Image clarity enhancement method and system for camera device

By training and optimizing high-resolution and low-resolution image data using convolutional neural networks, an image sharpness enhancement network is obtained. This solves the problem of complex image enhancement operations and limited effects in existing technologies, and realizes intelligent and adaptive image sharpness enhancement, thereby improving the efficiency of image quality adjustment.

CN118134815BActive Publication Date: 2024-11-12TIANCHUANG HENGDA DIGITAL VIDEO TECH DEV (BEIJING) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410103194.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-01-25
Publication Date
2024-11-12
Estimated Expiration
2044-01-25

AI Technical Summary

Technical Problem

Existing image enhancement operations are complex and have limited effects, resulting in low efficiency in image quality adjustment.

Method used

A convolutional neural network structure is used to train and optimize high-definition and low-definition camera image datasets to obtain an image sharpness enhancement network, which is then integrated into the image enhancement module. Intelligent and adaptive image sharpness enhancement is achieved through image region enhancement integration.

Benefits of technology

It achieves intelligent and efficient enhancement of image sharpness, reduces the complexity of image enhancement processing, and improves the efficiency of image quality adjustment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118134815B_ABST
    Figure CN118134815B_ABST
Patent Text Reader

Abstract

The present invention discloses an image definition enhancement method and system for a camera device, and relates to the field of image processing technology. The method comprises: performing definition loss processing on a high-definition camera image data set to obtain a low-definition camera image data set; performing mapping association preprocessing on the low-definition camera image data set and the high-definition camera image data set, determining a camera image sample data set for training optimization, obtaining an image definition enhancement network, and integrating and deploying it into an image enhancement module; performing definition recognition and division on target camera image information to determine image region information to be enhanced; enhancing and integrating the image region information to be enhanced based on the image enhancement module to obtain a target high-definition camera image. The technical effect of realizing intelligent, adaptive and efficient enhancement of image definition, reducing the complexity of image enhancement processing, ensuring image definition enhancement effect, and thus improving image quality adjustment efficiency is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image clarity enhancement method and system for a camera device. Background Art

[0002] With the development of science and technology, cameras have penetrated into all aspects of people's daily life and work, from smartphone cameras that record daily life, to professional cameras used at work, to security monitoring systems, etc., they all play an important role. However, in actual application, due to the influence of factors such as lighting and camera quality, the captured images may be blurred or unclear. Therefore, in order to ensure the quality of the captured images, it is crucial to enhance the image clarity. However, the existing image enhancement operation is complex and has limited effect, resulting in low efficiency in image quality adjustment. Summary of the invention

[0003] The present application solves the technical problem that the image enhancement operation in the prior art is complex and has limited effect, resulting in low efficiency of image quality adjustment by providing an image clarity enhancement method and system for a camera device. The application achieves the technical effect of realizing intelligent, adaptive and efficient enhancement of image clarity, reducing the complexity of image enhancement processing, ensuring the image clarity enhancement effect, and thereby improving the image quality adjustment efficiency.

[0004] In view of the above problems, the present invention provides an image definition enhancement method and system for a camera device.

[0005] In a first aspect, the present application provides an image clarity enhancement method for a camera device, the method comprising: obtaining an image enhancement module, the image enhancement module being communicatively connected to a target camera device; acquiring a high-definition camera image data set, performing clarity loss processing on the high-definition camera image data set, and obtaining a low-definition camera image data set; performing mapping and association preprocessing on the low-definition camera image data set and the high-definition camera image data set to determine a camera image sample data set; training and optimizing the camera image sample data set using a convolutional neural network structure to acquire an image clarity enhancement network, and integrating and deploying the image clarity enhancement network into the image enhancement module; acquiring target camera image information through the target camera device, performing clarity recognition and division on the target camera image information, and determining image area information to be enhanced; performing image area enhancement integration on the image area information to be enhanced based on the image enhancement module to obtain a target high-definition camera image.

[0006] On the other hand, the present application also provides an image clarity enhancement system for a camera device, the system comprising: an image enhancement module for acquiring an image enhancement module, the image enhancement module being communicatively connected to a target camera device; a clarity loss processing module for acquiring a high-definition camera image data set, performing clarity loss processing on the high-definition camera image data set, and obtaining a low-definition camera image data set; a mapping association preprocessing module for performing mapping association preprocessing on the low-definition camera image data set and the high-definition camera image data set to determine a camera image sample data set A model training optimization module is used to train and optimize the camera image sample data set using a convolutional neural network structure, obtain an image clarity enhancement network, and integrate the image clarity enhancement network into the image enhancement module; a clarity recognition and division module is used to acquire target camera image information through the target camera device, perform clarity recognition and division on the target camera image information, and determine the image area information to be enhanced; an image area enhancement integration module is used to perform image area enhancement integration on the image area information to be enhanced based on the image enhancement module to obtain a target high-definition camera image.

[0007] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0008] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The invention adopts a technical solution that performs clarity loss processing on a high-definition camera image data set to obtain a low-definition camera image data set, and then performs mapping association preprocessing on the low-definition camera image data set and the high-definition camera image data set, determines a camera image sample data set for training optimization, obtains an image clarity enhancement network, and integrates and deploys the image clarity enhancement network into an image enhancement module; collects and obtains target camera image information for clarity recognition and division, determines the image area information to be enhanced; and performs image area enhancement integration on the image area information to be enhanced based on the image enhancement module to obtain the target high-definition camera image. Thus, the technical effect of realizing intelligent, adaptive and efficient enhancement of image clarity, reducing the complexity of image enhancement processing, ensuring the image clarity enhancement effect, and thus improving the efficiency of image quality adjustment is achieved.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a flow chart of the method for enhancing image clarity of a camera device according to the present application;

[0013] Figure 2 A schematic diagram of a flow chart of obtaining a low-definition camera image data set in the image definition enhancement method for a camera device in the present application;

[0014] Figure 3 This is a structural schematic diagram of an image clarity enhancement system for a camera device in the present application;

[0015] Figure 4 This is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0016] Explanation of the reference numerals: image enhancement module 11, clarity loss processing module 12, mapping association preprocessing module 13, model training optimization module 14, clarity recognition and division module 15, image area enhancement integration module 16, bus 1110, processor 1120, transceiver 1130, bus interface 1140, memory 1150, operating system 1151, application 1152 and user interface 1160. DETAILED DESCRIPTION

[0017] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0018] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0019] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0020] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0021] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0022] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0023] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0024] The present application is described below in conjunction with the drawings in the present application.

[0025] Embodiment 1

[0026] like Figure 1 As shown, the present application provides an image clarity enhancement method for a camera device, the method comprising:

[0027] Step S1: obtaining an image enhancement module, wherein the image enhancement module is communicatively connected with a target camera device;

[0028] Specifically, in order to achieve intelligent and efficient enhancement of image clarity, an image enhancement module is set up. The image enhancement module is a functional application module for image clarity processing and is communicatively connected to a target camera device, wherein the target camera device is an image acquisition device applied by a user. By functionally connecting the image enhancement module, the blurry and unclear images acquired by the target camera device can be efficiently and timely enhanced in clarity to ensure the image application quality.

[0029] Step S2: acquiring a high-definition camera image data set, and performing definition loss processing on the high-definition camera image data set to obtain a low-definition camera image data set;

[0030] like Figure 2 As shown, further, the step of obtaining the low-resolution camera image data set in this application also includes:

[0031] Acquiring multi-dimensional index information of clarity, wherein the multi-dimensional index information of clarity includes resolution, contrast, edge sharpness, texture detail, and color accuracy;

[0032] Performing a multi-dimensional weighted definition evaluation on each image data in the high-definition camera image data set by using the definition multi-dimensional index information to obtain a camera image high-definition evaluation value set;

[0033] According to the camera image high definition evaluation value set, an image definition loss element process is configured, and the image definition loss element process is orthogonally designed and combined to obtain an image definition loss processing array;

[0034] The high-definition camera image data set is subjected to definition loss processing based on the image definition loss processing array to obtain the low-definition camera image data set.

[0035] Specifically, a high-definition camera image data set is acquired through big data technology, and the high-definition camera image data set is the historical high-definition camera image information captured and collected by various types of camera devices. In order to obtain the corresponding low-definition camera images, the high-definition camera image data set is subjected to clarity loss processing, and firstly, the clarity multi-dimensional index information is formulated and acquired, and the clarity multi-dimensional index information is used to perform a multi-dimensional and comprehensive evaluation of the image clarity, including resolution, the pixel density in the image; contrast, the brightness difference between the brightest and darkest parts of the image; edge sharpness, the clarity of the image edge; texture details, the richness and fineness of the texture in the image; color accuracy, the accuracy of the color in the image. Through the clarity multi-dimensional index information, each image data in the high-definition camera image data set is subjected to a multi-dimensional weighted clarity evaluation, and the evaluation value rules for each index can be set by itself, and then the evaluation value of each index is weightedly calculated by the same index weight to obtain the corresponding camera image high-definition evaluation value set of each high-definition camera image data.

[0036] The image clarity loss element process is configured according to the camera image high-definition evaluation value set. The image clarity loss element process is the image clarity loss processing method and the degree of processing of each method, including interpolation method to reduce resolution, add noise, blur and other methods. Then, the parameters of each loss processing method in the image clarity loss element process are orthogonally designed and combined to improve the diversity of loss processing method parameters, thereby obtaining an image clarity loss processing array, which is an arrangement and combination of loss processing parameters for each high-definition image. Based on the image clarity loss processing array, each image data in the high-definition camera image data set is subjected to clarity loss processing to obtain a corresponding low-definition camera image data set, which is a low-definition image set obtained after each high-definition image is operated with different loss processing parameters. Improve the diversity and comprehensiveness of low-definition image processing, increase the amount of image sample data, and thus ensure the accuracy of the subsequent image clarity enhancement network.

[0037] Step S3: performing mapping association preprocessing on the low-definition camera image data set and the high-definition camera image data set to determine a camera image sample data set;

[0038] Furthermore, the step of determining the camera image sample data set also includes:

[0039] Matching and mapping the low-resolution camera image data set and the high-resolution camera image data set to obtain an equivalent photographic image data set;

[0040] Performing scaling and normalization preprocessing on each equivalent image in the equivalent photographic image data set to obtain a standard photographic image data set;

[0041] According to the image enhancement requirement, image change matrix information is determined, and data enhancement is performed on the standard photographic image data set based on the image change matrix information to obtain a camera-enlarged image data set;

[0042] The photographic image sample data set is determined based on the standard photographic image data set and the photographic augmented image data set.

[0043] Specifically, the low-definition camera image data set and the high-definition camera image data set are mapped and associated preprocessed. First, the low-definition camera image data set and the high-definition camera image data set are matched and mapped, that is, each high-definition camera image data is matched and integrated with the corresponding low-definition camera image data set after its clarity loss processing, and an equivalent photographic image data set is obtained. The equivalent photographic image data set is each type of photographic image data before and after the clarity loss processing. In order to improve the efficiency of model training, each equivalent image in the equivalent photographic image data set is scaled, that is, the size of the image is adjusted to the size required for the model input. For example, for some convolutional neural network models, the size of the input image is usually 224*224 pixels or 320*320 pixels; normalization preprocessing, that is, the pixel value range of the image is converted from an integer range of 0-255 to a floating point range of 0-1, so that the model training is more stable and the convergence speed can be accelerated, and the preprocessed standard photographic image data set is obtained.

[0044] In order to increase the amount of model training data, the image change matrix information is determined according to the image enhancement requirements, wherein the image enhancement requirements are image data transformation type requirements to increase the amount of image data, including rotation, flipping, cropping, etc., and the image change matrix corresponding to the image transformation type is determined by using the geometric transformation of computer graphics. Different image transformation types have different corresponding image change matrices, and the image change matrix is ​​used to perform product transformation on the image data vector. Based on the image change matrix information, the standard photographic image data set is data enhanced, that is, each standard photographic image data is transformed and enhanced by various types of image change matrix information to obtain a camera augmented image data set after data enhancement. Based on the standard photographic image data set and the camera augmented image data set, a camera image sample data set is determined as the model training sample data. Increasing the amount of model sample training data improves the generalization ability of the model, thereby improving the training efficiency and training performance of the model.

[0045] Step S4: using a convolutional neural network structure to train and optimize the camera image sample data set, obtaining an image definition enhancement network, and integrating and deploying the image definition enhancement network into the image enhancement module;

[0046] Furthermore, the step of acquiring the image definition enhancement network in this application further includes:

[0047] Acquire a convolutional neural network structure, wherein the convolutional neural network structure includes a plurality of convolutional layers, a pooling layer, and a fully connected layer;

[0048] Performing definition enhancement training on the camera image sample data set using the convolutional neural network structure to generate a basic definition enhancement network;

[0049] Define a network loss function to perform a verification test on the basic definition enhancement network, and determine a network enhancement loss verification result;

[0050] The basic definition enhancement network is tuned based on the network enhancement loss verification result to obtain the image definition enhancement network.

[0051] Furthermore, the step of obtaining the image definition enhancement network in this application further includes:

[0052] Extracting model parameters of the basic definition enhancement network and determining network weights and network bias items;

[0053] Iteratively updating the network weights and network bias items through a back-propagation algorithm and the network enhancement loss verification result to obtain network update parameter information;

[0054] The basic definition enhancement network is tuned based on the network update parameter information to obtain the image definition enhancement network.

[0055] Specifically, the camera image sample data set is trained and optimized using a convolutional neural network structure. First, a deep learning framework is used to obtain a convolutional neural network structure, which includes multiple convolutional layers, pooling layers, and fully connected layers. The convolutional layers are used to extract local features in the image, the pooling layers are used to reduce the feature dimension, and the fully connected layers are used to map the features to the final output. The camera image sample data set is trained for clarity enhancement using the convolutional neural network structure to generate a basic clarity enhancement network, which is used to learn the feature representation of a high-definition image from a low-definition image. In order to measure the performance of the model, a network loss function is defined to verify and test the basic clarity enhancement network. For image clarity enhancement tasks, commonly used loss functions include perceptual loss functions, adversarial loss functions, etc. The network enhancement loss verification result is calculated and determined. The network enhancement loss verification result is the model enhancement processing effect, which is used to measure the difference between the image output by the model and the high-definition image.

[0056] Based on the network enhancement loss verification result, the basic definition enhancement network is tuned. First, the model parameters of the basic definition enhancement network are extracted to determine the model parameters, including network weights, which are used to represent the connection strength between each neuron in the neural network; the network bias term is a fixed input of each neuron, which can increase or decrease the output of the neuron. The network weights and network bias terms are iteratively updated through the back propagation algorithm and the network enhancement loss verification result, that is, the model parameters are adjusted according to the input data and the error, so as to better learn and predict the output, and the weights and bias terms of the model are continuously adjusted through the back propagation algorithm to minimize the value of the loss function, so that the network output can better adapt to the training data, so as to obtain the network update parameter information after iterative optimization, and the network update parameter information includes the network weights and network bias terms after parameter optimization and update. And based on the network update parameter information, the basic definition enhancement network is tuned and updated to obtain an image definition enhancement network after the model parameters are optimized for low-definition image enhancement processing. And the image definition enhancement network is integrated and deployed into the image enhancement module to facilitate real-time processing and enhancement of the acquired image. By tuning the model parameters, the model performance is improved, the image clarity is intelligently and efficiently enhanced, the complexity of image enhancement processing is reduced, and the quality of image clarity enhancement is ensured.

[0057] Step S5: acquiring target camera image information through the target camera device, performing definition recognition and division on the target camera image information, and determining the image area information to be enhanced;

[0058] Furthermore, the step of determining the image area information to be enhanced in this application further includes:

[0059] Divide the target camera image information into grids of preset sizes to obtain a camera image grid area information set;

[0060] Performing clarity evaluation on each grid area in the camera image grid area information set using the clarity multi-dimensional index information to obtain an image grid area clarity evaluation value set;

[0061] Compare and divide the grid areas that do not meet the preset clarity threshold in the image grid area clarity evaluation value set to determine clarity level information to be optimized;

[0062] Based on the clarity level information to be optimized, the grid area that does not meet the preset clarity threshold is enhanced and marked to determine the image area information to be enhanced.

[0063] Specifically, the target camera image information is acquired through the target camera device, and the target camera image information is a photographic image to be processed that is acquired in real time. In order to improve the image clarity enhancement processing efficiency, the target camera image information is divided for clarity recognition. First, the target camera image information is divided into a grid of a preset size, wherein the preset size grid is set according to the image acquisition size and the division fineness requirement, and the camera image grid area information set after grid division is obtained, and the entire camera image is divided into a grid area set of preset size. Then, the clarity of each grid area in the camera image grid area information set is evaluated through the clarity multidimensional indicator information to obtain a corresponding image grid area clarity evaluation value set.

[0064] The grid areas in the image grid area clarity evaluation value set that do not meet the preset clarity threshold are compared and divided, wherein the preset clarity threshold is the application clarity benchmark of the camera image, which can be determined according to the application requirements, and the clarity difference of the grid areas that do not meet the preset clarity threshold is used as the clarity level information to be optimized, that is, the degree of image clarity that needs to be optimized and enhanced. Based on the clarity level information to be optimized, the grid areas that do not meet the preset clarity threshold are enhanced and marked, and the image area information to be enhanced that needs clarity enhancement in the target camera image information is determined. Adaptive image clarity enhancement is achieved through image gridding area division, ensuring personalized image clarity enhancement and image clarity enhancement effect, thereby improving the image clarity enhancement adjustment efficiency.

[0065] Step S6: Based on the image enhancement module, image region enhancement integration is performed on the image region information to be enhanced to obtain a target high-definition camera image.

[0066] Furthermore, the step of obtaining the target high-definition camera image also includes:

[0067] Determining an image grid area code according to the camera image grid area information set;

[0068] Based on the image definition enhancement network, the definition of the image area information to be enhanced is respectively enhanced, and the grid area definition enhancement information is output;

[0069] The grid area definition enhancement information is integrated into the image area according to the image grid area coding to obtain the target high-definition camera image.

[0070] Specifically, based on the image enhancement module, the image region information to be enhanced is integrated for image region enhancement. First, a region coding rule is set. For example, each image grid region in the camera image grid region information set is sequentially encoded according to the coding rules from top to bottom and from left to right, so as to determine the image grid region coding, and improve the image processing standardization and processing efficiency through region coding. Then, based on the image clarity enhancement network in the image enhancement module, the image region information to be enhanced is respectively enhanced for clarity, and the corresponding grid region clarity enhancement information is output. The grid region clarity enhancement information is the image grid region information after the clarity enhancement of the image region information to be enhanced. Finally, the grid region clarity enhancement information is integrated according to the image grid region coding to ensure that the clarity of each image grid region can meet the application standard, so as to obtain the target high-definition camera image, and the target high-definition camera image is the target camera image information after the clarity enhancement processing. The image clarity is adaptively and efficiently enhanced, the complexity of image enhancement processing is reduced, the image clarity enhancement effect is ensured, and the image quality adjustment efficiency is improved.

[0071] In summary, the image clarity enhancement method and system for a camera device provided by the present application have the following technical effects:

[0072] The invention adopts a technical solution that performs clarity loss processing on a high-definition camera image data set to obtain a low-definition camera image data set, and then performs mapping association preprocessing on the low-definition camera image data set and the high-definition camera image data set, determines a camera image sample data set for training optimization, obtains an image clarity enhancement network, and integrates and deploys the image clarity enhancement network into an image enhancement module; collects and obtains target camera image information for clarity recognition and division, determines the image area information to be enhanced; and performs image area enhancement integration on the image area information to be enhanced based on the image enhancement module to obtain the target high-definition camera image. Thus, the technical effect of realizing intelligent, adaptive and efficient enhancement of image clarity, reducing the complexity of image enhancement processing, ensuring the image clarity enhancement effect, and thus improving the efficiency of image quality adjustment is achieved.

[0073] Embodiment 2

[0074] Based on the same inventive concept as the image definition enhancement method for a camera device in the aforementioned embodiment, the present invention also provides an image definition enhancement system for a camera device, such as Figure 3 As shown, the system comprises:

[0075] An image enhancement module 11, used to obtain an image enhancement module, wherein the image enhancement module is communicatively connected to a target camera device;

[0076] The definition loss processing module 12 is used to collect and obtain a high-definition camera image data set, and perform definition loss processing on the high-definition camera image data set to obtain a low-definition camera image data set;

[0077] A mapping association preprocessing module 13 is used to perform mapping association preprocessing on the low-definition camera image data set and the high-definition camera image data set to determine a camera image sample data set;

[0078] A model training optimization module 14 is used to train and optimize the camera image sample data set using a convolutional neural network structure, obtain an image definition enhancement network, and integrate and deploy the image definition enhancement network into the image enhancement module;

[0079] A definition recognition and division module 15 is used to acquire target camera image information through the target camera device, perform definition recognition and division on the target camera image information, and determine the image area information to be enhanced;

[0080] The image region enhancement integration module 16 is used to perform image region enhancement integration on the image region information to be enhanced based on the image enhancement module to obtain a target high-definition camera image.

[0081] Furthermore, the system also includes:

[0082] A clarity multi-dimensional index acquisition unit, used to acquire clarity multi-dimensional index information, wherein the clarity multi-dimensional index information includes resolution, contrast, edge sharpness, texture details, and color accuracy;

[0083] A multi-dimensional weighted evaluation unit, configured to perform a multi-dimensional weighted definition evaluation on each image data in the high-definition camera image data set according to the definition multi-dimensional index information, so as to obtain a camera image high-definition evaluation value set;

[0084] An orthogonal design combination unit, configured to configure an image clarity loss element process according to the camera image high-definition evaluation value set, and perform orthogonal design combination on the image clarity loss element process to obtain an image clarity loss processing array;

[0085] The clarity loss processing unit is used to perform clarity loss processing on the high-definition camera image data set based on the image clarity loss processing array to obtain the low-definition camera image data set.

[0086] Furthermore, the system also includes:

[0087] A matching and mapping unit, used for matching and mapping the low-definition camera image data set and the high-definition camera image data set to obtain an equivalent photographic image data set;

[0088] An image preprocessing unit, used for performing scaling and normalization preprocessing on each equivalent image in the equivalent photographic image data set to obtain a standard photographic image data set;

[0089] An image data enhancement unit, configured to determine image change matrix information according to image enhancement requirements, and perform data enhancement on the standard photographic image data set based on the image change matrix information to obtain a camera-enlarged image data set;

[0090] The image sample data determining unit is used to determine the camera image sample data set based on the standard photographic image data set and the camera amplified image data set.

[0091] Furthermore, the system also includes:

[0092] A network structure acquisition unit, used to acquire a convolutional neural network structure, wherein the convolutional neural network structure includes a plurality of convolutional layers, a pooling layer, and a fully connected layer;

[0093] A definition enhancement training unit, used to perform definition enhancement training on the camera image sample data set using the convolutional neural network structure to generate a basic definition enhancement network;

[0094] A network verification test unit, used to define a network loss function to perform a verification test on the basic definition enhancement network and determine a network enhancement loss verification result;

[0095] A definition enhancement network acquisition unit is used to tune the basic definition enhancement network based on the network enhancement loss verification result to obtain the image definition enhancement network.

[0096] Furthermore, the system also includes:

[0097] A model parameter extraction unit, used to extract model parameters of the basic definition enhancement network and determine network weights and network bias items;

[0098] A parameter iterative updating unit, used for iteratively updating the network weight and the network bias item through a back propagation algorithm and the network enhancement loss verification result to obtain network update parameter information;

[0099] The enhancement network tuning unit is used to tune the basic definition enhancement network based on the network update parameter information to obtain the image definition enhancement network.

[0100] Furthermore, the system also includes:

[0101] An image grid division unit, used to divide the target camera image information into grids of a preset size to obtain a camera image grid area information set;

[0102] A clarity evaluation unit, configured to perform clarity evaluation on each grid area in the camera image grid area information set according to the clarity multi-dimensional index information, and obtain an image grid area clarity evaluation value set;

[0103] A region comparison and division unit, used for comparing and dividing the grid regions that do not meet the preset clarity threshold in the image grid region clarity evaluation value set, and determining clarity level information to be optimized;

[0104] The area enhancement marking unit is used to enhance and mark the grid area that does not meet the preset clarity threshold based on the clarity level information to be optimized, and determine the image area information to be enhanced.

[0105] Furthermore, the system also includes:

[0106] An image grid area code determination unit, used to determine the image grid area code according to the camera image grid area information set;

[0107] A definition enhancement unit, configured to respectively enhance the definition of the image area information to be enhanced based on the image definition enhancement network, and output grid area definition enhancement information;

[0108] The image area integration unit is used to perform image area integration on the grid area definition enhancement information according to the image grid area coding to obtain the target high-definition camera image.

[0109] The foregoing Figure 1 The various variations and specific examples of the image clarity enhancement method for a camera device in Embodiment 1 are also applicable to the image clarity enhancement system for a camera device in this embodiment. Through the above detailed description of the image clarity enhancement method for a camera device, those skilled in the art can clearly understand the implementation method of the image clarity enhancement system for a camera device in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0110] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and run on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method embodiment for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0111] Exemplary Electronic Devices

[0112] For details, see Figure 4 As shown, the present application also provides an electronic device, which includes a bus 1110 , a processor 1120 , a transceiver 1130 , a bus interface 1140 , a memory 1150 and a user interface 1160 .

[0113] In the present application, the electronic device further includes: a computer program stored in the memory 1150 and executable on the processor 1120, and when the computer program is executed by the processor 1120, each process of the above-mentioned method embodiment for controlling output data is implemented.

[0114] The transceiver 1130 is configured to receive and send data under the control of the processor 1120 .

[0115] In the present application, a bus architecture (represented by bus 1110 ) may include any number of interconnected buses and bridges, and bus 1110 connects various circuits including one or more processors represented by processor 1120 and a memory represented by memory 1150 .

[0116] Bus 1110 represents one or more of any of several types of bus structures, including a memory bus and memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. Such architectures include, by way of example and not limitation, an Industry Standard Architecture bus, a Micro Channel Architecture bus, an expansion bus, a Video Electronics Standards Association, a Peripheral Component Interconnect bus.

[0117] The processor 1120 may be an integrated circuit chip having signal processing capabilities. In the implementation process, each step of the above method embodiment may be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processors include: a general-purpose processor, a central processing unit, a network processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, a complex programmable logic device, a programmable logic array, a microcontroller unit or other programmable logic device, a discrete gate, a transistor logic device, and a discrete hardware component. The various methods, steps, and logic block diagrams disclosed in this application may be implemented or executed. For example, the processor may be a single-core processor or a multi-core processor, and the processor may be integrated into a single chip or located on multiple different chips.

[0118] Processor 1120 may be a microprocessor or any conventional processor. The method steps disclosed in the present application may be directly executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a readable storage medium known in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, a register, etc. The readable storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0119] The bus 1110 may also connect various other circuits such as peripheral devices, voltage regulators or power management circuits, and the bus interface 1140 provides an interface between the bus 1110 and the transceiver 1130, which are well known in the art. Therefore, this application will not further describe them.

[0120] The transceiver 1130 may be one element or multiple elements, such as multiple receivers and transmitters, and provides a unit for communicating with various other devices on a transmission medium. For example, the transceiver 1130 receives external data from other devices, and the transceiver 1130 is used to send data processed by the processor 1120 to other devices. Depending on the nature of the computer device, a user interface 1160 may also be provided, such as a touch screen, a physical keyboard, a display, a mouse, a speaker, a microphone, a trackball, a joystick, or a stylus.

[0121] It should be understood that in the present application, the memory 1150 may further include a memory remotely arranged relative to the processor 1120, and these remotely arranged memories may be connected to the server through a network. One or more parts of the above network may be a self-organizing network, an intranet, an extranet, a virtual private network, a local area network, a wireless local area network, a wide area network, a wireless wide area network, a metropolitan area network, the Internet, a public switched telephone network, a plain old telephone service network, a cellular telephone network, a wireless network, a wireless fidelity network, and a combination of two or more of the above networks. For example, the cellular telephone network and the wireless network may be a global mobile communication device, a code division multiple access device, a global microwave interconnection access device, a general packet radio service device, a wideband code division multiple access device, a long term evolution device, a LTE frequency division duplex device, a LTE time division duplex device, an advanced long term evolution device, a universal mobile communication device, an enhanced mobile broadband device, a massive machine type communication device, an ultra-reliable low latency communication device, and the like.

[0122] It should be understood that the memory 1150 in the present application may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory includes: a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, or a flash memory.

[0123] Volatile memory includes random access memory, which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronously linked dynamic random access memory, and direct memory bus random access memory. The memory 1150 of the electronic device described in the present application includes, but is not limited to, the above and any other suitable types of memory.

[0124] In the present application, the memory 1150 stores the following elements of the operating system 1151 and the application program 1152: executable modules, data structures, or subsets thereof, or extended sets thereof.

[0125] Specifically, the operating system 1151 includes various device programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 1152 includes various application programs, such as a media player and a browser, which are used to implement various application services. The program implementing the method of the present application may be included in the application 1152. The application 1152 includes applets, objects, components, logic, data structures, and other computer device executable instructions that perform specific tasks or implement specific abstract data types.

[0126] In addition, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned method embodiment for controlling output data are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0127] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for enhancing image clarity of a camera device, characterized in that: The method comprises: Acquire an image enhancement module, wherein the image enhancement module is communicatively connected to a target camera device; Acquiring a high-definition camera image data set, and performing definition loss processing on the high-definition camera image data set to obtain a low-definition camera image data set; Performing mapping association preprocessing on the low-definition camera image data set and the high-definition camera image data set to determine a camera image sample data set; Using a convolutional neural network structure to train and optimize the camera image sample data set, obtain an image definition enhancement network, and integrate and deploy the image definition enhancement network into the image enhancement module; Acquire target camera image information through the target camera device, perform definition recognition and division on the target camera image information, and determine the image area information to be enhanced; Based on the image enhancement module, image region enhancement integration is performed on the image region information to be enhanced to obtain a target high-definition camera image; The determining of the image region information to be enhanced includes: Divide the target camera image information into grids of preset sizes to obtain a camera image grid area information set; Performing clarity evaluation on each grid area in the camera image grid area information set according to the clarity multi-dimensional index information to obtain an image grid area clarity evaluation value set; Compare and divide the grid areas that do not meet the preset clarity threshold in the image grid area clarity evaluation value set to determine clarity level information to be optimized; Based on the clarity level information to be optimized, the grid area that does not meet the preset clarity threshold is enhanced and marked, and the image area information to be enhanced is determined; The step of obtaining a high-definition camera image of a target comprises: Determining an image grid area code according to the camera image grid area information set; Based on the image definition enhancement network, the definition of the image area information to be enhanced is respectively enhanced, and the grid area definition enhancement information is output; The grid area definition enhancement information is integrated into the image area according to the image grid area coding to obtain the target high-definition camera image.

2. The method according to claim 1, characterized in that The step of obtaining a low-resolution camera image data set comprises: Acquiring multi-dimensional index information of clarity, wherein the multi-dimensional index information of clarity includes resolution, contrast, edge sharpness, texture detail, and color accuracy; Performing a multi-dimensional weighted definition evaluation on each image data in the high-definition camera image data set by using the definition multi-dimensional index information to obtain a camera image high-definition evaluation value set; According to the camera image high definition evaluation value set, an image definition loss element process is configured, and the image definition loss element process is orthogonally designed and combined to obtain an image definition loss processing array; The high-definition camera image data set is subjected to definition loss processing based on the image definition loss processing array to obtain the low-definition camera image data set.

3. The method according to claim 1, characterized in that The step of determining a camera image sample data set comprises: Matching and mapping the low-resolution camera image data set and the high-resolution camera image data set to obtain an equivalent photographic image data set; Performing scaling and normalization preprocessing on each equivalent image in the equivalent photographic image data set to obtain a standard photographic image data set; According to the image enhancement requirement, image change matrix information is determined, and data enhancement is performed on the standard photographic image data set based on the image change matrix information to obtain a camera-enlarged image data set; The photographic image sample data set is determined based on the standard photographic image data set and the photographic augmented image data set.

4. The method according to claim 1, characterized in that The method of acquiring an image definition enhancement network comprises: Acquire a convolutional neural network structure, wherein the convolutional neural network structure includes a plurality of convolutional layers, a pooling layer, and a fully connected layer; Performing definition enhancement training on the camera image sample data set using the convolutional neural network structure to generate a basic definition enhancement network; Define a network loss function to perform a verification test on the basic definition enhancement network, and determine a network enhancement loss verification result; The basic definition enhancement network is tuned based on the network enhancement loss verification result to obtain the image definition enhancement network.

5. The method according to claim 4, characterized in that The obtaining of the image definition enhancement network comprises: Extracting model parameters of the basic definition enhancement network and determining network weights and network bias items; Iteratively updating the network weights and network bias items through a back-propagation algorithm and the network enhancement loss verification result to obtain network update parameter information; The basic definition enhancement network is tuned based on the network update parameter information to obtain the image definition enhancement network.

6. An image definition enhancement system for a camera device, characterized in that: The system comprises: An image enhancement module, used to obtain an image enhancement module, wherein the image enhancement module is communicatively connected to a target camera device; A definition loss processing module is used to collect and obtain a high-definition camera image data set, and perform definition loss processing on the high-definition camera image data set to obtain a low-definition camera image data set; A mapping association preprocessing module, used for performing mapping association preprocessing on the low-definition camera image data set and the high-definition camera image data set to determine a camera image sample data set; A model training optimization module, used to train and optimize the camera image sample data set using a convolutional neural network structure, obtain an image definition enhancement network, and integrate and deploy the image definition enhancement network into the image enhancement module; A definition recognition and division module is used to acquire target camera image information through the target camera device, perform definition recognition and division on the target camera image information, and determine the image area information to be enhanced; An image region enhancement integration module, used to perform image region enhancement integration on the image region information to be enhanced based on the image enhancement module, so as to obtain a target high-definition camera image; The clarity recognition and division module comprises: An image grid division unit, used to divide the target camera image information into grids of a preset size to obtain a camera image grid area information set; A clarity evaluation unit, configured to perform clarity evaluation on each grid area in the camera image grid area information set according to the clarity multi-dimensional index information, and obtain an image grid area clarity evaluation value set; A region comparison and division unit, used for comparing and dividing the grid regions that do not meet the preset clarity threshold in the image grid region clarity evaluation value set, and determining clarity level information to be optimized; A region enhancement marking unit, configured to enhance and mark the grid region that does not meet the preset definition threshold based on the definition level information to be optimized, and determine the image region information to be enhanced; The image area enhancement integration module includes: An image grid area code determination unit, used to determine the image grid area code according to the camera image grid area information set; A definition enhancement unit, configured to respectively enhance the definition of the image area information to be enhanced based on the image definition enhancement network, and output grid area definition enhancement information; The image area integration unit is used to perform image area integration on the grid area definition enhancement information according to the image grid area coding to obtain the target high-definition camera image.

7. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps of the image definition enhancement method for a camera device according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the image definition enhancement method for a camera device according to any one of claims 1 to 5 are implemented.