Picture quality enhancement method and apparatus, and storage medium and electronic device

Abstract

The present application relates to the technical field of picture quality enhancement. Disclosed are a picture quality enhancement method and apparatus, and a storage medium and an electronic device. The method comprises: performing detection on the basis of image feature information of an image frame; if a detection result is that a scene is switched, using a preset picture quality enhancement model to perform reasoning on an image frame at the position where the scene is switched, so as to obtain a dynamic enhancement parameter; and if the detection result is that the scene is not switched, acquiring a pre-stored enhancement parameter. The present application reduces the occupation of computing resources caused by picture quality enhancement processing.

Description

Image quality enhancement method, device, storage medium and electronic device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on January 26, 2024, with application number 202410110997.X and application name “Image quality enhancement method, device, storage medium and electronic device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of image quality enhancement technology, and specifically to an image quality enhancement method, device, storage medium and electronic device. Background Art

[0003] The continuous improvement in computing power of GPUs / NPUs in devices like TVs and monitors has bolstered the application of AI technology in these devices. However, running complex AI models, multiple AI models, or high refresh rates still pose significant computing resource challenges. Currently, AI models are often applied to devices to enhance image quality. Technical issues

[0004] Applying AI models to enhance image quality usually consumes a lot of computing resources in the device, making the image quality enhancement process time-consuming, making the device unable to meet high refresh rate display requirements, and affecting the user experience. Technical Solutions

[0005] The embodiment of the present application provides a picture quality enhancement solution, which can effectively reduce the occupation of computing resources for picture quality enhancement processing while ensuring the picture quality enhancement effect, improve the efficiency of picture quality enhancement, enable the device to meet high refresh screen display, and improve user experience.

[0006] The embodiments of this application provide the following technical solutions:

[0007] According to one embodiment of the present application, a method for image quality enhancement includes: performing scene switching detection based on image feature information of image frames in a sequence of image frames to be processed to obtain a detection result; if the detection result is a scene switch, using a preset image quality enhancement model to perform calculation and reasoning on the image frames at the scene switch to obtain dynamic enhancement parameters; if the detection result is that the scene has not switched, obtaining pre-stored enhancement parameters from a predetermined position; performing image quality enhancement on the image frames at the scene switch based on the dynamic enhancement parameters, or performing image quality enhancement on the image frames at the scene where the scene has not switched based on the pre-stored enhancement parameters.

[0008] In some embodiments of the present application, the image feature information includes multi-dimensional sub-image feature information; the scene switching detection is performed based on the image feature information of the image frames in the image frame sequence to be processed to obtain the detection results, including: performing scene switching detection based on the multi-dimensional sub-image feature information corresponding to each of the image frames to obtain the multi-dimensional sub-detection results corresponding to each of the image frames; and performing a comprehensive judgment based on the sub-detection results of multiple dimensions corresponding to each of the image frames to obtain the detection results corresponding to each of the image frames.

[0009] In some embodiments of the present application, the multidimensional sub-image feature information includes at least two of histogram feature information, peak signal-to-noise ratio information, and depth image feature information; the scene switching detection is performed according to the multidimensional sub-image feature information corresponding to each of the image frames to obtain a multidimensional sub-detection result corresponding to each of the image frames, including at least two of the following methods: performing histogram detection according to the histogram feature information corresponding to each of the image frames to obtain a first sub-detection result corresponding to each of the image frames; performing feature similarity detection according to the peak signal-to-noise ratio information corresponding to each of the image frames to obtain a second sub-detection result corresponding to each of the image frames; performing depth image feature detection according to the depth image feature information corresponding to each of the image frames to obtain a third sub-detection result corresponding to each of the image frames.

[0010] In some embodiments of the present application, after the preset image quality enhancement model is used to perform calculation and reasoning on the image frame at the scene switching point to obtain dynamic enhancement parameters, the method further includes: replacing the pre-stored enhancement parameters at the predetermined position based on the dynamic enhancement parameters to obtain updated pre-stored enhancement parameters.

[0011] In some embodiments of the present application, the use of a preset image quality enhancement model to perform computational reasoning on the image frames at the scene switching point to obtain dynamic enhancement parameters includes: determining target computing resources; using a preset image quality enhancement model to perform computational reasoning on the image frames at the scene switching point based on the target computing resources to obtain computational reasoning results; and obtaining the dynamic enhancement parameters based on the computational reasoning results.

[0012] In some embodiments of the present application, determining the target computing resource includes: detecting whether a graphics processor exists; and if so, determining the graphics processor as the target computing resource.

[0013] In some embodiments of the present application, determining the target computing resource includes: calculating a scene switching frequency; if the scene switching frequency is less than a predetermined threshold, determining a network processor as the target computing resource; if the scene switching frequency is greater than the predetermined threshold, determining a graphics processor as the target computing resource.

[0014] In some embodiments of the present application, before performing scene switching detection based on image feature information of image frames in the image frame sequence to be processed and obtaining detection results, the method further includes: performing multi-dimensional feature extraction on the image frames in the image frame sequence to obtain multi-dimensional sub-image feature information corresponding to the image frames in the image frame sequence; and obtaining image feature information corresponding to each image frame based on the multi-dimensional sub-image feature information corresponding to each image frame.

[0015] In some embodiments of the present application, the multi-dimensional feature extraction is performed on the image frames in the image frame sequence to obtain multi-dimensional sub-image feature information corresponding to the image frames in the image frame sequence, including at least two of the following methods: performing histogram feature extraction on each of the image frames to obtain histogram feature information corresponding to each of the image frames; performing peak signal-to-noise ratio extraction on each of the image frames to obtain peak signal-to-noise ratio information corresponding to each of the image frames; performing depth image feature extraction on each of the image frames to obtain depth image feature information corresponding to each of the image frames.

[0016] According to one embodiment of the present application, a picture quality enhancement device includes: a detection module, which is used to perform scene switching detection based on image feature information of image frames in a sequence of image frames to be processed to obtain a detection result; an inference module, which is used to use a preset picture quality enhancement model to perform calculation and inference on the image frames at the scene switching location to obtain dynamic enhancement parameters if the detection result is a scene switching; an acquisition module, which is used to obtain pre-stored enhancement parameters from a predetermined location if the detection result is that the scene has not switched; and an enhancement module, which is used to perform picture quality enhancement on the image frames at the scene switching location based on the dynamic enhancement parameters, or to perform picture quality enhancement on the image frames at the scene not switching location based on the pre-stored enhancement parameters.

[0017] In some embodiments of the present application, the image feature information includes multi-dimensional sub-image feature information; the detection module is used to: perform scene switching detection according to the multi-dimensional sub-image feature information corresponding to each of the image frames to obtain multi-dimensional sub-detection results corresponding to each of the image frames; perform comprehensive judgment based on the sub-detection results of multiple dimensions corresponding to each of the image frames to obtain detection results corresponding to each of the image frames.

[0018] In some embodiments of the present application, the multi-dimensional sub-image feature information includes at least two of histogram feature information, peak signal-to-noise ratio information, and depth image feature information; the detection module is used to implement at least two of the following methods: performing histogram detection based on the histogram feature information corresponding to each of the image frames to obtain a first sub-detection result corresponding to each of the image frames; performing feature similarity detection based on the peak signal-to-noise ratio information corresponding to each of the image frames to obtain a second sub-detection result corresponding to each of the image frames; performing depth image feature detection based on the depth image feature information corresponding to each of the image frames to obtain a third sub-detection result corresponding to each of the image frames.

[0019] In some embodiments of the present application, after the preset image quality enhancement model is used to perform calculation and reasoning on the image frame at the scene switching point to obtain dynamic enhancement parameters, the device also includes an update module for: replacing the pre-stored enhancement parameters at the predetermined position based on the dynamic enhancement parameters to obtain updated pre-stored enhancement parameters.

[0020] In some embodiments of the present application, the reasoning module is used to: determine the target computing resources; use a preset image quality enhancement model to perform computational reasoning on the image frames at the scene switching point based on the target computing resources to obtain computational reasoning results; and obtain the dynamic enhancement parameters based on the computational reasoning results.

[0021] In some embodiments of the present application, the inference module is configured to: detect whether a graphics processor exists; and if so, determine the graphics processor as the target computing resource.

[0022] In some embodiments of the present application, the inference module is used to: calculate the scene switching frequency; if the scene switching frequency is less than a predetermined threshold, determine the network processor as the target computing resource; if the scene switching frequency is greater than the predetermined threshold, determine the graphics processor as the target computing resource.

[0023] In some embodiments of the present application, before performing scene switching detection based on image feature information of image frames in the image frame sequence to be processed and obtaining a detection result, the device also includes an extraction module for: performing multi-dimensional feature extraction on the image frames in the image frame sequence to obtain multi-dimensional sub-image feature information corresponding to the image frames in the image frame sequence; and obtaining image feature information corresponding to each image frame based on the multi-dimensional sub-image feature information corresponding to each image frame.

[0024] In some embodiments of the present application, the extraction module is used to implement at least two of the following methods: performing histogram feature extraction on each of the image frames to obtain histogram feature information corresponding to each of the image frames; performing peak signal-to-noise ratio extraction on each of the image frames to obtain peak signal-to-noise ratio information corresponding to each of the image frames; performing depth image feature extraction on each of the image frames to obtain depth image feature information corresponding to each of the image frames.

[0025] According to another embodiment of the present application, a storage medium stores a computer program thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the method described in the embodiment of the present application.

[0026] According to another embodiment of the present application, an electronic device may include: a memory storing a computer program; and a processor reading the computer program stored in the memory to execute the method described in the embodiment of the present application.

[0027] According to another embodiment of the present application, a computer program product or computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in various optional implementations described in the embodiments of the present application. Beneficial effects

[0028] In an embodiment of the present application, scene switching detection is performed based on image feature information of image frames in a sequence of image frames to be processed to obtain a detection result; if the detection result is a scene switch, a preset image quality enhancement model is used to perform calculation and reasoning on the image frames at the scene switch to obtain dynamic enhancement parameters; if the detection result is that the scene has not switched, pre-stored enhancement parameters are obtained from a predetermined position; the image quality of the image frames at the scene switch is enhanced based on the dynamic enhancement parameters, or the image quality of the image frames at the scene where the scene has not switched is enhanced based on the pre-stored enhancement parameters.

[0029] In this way, a scene switch detection is performed on the image frames in the sequence of image frames to be processed to determine whether a scene switch occurs. If a scene switch occurs, a preset image quality enhancement model is used to perform calculation and reasoning on the image frames at the scene switch location to obtain dynamic enhancement parameters, and image quality enhancement is performed on the image frames at the scene switch location based on the dynamic enhancement parameters. Image frames at locations where the scene has not switched are enhanced by obtaining pre-stored enhancement parameters. Thus, the model is only used for calculation and reasoning at the scene switch location to reduce resource usage. This can effectively reduce the occupation of computing resources for image quality enhancement processing while ensuring the image quality enhancement effect, thereby improving image quality enhancement efficiency, enabling the device to meet high refresh rate screen display requirements, and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0031] FIG1 shows a flowchart of a method for enhancing image quality according to an embodiment of the present application.

[0032] FIG2 shows a flowchart of image feature extraction according to an embodiment of the present application.

[0033] FIG3 shows a flowchart of enhanced parameter analysis according to an embodiment of the present application.

[0034] FIG4 shows a block diagram of a device for enhancing image quality according to an embodiment of the present application.

[0035] FIG5 shows a block diagram of an electronic device according to an embodiment of the present application.

[0036] Implementation Methods of the Application

[0037] The present disclosure will be further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the examples provided herein are merely for explaining the present disclosure and are not intended to limit the present disclosure. In addition, the examples provided below are partial examples for implementing the present disclosure, rather than providing all examples for implementing the present disclosure. In the absence of conflict, the technical solutions described in the examples of the present disclosure may be implemented in any combination.

[0038] It should be noted that, in the embodiments of the present disclosure, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a method or apparatus comprising a series of elements includes not only the elements explicitly stated, but also other elements not explicitly listed, or also includes elements inherent to the implementation of the method or apparatus. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other related elements (such as steps in the method or units in the apparatus, for example, a unit may be part of a circuit, part of a processor, part of a program or software, etc.) in the method or apparatus comprising the element.

[0039] For example, the image quality enhancement method provided by the embodiment of the present disclosure includes a series of steps, but the image quality enhancement method provided by the embodiment of the present disclosure is not limited to the recorded steps. Similarly, the image quality enhancement device provided by the embodiment of the present disclosure includes a series of units, but the device provided by the embodiment of the present disclosure is not limited to including the units explicitly recorded, and may also include units that need to be set up to obtain relevant information or perform processing based on the information.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present disclosure pertains. The terms used herein are for the purpose of describing specific embodiments only and are not intended to limit the present disclosure.

[0041] Figure 1 schematically illustrates a flow chart of a method for enhancing image quality according to an embodiment of the present application. The method can be executed by any device or server with communication capabilities, such as a television, computer, mobile phone, smartwatch, or home appliance, and a server such as a cloud server or a physical server.

[0042] As shown in FIG. 1 , the image quality enhancement method may include steps S110 to S140 .

[0043] Step S110, performing scene switching detection based on the image feature information of the image frames in the image frame sequence to be processed to obtain a detection result; Step S120, if the detection result is a scene switch, using a preset image quality enhancement model to perform calculation and reasoning on the image frames at the scene switch to obtain dynamic enhancement parameters; Step S130, if the detection result is that the scene has not switched, obtaining pre-stored enhancement parameters from a predetermined position; Step S140, performing image quality enhancement on the image frames at the scene switch based on the dynamic enhancement parameters, or performing image quality enhancement on the image frames at the scene where the scene has not switched based on the pre-stored enhancement parameters.

[0044] The image frame sequence to be processed may include multiple image frames. The image frame sequence to be processed may be a sequence of image frames in a video or an image frame sequence formed by other means. For example, in one scenario, the image frame sequence to be processed may be a sequence of image frames in a video played on a television, and the image quality of each image frame in the video needs to be enhanced when the television plays the video.

[0045] Image feature information can be extracted for the image frames in the image frame sequence to be processed, and scene switching detection can be performed based on the image feature information of the image frames in the image frame sequence to be processed to obtain a detection result. The detection result can be a scene switch (that is, the scene in a certain image frame has changed compared to the scene in the previous image frame) or a scene no switch (that is, the scene in a certain image frame has not changed compared to the scene in the previous image frame).

[0046] If the detection result is a scene switch, the preset image quality enhancement model is used to perform calculation and reasoning on the image frame at the scene switch to obtain dynamic enhancement parameters. For example, if a scene switch is detected at a certain image frame, the image frame is input into the preset image quality enhancement model for calculation and reasoning to obtain the reasoning result, and the dynamic enhancement parameters can be obtained based on the reasoning result.

[0047] A preset image quality enhancement model is used to perform computational inference on image frames at scene transitions. This computational inference can be performed using the NPU or GPU, which consumes NPU or GPU computing resources. Dynamic enhancement parameters are image quality enhancement parameters (PQ (Picture Quality) parameters) used to enhance the image quality of image frames at scene transitions. Image quality enhancement is performed on image frames at scene transitions based on the dynamic enhancement parameters, resulting in enhanced image frames.

[0048] Conversely, if the detection result indicates that the scene has not changed, pre-stored enhancement parameters are retrieved from a predetermined location, such as a register, to enhance the image quality of the image frame at the scene where the scene has not changed. The image quality of the image frame at the scene where the scene has not changed is enhanced based on the pre-stored enhancement parameters, thereby obtaining an enhanced image frame.

[0049] For example, the first image frame in the sequence of image frames to be processed is regarded as a scene switch, and the first image frame is calculated and inferred using a preset image quality enhancement model to obtain dynamic enhancement parameters for image quality enhancement. If the scene has not switched for the second to fifth image frames, the pre-stored enhancement parameters are obtained for image quality enhancement; if the scene has switched for the sixth image frame, the sixth image frame is calculated and inferred using a preset image quality enhancement model to obtain dynamic enhancement parameters for image quality enhancement, and so on, until image quality enhancement is completed for the image frames in the sequence of image frames to be processed.

[0050] It is understood that the scenarios described in the embodiments of this application can be defined based on actual circumstances. For example, in one example, different scenarios can specifically be home scenes, outdoor scenes, highway scenes, etc.; in other examples, different scenarios can be other scenarios defined by the user based on their needs. Picture quality enhancement parameters (PQ (Picture Quality) parameters) may include, but are not limited to, contrast enhancement parameters, color enhancement parameters, clarity enhancement parameters, SR (Super Resolution) enhancement parameters, HDR (High Dynamic Range Imaging) enhancement parameters, etc.

[0051] In this way, based on steps S110 to S140, a scene switching detection is performed on the image frames in the image frame sequence to be processed to determine whether a scene switching occurs. If a scene switching occurs, a preset image quality enhancement model is used to perform calculation and reasoning on the image frames at the scene switching location to obtain dynamic enhancement parameters, and the image quality of the image frames at the scene switching location is enhanced based on the dynamic enhancement parameters, while the image frames at the location where the scene has not switched are enhanced by obtaining pre-stored enhancement parameters. Thus, only the model is used for calculation and reasoning at the scene switching location to reduce resource usage. On the basis of ensuring the image quality enhancement effect, the image quality enhancement processing can effectively reduce the occupation of computing resources, improve the image quality enhancement efficiency, enable the device to meet high refresh screen display requirements, and enhance user experience.

[0052] The following describes further optional specific embodiments of each step performed when image quality enhancement is performed in the embodiment of FIG. 1 .

[0053] In one embodiment, referring to FIG. 2 , before performing scene switching detection based on image feature information of image frames in the sequence of image frames to be processed and obtaining a detection result, the method further includes:

[0054] In step S210, multi-dimensional feature extraction is performed on the image frames in the image frame sequence to obtain multi-dimensional sub-image feature information corresponding to the image frames in the image frame sequence; in step S220, image feature information corresponding to each image frame is obtained based on the multi-dimensional sub-image feature information corresponding to each image frame.

[0055] Multi-dimensional means at least two dimensions. Multi-dimensional feature extraction can be performed on each image frame in the image frame sequence to obtain multi-dimensional sub-image feature information corresponding to each image frame. The multi-dimensional sub-image feature information corresponding to each image frame is combined together to obtain the image feature information corresponding to each image frame.

[0056] Furthermore, for each image frame, the multi-dimensional sub-image feature information can be comprehensively evaluated to determine whether a scene switch has occurred, thereby improving the accuracy of scene switch detection and subsequently improving the reliability of reducing computing resource usage during the image quality enhancement process.

[0057] Furthermore, the performing of multi-dimensional feature extraction on the image frames in the image frame sequence to obtain multi-dimensional sub-image feature information corresponding to the image frames in the image frame sequence may specifically include at least two of the following methods:

[0058] The first method is to perform histogram feature extraction on each of the image frames to obtain histogram feature information corresponding to each of the image frames;

[0059] The second method is to extract the peak signal-to-noise ratio of each image frame to obtain peak signal-to-noise ratio information corresponding to each image frame;

[0060] The third method is to perform depth image feature extraction on each of the image frames to obtain depth image feature information corresponding to each of the image frames.

[0061] In the first method, histogram feature extraction is performed on each image frame to obtain the histogram feature information corresponding to each image frame. Specifically, HSV histogram feature information containing image brightness and color information can be extracted, where H is hue, S is saturation, and V is image brightness. The image brightness is the maximum value of the red, green, and blue signals of the image, which can be expressed as V=max(R,G,B).

[0062] In the second method, peak signal to noise ratio (PSNR) information is extracted from each image frame to obtain peak signal to noise ratio information corresponding to each image frame. Specifically, PSNR (Peak Signal to Noise Ratio) information can be extracted.

[0063] In the third method, depth image features are extracted from each image frame to obtain depth image feature information corresponding to each image frame. Specifically, a depth feature extraction neural network can be used to extract depth image features from the image frames to obtain depth image feature information.

[0064] Multi-dimensional sub-image feature information is extracted using at least two of the above three methods, that is, the multi-dimensional sub-image feature information includes at least two of histogram feature information, peak signal-to-noise ratio information and depth image feature information, which can effectively improve the accuracy of scene switching detection.

[0065] Among them, in one method, the multi-dimensional sub-image feature information specifically includes histogram feature information, peak signal-to-noise ratio information and depth image feature information, which can most effectively improve the accuracy of scene switching detection.

[0066] In other embodiments, before performing scene switching detection based on image feature information of image frames in the image frame sequence to be processed and obtaining detection results, the method may further include: performing feature extraction of a specified dimension on the image frames in the image frame sequence to obtain image feature information corresponding to the image frames in the image frame sequence.

[0067] In one embodiment, the image feature information includes multi-dimensional sub-image feature information; and performing scene switching detection based on the image feature information of the image frames in the sequence of image frames to be processed to obtain a detection result includes:

[0068] Scene switching detection is performed separately according to the multi-dimensional sub-image feature information corresponding to each of the image frames to obtain the multi-dimensional sub-detection results corresponding to each of the image frames; and comprehensive judgment is performed based on the multiple dimensional sub-detection results corresponding to each of the image frames to obtain the detection results corresponding to each of the image frames.

[0069] For each image frame, scene switching detection can be performed separately based on the sub-image feature information of each dimension corresponding to each image frame to obtain the sub-detection results of each image frame in each dimension, and then the multi-dimensional sub-detection results corresponding to the image frame are obtained. Each sub-detection result can reflect whether a scene switching occurs.

[0070] Furthermore, by comprehensively evaluating whether a scene switch has occurred by integrating the sub-detection results of multiple dimensions, the accuracy of scene switch detection can be effectively improved, thereby improving the reliability of reducing computing resource usage during the image quality enhancement process.

[0071] Furthermore, in one embodiment, the multi-dimensional sub-image feature information includes at least two of histogram feature information, peak signal-to-noise ratio information, and depth image feature information; and performing scene change detection based on the multi-dimensional sub-image feature information corresponding to each of the image frames to obtain a multi-dimensional sub-detection result corresponding to each of the image frames may specifically include at least two of the following methods:

[0072] First, performing histogram detection according to the histogram feature information corresponding to each of the image frames to obtain a first sub-detection result corresponding to each of the image frames;

[0073] The second method is to perform feature similarity detection based on peak signal-to-noise ratio information corresponding to each of the image frames to obtain a second sub-detection result corresponding to each of the image frames;

[0074] The third method is to perform depth image feature detection according to the depth image feature information corresponding to each of the image frames to obtain a third sub-detection result corresponding to each of the image frames.

[0075] In the first approach, histogram detection is performed based on histogram feature information corresponding to the image frames. The difference between the histogram feature information corresponding to the current image frame and the histogram feature information of the previous image frame can be detected, and a first sub-detection result is obtained based on the difference. Specifically, if the first difference is greater than a first predetermined difference condition, the first sub-detection result indicates a scene change; if the first difference is not greater than the first predetermined difference condition, the first sub-detection result indicates no scene change.

[0076] In the second method, feature similarity detection is performed based on the peak signal-to-noise ratio information corresponding to the image frames. A second difference between the peak signal-to-noise ratio information corresponding to the current image frame and the peak signal-to-noise ratio information of the previous image frame can be detected, and a second sub-detection result is obtained based on the second difference. Specifically, if the second difference is greater than a second predetermined difference condition, the second sub-detection result indicates a scene change; if the second difference is not greater than the second predetermined difference condition, the second sub-detection result indicates no scene change.

[0077] In the third approach, depth image feature detection is performed based on the depth image feature information corresponding to the image frames. A third difference between the depth image feature information corresponding to the current image frame and the depth image feature information of the previous image frame can be detected, and a third sub-detection result is obtained based on the third difference. Specifically, if the third difference is greater than a third predetermined difference condition, the third sub-detection result indicates a scene change; if the third difference is not greater than the third predetermined difference condition, the third sub-detection result indicates no scene change.

[0078] The multi-dimensional sub-detection results are obtained by extracting at least two of the above three methods, that is, the multi-dimensional sub-detection results include at least two of the first sub-detection results, the second sub-detection results and the third sub-detection results, which can effectively improve the accuracy of scene switching detection.

[0079] Among them, in one method, the multi-dimensional sub-detection results include three types: a first sub-detection result, a second sub-detection result, and a third sub-detection result. This can most effectively improve the accuracy of scene switching detection.

[0080] Furthermore, a comprehensive judgment is made based on the multiple dimensional sub-detection results corresponding to each of the image frames to obtain the detection results corresponding to each of the image frames. Specifically, it can be: if the multi-dimensional sub-detection results include two sub-detection results, then if both of the two sub-detection results are scene switches, then it is determined that the scene has switched; otherwise, it is determined that the scene has not switched; if the multi-dimensional sub-detection results include at least three sub-detection results, then if more than half of the at least three sub-detection results are scene switches, then it is determined that the scene has switched; otherwise, it is determined that the scene has not switched.

[0081] In one embodiment, referring to FIG3 , the method of using a preset image quality enhancement model to calculate and infer image frames at scene switching to obtain dynamic enhancement parameters may include:

[0082] Step S310, determine the target computing resources; step S320, use a preset image quality enhancement model, perform computational reasoning on the image frame at the scene switching point based on the target computing resources, and obtain computational reasoning results; step S330, obtain the dynamic enhancement parameters based on the computational reasoning results.

[0083] After determining the target computing resources, a preset image quality enhancement model is used to perform computational inference on the image frames at the scene transition based on the target computing resources to obtain computational inference results. Dynamic enhancement parameters can then be derived based on the computational inference results. In some approaches, the computational inference results are image quality enhancement parameters, which can be directly used as dynamic enhancement parameters. In other approaches, the computational inference results are image quality information, which can be further calculated based on the image quality information to obtain dynamic enhancement parameters.

[0084] Furthermore, in one embodiment, the determining the target computing resource includes: detecting whether a graphics processor exists; and if so, determining the graphics processor as the target computing resource.

[0085] If a graphics processing unit (GPU) is detected in the device, the graphics processing unit is determined as the target computing resource, and then the GPU is used to run the AI ​​algorithm model reasoning, which not only takes into account the reasoning speed but also avoids using CPU reasoning and occupying a large amount of CPU.

[0086] Furthermore, in devices such as televisions, SOCs with NPUs can be replaced with SOCs without NPUs, thereby reducing costs.

[0087] Furthermore, in one embodiment, determining the target computing resource includes: calculating a scene switching frequency; if the scene switching frequency is less than a predetermined threshold, determining a network processor as the target computing resource; if the scene switching frequency is greater than the predetermined threshold, determining a graphics processor as the target computing resource.

[0088] The scene switching frequency can be obtained by dividing the predetermined time period by the total number of scene switching times within the predetermined time period. The predetermined time period can specifically be a time period of a predetermined length before the current image frame as the starting point.

[0089] When a graphics processing unit (GPU) and a network processing unit (NPU) are present in the device, if the scene switching frequency is less than a predetermined threshold, the network processor is determined as the target computing resource; if the scene switching frequency is greater than the predetermined threshold, the graphics processor is determined as the target computing resource, thereby further improving the rationality of the allocation of computing resources in the image quality enhancement scenario and improving the reliability of image quality enhancement.

[0090] In one embodiment, after the preset image quality enhancement model is used to perform calculation and inference on the image frame at the scene switching point to obtain dynamic enhancement parameters, the method also includes: replacing the pre-stored enhancement parameters at the predetermined position based on the dynamic enhancement parameters to obtain updated pre-stored enhancement parameters.

[0091] For example, the first image frame in the sequence of image frames to be processed is regarded as a scene switch, and the first image frame uses a preset image quality enhancement model to perform calculation and reasoning to obtain dynamic enhancement parameters for image quality enhancement, and the dynamic enhancement parameters are saved to a predetermined position as pre-stored enhancement parameters. If the scene has not switched for the second to fifth image frames, the pre-stored enhancement parameters are obtained for image quality enhancement; if the scene has switched for the sixth image frame, the sixth image frame uses a preset image quality enhancement model to perform calculation and reasoning to obtain dynamic enhancement parameters for image quality enhancement, and the dynamic enhancement parameters replace the pre-stored enhancement parameters at the predetermined position to obtain updated pre-stored enhancement parameters; if the scene has not switched for the seventh to fifteenth image frames, the updated pre-stored enhancement parameters are obtained for image quality enhancement; and so on, image quality enhancement is completed for the image frames in the sequence of image frames to be processed.

[0092] In this manner of this embodiment, the image quality enhancement effect of the image frames in the image frame sequence to be processed can be further improved on the basis of reducing the occupation of computing resources by the image quality enhancement processing and improving the image quality enhancement efficiency.

[0093] To facilitate better implementation of the image quality enhancement method provided in the embodiments of this application, the embodiments of this application also provide an image quality enhancement device based on the aforementioned image quality enhancement method. The meanings of the terms herein are the same as those in the aforementioned image quality enhancement method. For specific implementation details, please refer to the description in the method embodiments. Figure 4 shows a block diagram of an image quality enhancement device according to one embodiment of the present application.

[0094] As shown in Figure 4, the image quality enhancement device 400 may include: a detection module 410 can be used to perform scene switching detection based on the image feature information of the image frame in the image frame sequence to be processed to obtain a detection result; an inference module 420 can be used to use a preset image quality enhancement model to perform calculation and inference on the image frame at the scene switching location to obtain dynamic enhancement parameters if the detection result is a scene switching; an acquisition module 430 can be used to obtain pre-stored enhancement parameters from a predetermined location if the detection result is that the scene has not switched; an enhancement module 440 can be used to perform image quality enhancement on the image frame at the scene switching location based on the dynamic enhancement parameters, or to perform image quality enhancement on the image frame at the scene not switching location based on the pre-stored enhancement parameters.

[0095] In some embodiments of the present application, the image feature information includes multi-dimensional sub-image feature information; the detection module is used to: perform scene switching detection according to the multi-dimensional sub-image feature information corresponding to each of the image frames to obtain multi-dimensional sub-detection results corresponding to each of the image frames; perform comprehensive judgment based on the sub-detection results of multiple dimensions corresponding to each of the image frames to obtain detection results corresponding to each of the image frames.

[0096] In some embodiments of the present application, the multi-dimensional sub-image feature information includes at least two of histogram feature information, peak signal-to-noise ratio information, and depth image feature information; the detection module is used to implement at least two of the following methods: performing histogram detection based on the histogram feature information corresponding to each of the image frames to obtain a first sub-detection result corresponding to each of the image frames; performing feature similarity detection based on the peak signal-to-noise ratio information corresponding to each of the image frames to obtain a second sub-detection result corresponding to each of the image frames; performing depth image feature detection based on the depth image feature information corresponding to each of the image frames to obtain a third sub-detection result corresponding to each of the image frames.

[0097] In some embodiments of the present application, after the preset image quality enhancement model is used to perform calculation and reasoning on the image frame at the scene switching point to obtain dynamic enhancement parameters, the device also includes an update module for: replacing the pre-stored enhancement parameters at the predetermined position based on the dynamic enhancement parameters to obtain updated pre-stored enhancement parameters.

[0098] In some embodiments of the present application, the reasoning module is used to: determine the target computing resources; use a preset image quality enhancement model to perform computational reasoning on the image frames at the scene switching point based on the target computing resources to obtain computational reasoning results; and obtain the dynamic enhancement parameters based on the computational reasoning results.

[0099] In some embodiments of the present application, the inference module is configured to: detect whether a graphics processor exists; and if so, determine the graphics processor as the target computing resource.

[0100] In some embodiments of the present application, the inference module is used to: calculate the scene switching frequency; if the scene switching frequency is less than a predetermined threshold, determine the network processor as the target computing resource; if the scene switching frequency is greater than the predetermined threshold, determine the graphics processor as the target computing resource.

[0101] In some embodiments of the present application, before performing scene switching detection based on image feature information of image frames in the image frame sequence to be processed and obtaining a detection result, the device also includes an extraction module for: performing multi-dimensional feature extraction on the image frames in the image frame sequence to obtain multi-dimensional sub-image feature information corresponding to the image frames in the image frame sequence; and obtaining image feature information corresponding to each image frame based on the multi-dimensional sub-image feature information corresponding to each image frame.

[0102] In some embodiments of the present application, the extraction module is used to implement at least two of the following methods: performing histogram feature extraction on each of the image frames to obtain histogram feature information corresponding to each of the image frames; performing peak signal-to-noise ratio extraction on each of the image frames to obtain peak signal-to-noise ratio information corresponding to each of the image frames; performing depth image feature extraction on each of the image frames to obtain depth image feature information corresponding to each of the image frames.

[0103] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0104] In addition, an embodiment of the present application further provides an electronic device, as shown in FIG5 . FIG5 shows a block diagram of an electronic device according to an embodiment of the present application. Specifically:

[0105] The electronic device may include components such as a processor 501 with one or more processing cores, a memory 502 with one or more computer-readable storage media, a power supply 503, and an input unit 504. Those skilled in the art will appreciate that the electronic device structure shown in FIG5 does not limit the electronic device and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0106] Processor 501 is the control center of the electronic device. It utilizes various interfaces and circuits to connect the various components of the entire computer device. By running or executing software programs and / or modules stored in memory 502 and accessing data stored in memory 502, it performs various computer device functions and processes data, thereby providing overall monitoring of the electronic device. Optionally, processor 501 may include one or more processing cores; preferably, processor 501 may integrate an application processor and a modem processor, wherein the application processor primarily processes the operating system, user interfaces, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 501.

[0107] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

[0108] The electronic device also includes a power supply 503 for supplying power to various components. Preferably, the power supply 503 can be logically connected to the processor 501 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 503 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0109] The electronic device may further include an input unit 504, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0110] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 501 in the electronic device will load the executable files corresponding to one or more computer program processes into the memory 502 according to the following instructions, and the processor 501 will run the computer program stored in the memory 502, thereby realizing the various functions of the aforementioned embodiments of the present application. For example, the processor 501 may perform the following steps:

[0111] Scene switching detection is performed based on image feature information of image frames in the image frame sequence to be processed to obtain a detection result; if the detection result is a scene switch, a preset image quality enhancement model is used to perform calculation and reasoning on the image frames at the scene switch to obtain dynamic enhancement parameters; if the detection result is that the scene has not switched, pre-stored enhancement parameters are obtained from a predetermined position; image quality enhancement is performed on the image frames at the scene switch based on the dynamic enhancement parameters, or image quality enhancement is performed on the image frames at the scene where the scene has not switched based on the pre-stored enhancement parameters.

[0112] In some embodiments of the present application, the image feature information includes multi-dimensional sub-image feature information; the scene switching detection is performed based on the image feature information of the image frames in the image frame sequence to be processed to obtain the detection results, including: performing scene switching detection based on the multi-dimensional sub-image feature information corresponding to each of the image frames to obtain the multi-dimensional sub-detection results corresponding to each of the image frames; and performing a comprehensive judgment based on the sub-detection results of multiple dimensions corresponding to each of the image frames to obtain the detection results corresponding to each of the image frames.

[0113] In some embodiments of the present application, the multidimensional sub-image feature information includes at least two of histogram feature information, peak signal-to-noise ratio information, and depth image feature information; the scene switching detection is performed according to the multidimensional sub-image feature information corresponding to each of the image frames to obtain a multidimensional sub-detection result corresponding to each of the image frames, including at least two of the following methods: performing histogram detection according to the histogram feature information corresponding to each of the image frames to obtain a first sub-detection result corresponding to each of the image frames; performing feature similarity detection according to the peak signal-to-noise ratio information corresponding to each of the image frames to obtain a second sub-detection result corresponding to each of the image frames; performing depth image feature detection according to the depth image feature information corresponding to each of the image frames to obtain a third sub-detection result corresponding to each of the image frames.

[0114] In some embodiments of the present application, after the preset image quality enhancement model is used to perform calculation and reasoning on the image frame at the scene switching point to obtain dynamic enhancement parameters, it also includes: replacing the pre-stored enhancement parameters at the predetermined position based on the dynamic enhancement parameters to obtain updated pre-stored enhancement parameters.

[0115] In some embodiments of the present application, the use of a preset image quality enhancement model to perform computational reasoning on the image frames at the scene switching point to obtain dynamic enhancement parameters includes: determining target computing resources; using a preset image quality enhancement model to perform computational reasoning on the image frames at the scene switching point based on the target computing resources to obtain computational reasoning results; and obtaining the dynamic enhancement parameters based on the computational reasoning results.

[0116] In some embodiments of the present application, determining the target computing resource includes: detecting whether a graphics processor exists; and if so, determining the graphics processor as the target computing resource.

[0117] In some embodiments of the present application, determining the target computing resource includes: calculating a scene switching frequency; if the scene switching frequency is less than a predetermined threshold, determining a network processor as the target computing resource; if the scene switching frequency is greater than the predetermined threshold, determining a graphics processor as the target computing resource.

[0118] In some embodiments of the present application, before performing scene switching detection based on the image feature information of the image frames in the image frame sequence to be processed and obtaining the detection results, it also includes: performing multi-dimensional feature extraction on the image frames in the image frame sequence to obtain multi-dimensional sub-image feature information corresponding to the image frames in the image frame sequence; and obtaining image feature information corresponding to each of the image frames based on the multi-dimensional sub-image feature information corresponding to each of the image frames.

[0119] In some embodiments of the present application, the multi-dimensional feature extraction is performed on the image frames in the image frame sequence to obtain multi-dimensional sub-image feature information corresponding to the image frames in the image frame sequence, including at least two of the following methods: performing histogram feature extraction on each of the image frames to obtain histogram feature information corresponding to each of the image frames; performing peak signal-to-noise ratio extraction on each of the image frames to obtain peak signal-to-noise ratio information corresponding to each of the image frames; performing depth image feature extraction on each of the image frames to obtain depth image feature information corresponding to each of the image frames.

[0120] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by a computer program, or by controlling related hardware through a computer program. The computer program may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0121] To this end, an embodiment of the present application further provides a storage medium storing a computer program, which can be loaded by a processor to execute the steps of any method provided in the embodiment of the present application.

[0122] The storage medium may be a computer-readable storage medium, and the storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0123] Since the computer program stored in the storage medium can execute the steps of any method provided in the embodiments of the present application, the beneficial effects that can be achieved by the method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0124] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0125] It should be understood that the present application is not limited to the embodiments that have been described above and shown in the accompanying drawings, but various modifications and changes may be made without departing from the scope thereof.

Claims

1. An image quality enhancement method, wherein, Including: Performing scene change detection based on the image feature information of the image frames in the sequence of image frames to be processed, and obtaining a detection result; If the detection result is a scene change, using a preset image quality enhancement model to perform computational inference on the image frames at the scene change to obtain dynamic enhancement parameters; If the detection result is that the scene has not changed, obtaining pre-stored enhancement parameters from a predetermined location; Performing image quality enhancement on the image frames at the scene change based on the dynamic enhancement parameters, or performing image quality enhancement on the image frames where the scene has not changed based on the pre-stored enhancement parameters.

2. The method according to claim 1, wherein, The image feature information includes multi-dimensional sub-image feature information; The performing scene change detection based on the image feature information of the image frames in the sequence of image frames to be processed and obtaining a detection result includes: Performing scene change detection respectively according to the multi-dimensional sub-image feature information corresponding to each image frame to obtain multi-dimensional sub-detection results corresponding to each image frame; Based on the sub-detection results of multiple dimensions corresponding to each image frame, performing comprehensive judgment to obtain the detection result corresponding to each image frame.

3. The method according to claim 2, wherein, The multi-dimensional sub-image feature information includes at least two of histogram feature information, peak signal-to-noise ratio information, and depth image feature information; the performing scene change detection respectively according to the multi-dimensional sub-image feature information corresponding to each image frame to obtain multi-dimensional sub-detection results corresponding to each image frame includes at least two of the following methods: Performing histogram detection according to the histogram feature information corresponding to each image frame to obtain a first sub-detection result corresponding to each image frame; Performing feature similarity detection according to the peak signal-to-noise ratio information corresponding to each image frame to obtain a second sub-detection result corresponding to each image frame; Performing depth image feature detection according to the depth image feature information corresponding to each image frame to obtain a third sub-detection result corresponding to each image frame.

4. The method according to claim 1, wherein After the using a preset image quality enhancement model to perform computational inference on the image frames at the scene change to obtain dynamic enhancement parameters, the method further includes: Replacing the pre-stored enhancement parameters at the predetermined location based on the dynamic enhancement parameters to obtain updated pre-stored enhancement parameters.

5. The method according to claim 1, wherein The using a preset image quality enhancement model to perform computational inference on the image frames at the scene change to obtain dynamic enhancement parameters includes: Determining target computing resources; Using a preset image quality enhancement model to perform computational inference on the image frames at the scene change based on the target computing resources to obtain a computational inference result; According to the computational inference result, obtaining the dynamic enhancement parameters.

6. The method according to claim 5, wherein The determining target computing resources includes: Detecting whether there is a graphics processor; If there is, determining the graphics processor as the target computing resources.

7. The method according to claim 5, wherein The determining target computing resources includes: Calculating the scene change frequency; If the scene change frequency is less than a predetermined threshold, determining the network processor as the target computing resources; If the scene change frequency is greater than the predetermined threshold, determining the graphics processor as the target computing resources.

8. The method according to claim 1, wherein Before the performing scene change detection based on the image feature information of the image frames in the sequence of image frames to be processed and obtaining a detection result, the method further includes: Extract multi-dimensional features from the image frames in the image frame sequence to obtain the multi-dimensional sub-image feature information corresponding to the image frames in the image frame sequence; Obtain the image feature information corresponding to each of the image frames according to the multi-dimensional sub-image feature information corresponding to each of the image frames.

9. The method according to claim 8, wherein The extracting multi-dimensional features from the image frames in the image frame sequence to obtain the multi-dimensional sub-image feature information corresponding to the image frames in the image frame sequence includes at least two of the following methods: Extract histogram features from each of the image frames to obtain the histogram feature information corresponding to each of the image frames; Extract the peak signal-to-noise ratio from each of the image frames to obtain the peak signal-to-noise ratio information corresponding to each of the image frames; Extract depth image features from each of the image frames to obtain the depth image feature information corresponding to each of the image frames.

10. The method according to claim 1, wherein, Before detecting scene switching based on the image feature information of the image frames in the to-be-processed image frame sequence to obtain a detection result, the method further includes: Extract features of a specified dimension from the image frames in the image frame sequence to obtain the image feature information corresponding to the image frames in the image frame sequence.

11. The method according to claim 3, wherein, The performing histogram detection according to the histogram feature information corresponding to each of the image frames to obtain the first sub-detection result corresponding to each of the image frames includes: Detect the first difference between the histogram feature information corresponding to each of the image frames and the histogram feature information of the previous image frame of each of the image frames; If the first difference is greater than the first predetermined difference condition, the first sub-detection result is scene switching; If the first difference is not greater than the first predetermined difference condition, the first sub-detection result is no scene switching.

12. The method according to claim 3, wherein The performing feature similarity detection according to the peak signal-to-noise ratio information corresponding to each of the image frames to obtain the second sub-detection result corresponding to each of the image frames includes: Detect the second difference between the peak signal-to-noise ratio information corresponding to each of the image frames and the peak signal-to-noise ratio information of the previous image frame of each of the image frames; If the second difference is greater than the second predetermined difference condition, the second sub-detection result is scene switching; If the second difference is not greater than the second predetermined difference condition, the second sub-detection result is no scene switching.

13. The method according to claim 3, wherein, The performing depth image feature detection according to the depth image feature information corresponding to each of the image frames to obtain the third sub-detection result corresponding to each of the image frames includes: Detect the third difference between the depth image feature information corresponding to each of the image frames and the depth image feature information of the previous image frame of each of the image frames; If the third difference is greater than the third predetermined difference condition, the third sub-detection result is scene switching; If the third difference is not greater than the third predetermined difference condition, the third sub-detection result is no scene switching.

14. The method according to claim 2, wherein The performing comprehensive judgment based on the sub-detection results of multiple dimensions corresponding to each of the image frames to obtain the detection result corresponding to each of the image frames includes: If the multi-dimensional sub-detection results corresponding to each of the image frames include two sub-detection results, then if both of the two sub-detection results are scene switching, the detection result corresponding to each of the image frames is scene switching, otherwise, the detection result corresponding to each of the image frames is no scene switching; If the multi-dimensional sub-detection results corresponding to each of the image frames include at least three sub-detection results, then if more than half of the at least three sub-detection results are scene switches, the detection result corresponding to each of the image frames is a scene switch; otherwise, the detection result corresponding to each of the image frames is that there is no scene switch.

15. An image quality enhancement device, wherein, Comprising: A detection module, configured to perform scene switch detection based on the image feature information of the image frames in the image frame sequence to be processed, and obtain a detection result; An inference module, configured to, if the detection result is a scene switch, use a preset image quality enhancement model to perform computational inference on the image frames at the scene switch to obtain dynamic enhancement parameters; An acquisition module, configured to, if the detection result is that there is no scene switch, acquire pre-stored enhancement parameters from a predetermined position; An enhancement module, configured to perform image quality enhancement on the image frames at the scene switch based on the dynamic enhancement parameters, or perform image quality enhancement on the image frames where there is no scene switch based on the pre-stored enhancement parameters.

16. The device according to claim 15, wherein The image feature information includes multi-dimensional sub-image feature information; the detection module is configured to: perform scene switch detection respectively according to the multi-dimensional sub-image feature information corresponding to each of the image frames to obtain multi-dimensional sub-detection results corresponding to each of the image frames; perform comprehensive judgment based on the sub-detection results of multiple dimensions corresponding to each of the image frames to obtain the detection result corresponding to each of the image frames.

17. The apparatus according to claim 16, wherein, The multi-dimensional sub-image feature information includes at least two of histogram feature information, peak signal-to-noise ratio information, and depth image feature information; the detection module is configured to implement at least two of the following methods: perform histogram detection according to the histogram feature information corresponding to each of the image frames to obtain a first sub-detection result corresponding to each of the image frames; perform feature similarity detection according to the peak signal-to-noise ratio information corresponding to each of the image frames to obtain a second sub-detection result corresponding to each of the image frames; perform depth image feature detection according to the depth image feature information corresponding to each of the image frames to obtain a third sub-detection result corresponding to each of the image frames.

18. The apparatus according to claim 15, wherein After using the preset image quality enhancement model to perform computational inference on the image frames at the scene switch to obtain dynamic enhancement parameters, the apparatus further includes an update module, configured to: replace the pre-stored enhancement parameters at the predetermined position based on the dynamic enhancement parameters to obtain updated pre-stored enhancement parameters.

19. A storage medium, wherein, It stores a computer program, and when the computer program is executed by a processor of the computer, the computer is caused to execute the method according to any one of claims 1 to 14.

20. An electronic device, wherein, Comprising: A memory, storing a computer program; A processor, reading the computer program stored in the memory to execute the method according to any one of claims 1 to 14.

Images