Photography parameter adaptive regulation and control method and system based on new media environment

Abstract

The invention relates to the technical field of photographing parameter regulation and control, in particular to a photographing parameter adaptability regulation and control method and system based on a new media environment, and the method comprises the steps: confirming photographing parameters, obtaining adjustment intervals, obtaining a plurality of adjustment intervals, combining the adjustment intervals, obtaining a plurality of parameter combinations, and obtaining an initial photographing object set; the method comprises the following steps: sequentially extracting a parameter combination from a plurality of parameter combinations, adjusting a camera, shooting to obtain a plurality of initial images, evaluating the corresponding parameter combination, determining an optimal parameter combination, constructing a parameter regulation database, obtaining a picture of a target shot object, retrieving the target shot object, and obtaining a reference shot object. And shooting by using the optimal parameter combination to obtain a shot image, transmitting the shot image to a new media environment to obtain a new media image, and completing the shooting parameter adaptive regulation and control method based on the new media environment based on the new media image. According to the invention, automatic photographing parameter adjustment can be realized and user experience can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photographic parameter regulation, and particularly to a method, system, electronic device, and computer-readable storage medium for adaptively regulating photographic parameters based on the new media environment. Background Art

[0002] With the rapid development of new media technologies, emerging media forms such as social media, short video platforms, and live broadcasts have gradually become important ways for people to share their lives and spread information. The method for adaptively regulating photographic parameters can effectively solve the problems of traditional manual adjustment being cumbersome, inaccurate, and not real-time by automatically analyzing the shooting environment and scene conditions and dynamically adjusting photographic parameters. It not only improves the user's shooting experience but also ensures that the image content captured in the new media environment meets the diverse platform requirements, having broad application prospects.

[0003] Traditional manual photographic parameter adjustment methods have played an important role in the history of photography development. However, with the rapid development of new media technologies and diverse shooting requirements, these methods have gradually exposed limitations such as cumbersome operation, inadaptability to dynamic environments, and new media requirements. Therefore, how to achieve automated photographic parameter adjustment and improve the user experience is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] The present invention provides a method for adaptively regulating photographic parameters based on the new media environment and a computer-readable storage medium, whose main purpose is to achieve automated photographic parameter adjustment and improve the user experience, reducing excessive consumption of time and human resources.

[0005] To achieve the above object, a method for adaptively regulating photographic parameters based on the new media environment provided by the present invention includes:

[0006] Identifying photographic parameters, where the photographic parameters include: brightness, color temperature, aperture, and color saturation;

[0007] Obtaining the adjustment intervals of each photographic parameter in the photographic parameters to obtain a plurality of adjustment intervals, where the plurality of adjustment intervals include: a brightness interval, a color temperature interval, an aperture interval, and a color saturation interval;

[0008] Combining the plurality of adjustment intervals to obtain a plurality of parameter combinations, and obtaining an initial set of shooting objects, where the initial set of shooting objects includes a plurality of initial shooting objects;

[0009] Successively extracting one parameter combination from the plurality of parameter combinations and performing the following operations on the extracted parameter combination:

[0010] Adjust the camera using the parameter combination, and capture the initial set of objects with the adjusted camera to obtain multiple initial images;

[0011] Evaluate the parameter combination corresponding to each of the multiple initial images to obtain a set of parameter evaluation values, confirm the optimal parameter combination based on the set of parameter evaluation values, and construct a parameter regulation database with the initial image corresponding to the optimal parameter combination;

[0012] Obtain a target object picture, retrieve similar objects for the target object in the parameter regulation database according to the pre-constructed image similarity technology and pre-constructed regulation factors, obtain the optimal parameter combination based on the reference object, where the target object picture includes the target object;

[0013] Capture an image using the optimal parameter combination, and transmit the captured image to the new media environment to obtain a new media image;

[0014] If it is confirmed that the new media image does not meet the preset image effect, return to the step of according to the pre-constructed image similarity technology and pre-constructed regulation factors until the new media image meets the preset image effect, and complete the method for adapting the photography parameters based on the new media environment based on the new media image.

[0015] Optionally, the combining according to the multiple adjustment intervals to obtain multiple parameter combinations includes:

[0016] Extract adjustment intervals from the multiple adjustment intervals in sequence, group the adjustment intervals according to a preset division constant to obtain multiple divided components, where the number of divided components in the multiple divided components is the division constant plus 1;

[0017] Calculate the data average value of each divided component in the multiple divided components respectively, and summarize the data average values to obtain a set of data average values;

[0018] Summarize the set of data average values to obtain a set of data average value sets, where the set of data average value sets includes: a set of brightness average values, a set of color temperature average values, a set of aperture average values, and a set of color saturation average values, and the set of data average value sets is represented as:

[0019] Q = {L, S, B, C}

[0020] L = [L1, …, L "

[0021] S = [S1, …, S "

[0022] B = [B1, …, B " ​​​

[0023] C = [C1, …, C "

[0024] where Q represents a set of data average values, L represents a set of luminance average values, S represents a set of color temperature average values, B represents a set of aperture average values, C represents a set of color saturation average values, L1 represents the first luminance data average value, L " represents the nth luminance data average value, n represents the number in the set of data average values, S1 represents the first color temperature data average value, S " represents the nth color temperature data average value, B1 represents the first aperture data average value, B " represents the nth aperture data average value, C1 represents the first color saturation data average value, C " represents the nth color saturation data average value;

[0025] Pair the luminance average value set, color temperature average value set, aperture average value set, and color saturation average value set in the set of data average values to obtain multiple parameter combinations, where the multiple parameter combinations are represented as:

[0026] K = [(L1, S1, B1, C1), …, (L # , S $ , B ％ , C c ), …, (L " , S " , B " , C " )]

[0027] 1 < l < n, 1 < s < n, 1 < b < n, 1 < c < n

[0028] where K represents multiple parameter combinations, L # represents the lth luminance average value, S $ represents the sth color temperature average value, B ％ represents the bth aperture average value, C c represents the cth color saturation.

[0029] Optionally, evaluating the parameter combinations corresponding to each of the multiple initial images to obtain a set of parameter evaluation values, and confirming the optimal parameter combination based on the set of parameter evaluation values includes:

[0030] Sequentially extract the parameter combinations corresponding to the initial images from the multiple initial images, and calculate the weights of each pre - constructed average parameter in the extracted parameter combinations to obtain an average weight set, where the average weight set includes: luminance average weight, color temperature average weight, aperture average weight, and color saturation average weight; ​

[0031] According to the average value weight group, parameter evaluation is performed on the parameter combination to obtain a parameter evaluation value;

[0032] Summarize the parameter evaluation values to obtain a set of parameter evaluation values;

[0033] Extract the maximum parameter evaluation value from the set of parameter evaluation values, and identify the optimal parameter combination corresponding to the maximum parameter evaluation value among the multiple parameter combinations.

[0034] Optionally, the step of retrieving similar photographed objects for the target photographed object in the parameter regulation database according to the pre-constructed image similarity technology and the pre-constructed regulation factors includes:

[0035] Sequentially extract target matching images from the parameter regulation database, and segment the target matching images according to a preset standard interval to obtain multiple matching regions;

[0036] Perform the following operations on each of the multiple matching regions:

[0037] Obtain the color histogram of the matching region to obtain a matching histogram;

[0038] Segment the target photographed object picture according to a preset standard interval to obtain multiple image regions;

[0039] Determine the same-position image region in the multiple image regions according to the matching region, obtain the color histogram of the same-position image region to obtain an image histogram, and compare the matching histogram with the image histogram to obtain a comparison graph, where the horizontal axis of the comparison graph is the color space and the vertical axis is the frequency;

[0040] Calculate the color similarity between the image region and the matching region according to the comparison graph and the pre-constructed color similarity formula;

[0041] Calculate the image texture similarity between the image region and the matching region, and determine the target region similarity according to the image texture similarity and the color similarity;

[0042] Summarize the target region similarities of the target matching images to obtain multiple target region similarities, and determine the target image similarity according to the multiple target region similarities;

[0043] If the target image similarity is greater than or equal to 90, use the target matching image as the reference photographed object and stop extracting the target matching image from the parameter regulation database;

[0044] If the target image similarity is less than 90, return to the step of sequentially extracting the target matching images from the parameter regulation database until the target image similarity is greater than or equal to 90, and then use the target matching image as the reference photographed object.

[0045] Optionally, the color similarity formula is as follows:

[0046]

[0047] where (R, B) represents color similarity, R represents the image histogram, B represents the matching histogram, N represents the number of pixels in the color space of the comparison image, i represents the pixel index in the comparison image, r i represents the frequency of the image histogram in the i-th color space, and b i represents the frequency of the matching histogram in the i-th color space, Max(r i , b i ) represents the maximum frequency between the frequency of the image histogram in the i-th color space and the frequency of the matching histogram in the i-th color space, and a represents a regulation factor.

[0048] Optionally, calculating the image texture similarity between the image region and the matching region includes:

[0049] Reducing both the image region and the matching region according to a preset reduction ratio to obtain a scaled image region and a scaled matching region;

[0050] Converting the scaled image region and the scaled matching region to grayscale to obtain a grayscale image region and a grayscale matching region;

[0051] Extracting the texture features in the grayscale image region to obtain first texture features, and synthesizing the first texture features to obtain a first synthesized vector, where the first synthesized vector includes: the second moment of the grayscale image region, the contrast of the grayscale image region, the inverse difference moment of the grayscale image region, and the entropy of the grayscale image region;

[0052] Extracting the texture features in the grayscale matching region to obtain second texture features, and synthesizing the second texture features to obtain a second synthesized vector, where the second synthesized vector includes: the second moment of the grayscale matching image, the contrast of the grayscale matching image, the inverse difference moment of the grayscale matching image, and the entropy of the grayscale matching image;

[0053] Calculating the cosine similarity between the first synthesized vector and the second synthesized vector using a pre-constructed cosine similarity formula to obtain the image texture similarity.

[0054] Optionally, the cosine similarity formula is as follows:

[0055]

[0056] where S represents the cosine similarity, E 1j represents the j-th element in the first synthesized vector, and E +jrepresents the j-th element in the second comprehensive vector, m represents the total number of elements in the first comprehensive vector and the second comprehensive vector, and j represents the index.

[0057] Optionally, constructing a parameter adjustment database with the initial image corresponding to the optimal parameter combination, including:

[0058] Judging the size of the initial image corresponding to the optimal parameter combination;

[0059] If it is confirmed that the size of the initial image is greater than the preset size range, perform intelligent cropping on the initial image, and use the pre-constructed saliency detection algorithm to retain the key area in the initial image until the size of the initial image is equal to the preset size range, obtaining a cropped image, and constructing a parameter adjustment database with the cropped image.

[0060] Optionally, calculating weights for each pre-constructed average parameter in the extracted parameter combination to obtain an average weight group, including:

[0061] Performing the following operations on each average parameter in the extracted parameter combination:

[0062] Normalizing the average parameter to obtain a normalized parameter, calculating the importance score of the normalized parameter according to the pre-constructed importance score, and calculating the average weight according to the importance score;

[0063] Among them, the weight calculation formula is as follows:

[0064]

[0065] Among them, w i represents the i-th average weight, Q i represents the importance score of the i-th normalized parameter, q represents the average index, u represents the number of parameters, and Q represents the importance score of the normalized parameter;

[0066] Summarize the average weights to obtain an average weight group.

[0067] To achieve the above object, the present invention also provides a photography parameter adaptive adjustment system based on a new media environment, including:

[0068] A photography parameter confirmation module for confirming photography parameters, where the photography parameters include: brightness, color temperature, aperture, and color saturation, obtaining the adjustment range of each photography parameter in the photography parameters, obtaining a plurality of adjustment ranges, where the plurality of adjustment ranges include: a brightness range, a color temperature range, an aperture range, and a color saturation range;

[0069] An initial image capture module, configured to combine the multiple adjustment intervals to obtain multiple parameter combinations, and acquire an initial set of captured objects, where the initial set of captured objects includes multiple initial captured objects. Sequentially extract one parameter combination from the multiple parameter combinations, and perform the following operations on the extracted parameter combination: adjust a camera using the parameter combination, and capture the initial set of captured objects using the adjusted camera to obtain multiple initial images. Evaluate the parameter combination corresponding to each initial image among the multiple initial images to obtain a set of parameter evaluation values. Confirm the optimal parameter combination based on the set of parameter evaluation values, and construct a parameter regulation database with the initial image corresponding to the optimal parameter combination;

[0070] A parameter regulation module, configured to obtain a target captured object picture, retrieve a reference captured object for the target captured object in the parameter regulation database according to a pre-constructed image similarity technique and a pre-constructed regulation factor, obtain an optimal parameter combination based on the reference captured object, where the target captured object picture includes the target captured object, capture a captured image using the optimal parameter combination, and transmit the captured image to a new media environment to obtain a new media image;

[0071] A new media image evaluation module, configured to, if it is confirmed that the new media image does not meet the preset image effect, return to the step of according to the pre-constructed image similarity technique and the pre-constructed regulation factor until the new media image meets the preset image effect, and complete the method for adapting and regulating photography parameters based on the new media environment based on the new media image.

[0072] To solve the above problems, the present invention further provides an electronic device, where the electronic device includes:

[0073] A memory, storing at least one instruction; and

[0074] A processor, executing the instruction stored in the memory to implement the above-mentioned method for adapting and regulating photography parameters based on the new media environment.

[0075] To solve the above problems, the present invention further provides a computer-readable storage medium, where at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned method for adapting and regulating photography parameters based on the new media environment.

[0076] To solve the problems described in the background art, the present invention identifies photographic parameters, where the photographic parameters include: brightness, color temperature, aperture, and color saturation. The adjustment range of each photographic parameter in the photographic parameters is obtained to get a plurality of adjustment ranges, where the plurality of adjustment ranges include: a brightness range, a color temperature range, an aperture range, and a color saturation range. Each adjustment range of the photographic parameters is refined and divided to obtain a plurality of specific divided ranges, which helps to more precisely control the parameter change range and improve the refinement degree of parameter adjustment. According to the plurality of divided ranges, a plurality of parameter combinations are obtained. An initial set of photographed objects is obtained, where the initial set of photographed objects includes a plurality of initial photographed objects. By combining a plurality of divided ranges, a plurality of parameter combinations are generated, providing a data basis for subsequent multi-parameter combination evaluation. One parameter combination is sequentially extracted from the plurality of parameter combinations, and the following operations are performed on the extracted parameter combination: adjusting the camera using the parameter combination, and photographing the initial set of photographed objects with the adjusted camera to obtain a plurality of initial images. Photographing the initial set of photographed objects with different parameter combinations to generate a plurality of initial images, which helps to quickly obtain a large amount of sample data and provide rich reference information for parameter evaluation and optimization. Each parameter combination corresponding to each of the plurality of initial images is evaluated to obtain a set of parameter evaluation values. Based on the set of parameter evaluation values, the best parameter combination is confirmed, and a parameter control database is constructed with the initial image corresponding to the best parameter combination. By evaluating the shooting effect corresponding to each parameter combination, a set of parameter evaluation values is obtained, and then the best parameter combination is confirmed, which ensures the scientificity and effectiveness of parameter selection. A target photographed object picture is obtained. According to the pre-constructed image similarity technology and the pre-constructed adjustment factor, a similar photographed object is retrieved for the target photographed object in the parameter control database to obtain a reference photographed object. Based on the reference photographed object, the optimal parameter combination is obtained, where the target photographed object picture includes the target photographed object. Constructing a parameter control database with the initial image corresponding to the best parameter combination provides data support for subsequent retrieval of the target photographed object, ensuring that the optimal parameter configuration can be quickly found in a similar scenario and improving the shooting efficiency. Photographing with the optimal parameter combination to obtain a photographed image, and transmitting the photographed image to the new media environment to obtain a new media image. Transmitting the photographed image to the new media environment to ensure that the content meets the requirements of the new media platform and improve the dissemination effect and user experience of the content. If it is confirmed that the new media image does not meet the preset image effect, then return to the step of according to the pre-constructed image similarity technology and the pre-constructed adjustment factor until the new media image meets the preset image effect. Based on the new media image, a photographic parameter adaptation control method based on the new media environment is completed. This feedback mechanism ensures the continuous optimization of the shooting result and improves the adaptive ability and robustness of the system. Therefore, the present invention can achieve automatic adjustment of photographic parameters and improve the user experience, reducing excessive consumption of time and human resources. Brief Description of the Drawings

[0077] Figure 1 It is a schematic flowchart of a method for adaptively adjusting photographic parameters based on a new media environment provided by an embodiment of the present invention;

[0078] Figure 2 It is a functional module diagram of a system for adaptively adjusting photographic parameters based on a new media environment provided by an embodiment of the present invention;

[0079] Figure 3 It is a schematic structural diagram of an electronic device for implementing the method for adaptively adjusting photographic parameters based on a new media environment provided by an embodiment of the present invention.

[0080] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0081] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0082] An embodiment of the present application provides a method for adaptively adjusting photographic parameters based on a new media environment. The execution subject of the method for adaptively adjusting photographic parameters based on a new media environment includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for adaptively adjusting photographic parameters based on a new media environment can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0083] Referring to Figure 1 As shown, it is a schematic flowchart of a method for adaptively adjusting photographic parameters based on a new media environment provided by an embodiment of the present invention. In this embodiment, the method for adaptively adjusting photographic parameters based on a new media environment includes:

[0084] S1. Identify photographic parameters, where the photographic parameters include: brightness, color temperature, aperture, and color saturation.

[0085] It should be explained that brightness refers to the overall light and dark degree of an image. The aperture refers to the length of time the camera shutter is open. The color saturation refers to the vividness of the colors in the image. The step of identifying the photographic parameters is: identifying the parameters according to the photographic theme.

[0086] Exemplarily, when Xiao Zhang is shooting a landscape, he increases the color saturation to display the natural colors, and when shooting a person, he adjusts the color temperature to avoid skin color distortion of the person.

[0087] S2. Obtain the adjustment range of each shooting parameter in the shooting parameters, and obtain a plurality of adjustment ranges, where the plurality of adjustment ranges include: a brightness range, a color temperature range, an aperture range, and a color saturation range.

[0088] It should be explained that the step of obtaining the adjustment range of each shooting parameter in the shooting parameters is: detecting brightness, color temperature, aperture, and color saturation according to the historical detection time period, so as to obtain the adjustment range of each shooting parameter.

[0089] Exemplarily, Xiao Zhang used a camera to shoot different environments on January 10, 2024, January 15, 2024, February 20, 2024, March 10, 2024, March 18, 2024, and March 25, 2024, and obtained a brightness range [50, 60, 40, 70, 30, 80], a color temperature range [5500, 6000, 5000, 5800, 4500, 6200], an aperture range [2.8, 3.2, 2.0, 4.0, 1.8, 3.5], and a color saturation range [70, 75, 65, 80, 60, 85].

[0090] S3. Combine according to the plurality of adjustment ranges to obtain a plurality of parameter combinations, and obtain an initial shooting object set, where the initial shooting object set includes a plurality of initial shooting objects.

[0091] Specifically, the combination according to the plurality of adjustment ranges to obtain a plurality of parameter combinations includes:

[0092] Extract the adjustment ranges from the plurality of adjustment ranges in turn, and group the adjustment ranges according to a preset division constant to obtain a plurality of divided components, where the number of divided components in the plurality of divided components is the division constant plus 1;

[0093] Calculate the data average value of each divided component in the plurality of divided components respectively, and summarize the data average values to obtain a data average value group;

[0094] Summarize the data average value group to obtain a data average value group set, where the data average value group set includes: a brightness average value group, a color temperature average value group, an aperture average value group, and a color saturation average value group, and the data average value group set is expressed as:

[0095] Q = {L, S, B, C}

[0096] L = [L1,..., L "

[0097] S = [S1,..., S "

[0098] B = [B1,..., B​​"

[0099] C = [C1, …, C "

[0100] where Q represents a set of data average values, L represents a set of luminance average values, S represents a set of color temperature average values, B represents a set of aperture average values, C represents a set of color saturation average values, L1 represents the first luminance data average value, L " represents the nth luminance data average value, n represents the number in the set of data average values, S1 represents the first color temperature data average value, S " represents the nth color temperature data average value, B1 represents the first aperture data average value, B " represents the nth aperture data average value, C1 represents the first color saturation data average value, C " represents the nth color saturation data average value;

[0101] Pair the luminance average value set, color temperature average value set, aperture average value set, and color saturation average value set in the set of data average values to obtain multiple parameter combinations, where the multiple parameter combinations are expressed as:

[0102] K = [(L1, S1, B1, C1), …, (L # , S $ , B ％ , C c ), …, (L " , S " , B " , C " )]

[0103] 1 < l < n, 1 < s < n, 1 < b < n, 1 < c < n

[0104] where K represents multiple parameter combinations, L # represents the lth luminance average value, S $ represents the sth color temperature average value, B ％ represents the bth aperture average value, C c represents the cth color saturation.

[0105] ​​It is understandable that in the embodiments of the present invention, the division constant refers to a preset integer used to determine how many equal sub-intervals the adjustment interval is divided into. The division components refer to the sub-intervals obtained by equally dividing the adjustment interval according to the division constant. The data average group refers to a group of averages obtained by calculating the averages of the data in each division component. Data pairing means arranging the elements in the brightness average group, color temperature average group, aperture average group, and color saturation average group in all possible combination ways to generate multiple parameter combinations. A parameter combination refers to a combination containing a brightness average, a color temperature average, an aperture average, and a color saturation average.

[0106] Exemplarily, there are multiple adjustment intervals including a brightness interval [50, 60, 40, 70, 30, 80], a color temperature interval [5500, 6000, 5000, 5800, 4500, 6200], an aperture interval [2.8, 3.2, 2.0, 4.0, 1.8, 3.5], and a color saturation interval [70, 75, 65, 80, 60, 85]. The brightness interval [50, 60, 40, 80, 70, 80] is extracted from the multiple adjustment intervals. According to the preset division constant 2, the brightness interval is divided to obtain the first division component [50, 60], the second division component [40, 80], and the third division component [70, 80]. The average of the data in each division component is calculated respectively. The data average of the first division component [50, 60] is 55, the data average of the second division component [40, 80] is 60, and the data average of the third division component [70, 80] is 75. The brightness data average group [55, 60, 75] is obtained according to the three division components.

[0107] S4. Sequentially extract a parameter combination from the multiple parameter combinations, and perform the following operations on the extracted parameter combination: adjust the camera using the parameter combination, and use the adjusted camera to shoot an initial set of objects to obtain multiple initial images.

[0108] It should be explained that the initial set of objects is a series of objects or scenes selected for shooting during the parameter optimization process. The camera is a device used to capture and record the initial images.

[0109] Exemplarily, Xiao Zhang extracts a parameter combination [35, 4700, 2.1, 65] from the multiple parameter combinations. Use the extracted parameter combination to adjust the camera, adjust the brightness of the camera to 35, the color temperature to 4700, the aperture to 2.1, and the color saturation to 65. Use the adjusted camera to shoot a red flower, a green leaf, and a blue water cup to obtain the initial image A, the initial image B, and the initial image C.

[0110] S5. Evaluate the parameter combinations corresponding to each of the multiple initial images to obtain a set of parameter evaluation values.

[0111] Specifically, the evaluating the parameter combinations corresponding to each of the multiple initial images to obtain a set of parameter evaluation values and confirming the optimal parameter combination based on the set of parameter evaluation values includes:

[0112] Extract the parameter combinations corresponding to the initial images from the multiple initial images in sequence, and calculate the weights of each pre-constructed average parameter in the extracted parameter combinations to obtain an average weight set, where the average weight set includes: brightness average weight, color temperature average weight, aperture average weight, and color saturation average weight;

[0113] Evaluate the parameter combinations according to the average weight set to obtain parameter evaluation values;

[0114] Summarize the parameter evaluation values to obtain a set of parameter evaluation values;

[0115] Extract the maximum parameter evaluation value from the set of parameter evaluation values, and identify the optimal parameter combination corresponding to the maximum parameter evaluation value among the multiple parameter combinations.

[0116] It should be explained that the average weight set refers to a set of weight values obtained by calculating the weights of the averages of brightness, color temperature, aperture, and color saturation when evaluating the effect of parameter combinations. The parameter evaluation value refers to a single value obtained by calculating each parameter combination by applying the average weight set, and is used to measure the comprehensive effect of the parameter combination.

[0117] Further, the calculating the weights of each pre-constructed average parameter in the extracted parameter combinations to obtain an average weight set includes:

[0118] Perform the following operations on each average parameter in the extracted parameter combinations:

[0119] Normalize the average parameter to obtain a normalized parameter, calculate the importance score of the normalized parameter according to the pre-constructed importance score, and calculate the average weight according to the importance score;

[0120] Among them, the weight calculation formula is as follows:

[0121]

[0122] Among them, w i represents the i-th average weight, Q i represents the importance score of the i-th normalized parameter, q represents the average index, u represents the number of parameters, and Q represents the importance score of the normalized parameter;

[0123] Summarize the average weights to obtain the average weight group.

[0124] Importantly, the normalized average parameter refers to the operation of normalizing each average parameter in each parameter combination. The normalization formula is as follows:

[0125]

[0126] Where P i / represents the i-th normalized parameter in the parameter combination, P i represents the i-th parameter average in the parameter combination, min(P) represents the minimum value of all parameters in the parameter combination, and max(P) represents the maximum value of all parameters in the parameter combination.

[0127] It should be explained that the step of calculating the importance score of the normalized parameter according to the pre-constructed importance score in the embodiment of the present invention is: performing a square operation on the normalized parameter to obtain the importance score of each parameter.

[0128] S6. Based on the parameter evaluation value set, confirm the best parameter combination, and construct a parameter adjustment database with the initial image corresponding to the best parameter combination.

[0129] Specifically, the step of constructing a parameter adjustment database with the initial image corresponding to the best parameter combination includes:

[0130] Judge the size of the initial image corresponding to the best parameter combination;

[0131] If it is confirmed that the size of the initial image is larger than the preset size range, perform intelligent cropping on the initial image, and use the pre-constructed saliency detection algorithm to retain the key area in the initial image until the size of the initial image is equal to the preset size range to obtain a cropped image, and use the cropped image to construct a parameter adjustment database.

[0132] It should be explained that the preset size range in the embodiment of the present invention refers to the size range preset according to the size of new media images. The parameter adjustment database refers to a database that stores the optimized and verified best parameter combinations and their corresponding initial images. The saliency detection algorithm is a computer vision technology used to identify important areas in the initial image. For example, if the initial image is a portrait of a person, the saliency detection algorithm is used to retain the facial features of the person in the initial image.

[0133] S7. Obtain the target object picture, retrieve similar objects of the target object in the parameter adjustment database according to the pre-constructed image similarity technology and the pre-constructed adjustment factors, obtain the reference object, and obtain the optimal parameter combination based on the reference object, where the target object picture includes the target object.

[0134] Specifically, the step of retrieving similar objects of the target object in the parameter adjustment database according to the pre-constructed image similarity technology and the pre-constructed adjustment factors to obtain the reference object includes:

[0135] Extract the target matching images from the parameter adjustment database in sequence, and segment the target matching images according to the preset standard interval to obtain multiple matching regions;

[0136] Perform the following operations on each of the multiple matching regions:

[0137] Obtain the color histogram of the matching region to obtain the matching histogram;

[0138] Segment the target object picture according to the preset standard interval to obtain multiple image regions;

[0139] Determine the same-position image regions in the multiple image regions according to the matching regions, obtain the color histogram of the same-position image regions to obtain the image histogram, and compare the matching histogram with the image histogram to obtain a comparison graph, where the horizontal axis of the comparison graph is the color space and the vertical axis is the frequency;

[0140] Calculate the color similarity between the image region and the matching region according to the comparison graph and the pre-constructed color similarity formula;

[0141] Calculate the image texture similarity between the image region and the matching region, and determine the target region similarity according to the image texture similarity and the color similarity;

[0142] Summarize the target region similarities of the target matching images to obtain multiple target region similarities, and determine the target image similarity according to the multiple target region similarities;

[0143] If the target image similarity is greater than or equal to 90, use the target matching image as the reference object and stop extracting the target matching images from the parameter adjustment database;

[0144] If the target image similarity is less than 90, return to the step of extracting the target matching images from the parameter adjustment database in sequence until the target image similarity is greater than or equal to 90, and then use the target matching image as the reference object.

[0145] It should be explained that the standard interval refers to the segmentation range predefined in image processing. The steps for obtaining the color histogram of the matching region are as follows: Map the color of each pixel in the matching region to a color space, such as RGB, and then count the frequency of each color to obtain a histogram. The color space refers to the way of representing and the range of colors. For example, in the RGB color space, the horizontal axis can be a combination of the red, green, and blue channels. The frequency refers to the proportion of the number of pixels of each color in the matching histogram and the image histogram to the total number of pixels.

[0146] It should also be explained that the similarity of the target region is an index for measuring the similarity between the image region and the matching region. The similarity of the target image is an index for measuring the similarity between the entire target matching image and the picture of the target object.

[0147] Specifically, the color similarity formula is as follows:

[0148]

[0149] Among them, (R, B) represents the color similarity, R represents the image histogram, B represents the matching histogram, N represents the number of pixels in the color space of the comparison graph, i represents the pixel index in the comparison graph, r i represents the frequency of the image histogram in the i-th color space, b i represents the frequency of the matching histogram in the i-th color space, Max(r i , b i ) represents the maximum frequency among the frequency of the image histogram in the i-th color space and the frequency of the matching histogram in the i-th color space, and a represents the regulation factor.

[0150] It should be explained that the regulation factor is a factor used to control the sensitivity of color similarity calculation.

[0151] Furthermore, calculating the image texture similarity between the image region and the matching region includes:

[0152] Shrink both the image region and the matching region according to a preset shrinkage ratio to obtain a scaled image region and a scaled matching region;

[0153] Convert the scaled image region and the scaled matching region to grayscale to obtain a grayscale image region and a grayscale matching region;

[0154] Extract the texture features in the grayscale image region to obtain the first texture features, and synthesize the first texture features to obtain the first synthetic vector, where the first synthetic vector includes: the second moment of the grayscale image region, the contrast of the grayscale image region, the inverse difference moment of the grayscale image region, and the entropy of the grayscale image region;

[0155] Extract the texture features in the grayscale matching region to obtain the second texture features, and synthesize the second texture features to obtain the second comprehensive vector, where the second comprehensive vector includes: the second-order moment of the grayscale matching image, the contrast of the grayscale matching image, the inverse difference moment of the grayscale matching image, and the entropy of the grayscale matching image;

[0156] Calculate the cosine similarity between the first comprehensive vector and the second comprehensive vector using the pre-constructed cosine similarity formula to obtain the image texture similarity.

[0157] Further, the cosine similarity formula is as follows:

[0158]

[0159] where S represents the cosine similarity, E 1j represents the j-th element in the first comprehensive vector, and E +j represents the j-th element in the second comprehensive vector, m represents the total number of elements in the first comprehensive vector and the second comprehensive vector, and j represents the index.

[0160] It should be explained that the reduction ratio refers to the preset image size range. Grayscale conversion refers to the operation of converting the color images of the scaled image region and the scaled matching region into grayscale images using the grayscale conversion formula, where the grayscale conversion formula is as follows:

[0161] Gray = 0.2989×R + + 0.5870×G + + 0.1140×B +

[0162] where Gray represents the grayscale value of the grayscale image region or the grayscale matching region, R + represents the value of the red channel in the scaled image region or the scaled matching region, G + represents the value of the green channel in the scaled image region or the scaled matching region, and B + represents the value of the blue channel in the scaled image region or the scaled matching region.

[0163] It can be understood that the step of extracting the texture features in the grayscale image region is: using a texture analysis algorithm to extract the texture features in the grayscale image region. The texture analysis algorithm in the embodiments of the present invention is a prior art and will not be elaborated here. The second-order moment refers to the uniformity of the grayscale distribution of the image. The contrast refers to the degree of grayscale contrast in the image. The inverse difference moment refers to the speed of grayscale change in the image. The entropy refers to the degree of chaos of the grayscale distribution in the image. The synthesis in the embodiments of the present invention refers to the operation of synthesizing the second-order moment of the grayscale image region, the contrast of the grayscale image region, the inverse difference moment of the grayscale image region, and the entropy of the grayscale image region into a vector.

[0164] Exemplarily, Xiao Zhang extracts texture features from the grayscale image region to obtain the first comprehensive vector [0.8, 50, 0.05, 7.0], and extracts texture features from the matching image region to obtain the second comprehensive vector [0.75, 45, 0.045, 6.8]. The following is the process of calculating the cosine similarity between the grayscale image region and the matching image region using the cosine similarity formula:

[0165]

[0166] S8. Shoot using the optimal parameter combination to obtain a captured image, and transmit the captured image to the new media environment to obtain a new media image.

[0167] It should be explained that the new media environment described in the embodiments of the present invention refers to modern digital media platforms and channels, such as social media, online video platforms, digital advertisements, etc. The step of transmitting the captured image to the new media environment is as follows: first, convert the format of the captured image according to different new media environments to obtain a converted image, compress the converted image using an image compression tool to obtain a compressed image, and upload the compressed image to the new media environment using an API interface.

[0168] S9. If it is confirmed that the new media image does not meet the preset image effect, then return to the step of according to the pre-constructed image similarity technology and the pre-constructed regulation factor until the new media image meets the preset image effect, and complete the photography parameter adaptability regulation method based on the new media environment based on the new media image.

[0169] It should be explained that the image effect refers to the performance of the image in terms of color, contrast, brightness, aperture, etc.

[0170] To solve the problems described in the background art, the present invention identifies photographic parameters, where the photographic parameters include: brightness, color temperature, aperture, and color saturation. The adjustment range of each photographic parameter in the photographic parameters is obtained to get a plurality of adjustment ranges, where the plurality of adjustment ranges include: a brightness range, a color temperature range, an aperture range, and a color saturation range. Each adjustment range of the photographic parameters is refined and divided to obtain a plurality of specific divided ranges, which helps to more precisely control the parameter change range and improve the refinement degree of parameter adjustment. According to the plurality of divided ranges, a plurality of parameter combinations are obtained. An initial set of photographed objects is obtained, where the initial set of photographed objects includes a plurality of initial photographed objects. By combining a plurality of divided ranges, a plurality of parameter combinations are generated, providing a data basis for subsequent multi-parameter combination evaluation. One parameter combination is sequentially extracted from the plurality of parameter combinations, and the following operations are performed on the extracted parameter combination: the camera is adjusted using the parameter combination, and the initial set of photographed objects is photographed using the adjusted camera to obtain a plurality of initial images. The initial set of photographed objects is photographed using different parameter combinations to generate a plurality of initial images, which helps to quickly obtain a large amount of sample data and provide rich reference information for parameter evaluation and optimization. Each parameter combination corresponding to each of the plurality of initial images is evaluated to obtain a parameter evaluation value set. Based on the parameter evaluation value set, the best parameter combination is confirmed, and a parameter control database is constructed with the initial image corresponding to the best parameter combination. By evaluating the shooting effect corresponding to each parameter combination, a parameter evaluation value set is obtained, and then the best parameter combination is confirmed, which ensures the scientificity and effectiveness of parameter selection. A target photographed object picture is obtained. According to the pre-constructed image similarity technology and the pre-constructed adjustment factor, a similar photographed object is retrieved for the target photographed object in the parameter control database to obtain a reference photographed object. Based on the reference photographed object, the optimal parameter combination is obtained, where the target photographed object picture includes the target photographed object. A parameter control database is constructed with the initial image corresponding to the best parameter combination, providing data support for subsequent retrieval of the target photographed object, ensuring that the optimal parameter configuration can be quickly found in a similar scenario and improving the shooting efficiency. The optimal parameter combination is used for shooting to obtain a shot image. The shot image is transmitted to the new media environment to obtain a new media image. Transmitting the shot image to the new media environment ensures that the content meets the requirements of the new media platform and improves the dissemination effect and user experience of the content. If it is confirmed that the new media image does not meet the preset image effect, then return to the step of according to the pre-constructed image similarity technology and the pre-constructed adjustment factor until the new media image meets the preset image effect. Based on the new media image, a photographic parameter adaptation control method based on the new media environment is completed. This feedback mechanism ensures the continuous optimization of the shooting result and improves the adaptive ability and robustness of the system. Therefore, the present invention can achieve automated adjustment of photographic parameters and enhance the user experience, reducing excessive consumption of time and human resources.

[0171] As shown Figure 2 in the figure, it is a functional module diagram of a photography parameter adaptive regulation system based on a new media environment provided by an embodiment of the present invention.

[0172] The photography parameter adaptive regulation system 100 based on the new media environment of the present invention can be installed in an electronic device. According to the functions achieved, the photography parameter adaptive regulation system 100 based on the new media environment can include a photography parameter confirmation module 101, an initial image shooting module 102, a parameter regulation module 103, and a new media image evaluation module 104. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device;

[0173] The photography parameter confirmation module 101 is used to confirm photography parameters, where the photography parameters include: brightness, color temperature, aperture, and color saturation, and obtain adjustment intervals for each photography parameter in the photography parameters, resulting in a plurality of adjustment intervals, where the plurality of adjustment intervals include: a brightness interval, a color temperature interval, an aperture interval, and a color saturation interval;

[0174] The initial image shooting module 102 is used to combine the plurality of adjustment intervals to obtain a plurality of parameter combinations, obtain an initial shooting object set, where the initial shooting object set includes a plurality of initial shooting objects, sequentially extract a parameter combination from the plurality of parameter combinations, and perform the following operations on the extracted parameter combination: adjust the camera using the parameter combination, and use the adjusted camera to shoot the initial shooting object set to obtain a plurality of initial images, evaluate the parameter combination corresponding to each initial image in the plurality of initial images to obtain a parameter evaluation value set, confirm the best parameter combination based on the parameter evaluation value set, and construct a parameter regulation database with the initial image corresponding to the best parameter combination;

[0175] The parameter regulation module 103 is used to obtain a target shooting object picture, retrieve similar shooting objects for the target shooting object in the parameter regulation database according to a pre-constructed image similarity technique and a pre-constructed regulation factor, obtain an optimal parameter combination based on the similar shooting objects, where the target shooting object picture includes the target shooting object, shoot a shooting image using the optimal parameter combination, and transmit the shooting image to the new media environment to obtain a new media image;

[0176] The new media image evaluation module 104 is configured to, if it is confirmed that the new media image does not meet the preset image effect, return to the step of according to the pre-constructed image similarity technology and the pre-constructed adjustment factor until the new media image meets the preset image effect, and complete the adaptive adjustment method of the photography parameters based on the new media environment based on the new media image.

[0177] Specifically, each module in the adaptive adjustment system 100 of the photography parameters based on the new media environment in the embodiment of the present invention adopts the same technical means as the Figure 1 adaptive adjustment method of the photography parameters based on the new media environment described above, and can produce the same technical effects, which will not be elaborated here.

[0178] As Figure 3 shown, it is a schematic structural diagram of an electronic device for implementing the adaptive adjustment method of the photography parameters based on the new media environment provided by an embodiment of the present invention.

[0179] The electronic device 1 may include a processor 10, a memory 11, and a bus 12, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as a program for the adaptive adjustment method of the photography parameters based on the new media environment.

[0180] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as the mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 1. Further, the memory 11 further includes the internal storage unit of the electronic device 1 and also includes the external storage device. The memory 11 can be used not only to store application software installed in the electronic device 1 and various types of data, such as the code of the program for the adaptive adjustment method of the photography parameters based on the new media environment, but also to temporarily store data that has been output or will be output.

[0181] In some embodiments, the processor 10 may be composed of an integrated circuit. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple packaged integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting various components of the entire electronic device through various interfaces and circuits, and by running or executing programs or modules stored in the memory 11 (such as the program for adaptively regulating photography parameters based on the new media environment, etc.), and calling the data stored in the memory 11, to execute various functions of the electronic device 1 and process data.

[0182] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is set to enable connection communication between the memory 11 and at least one processor 10, etc.

[0183] Figure 3 Only the electronic device with components is shown. Those skilled in the art can understand that, Figure 3 The shown structure does not constitute a limitation on the electronic device 1, and it may include fewer or more components than shown, or combine certain components, or have a different component arrangement.

[0184] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so as to implement functions such as charge management, discharge management, and power consumption management through the power management device. The power source may also include any components such as one or more DC or AC power sources, a recharge device, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device 1 may also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0185] Furthermore, the electronic device 1 may further include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0186] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0187] The program of the method for adaptively regulating photographic parameters based on the new media environment stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, and when running in the processor 10, it can implement:

[0188] Identify photographic parameters, where the photographic parameters include: brightness, color temperature, aperture, and color saturation;

[0189] Obtain the adjustment range of each photographic parameter in the photographic parameters to obtain a plurality of adjustment ranges, where the plurality of adjustment ranges include: a brightness range, a color temperature range, an aperture range, and a color saturation range;

[0190] Combine the plurality of adjustment ranges to obtain a plurality of parameter combinations, and obtain an initial set of shooting objects, where the initial set of shooting objects includes a plurality of initial shooting objects;

[0191] Sequentially extract a parameter combination from the plurality of parameter combinations, and perform the following operations on the extracted parameter combination:

[0192] Adjust the camera using the parameter combination, and use the adjusted camera to shoot the initial set of shooting objects to obtain a plurality of initial images;

[0193] Evaluate the parameter combination corresponding to each initial image in the plurality of initial images to obtain a set of parameter evaluation values, confirm the optimal parameter combination based on the set of parameter evaluation values, and construct a parameter regulation database with the initial image corresponding to the optimal parameter combination;

[0194] Obtain a target shooting object picture, retrieve similar shooting objects for the target shooting object in the parameter regulation database according to the pre-constructed image similarity technology and the pre-constructed regulation factors, obtain a reference shooting object, and obtain an optimal parameter combination based on the reference shooting object, where the target shooting object picture includes the target shooting object;

[0195] Shoot using the optimal parameter combination to obtain a captured image, and transmit the captured image to the new media environment to obtain a new media image;

[0196] If it is confirmed that the new media image does not meet the preset image effect, return to the step of using the pre-constructed image similarity technique and the pre-constructed adjustment factor until the new media image meets the preset image effect, and complete the photographic parameter adaptation adjustment method based on the new media environment based on the new media image.

[0197] Specifically, for the specific implementation method of the above instructions by the processor 10, reference can be made to Figures 1 to 3 the description of the relevant steps in the corresponding embodiment, which will not be elaborated here.

[0198] Furthermore, if the modules / units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory).

[0199] The present invention also provides a computer-readable storage medium, and the readable storage medium stores a computer program, which when executed by a processor of an electronic device, can implement:

[0200] Confirm photographic parameters, where the photographic parameters include: brightness, color temperature, aperture, and color saturation;

[0201] Obtain the adjustment range of each photographic parameter in the photographic parameters to obtain a plurality of adjustment ranges, where the plurality of adjustment ranges include: a brightness range, a color temperature range, an aperture range, and a color saturation range;

[0202] Combine the plurality of adjustment ranges to obtain a plurality of parameter combinations, and obtain an initial set of shooting objects, where the initial set of shooting objects includes a plurality of initial shooting objects;

[0203] Successively extract a parameter combination from the plurality of parameter combinations, and perform the following operations on the extracted parameter combination:

[0204] Adjust the camera using the parameter combination, and use the adjusted camera to shoot the initial set of shooting objects to obtain a plurality of initial images;

[0205] Evaluate the parameter combinations corresponding to each of the multiple initial images to obtain a set of parameter evaluation values. Based on the set of parameter evaluation values, confirm the optimal parameter combination, and construct a parameter regulation database with the initial image corresponding to the optimal parameter combination;

[0206] Obtain a picture of the target object to be photographed. According to the pre-constructed image similarity technology and the pre-constructed regulation factors, retrieve similar objects to be photographed for the target object in the parameter regulation database to obtain a reference object to be photographed. Based on the reference object to be photographed, obtain the optimal parameter combination. Among them, the picture of the target object to be photographed includes the target object;

[0207] Use the optimal parameter combination to take a picture to obtain a photographed image, and transmit the photographed image to the new media environment to obtain a new media image;

[0208] If it is confirmed that the new media image does not meet the preset image effect, return to the step of according to the pre-constructed image similarity technology and the pre-constructed regulation factors until the new media image meets the preset image effect, and complete the method for adapting and regulating the photographic parameters based on the new media environment based on the new media image.

[0209] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiment described above is only illustrative, and there may be other division methods in actual implementation.

[0210] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0211] In addition, each functional module in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware, or in the form of a combination of hardware and software functional modules.

[0212] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention.

[0213] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for adaptively controlling photographic parameters based on a new media environment, characterized in that: The method comprises: Confirming photography parameters, wherein the photography parameters include: brightness, color temperature, aperture and color saturation; Acquire an adjustment interval of each photographic parameter in the photographic parameters to obtain a plurality of adjustment intervals, wherein the plurality of adjustment intervals include: a brightness interval, a color temperature interval, an aperture interval, and a color saturation interval; Combining the multiple adjustment intervals to obtain multiple parameter combinations, and acquiring an initial object set, wherein the initial object set includes multiple initial objects; Extract one parameter combination from the multiple parameter combinations in sequence, and perform the following operations on the extracted parameter combination: Using the parameter combination to adjust the camera, and using the adjusted camera to shoot the initial set of objects to obtain a plurality of initial images; Evaluate the parameter combination corresponding to each of the multiple initial images to obtain a parameter evaluation value set, confirm the best parameter combination based on the parameter evaluation value set, and build a parameter control database with the initial image corresponding to the best parameter combination; Obtain a target object image, perform a similar object search on the target object in a parameter control database based on a pre-constructed image similarity technology and a pre-constructed control factor to obtain a reference object, and obtain an optimal parameter combination based on the reference object, wherein the target object image includes the target object; Using the optimal parameter combination to shoot, obtain a shot image, and transmit the shot image to a new media environment to obtain a new media image; If it is confirmed that the new media image does not meet the preset image effect, return to the step based on the pre-constructed image similarity technology and the pre-constructed control factor until the new media image meets the preset image effect, and complete the adaptive control method of photographic parameters based on the new media environment based on the new media image.

2. The method for adaptively controlling photographic parameters based on a new media environment as claimed in claim 1, characterized in that: The combining according to the multiple adjustment intervals to obtain multiple parameter combinations includes: Extracting adjustment intervals from the multiple adjustment intervals in sequence, and grouping the adjustment intervals according to a preset division constant to obtain multiple division components, wherein the number of division components in the multiple division components is the division constant plus 1; Calculating the data average of each of the multiple divided components respectively, and summarizing the data averages to obtain a data average group; The data average value groups are aggregated to obtain a data average value group set, wherein the data average value group set includes: a brightness average value group, a color temperature average value group, an aperture average value group and a color saturation average value group, and the data average value group set is expressed as: Q={L,S,B,C} L=[L1,…,L " ] S=[S1,…,S " ] B=[B1,…,B " ] C=[C1,…,C " ] Among them, Q represents the data average value group, L represents the brightness average value group, S represents the color temperature average value group, B represents the aperture average value group, C represents the color saturation average value group, L1 represents the first brightness data average value, L " represents the nth brightness data average, n represents the number of data average groups, S1 represents the first color temperature data average, S " represents the average value of the nth color temperature data, B1 represents the average value of the first aperture data, B " represents the average value of the nth aperture data, C1 represents the average value of the first color saturation data, C " Indicates the average value of the nth color saturation data; The brightness average value group, the color temperature average value group, the aperture average value group and the color saturation average value group in the data average value group set are paired to obtain multiple parameter combinations, wherein the multiple parameter combinations are expressed as: K=[(L1,S1,B1,C1),…,(L # ,S $ ,B ％ ,C c ),…,(L " ,S " ,B " ,C " )] 1 <l<n,1<s<n,1<b<n,1<c<n Among them, K represents multiple parameter combinations, L # represents the average brightness of the lth pixel, S $ Indicates the average color temperature of the sth color, B ％ represents the average value of the bth aperture, C c Indicates the saturation of the cth color.

3. The method for adaptively controlling photographic parameters based on a new media environment as claimed in claim 2, characterized in that: The step of evaluating the parameter combination corresponding to each of the plurality of initial images to obtain a parameter evaluation value set, and determining the best parameter combination based on the parameter evaluation value set, comprises: Extracting parameter combinations corresponding to the initial images from the multiple initial images in turn, and performing weight calculation on each pre-constructed average value parameter in the extracted parameter combination to obtain an average value weight group, wherein the average value weight group includes: brightness average value weight, color temperature average value weight, aperture average value weight and color saturation average value weight; According to the average weight group, the parameter combination is evaluated to obtain the parameter evaluation value; Summarizing the parameter evaluation values ​​to obtain a parameter evaluation value set; A maximum parameter evaluation value is extracted from the parameter evaluation value set, and an optimal parameter combination corresponding to the maximum parameter evaluation value is identified from the multiple parameter combinations.

4. The method for adaptively controlling photographic parameters based on a new media environment as claimed in claim 3, characterized in that: The method of searching for similar objects to the target object in the parameter control database according to the pre-constructed image similarity technology and the pre-constructed control factor to obtain the reference object includes: Extracting target matching images from the parameter control database in sequence, and segmenting the target matching images according to a preset standard interval to obtain multiple matching areas; For each of the multiple matching regions, perform the following operations: Get the color histogram of the matching area to obtain the matching histogram; Segment the target object image according to a preset standard interval to obtain multiple image regions; Determine a co-located image region in the plurality of image regions according to the matching region, obtain a color histogram of the co-located image region to obtain an image histogram, and compare the matching histogram with the image histogram to obtain a comparison graph, wherein the horizontal axis of the comparison graph is the color space and the vertical axis is the frequency; Calculate the color similarity between the image area and the matching area according to the comparison chart and the pre-constructed color similarity formula; Calculate the image texture similarity between the image area and the matching area, and determine the target area similarity based on the image texture similarity and color similarity; Summarizing the target region similarities of the target matching image to obtain multiple target region similarities, and determining the target image similarity according to the multiple target region similarities; If the target image similarity is greater than or equal to 90, the target matching image is used as the reference object, and the extraction of the target matching image from the parameter control database is stopped; If the target image similarity is less than 90, return to the step of sequentially extracting target matching images from the parameter control database until the target image similarity is greater than or equal to 90, and then use the target matching image as the reference object.

5. The method for adaptively controlling photographic parameters based on a new media environment as claimed in claim 4, characterized in that: The color similarity formula is as follows: Among them, (R, B) represents color similarity, R represents image histogram, B represents matching histogram, N represents the number of pixels in the color space of the comparison image, i represents the pixel index in the comparison image, and r represents the pixel index in the comparison image. i represents the frequency of the image histogram in the i-th color space, b i Represents the frequency of the matching histogram in the i-th color space, Max(r i ,b i ) represents the maximum frequency between the frequency of the image histogram in the i-th color space and the frequency of the matching histogram in the i-th color space, and a represents the regulation factor.

6. The method for adaptively controlling photographic parameters based on a new media environment as claimed in claim 5, characterized in that: The calculating the image texture similarity between the image area and the matching area comprises: The image area and the matching area are both reduced according to a preset reduction ratio to obtain a scaled image area and a scaled matching area; The scaled image area and the scaled matching area are converted into grayscale to obtain a grayscale image area and a grayscale matching area; Extracting texture features in the grayscale image region to obtain a first texture feature, and synthesizing the first texture feature to obtain a first synthesis vector, wherein the first synthesis vector includes: a second-order moment of the grayscale image region, a contrast of the grayscale image region, an inverse moment of the grayscale image region, and an entropy of the grayscale image region; Extracting texture features in the grayscale matching area to obtain a second texture feature, and synthesizing the second texture feature to obtain a second synthesis vector, wherein the second synthesis vector includes: the second-order moment of the grayscale matching image, the contrast of the grayscale matching image, the inverse moment of the grayscale matching image, and the entropy of the grayscale matching image; The cosine similarity between the first integrated vector and the second integrated vector is calculated using a pre-constructed cosine similarity formula to obtain the image texture similarity.

7. The method for adaptively controlling photographic parameters based on a new media environment as claimed in claim 6, characterized in that: The cosine similarity formula is as follows: Among them, S represents cosine similarity, E 1j represents the jth element in the first comprehensive vector, E +j represents the j-th element in the second integrated vector, m represents the total number of elements in the first integrated vector and the second integrated vector, and j represents the index.

8. The method for adaptively controlling photographic parameters based on a new media environment as claimed in claim 7, characterized in that: The parameter control database is constructed using the initial image corresponding to the optimal parameter combination, including: Determine the size of the initial image corresponding to the best parameter combination; If it is confirmed that the size of the initial image is larger than the preset size range, the initial image is intelligently cropped, and the key areas in the initial image are retained using a pre-built saliency detection algorithm until the size of the initial image is equal to the preset size range, to obtain a cropped image, and use the cropped image to construct a parameter control database.

9. The method for adaptively controlling photographic parameters based on a new media environment as claimed in claim 8, characterized in that: The method further comprises performing weight calculation on each pre-constructed average value parameter in the extracted parameter combination to obtain an average value weight group, including: Perform the following operations on each average value parameter in the extracted parameter combination: Normalize the average parameter to obtain a normalized parameter, calculate the importance score of the normalized parameter according to the pre-constructed importance score, and calculate the average weight according to the importance score; The weight calculation formula is as follows: Among them, w i represents the i-th average weight, Q i represents the importance score of the i-th normalized parameter, q represents the mean value index, u represents the number of parameters, and Q represents the importance score of the normalized parameter; Sum up the mean weights to get the mean weight group.

10. A photography parameter adaptive control system based on a new media environment, characterized in that: The system comprises: A photographic parameter confirmation module, used to confirm photographic parameters, wherein the photographic parameters include: brightness, color temperature, aperture and color saturation, obtain an adjustment interval of each photographic parameter in the photographic parameters, and obtain multiple adjustment intervals, wherein the multiple adjustment intervals include: a brightness interval, a color temperature interval, an aperture interval and a color saturation interval; An initial image shooting module is used to combine according to the multiple adjustment intervals to obtain multiple parameter combinations, obtain an initial shooting object set, wherein the initial shooting object set includes multiple initial shooting objects, extract a parameter combination from the multiple parameter combinations in turn, and perform the following operations on the extracted parameter combination: adjust the camera using the parameter combination, and use the adjusted camera to shoot the initial shooting object set to obtain multiple initial images, evaluate the parameter combination corresponding to each of the multiple initial images to obtain a parameter evaluation value set, confirm the best parameter combination based on the parameter evaluation value set, and build a parameter control database with the initial image corresponding to the best parameter combination; a parameter control module, used to obtain a target object image, perform a similar object search on the target object in a parameter control database according to a pre-constructed image similarity technology and a pre-constructed control factor, obtain a reference object, obtain an optimal parameter combination based on the reference object, wherein the target object image includes the target object, and the target object is photographed using the optimal parameter combination to obtain a photographed image, and the photographed image is transmitted to a new media environment to obtain a new media image; The new media image evaluation module is used to return to the step based on the pre-constructed image similarity technology and the pre-constructed control factor if it is confirmed that the new media image does not meet the preset image effect, until the new media image meets the preset image effect, and complete the adaptive control method of photographic parameters based on the new media environment based on the new media image.

Images