Video transcoding coding parameter determination method and device, electronic equipment and medium

Abstract

The embodiment of the invention provides a coding parameter determination method and device for video transcoding, electronic equipment and a storage medium, and belongs to the technical field of video processing. The method comprises the following steps: acquiring attribute parameter ranges of a to-be-transcoded video and a target transcoded video; predicting a transcoding result of the to-be-transcoded video under the at least one group of coding parameter combination through the video transcoding prediction model to obtain an attribute parameter prediction value; screening the attribute parameter predicted value of each coding parameter combination according to the attribute parameter range to obtain a candidate coding parameter combination; and comparing the attribute parameter predicted values corresponding to the candidate coding parameter combinations based on a decision algorithm, and determining a target coding parameter combination. According to the method, video attribute parameters under different coding parameter combinations are predicted firstly, then a target coding parameter combination meeting transcoding requirements is selected based on a decision algorithm, and decision requirements of different application scenes can be met by flexibly adjusting the decision algorithm.

Description

Technical Field

[0001] This disclosure relates to the field of video processing technology, and more specifically, to a method, apparatus, electronic device, computer program product, and storage medium for determining encoding parameters in video transcoding. Background Technology

[0002] With the explosive growth in demand for video consumption, video platforms face the challenge of efficiently adapting to diverse terminal devices and network environments. Due to significant differences in user device performance (such as mobile phones, tablets, and smart TVs) and network conditions (5G, 4G, and Wi-Fi), platforms need to transcode the same video source into multiple levels, covering different resolutions (such as 1080P and 720P), image quality (high definition and standard definition), and bitrates (from 500kbps to 10Mbps, etc.) to ensure smooth playback and the best viewing experience.

[0003] Different video content may require different optimal transcoding parameters. For example, some videos need higher resolution, while others show little difference in image quality between high and low resolutions; some videos require specific preprocessing, while others can be directly encoded. Encoding a video with its optimal parameters can achieve higher image quality and improve user experience, as well as lower bitrates and reduce bandwidth costs. Therefore, determining the appropriate encoding parameters for a given video content has become a pressing issue in this field. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, computer program product, and storage medium for determining encoding parameters in video transcoding.

[0005] According to a first aspect of the present disclosure, a method for determining encoding parameters for video transcoding is provided, comprising: obtaining attribute parameter ranges of a video to be transcoded and a target video to be transcoded; predicting the transcoding result of the video to be transcoded under at least one set of encoding parameter combinations using a pre-trained video transcoding prediction model to obtain attribute parameter prediction values ​​corresponding to each of the encoding parameter combinations; the encoding parameter combinations include encoding parameter values ​​corresponding to at least one encoding parameter type; filtering the attribute parameter prediction values ​​of each of the encoding parameter combinations according to the attribute parameter ranges to obtain at least one set of candidate encoding parameter combinations; and comparing the attribute parameter prediction values ​​corresponding to each of the candidate encoding parameter combinations based on a preset decision algorithm to determine a target encoding parameter combination.

[0006] In some exemplary embodiments of this disclosure, obtaining the attribute parameter ranges of the video to be transcoded and the target transcoded video further includes: obtaining at least one video transcoding level of the target transcoded video; and determining the attribute parameter ranges corresponding to each video transcoding level based on the video transcoding level.

[0007] In some exemplary embodiments of this disclosure, the attribute parameters include at least: bitrate parameters and image quality parameters.

[0008] In some exemplary embodiments of this disclosure, the training process of the video transcoding prediction model includes: acquiring a training dataset comprising multiple video transcoding prediction training samples; each video transcoding prediction training sample comprising at least one video sample; performing video transcoding processing on the video sample based on the at least one set of encoding parameter combinations to obtain attribute parameter label values ​​corresponding to each of the encoding parameter combinations; predicting the transcoding result of the video sample under the at least one set of encoding parameter combinations using the video transcoding prediction model to be trained to obtain attribute parameter training values ​​corresponding to each of the encoding parameter combinations; generating a prediction loss value based on the attribute parameter training values ​​and attribute parameter label values ​​corresponding to each of the encoding parameter combinations; and training the video transcoding prediction model to be trained based on the prediction loss value to obtain the video transcoding prediction model.

[0009] In some exemplary embodiments of this disclosure, the training process of the video transcoding prediction model further includes: extracting features from the video sample using at least one video feature extraction module to obtain at least one video feature; and using the video transcoding prediction model to be trained to predict the transcoding result of the video sample under the at least one set of encoding parameter combinations based on the at least one video feature to obtain the attribute parameter training value corresponding to each of the encoding parameter combinations.

[0010] In some exemplary embodiments of this disclosure, the training process of the video transcoding prediction model further includes: precoding the video sample to obtain at least one precoded feature; and using the video transcoding prediction model to be trained to predict the transcoding result of the video sample under the at least one set of encoding parameter combinations based on the at least one video feature and / or the at least one precoded feature, to obtain the attribute parameter training value corresponding to each of the encoding parameter combinations.

[0011] In some exemplary embodiments of this disclosure, the method further includes: determining the decision algorithm based on the application scenario corresponding to the video to be transcoded.

[0012] In some exemplary embodiments of this disclosure, the step of determining the target coding parameter combination by comparing the predicted attribute parameters corresponding to each candidate coding parameter combination based on a preset decision algorithm includes: obtaining the bitrate parameter and image quality parameter corresponding to each candidate coding parameter combination; calculating the rate-distortion cost value corresponding to each candidate coding parameter combination based on the bitrate parameter and image quality parameter; and determining the target coding parameter combination based on comparing the rate-distortion cost values ​​corresponding to each candidate coding parameter combination.

[0013] In some exemplary embodiments of this disclosure, the step of calculating the rate-distortion cost value corresponding to each candidate coding parameter combination based on the bitrate parameter and the image quality parameter includes: determining the corresponding rate-distortion hyperparameter based on the video transcoding level corresponding to the target transcoded video; and calculating the rate-distortion cost value corresponding to each candidate coding parameter combination based on the rate-distortion hyperparameter, the bitrate parameter, and the image quality parameter.

[0014] In some exemplary embodiments of this disclosure, the method further includes: performing interpolation processing based on each of the encoding parameter combinations and the corresponding attribute parameter prediction values, and adding at least one set of interpolation encoding parameter combinations and the corresponding interpolation attribute parameter prediction values.

[0015] In some exemplary embodiments of this disclosure, the method further includes: comparing the attribute parameter similarity between the attribute parameter prediction values ​​of each of the video transcoding levels under the target encoding parameter combination; merging the target encoding parameter combinations corresponding to two video transcoding levels in response to the attribute parameter similarity being less than a first similarity threshold; and adding a video transcoding level between the corresponding two video transcoding levels in response to the attribute parameter similarity being greater than a second similarity threshold.

[0016] According to a second aspect of the present disclosure, a video transcoding parameter determination apparatus is provided, comprising: a video acquisition module configured to acquire attribute parameter ranges of a video to be transcoded and a target transcoded video; an attribute parameter prediction module configured to predict the transcoding result of the video to be transcoded under at least one set of encoding parameter combinations using a pre-trained video transcoding prediction model, to obtain attribute parameter prediction values ​​corresponding to each of the encoding parameter combinations; wherein the encoding parameter combinations include encoding parameter values ​​corresponding to at least one encoding parameter type; an encoding parameter combination filtering module configured to filter the attribute parameter prediction values ​​of each of the encoding parameter combinations according to the attribute parameter ranges, to obtain at least one set of candidate encoding parameter combinations; and an encoding parameter combination determination module configured to compare the attribute parameter prediction values ​​corresponding to each of the candidate encoding parameter combinations based on a preset decision algorithm, to determine a target encoding parameter combination.

[0017] According to a third aspect of the present disclosure, an electronic device is provided, characterized in that it includes: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the executable instructions to implement the video transcoding encoding parameter determination method according to any one of the present invention.

[0018] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the video transcoding parameter determination method described in any one of the present invention.

[0019] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that is executed by a processor to determine the encoding parameters of any one of the video transcoding methods described above.

[0020] The video transcoding parameter determination method provided in this disclosure involves obtaining the video to be transcoded and the range of attribute parameters; predicting the transcoding result of the video under multiple encoding parameter combinations using a video transcoding prediction model; and comparing the predicted attribute parameter values ​​corresponding to each candidate encoding parameter combination based on a preset decision algorithm to determine the target encoding parameter combination. This method does not directly predict the encoding parameters, but first predicts the video attribute parameters under different encoding parameter combinations, and then selects the target encoding parameter combination that meets the transcoding requirements based on the decision algorithm. This prediction process does not require a large amount of repetitive transcoding and the decision algorithm can be flexibly adjusted as needed to determine the encoding parameters suitable for the application scenario.

[0021] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0023] Figure 1 A schematic diagram of an exemplary system architecture to which the methods of embodiments of this disclosure can be applied is shown.

[0024] Figure 2 This is a flowchart illustrating a method for determining encoding parameters for video transcoding according to an exemplary embodiment.

[0025] Figure 3 This is a schematic diagram illustrating the relationship between encoding parameters and video attribute parameters, based on an example.

[0026] Figure 4 This is based on an example of the training process for a video transcoding prediction model. Figure 1 .

[0027] Figure 5This is based on an example of the training process for a video transcoding prediction model. Figure 2 .

[0028] Figure 6 It is a flowchart of a decision-making process based on a target encoding parameter combination as shown in an example.

[0029] Figure 7 This is a flowchart illustrating the video transcoding bit merging / addition process, as shown in the example.

[0030] Figure 8 This is a block diagram illustrating a video transcoding parameter determination apparatus according to an exemplary embodiment.

[0031] Figure 9 This is a schematic diagram illustrating the structure of an electronic device suitable for implementing exemplary embodiments of the present disclosure, according to an exemplary embodiment. Detailed Implementation

[0032] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0033] The features, structures, or characteristics described in this disclosure can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more specific details omitted, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0034] The accompanying drawings are merely illustrative of this disclosure, and the same reference numerals in the drawings denote the same or similar parts, thus omitting repeated descriptions of them. Some block diagrams shown in the drawings do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in at least one hardware module or integrated circuit, or in different network and / or processor devices and / or microcontroller devices.

[0035] The flowchart shown in the accompanying drawings is merely illustrative and does not necessarily include all content and steps, nor does it require execution in the described order. For example, some steps may be broken down, while others may be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0036] In this specification, the terms “a,” “an,” “the,” “the,” and “at least one” are used to indicate the presence of at least one element / component / etc.; the terms “comprising,” “including,” and “having” are used to indicate an open-ended inclusion and to mean that there may be other elements / components / etc. in addition to the listed elements / components / etc.; the terms “first,” “second,” and “third,” etc., are used only as markings and are not a limitation on the number of objects.

[0037] Figure 1 A schematic diagram of an exemplary system architecture to which the methods of embodiments of this disclosure can be applied is shown.

[0038] like Figure 1 As shown, the system architecture may include server 101, network 102, terminal device 103, terminal device 104, and terminal device 105. Network 102 serves as the medium for providing a communication link between terminal device 103, terminal device 104, or terminal device 105 and server 101. Network 102 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0039] Server 101 can be a server that provides various services, such as a back-end management server that supports the devices operated by users using terminal devices 103, 104, or 105. The back-end management server can analyze and process received requests and other data, and feed back the processing results to terminal devices 103, 104, or 105.

[0040] Terminal devices 103, 104, and 105 can be smartphones, tablets, laptops, desktop computers, smart speakers, wearable smart devices, virtual reality devices, augmented reality devices, etc., but are not limited to these.

[0041] It should be understood that Figure 1 The number of terminal devices 103, 104, 105, network 102, and server 101 in the diagram is merely illustrative. Server 101 can be a single physical server, a server cluster consisting of multiple servers, or a cloud server. Depending on actual needs, it can have any number of terminal devices, networks, and servers.

[0042] The steps of the method in the exemplary embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings and examples.

[0043] Figure 2 This is a flowchart illustrating a method for determining encoding parameters for video transcoding according to an exemplary embodiment. Figure 2 The method provided in the embodiments can be executed by any electronic device, such as the one described above. Figure 1 Terminal devices in or Figure 1 The server in, or Figure 1 The terminal devices and servers in the process are executed together, but this disclosure does not limit this.

[0044] In step S210, the attribute parameter ranges of the video to be transcoded and the target video to be transcoded are obtained.

[0045] In related technologies, due to significant differences in user device performance (such as mobile phones, tablets, and smart TVs) and network conditions (5G, 4G, Wi-Fi), platforms need to transcode the same video source into transcoded videos corresponding to multiple transcoding levels to meet the video browsing needs of different users. Different encoding parameters need to be set for video transcoding at different transcoding levels. These encoding parameters can include various image transcoding processing configuration parameters, such as resolution, unsharpness, constant rate factor (CRF), blur intensity, and texture enhancement intensity. Because different combinations of encoding parameters have different effects on video bitrate and image quality in different scenarios, for example… Figure 3 As shown, for different Unsharp processing parameters, under the same encoding parameters (such as CRF), the bitrate and image quality of the transcoded video vary. For environments requiring high bitrate, processing parameter 1 is superior. For environments requiring low bitrate, processing parameter 2 is superior. Based on this, the optimal combination of encoding parameters needs to be determined according to the video content and video environment requirements.

[0046] In this embodiment of the disclosure, the optimal combination of encoding parameters differs due to the varying characteristics of different video content (such as animation, sports events, and movies). For example, animation can maintain good image quality at low bitrates, while high-speed motion scenes require higher bitrates. Therefore, it is necessary to acquire the video to be transcoded and analyze the source video content to determine its optimal combination of encoding parameters.

[0047] In this embodiment, it is also necessary to obtain the attribute parameter range of the target transcoded video. These attribute parameters may include parameters characterizing the attributes of the target transcoded video, such as bitrate parameters and image quality parameters. Typically, the corresponding attribute parameter range is determined based on the video transcoding level of the target transcoded video to ensure that the transcoded target video meets the playback requirements of the corresponding video transcoding level. For example, image quality parameters may include: smooth, standard definition, high definition, 4K, etc. Bitrate parameters may include: 5-10Mbps, 10-20Mbps, 50-100Mbps.

[0048] In an exemplary embodiment, multiple video transcoding levels corresponding to the target transcoded video are obtained. Based on the playback environment requirements of each video transcoding level, the attribute parameter range corresponding to each video transcoding level is determined. The attribute parameters of the target transcoded video generated based on the combination of encoding parameters should meet the attribute parameter range requirements of the corresponding video transcoding level.

[0049] In step S220, the transcoding result of the video to be transcoded under at least one set of encoding parameter combinations is predicted by a pre-trained video transcoding prediction model to obtain the attribute parameter prediction value corresponding to each of the encoding parameter combinations; the encoding parameter combination includes encoding parameter values ​​corresponding to at least one encoding parameter type.

[0050] In this embodiment of the disclosure, multiple candidate encoding parameters are pre-set. These candidate encoding parameters may include multiple different encoding parameter types and corresponding multiple different encoding parameter values. For example, resolution R = {1080P, 720P}; unsharp = {0.1, 0.2, 1.0}; CRF = {20, 21, ... 45}, etc. Multiple encoding parameter combinations are formed by iterating through and combining these multiple candidate encoding parameters. Each encoding parameter combination includes encoding parameter values ​​corresponding to the aforementioned encoding parameter types.

[0051] In this embodiment, a pre-trained video transcoding prediction model predicts the transcoding results of the video to be transcoded under the aforementioned multiple combinations of encoding parameters, obtaining predicted attribute parameter values ​​corresponding to each combination of encoding parameters. This pre-trained video transcoding prediction model is used to predict the transcoding results of the video content under different combinations of encoding parameters, thereby obtaining corresponding attribute parameter prediction results. Based on the attribute parameter prediction results corresponding to each combination of encoding parameters, the optimal combination of encoding parameters is determined.

[0052] In an exemplary embodiment, the attribute parameter prediction results obtained by the video transcoding prediction model described above are discrete, while the actual optimal parameters may exist among these discrete results. Therefore, based on the attribute parameter prediction results described above, we can further perform interpolation processing according to each combination of coding parameters and the corresponding predicted attribute parameter values, adding at least one set of interpolated coding parameter combinations and corresponding interpolated predicted attribute parameter values, thereby expanding the parameter candidate space to improve decision accuracy.

[0053] Specifically, the interpolation process first uses the discrete attribute parameter prediction results from the model (e.g., a bitrate of 500kbps when CRF=30, and a bitrate of 600kbps when CRF=31) to construct a continuous functional relationship between adjacent discrete points using a linear interpolation algorithm, thereby calculating the bitrate and image quality corresponding to any intermediate parameter value (e.g., a bitrate of 550kbps when CRF=30.5). This process is not only applicable to CRF but can also be extended to other coding parameters. Furthermore, the interpolation algorithm is not limited to the aforementioned linear interpolation; any possible interpolation algorithm, such as polynomial interpolation, can be used, and this disclosure makes no limitation. The continuous parameter space after interpolation can more accurately capture the optimal solution of the attribute parameters, thereby obtaining a better combination of coding parameters.

[0054] In step S230, the predicted values ​​of the attribute parameters of each combination of encoding parameters are filtered according to the attribute parameter range to obtain at least one set of candidate encoding parameter combinations.

[0055] In this embodiment of the disclosure, the predicted attribute parameter values ​​of the video transcoding prediction model are filtered according to the attribute parameter range corresponding to the target transcoded video, and the predicted attribute parameter values ​​that meet the requirement of the attribute parameter range are selected. The combination of encoding parameters corresponding to the filtered predicted attribute parameter values ​​is used as a candidate encoding parameter combination.

[0056] In step S240, the predicted values ​​of attribute parameters corresponding to each candidate coding parameter combination are compared based on a preset decision algorithm to determine the target coding parameter combination.

[0057] In this embodiment of the disclosure, the predicted attribute parameters corresponding to each of the selected candidate encoding parameter combinations are compared based on a pre-set decision algorithm to determine the optimal predicted attribute parameter value required for the target transcoded video playback scenario. The encoding parameter combination corresponding to the selected predicted attribute parameter value is determined as the target encoding parameter combination. Based on the encoding parameter values ​​of each encoding parameter type in the target encoding parameter combination, video transcoding processing is performed on the video to be transcoded to obtain the target transcoded video.

[0058] It should be noted that different application scenarios have different requirements for the video attributes of the target transcoded video. For example, some application scenarios require a high bitrate; some require a high image quality; and some require high bitrate stability between different transcoding levels (i.e., the bitrates at each level should be as close as possible). Therefore, a suitable decision algorithm can be determined based on the application scenario corresponding to the video to be transcoded. This disclosure does not limit the specific algorithmic method of this decision algorithm.

[0059] The video transcoding parameter determination method provided in this disclosure involves obtaining the video to be transcoded and the range of attribute parameters; predicting the transcoding result of the video under multiple encoding parameter combinations using a video transcoding prediction model; and comparing the predicted attribute parameter values ​​corresponding to each candidate encoding parameter combination based on a preset decision algorithm to determine the target encoding parameter combination. This method does not directly predict the encoding parameters, but first predicts the video attribute parameters under different encoding parameter combinations, and then selects the target encoding parameter combination that meets the transcoding requirements based on the decision algorithm. This prediction process does not require a large amount of repetitive transcoding and the decision algorithm can be flexibly adjusted as needed to determine the encoding parameters suitable for the application scenario.

[0060] Figure 4 This is based on an example of the training process for a video transcoding prediction model. Figure 1 .like Figure 4 As shown in the figure, the training process of the video transcoding prediction model in this embodiment includes the following steps.

[0061] In step S410, a training dataset including multiple video transcoding prediction training samples is obtained; each of the video transcoding prediction training samples includes at least: video samples.

[0062] In this embodiment of the disclosure, a training dataset comprising multiple video transcoding prediction training samples is obtained. Each video transcoding prediction training sample includes at least one video sample. The video sample includes sample types corresponding to various video content scenes, enabling the trained model to learn predictions for various video content.

[0063] In step S420, the video sample is transcoded based on the at least one set of encoding parameter combinations to obtain attribute parameter label values ​​corresponding to each of the encoding parameter combinations.

[0064] In this embodiment, the video sample is transcoded based on at least one set of encoding parameter combinations to obtain a corresponding transcoded video. The attribute parameter label values ​​corresponding to each encoding parameter combination are determined based on the transcoded video. These attribute parameter label values ​​are used as the ground truth values ​​for model training. The at least one set of encoding parameter combinations can be the multiple encoding parameter combinations formed by iterating through and combining multiple candidate encoding parameters as described in step S220 above, and will not be repeated here.

[0065] In step S430, the transcoding result of the video sample under the at least one set of encoding parameter combinations is predicted by the video transcoding prediction model to be trained, so as to obtain the attribute parameter training values ​​corresponding to each of the encoding parameter combinations.

[0066] In this embodiment of the disclosure, the transcoding result of the video sample under various combinations of encoding parameters is predicted by the video transcoding prediction model to be trained, thereby obtaining the attribute parameter training values ​​corresponding to each combination of encoding parameters. The model prediction process is similar to the model prediction process described in step S220 above, and will not be repeated here.

[0067] In step S440, a prediction loss value is generated based on the training values ​​of the attribute parameters and the label values ​​of the attribute parameters corresponding to each of the encoding parameter combinations.

[0068] In this embodiment of the disclosure, the training value of the attribute parameter is used as the predicted value, and the label value of the attribute parameter is used as the true value. A prediction loss value is generated based on the training value and label value of the attribute parameter corresponding to the same combination of encoding parameters. This prediction loss value is used to represent the degree of difference between the training value and the label value of the attribute parameter.

[0069] In step S450, the video transcoding prediction model to be trained is trained according to the predicted loss value to obtain the video transcoding prediction model.

[0070] In this embodiment of the disclosure, the video transcoding prediction model can be trained using the predicted loss value, so that the model's predicted value gets closer and closer to the label value. When the video transcoding prediction model meets the preset convergence condition, the parameter-adjusted video transcoding prediction model becomes the target video transcoding prediction model.

[0071] Figure 5 This is based on an example of the training process for a video transcoding prediction model. Figure 2 .

[0072] In this embodiment of the disclosure, Figure 5 Steps S510, S520, S540, and S550 in the training process of the video transcoding prediction model shown are respectively related to... Figure 4The steps S410, S420, S440 and S450 in the training process of the video transcoding prediction model shown correspond to each other and will not be repeated here.

[0073] In some exemplary embodiments, in Figure 4 Based on the training process of the video transcoding prediction model shown. Figure 5 The training process of the video transcoding prediction model shown may also include the following steps.

[0074] In step S531, the video sample is subjected to feature extraction by at least one video feature extraction module to obtain at least one video feature.

[0075] In this embodiment of the disclosure, to improve the accuracy of the video transcoding prediction model in predicting transcoding results, at least one video feature extraction module is used to extract features from the video sample to obtain at least one video feature. This video feature can be any video feature related to the video sample. For example, video complexity features (such as spatiotemporal information content, motion vector amplitude, inter-frame differences, texture complexity, etc.) are used to quantify the encoding difficulty of the video content; image quality features (such as objective indicators like PSNR, SSIM, VMAF, etc., and subjective influencing factors like noise level and blur) are used to evaluate the basic visual quality of the video; scene features (such as scene switching frequency, camera movement type, content category such as animation / sports / film, etc.) are used to identify the structural and semantic characteristics of the video.

[0076] In step S533, the video transcoding prediction model to be trained predicts the transcoding result of the video sample under the at least one set of encoding parameter combinations based on the at least one video feature, thereby obtaining the attribute parameter training values ​​corresponding to each of the encoding parameter combinations.

[0077] In this embodiment of the disclosure, based on the aforementioned step S430, the video transcoding prediction model also refers to at least one of the extracted video features during the prediction of the transcoding result, so that the video transcoding prediction model can refer to more information, thereby improving the accuracy of the prediction of the transcoding result. This model prediction process is similar to the model prediction process described in step S430, and will not be repeated here.

[0078] In some exemplary embodiments, in Figure 4 Based on the training process of the video transcoding prediction model shown. Figure 5 The training process of the video transcoding prediction model shown may also include the following steps.

[0079] In step S532, the video sample is pre-encoded to obtain at least one pre-encoded feature.

[0080] In this embodiment of the disclosure, to improve the accuracy of the video transcoding prediction model in predicting transcoding results, a fast and lightweight precoding process can be performed on the video sample to extract at least one precoding feature from the precoding process. These precoding features can deeply reflect the coding characteristics of the video sample during the coding process, thereby providing reference information for model prediction. For example, coding cost features (such as the cost of intra / inter-frame prediction modes, motion estimation residuals, transform coefficient energy distribution, etc.) directly reflect the applicability of different coding modes to the video sample; coding mode decision results (such as CU partitioning depth distribution, frame type distribution, etc.) reflect the spatial and temporal redundancy characteristics of the video content; precoding attribute parameters (such as estimated bitrate, estimated image quality, QP value fluctuation, etc.) provide a reference benchmark for subsequent coding attribute prediction.

[0081] In step S533, the video transcoding prediction model to be trained predicts the transcoding result of the video sample under the at least one set of coding parameter combinations based on the at least one precoding feature, thereby obtaining the attribute parameter training values ​​corresponding to each of the coding parameter combinations.

[0082] In this embodiment of the disclosure, based on the aforementioned step S430, the video transcoding prediction model also references at least one precoding feature obtained above during the prediction of the transcoding result, so that the video transcoding prediction model can refer to more information, thereby improving the accuracy of the prediction of the transcoding result. This model prediction process is similar to the model prediction process described in step S430 above, and will not be repeated here.

[0083] In some exemplary embodiments, in Figure 4 Based on the training process of the video transcoding prediction model shown. Figure 5 The training process of the video transcoding prediction model shown may also include the following steps.

[0084] In step S531, the video sample is subjected to feature extraction by at least one video feature extraction module to obtain at least one video feature.

[0085] In step S532, the video sample is pre-encoded to obtain at least one pre-encoded feature.

[0086] In step S533, the video transcoding prediction model to be trained predicts the transcoding result of the video sample under the at least one set of coding parameter combinations based on the at least one video feature and the at least one precoding feature, thereby obtaining the attribute parameter training values ​​corresponding to each of the coding parameter combinations.

[0087] In this embodiment, the relevant feature extraction and model prediction processes are similar to those in the previous embodiments, and will not be repeated here.

[0088] The video transcoding parameter determination method provided in this disclosure, by training a video transcoding prediction model, enables the model to learn the ability to predict transcoding results for different videos under different combinations of encoding parameters, thereby enabling accurate prediction of video attribute parameters for various videos. Furthermore, by introducing video features extracted by a video feature extraction module and pre-encoded features obtained from pre-encoding, the accuracy of the video transcoding prediction model in predicting transcoding results is further improved.

[0089] Figure 6 This is a flowchart illustrating a decision-making process based on a combination of target encoding parameters, as shown in the example. Figure 6 As shown in the present embodiment, the aforementioned step S240 may include the following steps.

[0090] In step S610, the bitrate parameter and image quality parameter corresponding to each candidate encoding parameter combination are obtained.

[0091] In this embodiment of the disclosure, the attribute parameters may include: bitrate parameters and image quality parameters. The transcoding results for each candidate encoding parameter combination are predicted using the video transcoding prediction model to obtain the predicted attribute parameter values ​​corresponding to each candidate encoding parameter combination. That is, the bitrate parameters and image quality parameters corresponding to each candidate encoding parameter combination are obtained.

[0092] In an exemplary embodiment, the predicted bitrate parameter and image quality parameter are B_a and Q_a corresponding to candidate coding parameter combination a; the predicted bitrate parameter and image quality parameter are B_b and Q_b corresponding to candidate coding parameter combination b; and the predicted bitrate parameter and image quality parameter are B_c and Q_c corresponding to candidate coding parameter combination c.

[0093] In step S620, the rate-distortion cost corresponding to each candidate coding parameter combination is calculated based on the bitrate parameter and the image quality parameter.

[0094] In this embodiment, Rate-Distortion Cost (RD cost) is a distortion metric used in video coding to measure the relationship between bitrate and image quality. Therefore, the decision algorithm can select coding parameter combinations based on the RD cost corresponding to each chosen combination. Specifically, the RD cost calculation can be expressed as: RD_cost(i) = RD_cost(B_i, Q_i).

[0095] In an exemplary embodiment, the rate-distortion costs corresponding to each of the above candidate coding parameter combinations can be calculated as RD_cost(a), RD_cost(b), and RD_cost(c).

[0096] In an exemplary embodiment, different video transcoding levels have varying requirements for bitrate and image quality parameters. For example, lower transcoding levels require higher bitrates, while higher transcoding levels require higher image quality. Therefore, to better compare and evaluate the predicted values ​​of various attribute parameters, a rate-distortion hyperparameter lambda is introduced into the rate-distortion cost calculation. The corresponding rate-distortion hyperparameter lambda is determined based on the video transcoding level corresponding to the target transcoded video. This rate-distortion hyperparameter lambda serves as the weight between the bitrate and image quality parameters during the rate-distortion cost calculation. Based on the rate-distortion hyperparameter, bitrate, and image quality parameters, the rate-distortion cost corresponding to each candidate encoding parameter combination is calculated. By introducing this rate-distortion hyperparameter lambda, the requirements of different video transcoding levels can be better adapted.

[0097] In step S630, the target coding parameter combination is determined based on comparing the rate-distortion cost corresponding to each of the candidate coding parameter combinations.

[0098] In this embodiment of the disclosure, the target coding parameter combination is determined by comparing the rate-distortion arithmetic values ​​corresponding to each candidate coding parameter combination. Specifically, the candidate coding parameter combination corresponding to the minimum rate-distortion arithmetic value among the various candidate coding parameter combinations can be determined as the target coding parameter combination.

[0099] The video transcoding parameter determination method provided in this disclosure utilizes the characteristic of rate-distortion cost as a distortion index to measure the relationship between bitrate and image quality. Based on comparing the rate-distortion cost values ​​corresponding to various candidate coding parameter combinations as a decision algorithm, it fully balances the bitrate and image quality attributes of the transcoded video. Furthermore, to meet the different requirements for bitrate and image quality at different video transcoding levels, a rate-distortion hyperparameter is introduced during the rate-distortion cost calculation process, thereby better adapting to the changing needs of different video transcoding levels.

[0100] Figure 7 This is a flowchart illustrating the video transcoding bit merging / addition process, as shown in the example. Figure 7 As shown in the embodiments of this disclosure, the method for determining the encoding parameters of video transcoding may further include the following steps.

[0101] In step S710, the similarity of attribute parameters among the predicted attribute parameter values ​​of each of the video transcoding levels under the target encoding parameter combination is compared.

[0102] In this embodiment of the disclosure, after determining the target encoding parameter combination corresponding to each video transcoding level, the predicted values ​​of the attribute parameters for each video transcoding level can be compared. For example, if the predicted values ​​of the attribute parameters for some video transcoding levels are relatively close (i.e., the effects of the two target transcoded videos are relatively similar), their target encoding parameter combinations can be merged, thereby skipping one of the video transcoding processes and saving related processing overhead. As another example, if the predicted values ​​of the attribute parameters for some video transcoding levels differ significantly, it is possible to consider adding a video transcoding level between the two video transcoding levels to make the transition between each video transcoding level smoother, providing users with a wider selection of video transcoding levels.

[0103] Based on this, the similarity of attribute parameters between the predicted attribute parameter values ​​for each video transcoding bit is calculated under the target encoding parameter combination. This similarity represents the degree of difference between the predicted attribute parameter values ​​corresponding to two video transcoding bits.

[0104] In step S720, in response to the similarity of the attribute parameters being less than a first similarity threshold, the target encoding parameter combinations corresponding to the two video transcoding levels are merged.

[0105] In this embodiment of the disclosure, when the similarity of the attribute parameter is less than a first similarity threshold, it indicates that the effects of the two target transcoded videos are relatively similar. Therefore, the target encoding parameter combinations corresponding to the two video transcoding levels can be merged, thereby skipping the transcoding process of one of the videos. This disclosure does not limit the relevant merging selection method.

[0106] In step S730, in response to the similarity of the attribute parameters being greater than the second similarity threshold, a video transcoding level is added between the corresponding two video transcoding levels.

[0107] In this embodiment of the disclosure, when the similarity of the attribute parameter is greater than a second similarity threshold, a new video transcoding level is added between the two corresponding video transcoding levels. The target encoding parameter combination for the added video transcoding level is between the target encoding parameter combinations of the two video transcoding levels, so that the attribute parameters of the target transcoded video corresponding to the added video transcoding level are between the target transcoded videos of the two video transcoding levels, thereby making the transition between each video transcoding level smoother and providing users with a wider selection of video transcoding levels.

[0108] The video transcoding parameter determination method provided in this disclosure compares the similarity of attribute parameters between the predicted attribute parameter values ​​corresponding to each video transcoding level, merges or adds video transcoding levels, thereby saving related processing overhead and making the transition between each video transcoding level smoother, providing users with a richer selection of video transcoding levels.

[0109] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0110] Figure 8 This is a block diagram illustrating a video transcoding parameter determination apparatus according to an exemplary embodiment. (Refer to...) Figure 8 The device 800 may include: a video acquisition module 810, an attribute parameter prediction module 820, an encoding parameter combination filtering module 830, and an encoding parameter combination determination module 840.

[0111] The video acquisition module 810 is configured to acquire the attribute parameter range of the video to be transcoded and the target video to be transcoded.

[0112] The attribute parameter prediction module 820 is configured to predict the transcoding result of the video to be transcoded under at least one set of encoding parameter combinations using a pre-trained video transcoding prediction model, and obtain attribute parameter prediction values ​​corresponding to each of the encoding parameter combinations; the encoding parameter combinations include encoding parameter values ​​corresponding to at least one encoding parameter type.

[0113] The encoding parameter combination filtering module 830 is configured to filter the predicted values ​​of the attribute parameters of each encoding parameter combination according to the attribute parameter range, so as to obtain at least one set of candidate encoding parameter combinations.

[0114] The encoding parameter combination determination module 840 is configured to compare the predicted values ​​of attribute parameters corresponding to each candidate encoding parameter combination based on a preset decision algorithm to determine the target encoding parameter combination.

[0115] In some exemplary embodiments of this disclosure, the video acquisition module 810 is further configured to acquire at least one video transcoding level of the target transcoded video; and determine the range of attribute parameters corresponding to each video transcoding level based on the video transcoding level.

[0116] In some exemplary embodiments of this disclosure, the attribute parameters include at least: bitrate parameters and image quality parameters.

[0117] In some exemplary embodiments of this disclosure, the training process of the video transcoding prediction model includes: acquiring a training dataset comprising multiple video transcoding prediction training samples; each video transcoding prediction training sample comprising at least one video sample; performing video transcoding processing on the video sample based on the at least one set of encoding parameter combinations to obtain attribute parameter label values ​​corresponding to each of the encoding parameter combinations; predicting the transcoding result of the video sample under the at least one set of encoding parameter combinations using the video transcoding prediction model to be trained to obtain attribute parameter training values ​​corresponding to each of the encoding parameter combinations; generating a prediction loss value based on the attribute parameter training values ​​and attribute parameter label values ​​corresponding to each of the encoding parameter combinations; and training the video transcoding prediction model to be trained based on the prediction loss value to obtain the video transcoding prediction model.

[0118] In some exemplary embodiments of this disclosure, the training process of the video transcoding prediction model further includes: extracting features from the video sample using at least one video feature extraction module to obtain at least one video feature; and using the video transcoding prediction model to be trained to predict the transcoding result of the video sample under the at least one set of encoding parameter combinations based on the at least one video feature to obtain the attribute parameter training value corresponding to each of the encoding parameter combinations.

[0119] In some exemplary embodiments of this disclosure, the training process of the video transcoding prediction model further includes: precoding the video sample to obtain at least one precoded feature; and using the video transcoding prediction model to be trained to predict the transcoding result of the video sample under the at least one set of encoding parameter combinations based on the at least one video feature and / or the at least one precoded feature, to obtain the attribute parameter training value corresponding to each of the encoding parameter combinations.

[0120] In some exemplary embodiments of this disclosure, the encoding parameter combination determination module 840 is further configured to determine the decision algorithm based on the application scenario corresponding to the video to be transcoded.

[0121] In some exemplary embodiments of this disclosure, the encoding parameter combination determination module 840 is further configured to obtain the bitrate parameter and image quality parameter corresponding to each of the candidate encoding parameter combinations; calculate the rate-distortion cost corresponding to each of the candidate encoding parameter combinations based on the bitrate parameter and image quality parameter; and determine the target encoding parameter combination based on comparing the rate-distortion cost corresponding to each of the candidate encoding parameter combinations.

[0122] In some exemplary embodiments of this disclosure, the encoding parameter combination determination module 840 is further configured to determine the corresponding rate-distortion hyperparameter based on the video transcoding level corresponding to the target transcoded video; and to calculate the rate-distortion cost corresponding to each candidate encoding parameter combination based on the rate-distortion hyperparameter, bitrate parameter, and image quality parameter.

[0123] In some exemplary embodiments of this disclosure, the attribute parameter prediction module 820 is further configured to perform interpolation processing based on each of the said encoding parameter combinations and the corresponding attribute parameter prediction values, thereby adding at least one set of interpolation encoding parameter combinations and the corresponding interpolation attribute parameter prediction values.

[0124] In some exemplary embodiments of this disclosure, the encoding parameter combination determination module 840 is further configured to compare the attribute parameter similarity between the attribute parameter prediction values ​​of each of the video transcoding levels under the target encoding parameter combination; merge the target encoding parameter combinations corresponding to two video transcoding levels in response to the attribute parameter similarity being less than a first similarity threshold; and add a video transcoding level between the corresponding two video transcoding levels in response to the attribute parameter similarity being greater than a second similarity threshold.

[0125] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0126] The following reference Figure 9 To describe an electronic device 900 according to such an embodiment of the present disclosure. Figure 9 The electronic device 900 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0127] like Figure 9 As shown, the electronic device 900 is presented in the form of a general-purpose computing device. The components of the electronic device 900 may include, but are not limited to: at least one processing unit 910, at least one storage unit 920, a bus 930 connecting different system components (including storage unit 920 and processing unit 910), and a display unit 940.

[0128] The storage unit stores program code, which can be executed by the processing unit 910 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 910 can perform actions such as... Figure 2 The steps shown.

[0129] For example, electronic devices can achieve such Figure 2 The steps shown.

[0130] Storage unit 920 may include readable media in the form of volatile storage units, such as random access memory (RAM) 921 and / or cache memory 922, and may further include read-only memory (ROM) 923.

[0131] The storage unit 920 may also include a program / utility 924 having a set (at least one) of program modules 925, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0132] Bus 930 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0133] Electronic device 900 can also communicate with one or more external devices 970 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 900, and / or with any device that enables electronic device 900 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 950. Furthermore, electronic device 900 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 960. As shown, network adapter 960 communicates with other modules of electronic device 900 via bus 930. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0134] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0135] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory including instructions that can be executed by a processor of the device to perform the described method. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0136] In an exemplary embodiment, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods described above.

[0137] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0138] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for determining encoding parameters for video transcoding, characterized in that, include: Get the attribute parameter range of the video to be transcoded and the target video to be transcoded; The transcoding result of the video to be transcoded is predicted by a pre-trained video transcoding prediction model under at least one set of encoding parameter combinations, and the predicted attribute parameter values ​​corresponding to each of the encoding parameter combinations are obtained; the encoding parameter combinations include encoding parameter values ​​corresponding to at least one encoding parameter type. Based on the range of attribute parameters, the predicted values ​​of the attribute parameters for each combination of coding parameters are filtered to obtain at least one set of candidate coding parameter combinations. The target coding parameter combination is determined by comparing the predicted values ​​of the attribute parameters corresponding to each candidate coding parameter combination based on a preset decision algorithm.

2. The method according to claim 1, characterized in that, The range of attribute parameters for obtaining the video to be transcoded and the target video to be transcoded also includes: Obtain at least one video transcoding bit of the target transcoded video; Based on the video transcoding level, determine the range of attribute parameters corresponding to each video transcoding level.

3. The method according to claim 1, characterized in that, The attribute parameters include at least: bitrate parameters and image quality parameters.

4. The method according to claim 1, characterized in that, The training process of the video transcoding prediction model includes: Obtain a training dataset comprising multiple video transcoding prediction training samples; each of the video transcoding prediction training samples includes at least: a video sample; Based on the at least one set of encoding parameter combinations, the video sample is transcoded to obtain attribute parameter label values ​​corresponding to each of the encoding parameter combinations; The video transcoding prediction model to be trained is used to predict the transcoding result of the video sample under the at least one set of encoding parameter combinations, so as to obtain the attribute parameter training values ​​corresponding to each of the encoding parameter combinations. Based on the training values ​​of the attribute parameters and the label values ​​of the attribute parameters corresponding to each of the aforementioned encoding parameter combinations, a prediction loss value is generated; The video transcoding prediction model is trained based on the predicted loss value to obtain the video transcoding prediction model.

5. The method according to claim 4, characterized in that, The training process of the video transcoding prediction model also includes: At least one video feature is obtained by extracting features from the video sample using at least one video feature extraction module. The video transcoding prediction model to be trained predicts the transcoding result of the video sample under the at least one set of encoding parameter combinations based on the at least one video feature, thereby obtaining the attribute parameter training values ​​corresponding to each of the encoding parameter combinations.

6. The method according to claim 4 or 5, characterized in that, The training process of the video transcoding prediction model also includes: The video samples are pre-encoded to obtain at least one pre-encoded feature; The video transcoding prediction model to be trained predicts the transcoding result of the video sample under the at least one set of coding parameter combinations based on the at least one video feature and / or the at least one precoding feature, thereby obtaining the attribute parameter training values ​​corresponding to each of the coding parameter combinations.

7. The method according to claim 1, characterized in that, The method further includes: The decision algorithm is determined based on the application scenario corresponding to the video to be transcoded.

8. The method according to claim 3, characterized in that, The step of comparing the predicted attribute parameter values ​​corresponding to each candidate coding parameter combination based on a preset decision algorithm to determine the target coding parameter combination includes: Obtain the bitrate parameter and image quality parameter corresponding to each of the candidate encoding parameter combinations; Based on the bitrate parameter and image quality parameter, calculate the rate-distortion cost corresponding to each of the candidate coding parameter combinations; The target coding parameter combination is determined by comparing the rate-distortion cost corresponding to each of the candidate coding parameter combinations.

9. The method according to claim 8, characterized in that, The step of calculating the rate-distortion cost corresponding to each candidate coding parameter combination based on the bitrate parameter and image quality parameter includes: Determine the corresponding rate-distortion hyperparameter based on the video transcoding level corresponding to the target transcoded video; Based on the rate-distortion hyperparameter, bitrate parameter, and image quality parameter, calculate the rate-distortion cost corresponding to each of the candidate coding parameter combinations.

10. The method according to claim 1, characterized in that, The method further includes: Interpolation is performed based on each of the aforementioned coding parameter combinations and the corresponding predicted attribute parameter values, thereby adding at least one set of interpolation coding parameter combinations and the corresponding predicted interpolation attribute parameter values.

11. The method according to claim 2, characterized in that, The method further includes: Compare the attribute parameter similarity among the predicted attribute parameter values ​​for each of the video transcoding levels under the target encoding parameter combination; In response to the similarity of the attribute parameters being less than a first similarity threshold, the target encoding parameter combinations corresponding to the two video transcoding levels are merged; In response to the similarity of the attribute parameters being greater than the second similarity threshold, a new video transcoding level is added between the two corresponding video transcoding levels.

12. A device for determining encoding parameters for video transcoding, characterized in that, include: The video acquisition module is configured to acquire the attribute parameter range of the video to be transcoded and the target video to be transcoded; The attribute parameter prediction module is configured to predict the transcoding result of the video to be transcoded under at least one set of encoding parameter combinations using a pre-trained video transcoding prediction model, and obtain the attribute parameter prediction value corresponding to each of the encoding parameter combinations; the encoding parameter combination includes encoding parameter values ​​corresponding to at least one encoding parameter type. The encoding parameter combination filtering module is configured to filter the predicted values ​​of the attribute parameters of each encoding parameter combination according to the attribute parameter range, so as to obtain at least one set of candidate encoding parameter combinations. The encoding parameter combination determination module is configured to compare the predicted values ​​of attribute parameters corresponding to each candidate encoding parameter combination based on a preset decision algorithm to determine the target encoding parameter combination.

13. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the executable instructions to implement the video transcoding parameter determination method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform a video transcoding parameter determination method as described in any one of claims 1 to 11.

15. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the method for determining encoding parameters for video transcoding as described in any one of claims 1 to 11.

Images