CN119815188A - Multi-scene adaptive image quality control method and system - Google Patents
Multi-scene adaptive image quality control method and system Download PDFInfo
- Publication number
- CN119815188A CN119815188A CN202411628895.3A CN202411628895A CN119815188A CN 119815188 A CN119815188 A CN 119815188A CN 202411628895 A CN202411628895 A CN 202411628895A CN 119815188 A CN119815188 A CN 119815188A
- Authority
- CN
- China
- Prior art keywords
- adjustment
- image quality
- image
- data
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a multi-scene self-adaptive image quality control method and a system, in particular to the technical field of image control. The method specifically comprises the steps of S1, collecting and preprocessing environment information and image data, S2, evaluating image quality, S3, adaptively adjusting image quality, S4, user feedback and personalized service, and S5, data storage, analysis and cloud cooperation. The invention integrates intelligent perception, image quality evaluation, self-adaptive adjustment strategy, user feedback and big data analysis technology, can remarkably improve image quality, adapts to different shooting environments, and meets personalized requirements of users, thereby enhancing user experience and applicability of the system.
Description
Technical Field
The invention relates to the technical field of image control, in particular to a multi-scene self-adaptive image quality control method and system.
Background
In the digital age, images and videos become important carriers for information transmission and expression, and whether social media, electronic commerce platforms, online education or other Internet application scenes, high-quality images have a vital role in improving user experience and enhancing information transmission effects.
However, with the increasing resolution and color depth of images, the size of image files increases, which brings great challenges to storage, transmission and processing of images, and thus the development of image quality optimization techniques is particularly important.
Although there are a variety of image quality optimization techniques such as image compression, image enhancement, image denoising, etc., these techniques still have a number of limitations in practical applications:
1. Conventional image compression algorithms tend to result in significant degradation of image quality, particularly at high compression ratios;
2. While some image enhancement algorithms may introduce additional noise or distortion that affects the visual effect of the image;
3. the existing image quality optimization technology is mostly optimized for specific types of images or application scenes, and lacks versatility and flexibility.
Aiming at the situation, the invention provides a multi-scene self-adaptive image quality control method and a multi-scene self-adaptive image quality control system, and the comprehensive optimization and personalized customization of the image quality are realized through the cooperative work of a self-adaptive adjustment module, a user feedback module and a data storage and analysis module.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks of the prior art, the present invention provides a multi-scene adaptive image quality control method and system, so as to solve the above-mentioned problems in the prior art.
In order to achieve the purpose, the multi-scene self-adaptive image quality control system comprises an intelligent sensing module, an image quality evaluation module, a self-adaptive adjustment module, a user feedback module and a data storage and analysis module, wherein the intelligent sensing module, the image quality evaluation module, the self-adaptive adjustment module, the user feedback module and the data storage and analysis module are connected through a data bus or a network to achieve data interaction and collaborative work.
Preferably, the intelligent sensing module is used for collecting multi-dimensional environment information and image data of a shooting scene, and further comprises an infrared sensor, a gyroscope and an accelerometer so as to realize multi-source sensor fusion.
Preferably, the image quality evaluation module is used for performing multidimensional quality evaluation including definition, contrast, noise level, color saturation, dynamic range and image stability on the image captured in real time, and high-speed image processing chip and parallel computing technology are adopted to ensure the high efficiency and instantaneity of the evaluation process.
Preferably, the adaptive adjustment module is used for generating and applying a fine adjustment strategy comprising different algorithms for different types of objects according to scene recognition results and image quality evaluation data, introducing a dynamic feedback module in the adjustment process, monitoring the adjustment effect in real time and automatically adjusting the strategy.
Preferably, the user feedback module is used for collecting and analyzing satisfaction data of the user on image quality, learning personalized preferences of the user, providing an intuitive and easy-to-use interactive adjustment interface, allowing the user to manually adjust image parameters and view effects in real time.
Preferably, the data storage and analysis module is used for efficiently storing, analyzing and cooperatively processing image data, an evaluation result, an adjustment strategy and user feedback data, supporting big data processing and cloud cooperative work, and realizing flexible configuration and sharing of resources.
A control method adopts the multi-scene self-adaptive image quality control system, and the method comprises the following steps:
S1, starting a multi-source sensor to acquire multi-dimensional environment information and image data of a shooting scene in real time by utilizing an intelligent sensing module, and preprocessing the acquired data, including denoising and filtering, so that the accuracy and the efficiency of subsequent processing are improved;
S2, the image quality evaluation module receives image data transmitted by the intelligent perception module, performs quality evaluation on the image by using a preset multi-dimensional quality evaluation index, and adopts a high-speed image processing chip and a parallel computing technology to ensure the high efficiency and real-time performance of the evaluation process and quickly generate an image quality evaluation report;
S3, the self-adaptive adjustment module receives scene recognition results and image quality evaluation data, generates and applies a fine adjustment strategy according to a preset algorithm and a strategy library, introduces a dynamic feedback module in the adjustment process, monitors adjustment effects in real time, and automatically adjusts the adjustment strategy according to the feedback results if the image quality changes before and after adjustment are compared, so that the image quality is ensured to be continuously optimized to an optimal state;
S4, a user feedback module collects satisfaction data of the user on image quality, user feedback is obtained through a questionnaire investigation and scoring system mode, user feedback data are analyzed, personalized preferences of the user are learned, including color preferences and brightness preferences, an intuitive and easy-to-use interactive adjustment interface is provided, the user is allowed to manually adjust image parameters, including exposure, white balance and sharpening, and adjustment effects are checked immediately;
S5, the data storage and analysis module is used for efficiently storing the image data, the evaluation result, the adjustment strategy and the user feedback data, carrying out deep analysis on the stored data by utilizing big data, mining rules and trends behind the data, and providing data support for system optimization, and the data storage and analysis module supports cloud collaborative work, and transfers part of calculation tasks and data storage to the cloud, so that flexible configuration and sharing of resources are realized.
Preferably, in S2, the preset multi-dimensional quality assessment indexes include, but are not limited to, sharpness, contrast, noise level, color saturation, dynamic range, and image stability of the image;
The high-speed image processing chip comprises, but is not limited to, a GPU, an FPGA or an ASIC to accelerate the image processing process, and has strong parallel processing capability and an optimized image processing algorithm library, so that the evaluation efficiency can be remarkably improved;
the parallel computing technology decomposes an image processing task into a plurality of subtasks and simultaneously executes the subtasks on a plurality of processors or computing units, so as to reduce processing time and improve evaluation instantaneity.
Preferably, in step S3, in particular;
S3.1, an adaptive adjustment module receives image quality evaluation data and scene recognition results from an image quality evaluation module and an intelligent perception module, analyzes the received data, and extracts key information such as image quality indexes and scene characteristics, wherein the image quality indexes comprise but are not limited to definition, contrast and noise level, and the scene characteristics comprise but are not limited to illumination conditions, scene types and motion states;
S3.2, inquiring a matched adjustment strategy in an algorithm and strategy library preset in the self-adaptive adjustment module according to the analyzed image quality index and scene characteristics, and selecting an adjustment strategy which is most suitable for the current scene and the image quality problem from the matched strategies;
S3.3, calculating required image processing parameters including exposure compensation values, white balance adjustment parameters and sharpening strength according to a selected adjustment strategy, configuring the calculated parameters into an image processing algorithm, and preparing for image adjustment;
s3.4, applying the configured image processing algorithm and parameters to process the image in real time so as to improve the image quality, and previewing the adjustment effect in real time in the adjustment process so as to primarily evaluate the effectiveness of the adjustment strategy;
S3.5, introducing a dynamic feedback module in the adjustment process, monitoring the image quality change after adjustment in real time, comparing the image quality before and after adjustment, and evaluating whether the adjustment effect reaches an expected target;
S3.6, analyzing the effectiveness of the adjustment strategy according to the effect evaluation result provided by the dynamic feedback module, if the adjustment effect is not ideal, automatically adjusting the adjustment strategy according to the feedback result, trying different algorithms and parameter settings, optimizing the adjustment strategy by continuous iteration and adjustment until the satisfactory image quality effect is achieved, and finally outputting the adjusted image to the display equipment or the storage medium.
The invention has the technical effects and advantages that:
1. The intelligent sensing module, the high-speed image quality evaluation and self-adaptive adjustment module can acquire multi-dimensional information of the shooting environment in real time and perform fine image quality evaluation and adjustment, so that the image quality is remarkably improved, the requirements of different shooting environments are met, and the experience of a final user is enhanced;
2. According to the invention, through the learning function of the user feedback module and the interactive adjustment interface, satisfaction degree data of the user on the image quality can be collected and analyzed, personalized preference of the user is further learned, so that the system can automatically optimize the image quality, and manual adjustment of image parameters can be performed according to personalized requirements of the user, thereby meeting customized requirements of different users;
3. The data storage and analysis module supports big data processing and cloud collaborative work, can efficiently store and deeply analyze image data, evaluation results and user feedback data, so as to mine rules and trends of the data and provide data support for continuous optimization of a system.
Drawings
Fig. 1 is an overall system diagram of the present invention.
Fig. 2 is an overall flow chart of the present invention.
Fig. 3 is a flowchart in step S3 of the present invention.
The reference sign is 1, intelligent perception module, 2, image quality evaluation module, 3, self-adaptive adjustment module, 4, user feedback module, 5, data storage and analysis module.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1,
The invention provides a multi-scene self-adaptive image quality control system, which comprises an intelligent sensing module 1, an image quality evaluation module 2, a self-adaptive adjustment module 3, a user feedback module 4 and a data storage and analysis module 5, wherein the intelligent sensing module 1, the image quality evaluation module 2, the self-adaptive adjustment module 3, the user feedback module 4 and the data storage and analysis module 5 are connected through a data bus or a network to realize data interaction and collaborative work;
The intelligent perception module 1 is used for acquiring multi-dimensional environment information and image data of a shooting scene, and further comprises an infrared sensor, a gyroscope and an accelerometer so as to realize multi-source sensor fusion;
The image quality evaluation module 2 is used for performing multidimensional quality evaluation including definition, contrast, noise level, color saturation, dynamic range and image stability on the image captured in real time, and high-speed image processing chips and parallel computing technology are adopted to ensure the high efficiency and instantaneity of the evaluation process;
The self-adaptive adjustment module 3 is used for generating and applying a fine adjustment strategy comprising different algorithms for different types of objects according to scene recognition results and image quality evaluation data, introducing a dynamic feedback module in the adjustment process, monitoring the adjustment effect in real time and automatically adjusting the strategy;
The user feedback module 4 is used for collecting and analyzing satisfaction data of the user on image quality, learning personalized preference of the user, providing an intuitive and easy-to-use interactive adjustment interface, allowing the user to manually adjust image parameters and view effects in real time;
The data storage and analysis module 5 is used for efficiently storing, analyzing and carrying out cloud collaborative processing on the image data, the evaluation result, the adjustment strategy and the user feedback data, supporting big data processing and cloud collaborative work, and realizing flexible configuration and sharing of resources.
Specifically, in the system, the intelligent perception module 1 firstly collects multi-dimensional environmental information of a shooting scene, such as illumination conditions, motion states and the like and image data in real time through integrated multi-source sensors such as infrared sensors, gyroscopes and accelerometers, and the information is comprehensively processed through a data fusion technology to provide basic data support for subsequent image quality evaluation and adjustment;
The image quality evaluation module 2 utilizes a high-speed image processing chip and a parallel computing technology to carry out multidimensional quality evaluation on the image captured in real time, wherein the multidimensional quality evaluation comprises key indexes such as definition, contrast, noise level, color saturation, dynamic range, image stability and the like;
The self-adaptive adjustment module 3 generates and applies fine adjustment strategies based on scene recognition results and image quality evaluation data, the strategies optimize different types of objects and scene characteristics by adopting different image processing algorithms, and meanwhile, by introducing the dynamic feedback module, the system can monitor the adjustment effect in real time and automatically adjust the strategies as required, so that the continuous optimization of the image quality is ensured.
The user feedback module 4 is responsible for collecting satisfaction data of users on image quality, and learning personalized preferences of the users through analysis, and in addition, an intuitive and easy-to-use interactive adjustment interface is provided, so that the users are allowed to manually adjust image parameters and view adjustment effects in real time, and the user participation mechanism enhances the flexibility and personalized service capability of the system;
the data storage and analysis module 5 is responsible for high-efficiency storage and deep analysis of image data, evaluation results, adjustment strategies and user feedback data generated in the whole system, and by supporting big data processing and cloud cooperative work, the module realizes flexible configuration and sharing of resources, and provides powerful support for continuous optimization and upgrading of the system.
In summary, the multi-scene self-adaptive image quality control system provided by the invention realizes a closed-loop control flow from environment perception to image quality optimization by integrating a plurality of functional modules such as intelligent perception, image quality evaluation, self-adaptive adjustment, user feedback, data storage analysis and the like, and remarkably improves the image quality and user experience.
EXAMPLE 2,
The embodiment provides a control method, which adopts the system, and comprises the following steps:
S1, starting a multi-source sensor by utilizing an intelligent perception module 1 to acquire multi-dimensional environment information and image data of a shooting scene in real time, preprocessing the acquired data, including denoising and filtering, and improving the accuracy and efficiency of subsequent processing.
Specifically, in this step, the intelligent sensing module 1 integrates various sensors, such as an infrared sensor, a gyroscope, an accelerometer, and an image sensor, which can capture multi-dimensional environmental information and image data of a shooting scene in real time, where the data includes but is not limited to illumination conditions, temperature, humidity, motion state, pixel values of an image, and the like, and the collected raw data often includes noise and redundant information, and these factors affect the accuracy and efficiency of subsequent processing, so that preprocessing needs to be performed on the data, and a high-quality data base is provided for subsequent image quality evaluation and optimization, thereby improving the accuracy and efficiency of the whole system.
S2, the image quality evaluation module 2 receives the image data transmitted by the intelligent perception module 1, performs quality evaluation on the image by using a preset multi-dimensional quality evaluation index, and adopts a high-speed image processing chip and a parallel computing technology to ensure the high efficiency and instantaneity of the evaluation process and quickly generate an image quality evaluation report;
The preset multi-dimensional quality evaluation indexes comprise, but are not limited to, image definition, contrast, noise level, color saturation, dynamic range and image stability, the high-speed image processing chip comprises, but is not limited to, a GPU (graphics processing unit), an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit) for accelerating the image processing process, the high-speed image processing chip has strong parallel processing capability and an optimized image processing algorithm library, the evaluation efficiency can be remarkably improved, the parallel computing technology can decompose the image processing task into a plurality of subtasks and simultaneously execute the subtasks on a plurality of processors or computing units, and the parallel computing technology is used for reducing processing time and improving the real-time performance of evaluation.
Specifically, the purpose of this step is mainly to perform comprehensive and accurate quality assessment on the image data transmitted by the intelligent perception module 1, and through preset multidimensional quality assessment indexes, the system can objectively measure the performances of the image in different aspects, such as sharpness, contrast, noise level, color saturation, dynamic range, image stability and the like, and this comprehensive assessment is helpful for the system to perform corresponding adjustment and optimization according to the assessment result so as to improve the overall quality of the image, and meanwhile, by adopting a high-speed image processing chip and parallel computing technology, the high efficiency and instantaneity of the assessment process can be ensured, which is particularly important for real-time image applications requiring quick response and processing, such as the fields of video monitoring, automatic driving and the like.
S3, the self-adaptive adjustment module 3 receives scene recognition results and image quality evaluation data, generates and applies a fine adjustment strategy according to a preset algorithm and a strategy library, introduces a dynamic feedback module in the adjustment process, monitors adjustment effects in real time, such as image quality change before and after adjustment, automatically adjusts the adjustment strategy according to the feedback results, and ensures that the image quality is continuously optimized to an optimal state, and specifically:
S3.1, an adaptive adjustment module 3 receives image quality evaluation data and scene recognition results from the image quality evaluation module 2 and the intelligent perception module 1, analyzes the received data, and extracts key information such as image quality indexes and scene characteristics, wherein the image quality indexes comprise but are not limited to definition, contrast and noise level, and the scene characteristics comprise but are not limited to illumination conditions, scene types and motion states;
s3.2, inquiring a matched adjustment strategy in an algorithm and strategy library preset in the self-adaptive adjustment module 3 according to the analyzed image quality index and scene characteristics, and selecting an adjustment strategy which is most suitable for the current scene and the image quality problem from the matched strategies;
S3.3, calculating required image processing parameters including exposure compensation values, white balance adjustment parameters and sharpening strength according to a selected adjustment strategy, configuring the calculated parameters into an image processing algorithm, and preparing for image adjustment;
s3.4, applying the configured image processing algorithm and parameters to process the image in real time so as to improve the image quality, and previewing the adjustment effect in real time in the adjustment process so as to primarily evaluate the effectiveness of the adjustment strategy;
S3.5, introducing a dynamic feedback module in the adjustment process, monitoring the image quality change after adjustment in real time, comparing the image quality before and after adjustment, and evaluating whether the adjustment effect reaches an expected target;
S3.6, analyzing the effectiveness of the adjustment strategy according to the effect evaluation result provided by the dynamic feedback module, if the adjustment effect is not ideal, automatically adjusting the adjustment strategy according to the feedback result, trying different algorithms and parameter settings, optimizing the adjustment strategy by continuous iteration and adjustment until the satisfactory image quality effect is achieved, and finally outputting the adjusted image to the display equipment or the storage medium.
Specifically, the self-adaptive adjustment module 3 in this step receives image quality evaluation data and scene recognition results from the image quality evaluation module 2 and the intelligent perception module 1, wherein the data comprise image quality indexes such as definition, contrast and noise level and scene characteristics such as illumination condition, scene type and motion state, the module analyzes the data to extract key information, the self-adaptive adjustment module 3 queries matched adjustment strategies in a preset algorithm and strategy library according to the analyzed image quality indexes and scene characteristics, the strategies are designed according to image quality problems and scene characteristics, the module selects the adjustment strategy which is most suitable for the current situation from the self-adaptive adjustment strategies, after the adjustment strategies are selected, the module calculates required image processing parameters such as exposure compensation values, white balance adjustment parameters and sharpening strength, the parameters are configured into an image processing algorithm to prepare for image adjustment, the configured image processing algorithm and parameters are applied to images to conduct real-time processing to improve the image quality, in the adjustment process, a user can preview the effectiveness of the adjustment strategies in real time so as to initially evaluate the effectiveness of the adjustment strategies, the dynamic feedback module monitors the image quality change after the adjustment in real time, compares the image quality before and after the adjustment, and automatically adjusts the image quality until the image quality is optimized according to the optimal adjustment strategy is continuously optimized, and the effectiveness of the adjustment algorithm is optimized.
The aim of the step is to finely adjust the image to optimize the image quality to the optimal state through the self-adaptive adjustment module 3 according to the image quality evaluation data and the scene recognition result, and the step aims to solve the possible quality problems of the image under different scenes, such as insufficient definition, poor contrast, excessive noise and the like, and simultaneously consider the influence of scene characteristics, such as illumination conditions, scene types, motion states and the like, on the image quality so as to generate and apply an adjustment strategy which is most suitable for the current scene and the image quality problem;
In general, the step performs fine adjustment on the image through the self-adaptive adjustment module 3 and performs continuous optimization by combining a dynamic feedback mechanism, so that the image quality is remarkably improved, the user experience is enhanced, and the system can adapt to the changes of different scenes and image quality problems
S4, the user feedback module 4 collects satisfaction data of the user on the image quality, acquires user feedback through a questionnaire investigation and scoring system mode, analyzes the user feedback data, learns personalized preferences of the user, including color preferences and brightness preferences, provides an intuitive and easy-to-use interactive adjustment interface, allows the user to manually adjust image parameters, including exposure, white balance and sharpening, and immediately checks adjustment effects.
The main purpose of this step is to further enhance the user experience and meet the user's personalized needs by collecting and analyzing the user's satisfaction data with the image quality and providing an interactive adjustment interface.
S5, the data storage and analysis module 5 is used for efficiently storing the image data, the evaluation result, the adjustment strategy and the user feedback data, deep analysis is carried out on the stored data by utilizing big data, rules and trends behind the data are mined, data support is provided for system optimization, the data storage and analysis module 5 supports cloud collaborative work, partial calculation tasks and data storage are migrated to the cloud, and flexible configuration and sharing of resources are achieved.
Specifically, the step is responsible for efficiently and orderly storing image data, evaluation results, adjustment strategies and user feedback data, the data are stored in a safe and reliable storage medium for subsequent analysis and use, a big data analysis technology is utilized, a module deeply excavates rules and trends after storing the data, the module discovers relativity and potential rules among the data through methods such as statistical analysis, machine learning and the like of the data, data support is provided for system optimization, the module provides suggestions and guidance for continuous optimization of the system based on the results of the big data analysis, the suggestions possibly relate to the aspects of adjustment of algorithm parameters, optimization of a processing flow, improvement of a user interface and the like, the aim is to improve the performance and user experience of the system, the module supports cooperative work, partial calculation tasks and data storage are migrated to a cloud, the cloud is used for flexibly configuring and sharing calculation resources and storage resources, the cloud cooperative work realizes the maximum utilization of resources and the system, the real-time synchronization and sharing of the data are also facilitated, and the cooperative efficiency of the system is improved;
the method aims at efficiently and orderly storing image data, evaluation results, adjustment strategies and user feedback data, and deeply excavating rules and trends behind the data through a big data analysis technology, so that powerful data support is provided for continuous optimization of a system.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (9)
1. The multi-scene self-adaptive image quality control system is characterized by comprising an intelligent sensing module (1), an image quality evaluation module (2), a self-adaptive adjustment module (3), a user feedback module (4) and a data storage and analysis module (5), wherein the intelligent sensing module (1), the image quality evaluation module (2), the self-adaptive adjustment module (3), the user feedback module (4) and the data storage and analysis module (5) are connected through a data bus or a network to realize data interaction and collaborative work.
2. The multi-scene adaptive image quality control system according to claim 1, wherein the intelligent perception module 1 is configured to collect multi-dimensional environmental information and image data of a photographed scene, and further comprises an infrared sensor, a gyroscope and an accelerometer to implement multi-source sensor fusion.
3. The multi-scene adaptive image quality control system according to claim 2, wherein the image quality evaluation module (2) is configured to perform multi-dimensional quality evaluation on the image captured in real time, including sharpness, contrast, noise level, color saturation, dynamic range, and image stability, and high-speed image processing chip and parallel computing technology are used to ensure the efficiency and instantaneity of the evaluation process.
4. The multi-scene adaptive image quality control system according to claim 3, wherein the adaptive adjustment module (3) is configured to generate and apply a fine adjustment strategy according to scene recognition results and image quality evaluation data, wherein the fine adjustment strategy comprises different algorithms for different types of objects, and a dynamic feedback module is introduced in the adjustment process to monitor the adjustment effect in real time and automatically adjust the strategy.
5. The multi-scene adaptive image quality control system of claim 4 wherein the user feedback module (4) is configured to collect and analyze user satisfaction data for image quality, learn user personalized preferences, and provide an intuitive and easy-to-use interactive adjustment interface allowing a user to manually adjust image parameters and view effects on-the-fly.
6. The multi-scene adaptive image quality control system according to claim 5, wherein the data storage and analysis module (5) is configured to store, analyze and cooperatively process image data, evaluation results, adjustment policies and user feedback data in a cloud end efficiently, support big data processing and cloud end cooperative work, and achieve flexible configuration and sharing of resources.
7. A control method employing the multi-scene adaptive image quality control system according to claim 6, characterized in that the method comprises the steps of:
S1, acquiring and preprocessing environment information and image data, starting a multi-source sensor to acquire multi-dimensional environment information and image data of a shooting scene in real time by using an intelligent perception module (1), preprocessing the acquired data, including denoising and filtering, and improving the accuracy and efficiency of subsequent processing;
s2, evaluating the image quality, wherein an image quality evaluation module (2) receives the image data transmitted by the intelligent perception module (1), evaluates the image quality by using a preset multi-dimensional quality evaluation index, and adopts a high-speed image processing chip and a parallel computing technology to ensure the high efficiency and instantaneity of an evaluation process and quickly generate an image quality evaluation report;
S3, image quality self-adaptive adjustment, wherein an adaptive adjustment module (3) receives scene recognition results and image quality evaluation data, generates and applies a fine adjustment strategy according to a preset algorithm and a strategy library, and introduces a dynamic feedback module in the adjustment process to monitor adjustment effects in real time, such as image quality change before and after adjustment, automatically adjusts the adjustment strategy according to the feedback results, and ensures that the image quality is continuously optimized to an optimal state;
S4, user feedback and personalized service, wherein a user feedback module (4) collects satisfaction data of users on image quality, acquires user feedback through a questionnaire investigation and scoring system mode, analyzes the user feedback data, learns personalized preferences of the users, including color preferences and brightness preferences, provides an intuitive and easy-to-use interactive adjustment interface, allows the users to manually adjust image parameters, including exposure, white balance and sharpening, and looks over adjustment effects in real time;
S5, the data storage and analysis module (5) is used for efficiently storing the image data, the evaluation result, the adjustment strategy and the user feedback data, deep analysis is carried out on the stored data by utilizing big data, rules and trends behind the data are mined, data support is provided for system optimization, the data storage and analysis module (5) supports cloud collaborative work, partial calculation tasks and data storage are migrated to the cloud, and flexible configuration and sharing of resources are achieved.
8. The control method according to claim 7, wherein in S2, the preset multi-dimensional quality assessment index includes, but is not limited to, sharpness, contrast, noise level, color saturation, dynamic range, and image stability of the image;
The high-speed image processing chip comprises, but is not limited to, a GPU, an FPGA or an ASIC to accelerate the image processing process, and has strong parallel processing capability and an optimized image processing algorithm library, so that the evaluation efficiency can be remarkably improved;
the parallel computing technology decomposes an image processing task into a plurality of subtasks and simultaneously executes the subtasks on a plurality of processors or computing units, so as to reduce processing time and improve evaluation instantaneity.
9. The control method according to claim 7, wherein in the step S3, specifically;
S3.1, data analysis and information extraction, wherein an adaptive adjustment module (3) receives image quality evaluation data and scene recognition results from an image quality evaluation module (2) and an intelligent perception module (1), analyzes the received data, and extracts key information such as image quality indexes and scene characteristics, wherein the image quality indexes comprise but are not limited to definition, contrast and noise level, and the scene characteristics comprise but are not limited to illumination conditions, scene types and motion states;
S3.2, selecting an adjustment strategy, namely inquiring a matched adjustment strategy in an algorithm and strategy library preset in the self-adaptive adjustment module (3) according to the analyzed image quality index and scene characteristics, and selecting the adjustment strategy which is most suitable for the current scene and the image quality problem from the matched strategies;
S3.3, calculating image processing parameters, namely calculating required image processing parameters including exposure compensation values, white balance adjustment parameters and sharpening strength according to a selected adjustment strategy, configuring the calculated parameters into an image processing algorithm, and preparing for image adjustment;
S3.4, adjusting and previewing the real-time image, and applying the configured image processing algorithm and parameters to process the image in real time so as to improve the image quality, wherein in the adjusting process, the adjusting effect can be previewed in real time, so that the effectiveness of the adjusting strategy can be estimated preliminarily;
S3.5, dynamically feeding back and evaluating the effect, wherein a dynamic feedback module is introduced in the adjustment process, the image quality change after adjustment is monitored in real time, the image quality before and after adjustment is compared, and whether the adjustment effect reaches an expected target is evaluated;
S3.6, strategy optimization and iterative adjustment, wherein the effectiveness of an adjustment strategy is analyzed according to an effect evaluation result provided by the dynamic feedback module, if the adjustment effect is not ideal, the adjustment strategy is automatically adjusted according to the feedback result, different algorithms and parameter settings are tried, the adjustment strategy is optimized through continuous iteration and adjustment until a satisfactory image quality effect is achieved, and finally the adjusted image is output to display equipment or a storage medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411628895.3A CN119815188A (en) | 2024-11-14 | 2024-11-14 | Multi-scene adaptive image quality control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411628895.3A CN119815188A (en) | 2024-11-14 | 2024-11-14 | Multi-scene adaptive image quality control method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119815188A true CN119815188A (en) | 2025-04-11 |
Family
ID=95266972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411628895.3A Pending CN119815188A (en) | 2024-11-14 | 2024-11-14 | Multi-scene adaptive image quality control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119815188A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120475111A (en) * | 2025-07-15 | 2025-08-12 | 北京东宇宏达科技有限公司 | A control system for infrared image transmission and reproduction |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101102405A (en) * | 2006-06-02 | 2008-01-09 | 罗技欧洲公司 | Intelligent image quality engine |
| US20120236173A1 (en) * | 2011-03-17 | 2012-09-20 | Telek Michael J | Digital camera user interface which adapts to environmental conditions |
| US9288374B1 (en) * | 2012-09-10 | 2016-03-15 | Amazon Technologies, Inc. | Systems and methods for updating camera characteristics using a remote computing device |
| CN107341516A (en) * | 2017-07-07 | 2017-11-10 | 广东中星电子有限公司 | Picture quality adjusting method and image procossing intelligent platform |
| CN108989565A (en) * | 2018-07-27 | 2018-12-11 | 中新工程技术研究院有限公司 | A kind of photo optimization method and device |
| CN109815939A (en) * | 2019-03-01 | 2019-05-28 | 北京当红齐天国际文化发展集团有限公司 | Projection display system and method based on human eye tracking |
| DE102019117387A1 (en) * | 2019-06-27 | 2020-12-31 | Connaught Electronics Ltd. | Method for controlling an image processing chain |
| WO2023065523A1 (en) * | 2021-10-20 | 2023-04-27 | 上海闻泰电子科技有限公司 | Isp-based image processing method and apparatus, storage medium, and camera device |
| CN118351078A (en) * | 2024-04-16 | 2024-07-16 | 上海深至信息科技有限公司 | Self-adaptive ultrasonic image quality evaluation optimization system and method |
| CN118400561A (en) * | 2024-05-15 | 2024-07-26 | 南通理工学院 | Adaptive image and video content adjustment system and method based on environmental perception |
| US20240404175A1 (en) * | 2021-10-09 | 2024-12-05 | Beijing Bytedance Network Technology Co., Ltd. | Method and apparatus for displaying three-dimensional object, and device and medium |
| CN119473193A (en) * | 2024-09-19 | 2025-02-18 | 广州市瀚丽美电子有限公司 | An intelligent interactive commercial display projection and multi-screen display system |
-
2024
- 2024-11-14 CN CN202411628895.3A patent/CN119815188A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101102405A (en) * | 2006-06-02 | 2008-01-09 | 罗技欧洲公司 | Intelligent image quality engine |
| US20120236173A1 (en) * | 2011-03-17 | 2012-09-20 | Telek Michael J | Digital camera user interface which adapts to environmental conditions |
| US9288374B1 (en) * | 2012-09-10 | 2016-03-15 | Amazon Technologies, Inc. | Systems and methods for updating camera characteristics using a remote computing device |
| CN107341516A (en) * | 2017-07-07 | 2017-11-10 | 广东中星电子有限公司 | Picture quality adjusting method and image procossing intelligent platform |
| CN108989565A (en) * | 2018-07-27 | 2018-12-11 | 中新工程技术研究院有限公司 | A kind of photo optimization method and device |
| CN109815939A (en) * | 2019-03-01 | 2019-05-28 | 北京当红齐天国际文化发展集团有限公司 | Projection display system and method based on human eye tracking |
| DE102019117387A1 (en) * | 2019-06-27 | 2020-12-31 | Connaught Electronics Ltd. | Method for controlling an image processing chain |
| US20240404175A1 (en) * | 2021-10-09 | 2024-12-05 | Beijing Bytedance Network Technology Co., Ltd. | Method and apparatus for displaying three-dimensional object, and device and medium |
| WO2023065523A1 (en) * | 2021-10-20 | 2023-04-27 | 上海闻泰电子科技有限公司 | Isp-based image processing method and apparatus, storage medium, and camera device |
| CN118351078A (en) * | 2024-04-16 | 2024-07-16 | 上海深至信息科技有限公司 | Self-adaptive ultrasonic image quality evaluation optimization system and method |
| CN118400561A (en) * | 2024-05-15 | 2024-07-26 | 南通理工学院 | Adaptive image and video content adjustment system and method based on environmental perception |
| CN119473193A (en) * | 2024-09-19 | 2025-02-18 | 广州市瀚丽美电子有限公司 | An intelligent interactive commercial display projection and multi-screen display system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120475111A (en) * | 2025-07-15 | 2025-08-12 | 北京东宇宏达科技有限公司 | A control system for infrared image transmission and reproduction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7684096B2 (en) | Automatic color correction for sequences of images | |
| KR102138950B1 (en) | Depth map generation from a monoscopic image based on combined depth cues | |
| US8730232B2 (en) | Director-style based 2D to 3D movie conversion system and method | |
| CN112584077A (en) | Video frame interpolation method and device and electronic equipment | |
| CN112492297B (en) | Video processing method and related equipment | |
| EP4101161B1 (en) | Multi-frame depth-based multi-camera relighting of images | |
| WO2022148248A1 (en) | Image processing model training method, image processing method and apparatus, electronic device, and computer program product | |
| CN119815188A (en) | Multi-scene adaptive image quality control method and system | |
| CN113706402A (en) | Neural network training method and device and electronic equipment | |
| CN115914765B (en) | Image quality adjusting method, device, equipment and medium | |
| Khan et al. | A deep hybrid few shot divide and glow method for ill-light image enhancement | |
| US9940543B2 (en) | Control of computer vision pre-processing based on image matching using structural similarity | |
| CN104885119A (en) | Image processing device, image processing method, and recording medium | |
| CN113762058A (en) | Video synthesis method and device, computer equipment and storage medium | |
| US20090123068A1 (en) | Method for adaptively adjusting image and image processing apparatus using the same | |
| Guthier et al. | Flicker reduction in tone mapped high dynamic range video | |
| CN119273590A (en) | A video image enhancement and restoration method and system using deep learning | |
| WO2018010026A1 (en) | Method of presenting wide dynamic range images and a system employing same | |
| CN118714244A (en) | Film and television production system based on deep learning reverse relighting algorithm | |
| US12159443B2 (en) | Previewing and generating stroke outlines in association with images | |
| US12141894B2 (en) | Multi-frame depth-based multi-camera relighting of images | |
| US12175645B2 (en) | Methods, systems and computer program products for generating high dynamic range image frames | |
| CN118312116A (en) | Display device, image processing method and apparatus | |
| CN120544502A (en) | Adaptive image processing and dimming method and system for MicroLED array | |
| JP7145651B2 (en) | Image processing device and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |