Video color space optimization enhancement system and method based on artificial intelligence

Abstract

The invention discloses a video color space optimization enhancement system and method based on artificial intelligence, and relates to the field of video color space enhancement. Video parameters in the process are adjusted from the setting angle of parameters such as the original brightness, contrast and color of a video in the process of color space enhancement of the video, so that the video color space is enhanced. The effect of the enhanced video is better; according to the method, a plurality of video quality grades are set, so that quantitative evaluation data are provided for subsequently evaluating the quality of the video; a judgment tool is provided for judging the quality grade of the video by constructing a final video quality grade mapping model; multiple iterations are simultaneously carried out on multiple parameters of the enhanced video by adopting a dogvessel optimization algorithm, and the quality level of the enhanced video is taken as a fitness function; therefore, along with iteration, the quality level of the enhanced video is higher and higher, and the requirements are finally met.

Description

Technical Field

[0001] The present invention belongs to the field of video color space enhancement. Specifically, it particularly relates to a video color space optimization and enhancement system and method based on artificial intelligence. Background Art

[0002] Video color space optimization and enhancement refers to adjusting video color parameters such as brightness, contrast, saturation, hue, etc. to improve the visual effect and quality of the video. However, if no parameter adjustment is performed during the video color space optimization and enhancement process, it may lead to color deviation when the video is displayed on different devices, inability to accurately restore the original color, and problems such as color overflow or undersaturation, affecting the visual effect of the video. Moreover, it may cause the contrast and brightness of the video not to meet expectations, making the picture too dark or too bright, affecting the viewing experience, and losing details in the dark or highlight parts, reducing the quality of the video. Summary of the Invention

[0003] Aiming at the problems in the related art, the present invention proposes a video color space optimization and enhancement system and method based on artificial intelligence to overcome the above-mentioned technical problems existing in the existing related technologies.

[0004] To solve the above technical problems, the present invention is realized through the following technical solutions:

[0005] The present invention is a video color space optimization and enhancement method based on artificial intelligence, including the following steps:

[0006] S1. Set several video quality levels to obtain a video quality level set; then collect several existing video samples and corresponding video quality level data to obtain an existing video sample set and an existing video quality level data set;

[0007] S2. Use the existing video sample set and the existing video quality level data set to construct a final video quality level mapping model;

[0008] S3. Perform color space enhancement operations on the video to be enhanced to obtain an enhanced video; use the final video quality level mapping model to map the enhanced video to obtain the quality level of the video to be enhanced; adjust the parameters of the enhanced video according to the quality level of the video to be enhanced to obtain a final enhanced video;

[0009] In this solution, the video parameters during the process are adjusted from the perspective of setting parameters such as the original brightness, contrast, and color of the video during the process of enhancing the color space of the video, so that the enhanced video has a better effect; among them, by setting several video quality levels, quantitative evaluation data is provided for subsequent evaluation of the video quality; by constructing a final video quality level mapping model, a determination tool is provided for determining the video quality level.

[0010] Preferably, S1 includes the following steps:

[0011] S11. Set several video quality levels to obtain a video quality level set;

[0012] S12. Collect several existing video samples to obtain an existing video sample set; in cooperation with the video quality level set, obtain the evaluation of the video quality level of each existing video sample in the existing video sample set by professionals to obtain an existing video quality level data set.

[0013] By collecting several existing video samples and their corresponding video quality levels, data support is provided for subsequent construction of a final video quality level mapping model.

[0014] Preferably, S2 includes the following steps:

[0015] S21. Construct an initial video quality level mapping model;

[0016] S22. Use the existing video sample set and the existing video quality level data set to train and test the initial video quality level mapping model to obtain a final video quality level mapping model; the initial video quality level mapping model is preferably a CNN neural network model.

[0017] Preferably, S22 includes the following steps:

[0018] S221. Set a training data ratio; according to the training data ratio, divide the existing video sample set and the existing video quality level data set to obtain an existing video training sample set, an existing video quality level training data set, an existing video test sample set, and an existing video quality level test data set.

[0019] S222. Set a training error threshold; input the existing video training sample set and the existing video quality level training data set as training data and training labels into the initial video quality level mapping model for training; during the training process, when the training error is less than the training error threshold, stop training to obtain a trained video quality level mapping model; otherwise, continue training until the training error is less than the training error threshold.

[0020] S223. Set the test accuracy rate threshold; use the existing video test sample set and the existing video quality level test data set as test data and test labels respectively, and input them into the trained video quality level mapping model for testing; after the testing is completed, obtain the test accuracy rate data; when the test accuracy rate data is greater than or equal to the test accuracy rate threshold, use the trained video quality level mapping model as the final video quality level mapping model; otherwise, return to S222 to continue training the trained video quality level mapping model until the test accuracy rate data is greater than or equal to the test accuracy rate threshold.

[0021] Preferably, S3 includes the following steps:

[0022] S31. Set the video to be enhanced; perform color space enhancement operations on the video to be enhanced to obtain the enhanced video; input the enhanced video into the final video quality level mapping model for mapping to obtain the quality level of the video to be enhanced.

[0023] S32. Adjust the parameters of the enhanced video according to the quality level of the video to be enhanced to obtain the final enhanced video.

[0024] By mapping the enhanced video, it can be determined whether the enhancement effect meets the requirements before the video parameters are adjusted, thus providing a determination basis for determining whether parameter adjustment is required.

[0025] Preferably, the color space enhancement operation on the video to be enhanced in S31 includes the following steps:

[0026] S311. Set several types of video parameters to obtain a video parameter type set; input the video to be enhanced into video processing software for color space enhancement to obtain the enhanced video.

[0027] Preferably, S32 includes the following steps:

[0028] S321. Set the video quality level threshold; when the quality level of the video to be enhanced is greater than or equal to the video quality level threshold, use the enhanced video as the final enhanced video.

[0029] Otherwise, in cooperation with the video parameter type set, adjust the parameters of the enhanced video until the quality level of the second video to be enhanced is greater than or equal to the video quality level threshold.

[0030] By setting the video quality level threshold, a quantitative determination basis is provided for determining whether the quality of the enhanced video meets the requirements in the subsequent stage.

[0031] Preferably, adjusting the parameters of the enhanced video in S321 includes the following steps:

[0032] S3211. Construct a salp swarm a for video parameter adjustment = {a 1 ,..., a i ,..., a a′}, where a i represents the i-th salp in the salp swarm for video parameter adjustment, and a' represents the size of the salp swarm for video parameter adjustment; set the maximum number of iterations of the salp swarm for video parameter adjustment to be and the current number of iterations to be , which are respectively denoted as the maximum number of iterations for parameter adjustment and the current number of iterations for parameter adjustment;

[0033] S3212. In coordination with the video parameter type set, set the value range of each parameter of the enhanced video to obtain an enhanced video parameter value range set respectively represent the lower limit and upper limit of the value of the i-th type of parameter of the enhanced video, and b represents the total number of set video parameter types; set the initial position of each salp in the salp swarm for video parameter adjustment according to the enhanced video parameter value range set to obtain an initial position matrix b'; as follows,

[0034]

[0035] where b j ′ i represents the position component of the initial position of the j-th salp in the salp swarm for video parameter adjustment in the dimension of the i-th type of video parameter; the generation formula is as follows,

[0036]

[0037] In the formula, rand ji represents a random number between 0 and 1 generated for b j ′ i ;

[0038] S3213. Set the fitness function of the salp swarm for video parameter adjustment as follows,

[0039]

[0040] In the formula, represents the video quality level data of the enhanced video after applying a set of video parameters updated in each iteration process to the enhanced video;

[0041] S3214. Start the iteration. Before the iteration, set the current iteration number of parameter adjustment to 1. During the first-round iteration, use the fitness function of the video parameter-adjusted salp swarm to calculate the fitness values of the initial positions of each salp in the initial position matrix, obtaining the first fitness value set. Take the maximum fitness value in the first fitness value set and the corresponding initial position of the salp as the first global best fitness and the first global best position respectively. Update the initial positions of each salp in the initial position matrix according to the first global best fitness and the first global best position. After the update is completed, increment the current iteration number of parameter adjustment by 1 and enter the next round of iteration.

[0042] During each subsequent round of iteration, use the fitness function of the video parameter-adjusted salp swarm to calculate the fitness values of the positions of each salp in the video parameter-adjusted salp swarm updated in the previous round of iteration, obtaining the second fitness value set. Take the maximum fitness value in the second fitness value set and the corresponding position of the salp as the second global best fitness and the second global best position respectively. Update the positions of each salp in the video parameter-adjusted salp swarm updated in the previous round of iteration according to the second global best fitness and the second global best position. After the update is completed, increment the current iteration number of parameter adjustment by 1 and enter the next round of iteration.

[0043] S3215. When holds, stop the iteration to obtain the final global best position and the final global best fitness; otherwise, continue the iteration until holds. Take the final global best fitness as the quality level of the video to be enhanced after optimization. When the quality level of the video to be enhanced after optimization is greater than or equal to the video quality level threshold, apply each position component of the final global best position to the enhanced video to obtain the final enhanced video; otherwise, return to S3214 to continue the iteration until the quality level of the video to be enhanced after optimization is greater than or equal to the video quality level threshold.

[0044] In the initial stage of the salp swarm optimization algorithm, the coefficient in the leader position update formula is relatively large. The salps will explore and develop in the area where the food source may exist as much as possible, with strong global search ability, and can find the optimal solution within a large range. In the later stage of the algorithm, the coefficient gradually decreases, and the salps will conduct more refined searches near the food source, which is conducive to improving the accuracy of the solution and better finding the local optimal solution. It can quickly converge to a better solution within a relatively small number of iterations, improving the efficiency of the algorithm. It has good adaptability to different types of optimization problems and objective functions. When dealing with complex non-linear and multi-modal problems, it can show good performance and is not easily trapped in local optimal solutions. Based on the above advantages, in this solution, the salp swarm optimization algorithm is used to perform multiple iterations on multiple parameters of the enhanced video simultaneously, and the quality level of the enhanced video is used as the fitness function. Therefore, as the iteration progresses, the quality level of the enhanced video becomes higher and higher, and finally meets the requirements.

[0045] A video color space optimization and enhancement system based on artificial intelligence, including a video quality level setting module, a sample data acquisition module, a video quality level mapping model construction module, a color space enhancement module, a mapping module, and an enhanced parameter adjustment module;

[0046] The video quality level setting module is used to set several video quality levels to obtain a video quality level set;

[0047] The sample data acquisition module is used to collect several existing video samples and corresponding video quality level data to obtain an existing video sample set and an existing video quality level data set;

[0048] The video quality level mapping model construction module is used to construct a final video quality level mapping model by using the existing video sample set and the existing video quality level data set;

[0049] The color space enhancement module is used to perform color space enhancement operations on the video to be enhanced according to the video quality level to be enhanced to obtain an enhanced video;

[0050] The mapping module is used to map the enhanced video by using the final video quality level mapping model to obtain the video quality level to be enhanced;

[0051] The enhanced parameter adjustment module is used to adjust the parameters of the enhanced video according to the video quality level to be enhanced to obtain a final enhanced video.

[0052] The present invention has the following beneficial effects:

[0053] 1. In the present invention, by adjusting the video parameters during the process of enhancing the color space of the video from the perspective of setting parameters such as the original brightness, contrast, and color of the video, the effect of the enhanced video is better; among them, by setting several video quality levels, quantitative evaluation data is provided for subsequent evaluation of the video quality; by constructing a final video quality level mapping model, a determination tool is provided for determining the quality level of the video.

[0054] 2. In the present invention, by mapping the enhanced video, it can be determined whether the enhancement effect meets the requirements before the video parameters are adjusted, thereby providing a determination basis for determining whether parameter adjustment is required.

[0055] 3. In the present invention, the salp swarm optimization algorithm is used to perform multiple iterations on multiple parameters of the enhanced video simultaneously, and the quality level of the enhanced video is used as the fitness function; therefore, as the iteration progresses, the quality level of the enhanced video becomes higher and higher and finally meets the requirements.

[0056] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the following will briefly introduce the drawings required for describing the embodiments. Obviously, the drawings in the following description are only some embodiments of the invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0058] Figure 1 It is a schematic flowchart of a method for optimizing and enhancing the video color space based on artificial intelligence according to the present invention;

[0059] Figure 2 It is a schematic diagram of the modules of a system for optimizing and enhancing the video color space based on artificial intelligence according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the invention with reference to the drawings in the embodiments of the invention. Obviously, the described embodiments are only some embodiments of the invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the invention without creative efforts belong to the scope of protection of the invention.

[0061] Embodiment 1

[0062] Please refer to Figure 1 , this embodiment is a method for optimizing and enhancing the video color space based on artificial intelligence, including the following steps:

[0063] S1. Set several video quality levels to obtain a video quality level set; then collect several existing video samples and the corresponding video quality level data to obtain an existing video sample set and an existing video quality level data set;

[0064] The S1 includes the following steps:

[0065] S11. Set several video quality levels to obtain a video quality level set; the video quality levels in the video quality level set are natural numbers, and the higher the video quality level value, the higher the quality of the video; for example, 1: poor quality; 2: bad; 3: average; 4: good; and 5: excellent, etc.;

[0066] S12. Collect several existing video samples to obtain an existing video sample set; in combination with the video quality level set, obtain the evaluation of the video quality level of each existing video sample in the existing video sample set by professionals to obtain an existing video quality level data set;

[0067] S2. Construct a final video quality level mapping model by using the existing video sample set and the existing video quality level data set;

[0068] The S2 includes the following steps:

[0069] S21. Construct an initial video quality level mapping model;

[0070] S22. Train and test the initial video quality level mapping model by using the existing video sample set and the existing video quality level data set to obtain a final video quality level mapping model; the initial video quality level mapping model is preferably a CNN neural network model;

[0071] The S22 includes the following steps:

[0072] S221. Set a training data ratio; divide the existing video sample set and the existing video quality level data set according to the training data ratio to obtain an existing video training sample set, an existing video quality level training data set, an existing video test sample set, and an existing video quality level test data set;

[0073] S222. Set a training error threshold; input the existing video training sample set and the existing video quality level training data set as training data and training labels into the initial video quality level mapping model for training; during the training process, when the training error is less than the training error threshold, stop training to obtain a trained video quality level mapping model; otherwise, continue training until the training error is less than the training error threshold;

[0074] S223. Set the test accuracy threshold; use the existing video test sample set and the existing video quality level test data set as test data and test labels respectively, and input them into the trained video quality level mapping model for testing; after the testing is completed, obtain the test accuracy data; when the test accuracy data is greater than or equal to the test accuracy threshold, use the trained video quality level mapping model as the final video quality level mapping model; otherwise, return to S222 to continue training the trained video quality level mapping model until the test accuracy data is greater than or equal to the test accuracy threshold.

[0075] S3. Perform color space enhancement operations on the video to be enhanced to obtain the enhanced video; use the final video quality level mapping model to map the enhanced video to obtain the quality level of the video to be enhanced; adjust the parameters of the enhanced video according to the quality level of the video to be enhanced to obtain the final enhanced video.

[0076] S3 includes the following steps:

[0077] S31. Set the video to be enhanced; perform color space enhancement operations on the video to be enhanced to obtain the enhanced video; input the enhanced video into the final video quality level mapping model for mapping to obtain the quality level of the video to be enhanced; the color space enhancement operation on the video to be enhanced can be performed using DaVinci software.

[0078] The color space enhancement operation on the video to be enhanced in S31 includes the following steps:

[0079] S311. Set several types of video parameters to obtain a video parameter type set; the video parameter type set includes highlight brightness, midtone brightness, shadow brightness, overall contrast, and saturation, etc.; input the video to be enhanced into video processing software for color space enhancement to obtain the enhanced video; the video processing software includes DaVinci, etc.; the color space enhancement includes converting SDR to HDR, etc.

[0080] S32. Adjust the parameters of the enhanced video according to the quality level of the video to be enhanced to obtain the final enhanced video.

[0081] S32 includes the following steps:

[0082] S321. Set the video quality level threshold; when the quality level of the video to be enhanced is greater than or equal to the video quality level threshold, use the enhanced video as the final enhanced video.

[0083] Otherwise, in combination with the set of video parameter types, adjust the parameters of the enhanced video until the quality level of the second video to be enhanced is greater than or equal to the video quality level threshold;

[0084] The adjustment of the parameters of the enhanced video in S321 includes the following steps:

[0085] S3211. Construct a video parameter adjustment salp swarm \(a = \{a 1 ,\cdots,a i ,\cdots,a a′ \}\), where \(a i \) represents the \(i\)-th salp in the video parameter adjustment salp swarm, and \(a'\) represents the size of the video parameter adjustment salp swarm; set the maximum number of iterations of the video parameter adjustment salp swarm as and the current number of iterations as , which are respectively recorded as the maximum number of parameter adjustment iterations and the current number of parameter adjustment iterations;

[0086] S3212. In combination with the set of video parameter types, set the value range of each parameter of the enhanced video to obtain the enhanced video parameter value range set \) respectively represent the lower limit and the upper limit of the value of the \(i\)-th type of parameter of the enhanced video, and \(b\) represents the total number of set video parameter types; set the initial position of each salp in the video parameter adjustment salp swarm according to the enhanced video parameter value range set to obtain the initial position matrix \(b'\); as follows,

[0087]

[0088] where \(b j '\) i represents the position component of the initial position of the \(j\)-th salp in the video parameter adjustment salp swarm in the \(i\)-th type of video parameter dimension; the generation formula is as follows,

[0089]

[0090] In the formula, \(rand ji represents a random number between 0 and 1 generated for \(b j '\) i ;

[0091] S3213. Set the fitness function of the video parameter adjustment salp swarm as follows,

[0092]

[0093] In the formula, Indicates the video quality level data of the enhanced video after applying a set of video parameters updated in each iteration process to the enhanced video;

[0094] S3214. Start the iteration. Before the iteration, set the parameter adjustment current iteration number to 1; in the first iteration process, use the video parameter adjustment to calculate the fitness value of the initial position of each salp in the initial position matrix of the salp population, and obtain the first fitness value set; take the maximum fitness value in the first fitness value set and the corresponding initial position of the salp as the first global best fitness and the first global best position respectively; update the initial position of each salp in the initial position matrix according to the first global best fitness and the first global best position; after the update is completed, increment the parameter adjustment current iteration number by 1 and enter the next iteration;

[0095] In each subsequent iteration process, use the video parameter adjustment to calculate the fitness value of the position of each salp in the video parameter adjustment salp population updated in the previous iteration process, and obtain the second fitness value set; take the maximum fitness value in the second fitness value set and the corresponding position of the salp as the second global best fitness and the second global best position respectively; update the position of each salp in the video parameter adjustment salp population updated in the previous iteration process according to the second global best fitness and the second global best position; after the update is completed, increment the parameter adjustment current iteration number by 1 and enter the next iteration;

[0096] S3215. When is satisfied, stop the iteration to obtain the final global best position and the final global best fitness; otherwise, continue the iteration until is satisfied; take the final global best fitness as the optimized video quality level to be enhanced; when the optimized video quality level to be enhanced is greater than or equal to the video quality level threshold, apply each position component of the final global best position to the enhanced video to obtain the final enhanced video; otherwise, return to S3214 to continue the iteration until the optimized video quality level to be enhanced is greater than or equal to the video quality level threshold.

[0097] Embodiment 2

[0098] Please refer to Figure 2 This embodiment discloses an artificial intelligence-based video color space optimization and enhancement system. The system can implement the method of the above embodiment, including a video quality level setting module, a sample data acquisition module, a video quality level mapping model construction module, a color space enhancement module, a mapping module, and an enhanced parameter adjustment module;

[0099] The video quality level setting module is used to set several video quality levels to obtain a video quality level set;

[0100] The sample data collection module is used to collect several existing video samples and corresponding video quality level data to obtain an existing video sample set and an existing video quality level data set;

[0101] The video quality level mapping model construction module is used to construct a final video quality level mapping model by using the existing video sample set and the existing video quality level data set;

[0102] The color space enhancement module is used to perform color space enhancement operations on the video to be enhanced according to the video quality level to be enhanced to obtain an enhanced video;

[0103] The mapping module is used to map the enhanced video by using the final video quality level mapping model to obtain the video quality level to be enhanced;

[0104] The enhanced parameter adjustment module is used to adjust the parameters of the enhanced video according to the video quality level to be enhanced to obtain a final enhanced video.

[0105] In the description of this specification, the descriptions with reference to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0106] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. The embodiments selected and specifically described in this specification are for better explaining the principle and practical application of the invention, so that those skilled in the art in the relevant technical field can well understand and utilize the invention.

Claims

1. A video color space optimization and enhancement method based on artificial intelligence, characterized in that: The following steps are involved: S1. Setting several video quality levels to obtain a video quality level set; then collecting several existing video samples and corresponding video quality level data to obtain an existing video sample set and an existing video quality level data set; S2, using the existing video sample set and the existing video quality level data set to build a final video quality level mapping model; S3, performing a color space enhancement operation on the video to be enhanced to obtain an enhanced video; Mapping the enhanced video using the final video quality level mapping model to obtain the quality level of the video to be enhanced; The parameters of the enhanced video are adjusted according to the quality level of the video to be enhanced to obtain a final enhanced video.

2. The method for optimizing and enhancing video color space based on artificial intelligence according to claim 1, characterized in that: The S1 comprises the following steps: S11, setting several video quality levels to obtain a video quality level set; S12, collecting a number of existing video samples to obtain an existing video sample set; and obtaining professionals to evaluate the video quality level of each existing video sample in the existing video sample set in conjunction with the video quality level set to obtain an existing video quality level data set.

3. The method for optimizing and enhancing video color space based on artificial intelligence according to claim 2, characterized in that: The S2 comprises the following steps: S21, constructing an initial video quality level mapping model; S22, using the existing video sample set and the existing video quality level data set to train and test the initial video quality level mapping model to obtain a final video quality level mapping model;.

4. The method for optimizing and enhancing video color space based on artificial intelligence according to claim 3, characterized in that: The initial video quality level mapping model described in S21 includes a CNN neural network model.

5. The method for optimizing and enhancing video color space based on artificial intelligence according to claim 4, characterized in that: The S22 comprises the following steps: S221, setting a training data ratio; dividing the existing video sample set and the existing video quality grade data set according to the training data ratio to obtain an existing video training sample set, an existing video quality grade training data set, an existing video test sample set, and an existing video quality grade test data set; S222, setting a training error threshold; inputting the existing video training sample set and the existing video quality level training data set as training data and training labels into the initial video quality level mapping model for training; during the training process, when the training error is less than the training error threshold, stopping the training to obtain a trained video quality level mapping model; otherwise, continuing the training until the training error is less than the training error threshold; S223, set a test accuracy threshold; input the existing video test sample set and the existing video quality level test data set as test data and test labels respectively into the trained video quality level mapping model for testing; after the test is completed, obtain the test accuracy data; when the test accuracy data is greater than or equal to the test accuracy threshold, use the trained video quality level mapping model as the final video quality level mapping model; otherwise, return to S222 to continue training the trained video quality level mapping model until the test accuracy data is greater than or equal to the test accuracy threshold.

6. The method for optimizing and enhancing video color space based on artificial intelligence according to claim 5, characterized in that: The S3 comprises the following steps: S31, setting a video to be enhanced; performing a color space enhancement operation on the video to be enhanced to obtain an enhanced video; inputting the enhanced video into a final video quality level mapping model for mapping to obtain a quality level of the video to be enhanced; S32: adjusting parameters of the enhanced video according to the quality level of the video to be enhanced to obtain a final enhanced video.

7. The method for optimizing and enhancing video color space based on artificial intelligence according to claim 6, characterized in that: The color space enhancement operation of the to-be-enhanced video in S31 comprises the following steps: S311, setting several types of video parameters to obtain a video parameter type set; inputting the video to be enhanced into a video processing software to perform color space enhancement to obtain an enhanced video.

8. The method for optimizing and enhancing video color space based on artificial intelligence according to claim 7, characterized in that: The S32 comprises the following steps: S321, setting a video quality level threshold, when the quality level of the video to be enhanced is greater than or equal to the video quality level threshold, using the enhanced video as the final enhanced video; Otherwise, the parameters of the enhanced video are adjusted in accordance with the video parameter type set until the quality level of the second video to be enhanced is greater than or equal to the video quality level threshold.

9. The method for optimizing and enhancing video color space based on artificial intelligence according to claim 8, characterized in that: The step of adjusting the parameters of the enhanced video in S321 includes the following steps: S3211, constructing video parameters to adjust the salp population; setting the maximum number of iterations of the video parameters to adjust the salp population is And the current number of iterations is They are recorded as the maximum number of iterations for parameter adjustment and the current number of iterations for parameter adjustment respectively; S3212, setting the value interval of each parameter of the enhanced video in accordance with the video parameter type set to obtain an enhanced video parameter value interval set; setting the video parameters according to the enhanced video parameter value interval set to adjust the initial position of each salp in the salp population to obtain an initial position matrix; S3213, setting the video parameters to adjust the fitness function of the salp population; S3214, start iteration, and set the current iteration number of the parameter adjustment to 1 before iteration; in the first round of iteration, use the video parameter to adjust the fitness function of the salp population to calculate the fitness value of the initial position of each salp in the initial position matrix to obtain a first fitness value set; use the maximum fitness value in the first fitness value set and the initial position of the corresponding salp as the first global optimal fitness and the first global optimal position respectively; update the initial position of each salp in the initial position matrix according to the first global optimal fitness and the first global optimal position; after the update is completed, add 1 to the current iteration number of the parameter adjustment and enter the next round of iteration; In each other round of iteration, the fitness function of the video parameter adjustment salp population is used to calculate the fitness value of the position of each salp in the video parameter adjustment salp population updated in the previous round of iteration to obtain a second fitness value set; the maximum fitness value in the second fitness value set and the position of the corresponding salp are respectively used as the second global optimal fitness and the second global optimal position; the position of each salp in the video parameter adjustment salp population updated in the previous round of iteration is updated according to the second global optimal fitness and the second global optimal position; after the update is completed, the current iteration number of the parameter adjustment is increased by 1 and the next iteration is entered; S3215, when When , stop the iteration and get the final global optimal position and the final global optimal fitness; otherwise, continue to iterate until until the time; taking the final global optimal fitness as the quality level of the optimized video to be enhanced; when the quality level of the optimized video to be enhanced is greater than or equal to the video quality level threshold, applying the various position components of the final global optimal position to the enhanced video to obtain the final enhanced video; otherwise, returning to S3214 to continue iterating until the quality level of the optimized video to be enhanced is greater than or equal to the video quality level threshold.

10. A system for implementing the video color space optimization and enhancement method based on artificial intelligence as described in any one of claims 1 to 9.

Images