detection result indicates that the metadata of the one or more frames of images are abnormal.

[0264] For the description of determining the scene switching frame in the video, please refer to the content shown in FIG. 7 , which will not be described in detail here.

[0265] As an example of a hardware functional unit, the first acquisition module 910 may include at least one computing device, such as a server. Alternatively, the first acquisition module 910 may be implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0266] It should be noted that, in other embodiments, the first acquisition module 910 can be used to execute any step in the metadata detection method, and the first processing module 920 can be used to execute any step in the metadata detection method. The steps that the first acquisition module 910 and the first processing module 920 are responsible for implementing can be specified as needed. The full functions of the first metadata detection device are achieved by having the first acquisition module 910 and the first processing module 920 respectively implement different steps in the metadata detection method.

[0267] It is worth noting that the first computing device 310 of the aforementioned embodiment may correspond to the first metadata detection device 900, and may correspond to the corresponding subject executing the method corresponding to Figures 2 to 7 according to the embodiment of the present application, and the operations and / or functions of the various modules in the first metadata detection device 900 are respectively for implementing the corresponding processes of the various methods of the corresponding embodiments in Figures 2 to 7. For the sake of brevity, they are not further described here.

[0268] The metadata detection method provided by the present application has been described in detail above with reference to Figures 1 and 8 . Now, a second metadata detection device provided by the present application will be described with reference to Figure 11 , which is a third schematic structural diagram of a metadata detection device provided by the present application. Second metadata detection device 1100 can be used to implement the functions of second computing device 320 in the aforementioned method embodiment, thereby also achieving the beneficial effects of the aforementioned method embodiment.

[0269] As shown in FIG11 , the second metadata detection apparatus 1100 includes a second acquisition module 1110 and a second processing module 1120. The second metadata detection apparatus 1100 is configured to implement the functionality of the second computing device 320 in the method embodiments corresponding to FIG1 and FIG8 . In one possible example, the specific process for the second metadata detection apparatus 1100 to implement the above-described metadata detection method includes the following steps:

[0270] The second acquisition module 1110 is configured to acquire metadata of the image data.

[0271] The second processing module 1120 is configured to process the metadata of the image data according to a detection strategy to obtain a detection result. The detection strategy is configured to indicate: determining the similarity of metadata between two adjacent frames of the multiple image frames; and / or detecting geometric characteristics of a brightness mapping curve of the image data, where the brightness mapping curve of a first image is obtained based on the metadata of the first image, where the first image is any frame of the image data.

[0272] To further implement the functions of the method embodiments shown in Figures 1 and 8 above, the present application also provides a metadata detection device, as shown in Figure 12. Figure 12 is a fourth structural diagram of a metadata detection device provided by the present application. The second metadata detection device 1100 further includes an alarm module 1130, a third update module 1140, and a fourth update module 1150.

[0273] Among them, the alarm module 1130 is used to issue an alarm based on the detection result when the detection result indicates that the similarity of metadata of two adjacent frames of images in multiple frames is less than or equal to a first threshold, and / or the geometric characteristic detection of the brightness mapping curve of at least one frame of image in the image data is abnormal.

[0274] The third updating module 1140 is configured to update the one or more frames of images with abnormal metadata indicated by the detection result to frames with normal metadata if the one or more frames of images with abnormal metadata indicated by the detection result are scene switching frames; the scene switching frame is a subsequent frame of the adjacent multiple frames of images whose metadata similarity is less than or equal to a fourth threshold.

[0275] The fourth updating module 1150 is configured to perform mapping processing on the one or more frames of images according to preset metadata if the detection result indicates that the metadata of one or more frames of images are abnormal, the one or more frames of images including the image with abnormal metadata.

[0276] It is worth noting that the second computing device 320 of the aforementioned embodiment may correspond to the second metadata detection device 1100, and may correspond to the corresponding subject corresponding to Figure 8 executing the method according to the embodiment of the present application, and the operations and / or functions of each module in the second metadata detection device 1100 are respectively for implementing the corresponding processes of each method of the corresponding embodiment in Figure 8. For the sake of brevity, they are not repeated here.

[0277] In addition, the metadata detection device shown in Figures 9 to 12 can also be implemented by a communication device, where the communication device may refer to the computing device (first computing device 310 or second computing device 320) in the aforementioned embodiment, or, when the communication device is a chip or chip system applied to a computing device, the metadata detection device can also be implemented by the chip or chip system.

[0278] An embodiment of the present application also provides a chip system, which includes a control circuit and an interface circuit. The interface circuit is used to obtain metadata of image data, and the control circuit is used to implement the functions of the computing device in the above method based on the metadata of the image data.

[0279] In a possible design, the chip system further includes a memory for storing program instructions and / or data. The chip system can be composed of a chip or include a chip and other discrete devices.

[0280] The present application also provides a computing device. As shown in Figure 13, Figure 13 is a schematic diagram of the structure of a computing device provided by the present application. The computing device 1300 includes: a bus 1302, a processor 1304, a memory 1306 and a communication interface 1308. The processor 1304, the memory 1306 and the communication interface 1308 communicate with each other through the bus 1302. The computing device 1300 can be a server, a terminal device or a decoder. The computing device 1300 can be the first computing device 310 or the second computing device 320 mentioned above. It is worth noting that the present application does not limit the number of processors and memories in the computing device 1300. The above-mentioned decoder may include a decoder or an encoder. When the computing device 1300 is an encoder, the computing device 1300 can be the first computing device 310 mentioned above; when the computing device 1300 is a decoder, the computing device 1300 can be the second computing device 320 mentioned above.

[0281] Bus 1302 may be, but is not limited to, a PCIe bus, a universal serial bus (USB), an inter-integrated circuit bus (I2C), an EISA bus, a USB, a CXL, or a CCIX bus. Bus 1302 may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, FIG13 shows only one line, but this does not imply that there is only one bus or only one type of bus. Bus 1302 may include a path for transmitting information between various components of computing device 1300 (e.g., memory 1306, processor 1304, and communication interface 1308).

[0282] The processor 1304 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0283] The memory 1306 may include volatile memory, such as random access memory (RAM). The memory 1306 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0284] The memory 1306 stores executable program code, and the processor 1304 executes the executable program code to implement the functions of the first acquisition module and the first processing module, thereby implementing the metadata detection method. In other words, the memory 1306 stores instructions for executing the metadata detection method.

[0285] Alternatively, the memory 1306 stores executable code, and the processor 1304 executes the executable code to respectively implement the functions of the second acquisition module and the second processing module, thereby implementing the metadata detection method. In other words, the memory 1306 stores instructions for executing the metadata detection method.

[0286] The communication interface 1308 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 1300 and other devices or a communication network.

[0287] The embodiment of the present application further provides a computing device cluster, which includes at least one computing device 1300. The memory 1306 of one or more computing devices 1300 in the computing device cluster may store the same instructions for executing the metadata detection method.

[0288] The computing device 1300 may be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device 1300 may also be a terminal device such as a desktop computer, a laptop computer, or a smart phone.

[0289] In some possible implementations, one or more computing devices in a computing device cluster may be connected via a network, which may be a wide area network or a local area network.

[0290] Embodiments of the present application also provide a computer program product containing instructions. This computer program product can be software or a program product containing instructions that can be executed on a computing device or stored on any available medium. When executed on at least one computing device, this computer program product causes the at least one computing device to perform the metadata detection method.

[0291] Embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium can be any available medium capable of being stored by a computing device, or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the metadata detection method.

[0292] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the process or function described in the embodiments of the present application is performed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device or other programmable device. The computer program or instruction can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instruction can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, a hard disk, or a tape; it can also be an optical medium, such as a digital video disc (DVD); it can also be a semiconductor medium, such as a solid state drive (SSD).

[0293] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A metadata detection method, characterized in that: The method is applied to a computing device, and the method comprises: Acquire metadata of image data; the image data includes one or more frames of image; Process the metadata of the image data according to the detection strategy to obtain a detection result; Among them, the detection strategy is used to indicate: determining the similarity of metadata of two adjacent frames of images in the multiple frames of images, and / or, detecting the geometric characteristics of the brightness mapping curve of the image data; the brightness mapping curve of the first image is obtained based on the metadata of the first image, and the first image is any frame image in the image data.

2. The method according to claim 1, characterized in that The metadata of the image data obtained includes: Receiving a trigger operation of a control component on a user interface; In response to the user's triggering operation on the control component, metadata of the image data is acquired.

3. The method according to claim 1 or 2, characterized in that: The step of processing the metadata of the image data according to the detection strategy to obtain the detection result includes: Determining a brightness mapping curve of the two adjacent frames of images according to metadata of the two adjacent frames of images; If the similarity of the brightness mapping curves of the two adjacent frames of images is less than a first threshold, the detection result is used to indicate that metadata of one of the two adjacent frames of images is abnormal; If the similarity of the brightness mapping curves of the two adjacent frames of images is greater than the first threshold, the detection result is used to indicate that the metadata of one of the two adjacent frames of images is normal; If the similarity of the brightness mapping curves of the two adjacent image frames is equal to the first threshold, the detection result is used to indicate whether the metadata of one of the two adjacent image frames is normal or abnormal.

4. The method according to any one of claims 1 to 3, characterized in that The brightness mapping curve corresponding to the second image includes multiple curves, the second image is any frame image in the image data, and the metadata of the image data is processed according to the detection strategy to obtain the detection result, including: Determine a plurality of display brightness values ​​corresponding to each of a plurality of original brightness values ​​of a plurality of curve segments corresponding to the second image; Calculating the difference between the plurality of display brightness values; If the difference values ​​are all less than or equal to the second threshold, the detection result is used to indicate that the metadata of the second image is normal; If there is at least one difference value greater than the second threshold, the detection result is used to indicate that the metadata of the second image is abnormal.

5. The method according to any one of claims 1 to 4, characterized in that The brightness mapping curve corresponding to the third image includes multiple curves, the third image is any frame image in the image data, and the metadata of the image data is processed according to the detection strategy to obtain the detection result, including: Determining the monotonicity of the multiple curves corresponding to the third image; If the monotony corresponding to the multiple curve segments is not uniform, the detection result is used to indicate that: the metadata of the third image is abnormal; If the monotonicity corresponding to the multiple curve segments is uniform, the detection result is used to indicate that the metadata of the third image is normal.

6. The method according to any one of claims 1 to 5, characterized in that The step of processing the metadata of the image data according to the detection strategy to obtain the detection result includes: Determine a target original brightness value corresponding to a target display brightness value in a brightness mapping curve corresponding to a fourth image, wherein the fourth image is any frame image in the image data; Calculate the ratio of the number of pixels in the fourth image that are greater than or less than the target original brightness value to the total number of pixels in the fourth image; If the proportion is greater than a third threshold, the detection result is used to indicate that: the metadata of the fourth image is abnormal; If the proportion is less than the third threshold, the detection result is used to indicate that the metadata of the fourth image is normal; If the proportion is equal to the third threshold, the detection result is used to indicate whether the metadata of the fourth image is normal or abnormal.

7. The method according to any one of claims 1 to 6, characterized in that The multiple frames of images are images between two scene switching frames, and the scene switching frame is a subsequent frame of image in the multiple adjacent frames of images whose metadata similarity is less than or equal to a fourth threshold.

8. The method according to any one of claims 1 to 6, characterized in that The method further comprises: If the one or more frames of images with abnormal metadata indicated by the detection result are scene switching frames, the one or more frames of images with abnormal metadata indicated by the detection result are updated to have normal metadata; the scene switching frame is the next frame of image in the adjacent multiple frames of images whose metadata similarity is less than or equal to a fourth threshold.

9. The method according to claim 7 or 8, characterized in that: The scene switching frame can be determined by: A scene switching identifier included in metadata of the fifth image is obtained, where the scene switching identifier is used to indicate that the fifth image is a scene switching frame, and the fifth image is any frame image in the image data.

10. The method according to claim 7 or 8, characterized in that: The scene switching frame can be determined by: Determine the similarity of attributes of pixel points in a sixth image and a seventh image; the sixth image and the seventh image are in the same sliding window, the seventh image is one or more frames of images adjacent to the sixth image, the sixth image and the seventh image are any frame of images in the image data, and the attributes include: one or more of brightness value or brightness-chrominance YUV; If the similarity between the attributes of the pixels in the sixth image and the seventh image is less than or equal to a fifth threshold, calculating the similarity between the metadata of the sixth image and the metadata of the seventh image; The sixth image is determined to be the scene switching frame; and a similarity between the metadata of the sixth image and the metadata of the seventh image is less than or equal to a sixth threshold.

11. The method according to any one of claims 1 to 10, characterized in that The method further comprises: If the detection result indicates that the metadata of one or more frames of images are abnormal, the metadata of the one or more frames of images with the abnormal metadata are updated.

12. The method according to any one of claims 1 to 10, characterized in that The method further comprises: If the detection result indicates that the similarity of metadata of two adjacent frames of images in the multiple frames is less than or equal to a first threshold, and / or the geometric characteristic detection of the brightness mapping curve of at least one frame of image in the image data is abnormal, an alarm is issued based on the detection result.

13. The method according to claim 12, characterized in that The method further comprises: If the detection result indicates that metadata of one or more frames of images are abnormal, mapping processing is performed on the one or more frames of images according to preset metadata, and the one or more frames of images include the image with abnormal metadata.

14. A metadata detection device, characterized in that: The device is applied to a computing device, and comprises: A first acquisition module, used to acquire metadata of image data; the image data includes one or more frames of images; A first processing module, used for processing the metadata of the image data according to the detection strategy to obtain a detection result; Among them, the detection strategy is used to indicate: determining the similarity of metadata of two adjacent frames of images in the image data, and / or, detecting the geometric characteristics of a brightness mapping curve of the image data, the brightness mapping curve of the first image is obtained based on the metadata of the first image, and the first image is any frame image in the multiple frames of images.

15. A chip, characterized in that: include: Processor and power supply circuit; The power supply circuit is used to supply power to the processor; The processor is configured to execute the method according to any one of claims 1 to 13.

16. A decoder, characterized in that: The method comprises a memory and a processor, wherein the memory is used to store computer instructions; when the processor executes the computer instructions, the method according to any one of claims 1 to 13 is implemented.

17. A computer-readable storage medium, characterized in that: The storage medium stores a computer program or instruction, and when the computer program or instruction is executed by a processing device, the method according to any one of claims 1 to 13 is implemented.

18. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed on a processing device, the method according to any one of claims 1 to 13 is implemented.

Images