CN115880180A

CN115880180A - Adaptive picture quality PQ debugging method, system, platform and storage medium

Info

Publication number: CN115880180A
Application number: CN202211657020.7A
Authority: CN
Inventors: 夏安安; 罗琨皓; 孙旭涛
Original assignee: Foxstar Technology Co ltd; Henan Costar Group Co Ltd
Current assignee: Foxstar Technology Co ltd; Henan Costar Group Co Ltd
Priority date: 2022-12-22
Filing date: 2022-12-22
Publication date: 2023-03-31

Abstract

The invention particularly relates to a self-adaptive picture quality PQ debugging method, a system, a platform and a storage medium. The method comprises the steps of obtaining image data to be subjected to image quality debugging through the method, and pre-debugging and processing parameter data corresponding to the image data in real time; constructing an image effect database model, and comparing the image quality PQ effect of the image data after the pre-debugging processing in real time according to the image effect database model; dynamically generating a color image picture based on different scenes after the image quality is enhanced, and a system, a platform and a storage medium corresponding to the method in real time; the saturation, brightness and contrast of the image can be improved in a self-adaptive mode, the details of a dark scene are enhanced, and the improvement of the color saturation, the definition and the details can be obviously seen from the processed video image.

Description

Adaptive picture quality PQ debugging method, system, platform and storage medium

Technical Field

The invention belongs to the technical field of image quality debugging processing, and particularly relates to a self-adaptive image quality PQ debugging method, a self-adaptive image quality PQ debugging system, a self-adaptive image quality PQ debugging platform and a storage medium.

Background

Traditional picture quality debugging effect comes out, and is basically invariable, and the picture quality completely depends on the stage effect of dispatching from the factory, and along with the ageing of projecting apparatus light source, the not equidimension change can appear in the picture quality, and manual regulation sets up menu picture effect, and the regulating parameter is limited, leads to the picture quality effect not good to the impression reduces.

Such as: the gamma is 2.2, when the light source ages, the efficiency of R, G and B lamps is attenuated, the brightness cannot reach the set target (320 lm), the change of color coordinates (such as the deviation of the set color temperature of 8000K, the color coordinates x =0.29 and y = 0.32) also causes white balance unbalance, color cast occurs, and the obvious visual effect is yellow and dark.

Therefore, in order to overcome the technical defects that the image quality effect is poor due to the limited adjustment parameters, and the visual perception is reduced, it is urgently needed to design and develop a method, a system, a platform and a storage medium for adaptive image quality PQ debugging.

Disclosure of Invention

In order to overcome the defects and difficulties of the prior art, the present invention provides a method, a system, a platform and a storage medium for adaptive quality PQ debugging, which can improve the saturation, brightness and contrast of an image and enhance the details of a dark scene, etc., and the improvement of color saturation, definition and details can be obviously seen in a processed video image.

The first objective of the present invention is to provide a method for adaptive picture quality PQ debugging;

a second object of the present invention is to provide an adaptive picture quality PQ debugging system;

the third objective of the present invention is to provide a self-adaptive picture quality PQ debugging platform;

a fourth object of the present invention is to provide a computer-readable storage medium;

the first object of the present invention is achieved by: the method comprises the following steps:

acquiring image data to be subjected to image quality debugging, and pre-debugging and processing parameter data corresponding to the image data in real time;

constructing an image effect database model, and comparing the image quality PQ effect of image data subjected to pre-debugging processing in real time according to the image effect database model;

and dynamically generating a color image picture with enhanced image quality based on different scenes in real time.

Further, the acquiring image data to be picture-quality debugged and pre-debugging and processing parameter data corresponding to the image data in real time further includes:

and sequentially debugging Gamma parameters, color temperature parameters, brightness contrast parameters, DLC parameters, color parameters and definition parameters in the image data to be subjected to image quality debugging.

Further, the sequentially debugging Gamma parameters, color temperature parameters, brightness contrast parameters, DLC parameters, color parameters and definition parameters in the image data to be subjected to image quality debugging further includes:

acquiring preset parameter data, and judging the matching degree of the parameter data of the image to be subjected to image quality debugging and the preset parameter data in real time;

and performing real-time adaptive debugging on the parameter data in the image to be debugged according to the judgment comparison data.

and carrying out real-time noise reduction on the image data to be picture debugged after pre-debugging processing.

Further, the constructing an image effect database model, and comparing the quality PQ effect of the image data after the pre-debugging processing in real time according to the image effect database model, further comprises:

judging whether the picture quality PQ effect of the image data after the pre-debugging processing meets the preset effect of the AI model, if so, dynamically generating a color image picture based on different scenes after the picture quality is enhanced, otherwise, executing the next step;

and processing parameter data corresponding to the image data in real time in a pre-debugging way.

Further, the constructing an image effect database model, and comparing the quality PQ effect of the image data after the pre-debugging processing in real time according to the image effect database model further includes:

and identifying the image type to be subjected to image quality debugging in real time by combining the AI model.

The second object of the present invention is achieved by: the system comprises:

the image quality adjusting device comprises an acquisition preprocessing unit, a parameter adjusting unit and a parameter adjusting unit, wherein the acquisition preprocessing unit is used for acquiring image data to be subjected to image quality adjustment and carrying out real-time pre-adjustment processing on parameter data corresponding to the image data;

the image quality comparison unit is used for constructing an image effect database model and comparing the image quality PQ effect of the image data after the pre-debugging processing in real time according to the image effect database model;

and the color image picture generating unit is used for dynamically generating the color image picture with the enhanced image quality based on different scenes in real time.

Further, the acquisition preprocessing unit further includes:

the parameter debugging module is used for sequentially debugging Gamma parameters, color temperature parameters, brightness contrast parameters, DLC parameters, color parameters and definition parameters in the image data to be subjected to picture quality debugging;

the noise reduction processing module is used for carrying out real-time noise reduction processing on the image data to be picture debugged after the pre-debugging processing;

and/or, the parameter debugging module further comprises:

the first judgment module is used for acquiring preset parameter data and judging the matching degree of the parameter data of the image to be subjected to picture quality debugging and the preset parameter data in real time;

the adaptive debugging module is used for adaptively debugging the parameter data in the image to be subjected to image quality debugging in real time according to the judgment comparison data;

and/or, the construction of the alignment unit further comprises:

the second judgment module is used for judging whether the picture quality PQ effect of the image data after the pre-debugging processing meets the preset effect of the AI model;

the pre-debugging processing module is used for pre-debugging and processing the parameter data corresponding to the image data in real time;

and the image type identification module is used for identifying the image type to be subjected to image quality debugging in real time by combining the AI model.

The third object of the present invention is achieved by: the system comprises a processor, a memory and a self-adaptive picture quality PQ debugging platform control program;

the processor executes the adaptive quality PQ debugging platform control program, the adaptive quality PQ debugging platform control program is stored in the memory, and the adaptive quality PQ debugging platform control program realizes the adaptive quality PQ debugging method.

The fourth object of the present invention is achieved by: the computer readable storage medium stores an adaptive quality PQ debugging platform control program, and the adaptive quality PQ debugging platform control program realizes the adaptive quality PQ debugging method.

The method comprises the steps of obtaining image data to be subjected to image quality debugging through the method, and pre-debugging and processing parameter data corresponding to the image data in real time; constructing an image effect database model, and comparing the image quality PQ effect of the image data after the pre-debugging processing in real time according to the image effect database model; dynamically generating a color image picture based on the enhanced image quality of different scenes in real time, and a system, a platform and a storage medium corresponding to the method; the saturation, brightness and contrast of the image can be improved in a self-adaptive mode, the details of a dark scene are enhanced, and the improvement of the color saturation, the definition and the details can be obviously seen from the processed video image.

That is to say, the scheme of the present invention can perform targeted image quality enhancement according to different scenes, and the research of the video image quality enhancement technology based on image classification is to perform image quality optimization on each scene by using an artificial intelligence technology, which is different from the conventional video image quality enhancement technology, and different parameters of different scenes can be optimized by using the artificial intelligence technology to realize common optimization. Starting from this direction, the AI technology is utilized to realize the judgment of the current image quality scene (such as human face, building, blue, green, color and night scene), the dynamic adjustment is carried out, the aspects of image color saturation, brightness, contrast and the like are mainly promoted, and the current image is adjusted to be deblurred, defogged, denoised and enhanced, so that the image color is richer and richer, and the image quality effect is more outstanding.

In other words, through a large amount of picture videos, the effect after manual adjustment is made as a preset value: the regulation is satisfied, for example: warm color mode, color temperature 7000K, color coordinates x =0.305, y =0.30; gamma2.2; definition presetting A; DLC takes one of 3 curves according to the brightness of the current picture; the saturation, brightness and the like are compared with a preset value and are adjusted to be within the range of the preset value.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a signal flow diagram illustrating an adaptive quality PQ debugging method according to the present invention;

FIG. 2 is a schematic diagram illustrating color adjustment of an adaptive quality PQ debugging method according to the present invention;

FIG. 3 is a flowchart illustrating an embodiment of a self-adaptive quality PQ debugging method according to the present invention;

FIG. 4 is a flowchart illustrating a method for adaptive picture quality PQ adjustment according to the present invention;

FIG. 5 is a diagram illustrating an architecture of an adaptive quality PQ debugging system according to the present invention;

FIG. 6 is a diagram illustrating an architecture of a self-adaptive quality PQ debugging platform according to the present invention;

FIG. 7 is a block diagram of a computer-readable storage medium according to an embodiment of the present invention;

the objects, features and advantages of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

For better understanding of the objects, aspects and advantages of the present invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings, and other advantages and capabilities of the present invention will become apparent to those skilled in the art from the description.

The invention is capable of other and different embodiments and its several details are capable of modification in various other respects, all without departing from the spirit and scope of the present invention.

It should be noted that, if directional indications (such as up, down, left, right, front, and back … …) are involved in the embodiment of the present invention, the directional indications are only used to explain the relative position relationship between the components, the motion situation, and the like in a specific posture (as shown in the drawing), and if the specific posture is changed, the directional indications are changed accordingly.

In addition, if there is a description of "first", "second", etc. in an embodiment of the present invention, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Secondly, the technical solutions in the embodiments can be combined with each other, but it must be based on the realization of those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not be within the protection scope of the present invention.

Preferably, the adaptive picture quality PQ debugging method is applied to one or more terminals or servers. The terminal is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.

The terminal can be a desktop computer, a notebook, a palm computer, a cloud server and other computing equipment. The terminal can be in man-machine interaction with a client in a keyboard mode, a mouse mode, a remote controller mode, a touch panel mode or a voice control device mode.

The invention provides a method, a system, a platform and a storage medium for realizing adaptive picture quality PQ debugging.

Fig. 4 is a flowchart illustrating an adaptive quality PQ debugging method according to an embodiment of the present invention.

In this embodiment, the adaptive quality PQ debugging method may be applied to a terminal with a display function or a fixed terminal, and the terminal is not limited to a personal computer, a smart phone, a tablet computer, a desktop computer or a all-in-one machine with a camera, and the like.

The adaptive quality PQ debugging method can also be applied to a hardware environment consisting of a terminal and a server connected to the terminal through a network. Networks include, but are not limited to: a wide area network, a metropolitan area network, or a local area network. The adaptive picture quality PQ debugging method in the embodiment of the invention can be executed by a server, a terminal or both.

For example, for a terminal that needs to perform adaptive picture quality PQ debugging, the adaptive picture quality PQ debugging function provided by the method of the present invention may be directly integrated into the terminal, or a client for implementing the method of the present invention may be installed. For another example, the method provided by the present invention may further be operated on a device such as a server in the form of a Software Development Kit (SDK), and an interface of the adaptive picture quality PQ debugging function is provided in the form of an SDK, so that the terminal or other devices can implement the adaptive picture quality PQ debugging function through the provided interface.

The invention is further elucidated with reference to the drawing.

As shown in fig. 1-7, the present invention provides a method for adaptive picture quality PQ debugging, which includes the following steps:

s1, acquiring image data to be subjected to picture quality debugging, and pre-debugging and processing parameter data corresponding to the image data in real time;

s2, constructing an image effect database model, and comparing the image quality PQ effect of the image data subjected to the pre-debugging processing in real time according to the image effect database model;

and S3, dynamically generating a color image picture based on different scenes after the image quality is enhanced in real time.

The acquiring image data to be subjected to image quality debugging and real-time pre-debugging processing of parameter data corresponding to the image data further comprises:

s11, sequentially debugging Gamma parameters, color temperature parameters, brightness contrast parameters, DLC parameters, color parameters and definition parameters in the image data to be subjected to image quality debugging.

The debugging in proper order waits Gamma parameter, colour temperature parameter, luminance contrast parameter, DLC parameter, color parameter and the definition parameter in the image data of picture quality debugging still includes:

s111, acquiring preset parameter data, and judging the matching degree of the parameter data of the image to be subjected to picture quality debugging and the preset parameter data in real time;

and S112, adaptively debugging the parameter data in the image to be debugged in real time according to the judgment comparison data.

and S12, carrying out real-time noise reduction on the image data to be debugged of the picture after pre-debugging processing.

The method for establishing the image effect database model and comparing the image quality PQ effect of the image data after the pre-debugging processing in real time according to the image effect database model further comprises the following steps:

s21, judging whether the picture quality PQ effect of the image data after the pre-debugging processing meets the AI model preset effect, if so, dynamically generating a color image picture based on different scenes after picture quality enhancement in real time, and if not, executing the next step;

and S22, real-time pre-debugging processing parameter data corresponding to the image data.

and S23, identifying the image type to be subjected to image quality debugging in real time by combining the AI model.

Specifically, in the embodiment of the present invention, the principle of automatic image quality adjustment is based on the MTK TV scheme SOC to explain the PQ debugging principle: (in FIG. 1, video; comb is the brightness of the analog signal; csc signal format decision; nr-noise reduction; hsvflter comb filter; csc signal format decision; pre-front-end brightness and contrast peaking, FCC signal filtering; sharpness; hue, saturation, brightness of ihc/icc/ibc color; dlc dynamic contrast; bwle black and white level extension; post back-end brightness contrast; back-end color saturation; 3*3 matrix; brightness; gamma).

SOC-ray machine-picture-camera capture-OPENCV analysis-adjustment SOC picture quality register; the mstar PQ processing flow is as follows, input signals will firstly pass through CSC (color space converter), RGB signals (the numerical range of RGB signals is two, full range is 0-255, limit range is 16-235) are converted into YCBCR signals (Y range is 16-235, CBCR range is 16-240), and one component can be processed independently after YC is separated. For example, definition (peaking/SR), layering (DLC), YNR of our IC are all processing for Y component, and color (IHC/ICC/IBC/FCC) is processing for C component. Color temperature, brightness and Gamma.

The adjusting steps are as follows:

1. adjusting gamma and color temperature

Presetting a light sensing module, and comparing a current image acquired by a camera with preset module data; according to the standard gamma value of NTSC video is 2.2, Y = (X + e) γ, where Y is luminance, X is output voltage, e is compensation coefficient, and the power value (γ) is gamma value, and the gamma curve can be changed by changing the magnitude of the power value (γ), and the gamma value of the television system is about 2.2.

Standard mode, color temperature 8000K, color coordinates x =0.29, y =0.32; cold color mode, color temperature 9500K, color coordinates x =0.275, y =0.505; warm color mode, color temperature 7000K, color coordinates x =0.305, y =0.30;

2. adjusting brightness contrast

The brightness of a 1080P LCD light machine is 320lm, a white field picture is obtained, a camera acquires a current picture, and the maximum value A is obtained when 320lm +/-10% of the current picture is used as a standard sampling value; contrast represents a measure of the different brightness levels in the picture between the brightest white and the darkest black of the bright and dark areas. The higher the contrast is, the clearer the image is, and the more vivid the color is; the smaller the contrast, the more gray shades the picture will display. Setting a contrast threshold B, greater than B being the standard setting.

3. Adjusting DLC

The depth of field (or called as hierarchical) of the picture, DLC mainly adjusts 3 curves of static curve L, static curve M and static curve H, presets into a system rom partition, captures the current picture contrast B threshold value interval 0-L-M-H according to the camera.

a, taking a static curve from the yarn-woven fabric (a: 0) and the yarn-woven fabric (B) and the yarn-woven fabric (L); l < B < M taking static curve M curve; m < B < H, taking static curve H.

4. Adjusting Color

255, R, G, and B, can be represented in three-dimensional coordinates XYZ to RGB, as shown below, can represent all colors within the length of one side of the cube. (R, G, B) region hue information from black (0,0,0) to white (255 ).

Firstly, a data model is established through a large number of videos and pictures, and colors are divided into 16 types through a Hue dividing model: color0 Color of very low concentration like background. Color1: red; color2, green; color3, blue; color4: cyan; color5: purple; color6: yellow; color7: skin Color (yellow-green-purple-red mixed); color8, yellow green; color9, cyan; color10, yellow orange; color11, red is purple and skin Color; color12 blue-cyan; color13, purple blue part; color14: skin tone (reddish part); color15: skin Color (a part with a pale and greenish concentration); capturing a current picture through a camera, processing values of (R, G and B) of different pixel points, determining the range of a color, and adjusting through a color preset value of a built model.

5. Adjusting sharpness

The sharpness is to make the edge of the original signal steeper, so that the whole image becomes sharper. The definition is not higher, the better the definition is, and the current picture is identified through the established data model to be adjusted; such as buildings, grey values of text information pictures, and increase the definition.

6. Adjusting noise reduction

The noise reduction and the definition are mutually exclusive, and the noise reduction is only carried out on a motion scene. And (3) dividing the motion scene by the opencv frame difference, and performing image noise reduction by using preset threshold opencv Gaussian filtering.

In the modeling, an image effect database model is built: 1. and extracting key frames from a large number of video sources to obtain images. 2. And acquiring the image by using the web crawler. Firstly, category keywords are determined, and then keyword expansion is performed, such as face expansion, for example, "people with white skin", "people with black skin", "skin", and the like. And finally, crawling each keyword from the network by using a web crawler. 3. Using related images in an open source dataset, such as the Place365 dataset, portions of the data of the dataset may be identified using faces therein. And manually classifying each image, wherein the classified images are the basis of model learning.

The PQ regulation strategy is as follows:

(1) The Hue range of each color in a scene is determined, the range of the Hue value Hue of a human face (6 < = H < = 23), the range of the Hue value Hue of green (45 < = H < = 72), the range of the Hue value Hue of blue (97 < = H < = 123), the range of the Hue value Hue of red (0 < = H < =5,166< = H < = 179), the range of the Hue value Hue of yellow (23 < = H < = 33), the range of the Hue value Hue of purple (124 < = H < = 125), which is a Hue range customized by a company, each company may be slightly different, but the approximate ranges should be the same.

(2) And detecting regions with human face features in the projection picture by using a Haar cascade classifier built in an opencv library, extracting the regions, reading the Hue value of the current image frame pixel by pixel if the result after model identification is a human face, and judging whether the Hue value is in the range of (6,23). If not, the original value is kept without any treatment. If the value is increased by 10 more values, but the maximum value should not exceed 25, i.e., more than 25 after 10 increase of Hue should be assigned 25 to ensure that the Hue does not deviate from the skin tone. And the saturation of the skin color can be properly increased, so that the face is healthier and more ruddy.

Similarly, when the labels are blue and green, the processing algorithm is the same as the human face.

(3) And (3) color: according to the three-dimensional coordinate values of the colors R, G and B of the pixel points, the whole range area is taken, the pixel values are read one by one, whether the range of the Hue value is in the range of skin color, green color, blue color, red color, yellow color and purple color is judged, and after the specific color gamut is determined, the saturation of each pixel is increased by only 10 values. Here, the operation of uniformly increasing by 10 values is not performed for all pixels, because this causes the entire tone of the image to deviate from the original tone, and even an overexposure phenomenon occurs.

(4) If the result after the model identification is a building, the image contrast is calculated by the ratio of different brightness levels between the brightest white RGB (255 ) and the darkest black RGB (0,0,0) in the light and dark area in the picture, and if the contrast ratio is less than 120. When the contrast ratio is 120, vivid and rich colors can be easily displayed, but the contrast ratio cannot be adjusted to be too high, namely about plus or minus 10%, and if the contrast ratio exceeds the positive or minus 10%, details in a dark scene are lost, and dark fields are not distinguished to be black.

(5) If the model is identified to be architecture, the sharpness parameter is increased by 25 (adjusted according to the difference of the optical machine models) by reading the fixed value A of the sharpness register, so that the building edge is sharper. And after the scene is switched, the sharpness register is restored and set back to A.

The above is the whole content of the PQ strategy, which can be added or modified later according to the actual needs of the study. At present, a single effect is added, the contrast, the brightness, the chromaticity and the definition cannot be simultaneously improved, and the main difficulty is how to determine the measurement standard after the mixed effect is added. Traditional image quality engineers can comprehensively enhance a plurality of angles such as saturation, contrast, definition, brightness and sharpness of an image, and the quality of the effect has strong subjectivity; however, the difficulty coefficient of automatically adjusting multiple parameters is large, the parameters are difficult to balance, and the effect has no uniform judgment standard, so that the existing PQ strategy is that only one parameter is adjusted in one kind of scenes, for example, a skin color scene is mainly color saturation, and a building scene is mainly definition. Only after the effect of one type of parameters is stable, the functions of other parameters are gradually increased.

The scene categories of the experimental data set are respectively: face, blue sky, sea, grassland, crowd, animal, sunrise and sunset, night scene, building, feature map, characters, fresh flower, food, snow scene, skating, racing car, waterfall, waterside, etc., for a total of 18 categories. And finally, the scene is divided into a human face, blue, green, night scene, building and 6 colored PQ debugging scenes.

1. Face: and (3) adjusting according to the modeling PQ adjusting strategy (2), so that the skin color becomes healthier and more ruddy.

2. Blue sky: a range (97 < = H < = 123) of the Hue value Hue of blue is searched for according to the modeled PQ adjustment strategy (1), and the original value is kept without any processing without being within the range. If the value is increased by 10 values, but the maximum value is not more than 123, the effect is that the blue sky is bluer and the appearance is better.

3. Grassland: a range (45 < = H < = 72) of the Hue value Hue of green is searched for according to the modeled PQ adjustment strategy (1), and the original value is kept without any processing without being within the range. If the grass is raised by 8 more values, but the maximum value is not more than 72, the original gray meadow is changed into the green oil meadow. The audience has better impression.

4. Building: and adjusting the PQ strategy (5) according to modeling, so that the corners of the floor tiles and the house are sharper and clearer, and the wall and the road surface are clearer.

5. Night scene: and (3) the night scene is a city night scene mostly, the contrast and the brightness of the night scene are mainly enhanced, and the brightness contrast is adjusted according to the adjusting step 2, so that the displayed picture is more vivid and rich in color.

6. And (3) color: and adjusting the PQ strategy (3) according to modeling, so that the whole picture is brighter and brighter, and the flowers are more delicate and vivid.

Specific PQ is made for 6 scenes such as human face, blue, green, night scene, building, color and the like

And the parameter adjustment strategy corresponds to the SOC register, so that real-time scene response of a hardware end and adjustment of the PQ parameter optimization video image standard are realized. The model is embedded into a TV chip, real-time response is carried out on a played video, the saturation, the brightness and the contrast of an image are improved by matching with a PQ parameter, the details of a dark scene are enhanced, and the improvement of the color saturation, the definition and the details can be obviously seen in the processed video image.

In order to achieve the above object, the present invention further provides an adaptive picture quality PQ debugging system, as shown in fig. 5, the system specifically includes:

and the color image picture generating unit is used for dynamically generating color image pictures with enhanced image quality based on different scenes in real time.

The acquisition preprocessing unit further comprises:

and/or, the parameter debugging module further comprises:

and/or, the construction of the alignment unit further comprises:

the second judgment module is used for judging whether the picture quality PQ effect of the image data after the pre-debugging processing meets the AI model preset effect;

In the embodiment of the system scheme of the present invention, the specific details of the method steps involved in the adaptive quality PQ debugging are described above and are not described herein again.

In order to achieve the above object, the present invention further provides an adaptive quality PQ debugging platform, as shown in fig. 6, including: a processor, a memory, and an adaptive picture quality PQ debugging platform control program;

wherein the processor executes the adaptive quality PQ debugging platform control program, the adaptive quality PQ debugging platform control program is stored in the memory, and the adaptive quality PQ debugging platform control program implements the adaptive quality PQ debugging method steps, such as:

s1, obtaining image data to be subjected to picture quality debugging, and pre-debugging and processing parameter data corresponding to the image data in real time;

The details of the steps have been set forth above and will not be described herein.

In an embodiment of the present invention, the adaptive quality PQ debugging platform may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, and include one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, and a combination of various control chips. The processor acquires each component by using various interfaces and line connections, and executes various functions and processes data by running or executing programs or units stored in the memory and calling data stored in the memory;

the memory is used for storing program codes and various data, is installed in the self-adaptive picture quality PQ debugging platform and realizes high-speed and automatic access of programs or data in the running process.

The Memory includes Read-Only Memory (ROM), random Access Memory (RAM), programmable Read-Only Memory (PROM), erasable Programmable Read-Only Memory (EPROM), one-time Programmable Read-Only Memory (OTPROM), electrically Erasable rewritable Read-Only Memory (EEPROM), compact Disc Read-Only Memory (CD-ROM) or other optical Disc Memory, magnetic disk Memory, tape Memory, or any other medium readable by a computer that can be used to carry or store data.

In order to achieve the above object, the present invention further provides a computer readable storage medium, as shown in fig. 5, in which an adaptive quality PQ debugging platform control program is stored, the adaptive quality PQ debugging platform control program implementing the adaptive quality PQ debugging method, including:

In describing embodiments of the present invention, it should be noted that any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and that the scope of the preferred embodiments of the present invention includes additional implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.

The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processing module-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM).

Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

In an embodiment of the present invention, to achieve the above object, the present invention further provides a chip system, where the chip system includes at least one processor, and when a program instruction is executed in the at least one processor, the chip system executes the adaptive quality PQ debugging method, for example:

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application. It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The method comprises the steps of obtaining image data to be subjected to image quality debugging through the method, and pre-debugging and processing parameter data corresponding to the image data in real time; constructing an image effect database model, and comparing the image quality PQ effect of the image data after the pre-debugging processing in real time according to the image effect database model; dynamically generating a color image picture based on different scenes after the image quality is enhanced, and a system, a platform and a storage medium corresponding to the method in real time; the saturation, brightness and contrast of the image can be improved in a self-adaptive mode, the details of a dark scene are enhanced, and the improvement of the color saturation, the definition and the details can be obviously seen from the processed video image.

That is to say, the scheme of the invention can carry out targeted image quality enhancement according to different scenes, and the research of the video image quality enhancement technology based on image classification utilizes the artificial intelligence technology to carry out image quality optimization on each scene, which is different from the traditional video image quality enhancement technology, and different parameters of different scenes can be optimized through the artificial intelligence technology to realize common optimization. Starting from this direction, the AI technology is utilized to realize the judgment of the current image quality scene (such as human face, building, blue, green, color and night scene), the dynamic adjustment is carried out, the aspects of image color saturation, brightness, contrast and the like are mainly promoted, and the current image is adjusted to be deblurred, defogged, denoised and enhanced, so that the image color is richer and richer, and the image quality effect is more outstanding.

In other words, through a large amount of picture videos, the effect after manual adjustment is made as a preset value: the adjustment is satisfied, for example: warm color mode, color temperature 7000K, color coordinates x =0.305, y =0.30; gamma2.2; definition presetting A; DLC takes one of 3 curves according to the brightness of the current picture; the saturation, brightness and the like are compared with a preset value and are adjusted to be within the range of the preset value.

The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A method for adaptive picture quality PQ debugging, the method comprising the steps of:

constructing an image effect database model, and comparing the image quality PQ effect of the image data after the pre-debugging processing in real time according to the image effect database model;

2. The adaptive quality PQ debugging method according to claim 1, wherein the acquiring of image data to be quality-debugged and the real-time pre-debugging of parameter data corresponding to the image data further comprise:

and sequentially debugging the Gamma parameter, the Color temperature parameter, the brightness contrast parameter, the DLC parameter, the Color parameter and the definition parameter in the image data to be subjected to image quality debugging.

3. The adaptive quality PQ debugging method of claim 2, wherein the sequentially debugging Gamma parameters, color temperature parameters, brightness contrast parameters, DLC parameters, color parameters and sharpness parameters in the image data to be quality-debugged further comprises:

4. The adaptive quality PQ debugging method according to claim 1 or2, wherein the obtaining of image data to be quality-debugged and the real-time pre-debugging of parameter data corresponding to the image data further comprise:

5. The adaptive picture quality PQ debugging method according to claim 1, wherein the method comprises the steps of constructing an image effect database model, and comparing the picture quality PQ effect of pre-debugged image data in real time according to the image effect database model, and further comprises the following steps:

judging whether the picture quality PQ effect of the image data after the pre-debugging processing meets the AI model preset effect, if so, dynamically generating a color image picture based on different scene picture quality enhancement in real time, and if not, executing the next step;

and performing real-time pre-debugging processing on parameter data corresponding to the image data.

6. The adaptive picture quality PQ debugging method according to claim 1 or5, wherein said constructing an image effect database model and comparing the picture quality PQ effect of the pre-debugged image data in real time according to the image effect database model further comprises:

7. An adaptive quality PQ debugging system, the system comprising:

the image quality debugging device comprises an acquisition preprocessing unit, a parameter data processing unit and a parameter data processing unit, wherein the acquisition preprocessing unit is used for acquiring image data to be subjected to image quality debugging and carrying out real-time preprocessing on parameter data corresponding to the image data;

8. The adaptive quality PQ debugging system according to claim 7, wherein the acquisition preprocessing unit further comprises:

and/or, the parameter debugging module further comprises:

and/or, the construction of the alignment unit further comprises:

9. A self-adaptive picture quality PQ debugging platform is characterized by comprising a processor, a memory and a self-adaptive picture quality PQ debugging platform control program;

the processor executes the adaptive quality PQ debugging platform control program, the adaptive quality PQ debugging platform control program is stored in the memory, and the adaptive quality PQ debugging platform control program realizes the adaptive quality PQ debugging method according to any one of claims 1 to 6.

10. A computer-readable storage medium storing an adaptive quality PQ debugging platform control program for implementing the adaptive quality PQ debugging method according to any one of claims 1 to 6.