WO2021244440A1

WO2021244440A1 - Method, apparatus, and system for adjusting image quality of television, and television set

Info

Publication number: WO2021244440A1
Application number: PCT/CN2021/096914
Authority: WO
Inventors: 李兵和; 廖家伟; 李强
Original assignee: 深圳市万普拉斯科技有限公司
Priority date: 2020-06-04
Filing date: 2021-05-28
Publication date: 2021-12-09
Also published as: CN113766341A

Abstract

The present invention provides a method, device, and system for adjusting image quality of a television, and a television set. The method comprises: receiving a television signal and decoding same to obtain video frame data; performing feature extraction on the video frame data using a pretrained deep learning model to obtain feature data, wherein the feature data is used for representing scene information corresponding to the video frame data; sending the feature data to a cloud server to obtain an image quality parameter returned by the cloud server on the basis of the feature data; and adjusting the video frame data using the image quality parameter and displaying the adjusted video frame data. The present application can dynamically load corresponding image quality parameters for video frame data in different scenes to improve an image quality effect of a television set, thus improving user experience.

Description

Television image quality adjustment method, device and system and television equipment

Technical field

The present invention relates to the technical field of televisions, in particular to a method, device and system for adjusting television image quality, and television equipment.

Background technique

At present, with the development of TV technology and the advent of the era of smart TV, TV devices are playing more and more content, and the quality of the playback is also very different. Therefore, users have higher and higher requirements for image quality adjustment. There are two main methods for adjusting the existing picture quality: one is that before the TV product leaves the factory, professional picture quality engineers adjust multiple sets of general picture quality parameters based on the TV signal input source and certain professional inspection pictures based on their experience. , And fixed in the TV product for the user to choose to use, this adjustment method will not change with the changes of the TV broadcast content, resulting in poor quality of some content; the other is to set the picture Quality adjustment interface, so that users can set a fixed set of picture quality parameters according to the TV signal source, film source name setting and automatic scene recognition. When the playback content has multiple scenes, the user needs to adjust the picture quality parameters multiple times, Bring great inconvenience to users. Therefore, the existing image quality adjustment is difficult to meet the needs of users.

Summary of the invention

In view of this, the purpose of the present invention is to provide a TV image quality adjustment method, device and system, and TV equipment to alleviate the above-mentioned problems, realize the dynamic loading of corresponding image quality parameters to the video frame data in different scenes, and improve the TV. The image quality of the device improves the user experience.

In the first aspect, an embodiment of the present invention provides a method for adjusting TV picture quality, which is applied to a TV device, wherein the TV device is in communication with a cloud server, and the method includes: receiving a TV signal, and decoding the TV signal to obtain Video frame data; using a pre-trained deep learning model to perform feature extraction on the video frame data to obtain feature data; wherein the feature data is used to characterize the scene information corresponding to the video frame data; the feature data is sent to the cloud server, To obtain the image quality parameter returned by the cloud server based on the characteristic data; apply the image quality parameter to adjust the video frame data; and display the adjusted video frame data.

The above method further includes: acquiring the current image quality parameter displayed by the television device; comparing the current image quality parameter with the above image quality parameter, and revising the above image quality parameter according to the comparison result.

The step of comparing the current image quality parameter with the image quality parameter and revising the image quality parameter according to the comparison result includes: calculating the difference between the current image quality parameter and the image quality parameter; judging whether the difference is within a preset range; If not, revise the above image quality parameters.

The step of applying the image quality parameter to adjust the video frame data includes: loading the image quality parameter into the video frame data according to a loading mode to adjust the video frame data; wherein the loading mode includes a frame image mode and a time axis mode.

If the above loading mode is frame picture mode, the above step of loading the image quality parameters into the video frame data according to the loading mode to adjust the video frame data includes: sequentially loading the image quality parameters into the above video frame data according to the preset number of frames To adjust the above video frame data.

If the above loading mode is the time axis mode, the above step of loading the image quality parameters into the video frame data according to the loading mode to adjust the video frame data includes: loading the image quality parameters successively according to the display time of the above video frame data to Adjust the above video frame data.

The above-mentioned deep learning model is a model obtained based on neural network training. The method further includes: obtaining a pre-stored video frame data set, where the video frame data set includes HDMI signals, AV signals, network video signals, multimedia video signals, and digital TV Signal; input the video frame data set to the neural network for training to obtain the above-mentioned deep learning model.

The aforementioned image quality parameters include at least one of the following: color temperature, color, brightness, grayscale, sharpness, contrast, sharpness, and image scaling parameters.

In a second aspect, an embodiment of the present invention also provides a television image quality adjustment device, which is installed in a television device, and the television device is in communication connection with a cloud server. The device includes a decoding module for receiving television signals and decoding televisions. The signal obtains the video frame data; the extraction module is used to apply the pre-trained deep learning model to perform feature extraction on the video frame data to obtain feature data; wherein the feature data is used to characterize the scene information corresponding to the video frame data; the acquisition module , For sending feature data to the cloud server to obtain the image quality parameters returned by the cloud server based on the feature data; an adjustment module for applying the image quality parameters to adjust the video frame data; a display module for displaying the adjusted The above video frame data.

In a third aspect, embodiments of the present invention also provide a television device, including a memory, a processor, and a computer program stored in the memory and running on the processor. The processor implements the above-mentioned television image quality adjustment when the above-mentioned computer program is executed. Method steps.

The above-mentioned television device further includes a sensor; the sensor is used to collect the current picture quality parameters displayed by the above-mentioned television device.

In a fourth aspect, an embodiment of the present invention also provides a television image quality adjustment system. The system includes the above-mentioned television device and also includes a cloud server communicatively connected with the television device; the cloud server is used to receive transmissions from the above-mentioned television device According to the feature data, the image quality parameters can be obtained based on the feature data.

The cloud server further includes: an identification unit for performing identification processing on the feature data to obtain scene information represented by the feature data; a processing unit for processing the scene information according to pre-stored image quality expert data to obtain image quality parameters.

The embodiments of the present invention bring the following beneficial effects:

The embodiments of the present invention provide a TV image quality adjustment method, device and system, and TV equipment. The video frame data is obtained by decoding the received TV signal, and a pre-trained deep learning model is used to perform feature extraction on the video frame data. Obtain feature data; send the feature data to the cloud server to obtain the image quality parameters returned by the cloud server based on the feature data; apply the image quality parameters to adjust the above-mentioned video frame data, and display the adjusted above-mentioned video frame data, so as to achieve The corresponding picture quality parameters are dynamically loaded to the video frame data in different scenes, which improves the picture quality effect of the TV equipment, and further improves the user experience.

Other features and advantages of the present invention will be described in the following description, and partly become obvious from the description, or understood by implementing the present invention. The purpose and other advantages of the present invention are realized and obtained in the structure specifically pointed out in the description and the drawings.

In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, preferred embodiments are described in detail below in conjunction with accompanying drawings.

Description of the drawings

In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the specific embodiments or the description of the prior art. Obviously, the appendix in the following description The drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative work, other drawings can be obtained based on these drawings.

FIG. 1 is a flowchart of a method for adjusting TV picture quality according to an embodiment of the present invention;

2 is a flowchart of another method for adjusting TV picture quality according to an embodiment of the present invention;

FIG. 3 is a flowchart of another method for adjusting TV picture quality according to an embodiment of the present invention;

4 is a schematic diagram of a television picture quality adjustment device provided by an embodiment of the present invention;

FIG. 5 is a schematic diagram of a television device provided by an embodiment of the present invention;

FIG. 6 is a schematic diagram of a television picture quality adjustment system provided by an embodiment of the present invention;

FIG. 7 is a schematic diagram of another television image quality adjustment system provided by an embodiment of the present invention.

icon:

41-decoding module; 411-HDMI signal decoding unit; 412-AV signal decoding unit; 413-multimedia video signal decoding unit; 42-extraction module; 43-acquisition module; 44-adjustment module; 45-display module; 5-TV Machine equipment; 50-memory; 51-processor; 52-bus; 53-communication interface; 6-cloud server; 61-identification unit; 62-processing unit; 7-collection module.

detailed description

In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them.的实施例。 Example. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

In view of the problem that the existing image quality adjustment method is difficult to meet the needs of users, the embodiments of the present invention provide a TV image quality adjustment method, device and system, and television equipment, which alleviate the above problems and realize the adjustment of video frame data in different scenarios. The corresponding picture quality parameters are dynamically loaded, which improves the picture quality effect of the TV device, and further improves the user experience.

In order to facilitate the understanding of this embodiment, a method for adjusting the image quality of a television provided by an embodiment of the present invention will be introduced in detail below.

Example one:

The embodiment of the present invention provides a method for adjusting the image quality of a television, which is applied to a television device, and the television device is in communication connection with a cloud server. Fig. 1 is a flowchart of a method for adjusting TV picture quality according to an embodiment of the present invention. As shown in Fig. 1, the method includes the following steps:

Step S102, receiving a TV signal, and decoding the TV signal to obtain video frame data.

Specifically, after receiving the TV signal, the TV device decodes the received TV signal to obtain video frame data; among them, the TV signal includes HDMI (High Definition Multimedia Interface, high-definition multimedia interface) signal, AV signal, network video One or more of a signal, a multimedia video signal, and a digital TV signal, where the AV signal is the TV signal received by the TV device through the AV connector (Composite video connector), such as NTSC (National Television Standards Committee, National Television Standards Committee) , PAL (Phase Alteration Line, Par system) and SECAM (Sequentiel Couleur A Memoire, Secon system), etc.

The above-mentioned video frame data includes standard pixel data of YUV or RGB (RGB color mode, RGB color mode). Among them, YUV or RGB is determined by the original format of the video signal input, and the combination of pixels is a video frame picture. For example, currently In a common 4K TV, a frame of 4K video contains 3840X2160 pixels, which means that there are 3840 dots in one row of the display screen, and there are 2160 rows in total. Each pixel contains RGB or YUV data. In addition, the video frame data also includes input signal encoding information, resolution, and film source name information. For example, if a multimedia video signal is input for a frame, the decoded video frame data is as follows: 4+3840-2160-60+128+3840x2160 , Where 4 represents the encoding information of the input signal, and the current input signal type can be identified according to the setting list. For example, set the HDMI signal to 1, the AV signal to 2, the digital TV signal to 3, the multimedia video signal to 4, and the network video The signal is 5 grades; 3840-2160-60 means that there are 3840 pixels in one line of the next frame, a total of 2160 lines, 60 frames per second; 128 means 128 characters of information; 3840x2160 means 3840x2160 RGB or YUV The pixel point data, and the specific form of the video frame data, can be set according to actual conditions, and the embodiment of the present invention does not limit this description.

Step S104, applying a pre-trained deep learning model to perform feature extraction on the video frame data to obtain feature data; wherein the feature data is used to characterize scene information corresponding to the video frame data.

The video frame data obtained by the above decoding is input into the pre-trained deep learning model, so that the deep learning model outputs feature data according to the video frame data; it should be noted that the feature extraction process does not modify the video frame data. The feature data here is used to characterize the scene information corresponding to the video frame data, such as images and sounds; among them, the scene information includes scenery, buildings, people, blue sky, green space, plants, food, night scenes, and sports, etc., and the specific video frame The scene information corresponding to the data can be set according to the actual TV signal, which is not limited in the embodiment of the present invention. In addition, the feature data is also used to characterize the scene block division information of each scene information corresponding to the video frame data. When the feature data is sent to the cloud server, the cloud server can obtain each scene information in the corresponding block according to the feature data. The picture quality parameters in the, thereby improving the picture quality effect of the entire video frame data.

Wherein, the above-mentioned deep learning model is a model obtained based on neural network training, and the method further includes: obtaining a pre-stored video frame data set, where the video frame data set includes HDMI signals, AV signals, network video signals, multimedia video signals, and Digital TV signal; then, the video frame data set is input to the neural network for training to obtain the above-mentioned deep learning model.

Step S106: Send the characteristic data to the cloud server to obtain the image quality parameters returned by the cloud server based on the characteristic data.

The TV device sends the feature data extracted by the above-mentioned deep learning model to the cloud server, so that the cloud server returns the image quality parameters according to the feature data, because the feature data represents the scene information corresponding to the video frame data and the scene block division of the scene information Therefore, the image quality parameters returned by the cloud server include the image quality parameters of each application scene in the corresponding block, where the image quality parameters include at least one of the following: color temperature, color, brightness, grayscale, sharpness, contrast , Sharpness and picture zoom parameters. In addition, after the cloud server receives the characteristic data, it also returns the reception status information to the television device, where the reception status information includes reception success information and reception failure information.

Here, the cloud server includes an identification unit and a processing unit, where the identification unit is used to identify the characteristic data to obtain the scene information represented by the characteristic data; specifically, for a TV station logo or LOGO (LOGOtype, trademark) or film with a characteristic The feature data of the source name information, input the feature data to the pre-trained recognition model, so that the recognition model outputs scene information based on the feature data, such as scenery, buildings, people, blue sky, green space, plants, food, night scenes and games Movement, etc.; and scene block division information of each scene information; at this time, the processing unit also processes the scene information according to pre-stored image quality expert data to obtain image quality parameters. Among them, the above-mentioned recognition model is a model obtained based on neural network training.

For feature data with obvious color, brightness, contrast, and chroma information, the feature data can be sent to a pre-trained recognition model so that the recognition model can recognize the scene information and the scene area of each scene information based on the feature data Block division information; at this time, the processing unit also processes the scene information according to the pre-stored image quality expert data to obtain image quality parameters.

For feature data with inconspicuous color, brightness, contrast, and chroma information, at this time, the cloud server returns the parameter adjustment information to the TV device, where the parameter adjustment information includes the number of comparison frames, the feature threshold, the acquisition frequency and time, etc. Among them, the common number of comparison frames is 3, that is, the current frame, the previous frame, and the next frame. If the cloud server does not recognize obvious characteristic data based on the current number of comparison frames, the cloud server returns to the TV device and needs to increase at this time. The number of comparison frames, the number of comparison frames can be set according to the experience of TV image quality engineers, such as the number of comparison frames returned for the first time is 4, the number of comparison frames returned for the second time is 5, and the number of comparison frames returned for the third time Because the feature data of the TV frame data requires memory, the current memory size set in the TV device is 6 frames, therefore, the number of comparison frames returned by the cloud server here does not exceed 6, and the number of frames returned here It is the number of video frames that have been decoded but not yet loaded for display in the TV device. In addition, the specific parameter adjustment information can be set according to the application scenario, which is not limited in the embodiment of the present invention.

In addition, after the processing unit obtains the scene information represented by the feature data, it processes the scene information according to the pre-stored image quality expert data, such as color, brightness, chroma, contrast, noise reduction, sharpness, clarity, etc. in the feature data. Adjust the picture scaling parameters, skin tone, de-jitter and picture smoothing, and adjust the Gamma curve, brightness curve and gray scale curve to obtain the set picture quality parameters. For example, for blue sky and green space, the blue and green are strengthened, and the size range of the enhancement can be 5% of the experience adjustment; for the night scene part, the Gamma curve can be dynamically adjusted to increase the bright area and dark area to increase The contrast of large scenes, while increasing the noise reduction value; for sports scenes, you can increase the smoothing function; for human scenes, you can increase the skin tone setting by one level; and for food scenes, you can increase For chromaticity improvement, etc., the feature data corresponding to different scene information can be set according to actual conditions, which is not limited in the embodiment of the present invention.

In step S108, the image quality parameter is applied to adjust the video frame data.

After receiving the image quality parameter returned by the cloud server, the TV device also applies the image quality parameter to adjust the video frame data to obtain the adjusted video frame data, and display the adjusted video frame data to realize different scenes The video frame data below dynamically loads the corresponding picture quality parameters, which improves the picture quality effect.

Step S110: Display the adjusted video frame data.

The television image quality adjustment method provided by the embodiment of the present invention obtains video frame data by decoding the received television signal; and uses a pre-trained deep learning model to perform feature extraction on the video frame data to obtain feature data; Among them, the feature data is used to characterize the scene information corresponding to the video frame data; the feature data is sent to the cloud server to obtain the image quality parameters returned by the cloud server based on the feature data; the image quality parameters are used to adjust the video frame data, and The above-mentioned video frame data after adjustment is displayed. The present application can dynamically load corresponding image quality parameters to video frame data in different scenarios, thereby improving the image quality effect of the television device, and further improving the user experience.

On the basis of FIG. 1, the embodiment of the present invention also provides another TV picture quality adjustment method. The method focuses on revising the picture quality parameters returned by the cloud server according to the collected current picture quality parameters of the television equipment. For the specific implementation process, see Figure 2. The method includes the following steps:

Step S202, receiving a TV signal, and decoding the TV signal to obtain video frame data.

Step S204, applying a pre-trained deep learning model to perform feature extraction on the video frame data to obtain feature data; wherein the feature data is used to characterize scene information corresponding to the video frame data.

Step S206: Send the characteristic data to the cloud server to obtain the image quality parameters returned by the cloud server based on the characteristic data.

For the above steps S202ˉS206, refer to step S102ˉS106 for details, and the details are not described herein again in this embodiment of the present invention.

Step S208: Obtain the current picture quality parameters displayed by the television device.

After receiving the image quality parameters returned by the cloud server, the television device also obtains the current image quality parameters displayed by the television device. Among them, the current picture quality parameter is the picture quality parameter of the currently displayed picture on the screen of the TV equipment collected. Here, the current picture quality parameter can be collected by the sensor built in the display screen, or the current picture can be obtained by moving the camera (such as the mobile phone camera). Quality parameters, or a sensor built in a portable device (such as a remote control) to acquire the current image quality parameters. When the sensor is built in the display screen, the sensor collects the color, brightness and gray scale of the current display screen, so as to obtain the digitized value of the current color RGB or YUV of the display screen, as well as the Gamma curve, brightness curve and gray scale curve.

Step S210: Calculate the difference between the current image quality parameter and the image quality parameter.

Calculate the image quality parameter returned by the cloud server with the current image quality parameter to obtain the difference between the current image quality parameter and the image quality parameter. Specifically, since the image quality parameter includes multiple parameter values, the image quality parameter value is Each parameter value is calculated with the corresponding parameter value in the current image quality parameter, thereby obtaining the difference of each parameter value, and the difference of all parameter values is the difference between the current image quality parameter and the image quality parameter.

Step S212, judging whether the difference is within a preset range;

At this time, it is judged whether the difference value is within the preset range, if yes, step S218 is executed; if not, step S214ˉS216 is executed.

Step S214, if not, revise the image quality parameter.

Specifically, the preset range includes the maximum threshold and the minimum threshold. If the difference is less than the minimum threshold or greater than the maximum threshold, the difference is not within the preset range. At this time, the image quality returned by the cloud server will be based on the current image quality parameters. The parameters are revised so that the difference between the revised image quality parameter and the current image quality parameter is within the preset range.

Step S216: Apply the revised image quality parameters to adjust the video frame data.

At this time, the TV device will apply the revised image quality parameters to adjust the video frame data, so that not only can the image quality parameters be dynamically adjusted for the video frame data of different scenes, but also the next frame can be adjusted based on the current image quality parameters of the current frame. The picture quality parameters of the picture are adjusted to avoid the large difference in picture quality effects of the two frames before and after, thereby further improving the picture quality effect of the TV equipment.

Step S218, if yes, apply the image quality parameter to adjust the video frame data.

Specifically, if the difference between the current image quality parameter and the image quality parameter is within the preset range, that is, the difference is greater than or equal to the minimum threshold, and less than or equal to the maximum threshold, the television device directly applies the image quality parameter adjustment returned by the cloud server Video frame data.

Step S220: Display the adjusted video frame data.

In addition, according to the judgment result of whether the difference is within the preset range, the television device in the embodiment of the present invention may also be provided with a state machine, wherein the state machine is set with a first state, a second state, and a third state. When the difference between the image quality parameter and the image quality parameter is within the preset range, the state machine is in the first state; when the difference is greater than the maximum threshold, the state machine is in the second state; when the difference is less than the minimum threshold, the state machine is The third state, so that when the state machine switches to the first state, the television device applies the image quality parameters to adjust the video frame data; when the state machine switches to the second state or the third state, the television device adjusts the video frame data according to the current image quality parameters The picture quality parameters are revised, and the revised picture quality parameters are applied to adjust the video frame data.

Further, on the basis of FIG. 1, the embodiment of the present invention also provides another method for adjusting the TV picture quality. The method focuses on the specific implementation process of adjusting video frame data by applying picture quality parameters. Refer to FIG. 3, this method It includes the following steps:

Step S302, receiving a TV signal, and decoding the TV signal to obtain video frame data.

Step S304, applying a pre-trained deep learning model to perform feature extraction on the video frame data to obtain feature data; wherein the feature data is used to characterize scene information corresponding to the video frame data.

Step S306: Send the characteristic data to the cloud server to obtain the image quality parameters returned by the cloud server based on the characteristic data.

For details of the foregoing steps S302ˉS306, refer to step S102ˉS106, and details are not described herein again in the embodiment of the present invention.

In step S308, the image quality parameters are loaded into the video frame data according to the loading mode to adjust the video frame data.

Among them, the loading mode includes frame picture mode and time axis mode. When the loading mode is frame picture mode, at this time, the picture quality parameters are sequentially loaded into the video frame data according to the preset number of frames to adjust the video frame data; here, the preset number of frames can be a single frame or multiple frames. The embodiment of the present invention does not limit this description.

When the loading mode is the time axis mode, the image quality parameters are sequentially loaded according to the display time of the video frame data to adjust the video frame data; for example, for a multimedia video signal with a playback duration of 90 minutes, the decoding process is obtained Video frame data, and feature extraction of the video frame data based on the deep learning model to obtain the feature data, and send the feature data to the cloud server so that the cloud server returns the corresponding image quality parameters within 90 minutes of the multimedia video signal. , According to the playback time, that is, the display time of the video frame data, the picture quality parameters are successively loaded into the video frame data to obtain the adjusted video frame data; this loading method can be loaded by itself only at the time point, thereby reducing the picture Transmission time and loading time of quality parameters. In addition, the selection of the above two loading modes can be set according to actual application scenarios, or can be automatically matched according to the image quality parameters returned by the cloud server, which is not limited in the embodiment of the present invention.

In addition, the above loading process is carried out in the vertical blanking area of the TV device, where the vertical blanking area refers to the time when the TV signal is received to the actual display, for example, for the current 4K display TV device, its effective pixel points It is 3840X2160, that is, a frame of picture has 3840 dots per line and a total of 2160 lines. However, the 4K display TV device really receives 4400x2250. Here, the 90 line time obtained from 2250 and 2160 is the vertical blanking area. The vertical blanking area does not display, that is, it does not affect the display effect of the TV device.

Step S310: Display the adjusted video frame data.

The above-mentioned TV image quality adjustment method obtains video frame data by decoding the received TV signal; and applies a pre-trained deep learning model to perform feature extraction on the above-mentioned video frame data to obtain feature data; and send the feature data To the cloud server to obtain the image quality parameters returned by the cloud server based on the above-mentioned characteristic data; and to apply the image quality parameters to adjust the above-mentioned video frame data, and display the adjusted above-mentioned video frame data, so as to realize the adjustment of the video frames in different scenes. The data dynamically loads the corresponding picture quality parameters, which improves the picture quality effect of the TV device, and further improves the user experience.

Based on the foregoing method embodiment, an embodiment of the present invention also provides a television image quality adjustment device, which is set in a television device, and the television device is in communication connection with a cloud server. As shown in Figure 4, the above-mentioned device includes:

The decoding module 41 is used for receiving TV signals, and decoding the TV signals to obtain video frame data.

Specifically, since the TV signal includes one or more of HDMI signal, AV signal, network video signal, multimedia video signal, and digital TV signal, the decoding module 41 here includes multiple decoding units, as shown in FIG. 7, as shown in FIG. The HDMI signal decoding unit 411 is used to decode the received HDMI signal; the AV signal decoding unit 412 is used to decode the received AV signal; the multimedia video signal decoding unit 413 is used to decode the received multimedia video signal and The digital TV signal is decoded.

The extraction module 42 is configured to apply a pre-trained deep learning model to perform feature extraction on the video frame data to obtain feature data; wherein the feature data is used to characterize scene information corresponding to the video frame data.

The obtaining module 43 is configured to send the characteristic data to the cloud server to obtain the image quality parameters returned by the cloud server based on the characteristic data.

The adjustment module 44 is used to adjust the video frame data by applying image quality parameters.

The display module 45 is used to display the adjusted video frame data.

The above-mentioned device further includes: acquiring the current picture quality parameter displayed by the television device; comparing the current picture quality parameter with the picture quality parameter, and revising the picture quality parameter according to the comparison result.

The foregoing compares the current image quality parameters with the image quality parameters, and revises the image quality parameters according to the comparison results, including: calculating the difference between the current image quality parameter and the image quality parameter; judging whether the difference is within the preset range; if not, Revise the picture quality parameter.

The aforementioned adjustment module 44 is further configured to: load the image quality parameters into the video frame data according to the loading mode to adjust the video frame data; wherein, the loading mode includes a frame image mode and a time axis mode.

If the above-mentioned loading mode is the frame mode, the above-mentioned loading the image quality parameters into the video frame data according to the loading mode to adjust the video frame data includes: loading the image quality parameters into the video frame data according to the preset number of frames in order to Adjust the video frame data.

If the above loading mode is the timeline mode, the above loading the image quality parameters into the video frame data according to the loading mode to adjust the video frame data includes: loading the image quality parameters successively according to the display time of the video frame data to adjust the video Frame data.

The above-mentioned deep learning model is a model obtained based on neural network training. The device further includes: obtaining a pre-stored video frame data set, where the video frame data set includes HDMI signals, AV signals, network video signals, multimedia video signals, and digital TV Signal; input the video frame data set to the neural network for training to obtain a deep learning model.

The implementation principles and technical effects of the television image quality adjustment device provided in the embodiments of this application are the same as those of the foregoing method embodiments. For a brief description, for the parts not mentioned in the embodiments of the television image quality adjustment device, please refer to the foregoing television Corresponding content in the embodiment of the image quality adjustment method.

The embodiment of the present invention also provides a television device. As shown in FIG. 5, it is a schematic diagram of the structure of the television device 5. A running computer program, when the processor 51 executes the computer program, the steps of the television image quality adjustment method provided in the foregoing embodiments are implemented.

In the embodiment shown in FIG. 5, the television device 5 further includes a bus 52 and a communication interface 53, wherein the processor 51, the communication interface 53 and the memory 50 are connected through the bus 52.

The memory 50 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 53 (which may be wired or wireless), and the Internet, a wide area network, a local network, a metropolitan area network, etc. may be used. The bus 52 may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnection standard) bus, or an EISA (Extended Industry Standard Architecture) bus or the like. The bus 52 can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one bidirectional arrow is used to indicate in FIG. 5, but it does not mean that there is only one bus or one type of bus.

The processor 51 may be an integrated circuit chip with signal processing capability. In the implementation process, the steps of the foregoing method can be completed by an integrated logic circuit of hardware in the processor 51 or instructions in the form of software. The aforementioned processor 51 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP), etc.; it may also be a digital signal processor (Digital Signal Processor, DSP for short). ), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers. The storage medium is located in the memory, and the processor 51 reads the information in the memory, and completes the steps of the television image quality adjustment method of the foregoing embodiment in combination with its hardware.

The above-mentioned television device 5 also includes a sensor; the sensor is used to collect the current picture quality parameters displayed by the television device. In addition, the sensor can be built into the display.

Based on the above-mentioned television equipment, the embodiment of the present invention also provides a television image quality adjustment system. As shown in FIG. 6, the system includes the above-mentioned television equipment 5, and also includes a cloud server 6 communicatively connected with the television equipment 5. ; The cloud server 6 is used to receive the feature data sent by the television device 5, and obtain image quality parameters according to the feature data.

The aforementioned cloud server 6 further includes: an identification unit 61, configured to perform identification processing on the feature data to obtain scene information represented by the feature data.

Specifically, the recognition unit here includes a pre-trained recognition model, which inputs feature data into the recognition model, so that the recognition model outputs scene information based on the feature data, such as scenery, buildings, people, blue sky, green space, plants, food, Night scenes and competition sports, etc.; and scene block division information for each scene information. Among them, the above-mentioned recognition model is a model obtained based on neural network training.

The processing unit 62 is configured to process scene information according to pre-stored image quality expert data to obtain image quality parameters.

Specifically, after the processing unit 62 obtains the scene information represented by the feature data, it processes the scene information according to the pre-stored image quality expert data, such as color, brightness, chroma, contrast, noise reduction, sharpness, and clarity in the feature data. Adjust the degree, picture scaling parameters, skin tone, de-jitter and picture smoothing, and adjust the Gamma curve, brightness curve and gray scale curve to obtain the set picture quality parameters.

For ease of understanding, an example is given here. FIG. 7 is a schematic diagram of a TV picture quality adjustment system provided by an embodiment of the present invention. As shown in FIG. 7, the TV device 5 receives TV signals, where the TV signals include HDMI signals, AV signals, network video signals, and multimedia video signals. And one or more of the digital TV signal, the decoding module 41 decodes the received TV signal, specifically, the HDMI signal decoding unit 411 is used to decode the received HDMI signal; the AV signal decoding unit 412, It is used to decode the received AV signal; the multimedia video signal decoding unit 413 is used to decode the received multimedia video signal and digital TV signal; after the decoding processing is completed, the video frame data corresponding to the TV signal is obtained, and Input the video frame data to the extraction module 42, so that the pre-trained deep learning model in the extraction module 42 performs feature extraction on the video frame data to obtain feature data; and the extraction module 42 sends the feature data to the cloud server 6, So that the cloud server 6 generates image quality parameters based on the characteristic data, and sends the image quality parameters to the adjustment module 44, where the adjustment module 44 may also be referred to as a loading module. After the adjustment module 44 receives the image quality parameters, it applies the image quality parameter adjustment Video frame data, that is, the image quality parameters are loaded into the video frame data according to the loading mode in the vertical blanking area of the television device, and the adjusted video frame data is displayed through the display module 45, where the display module 45 is the television device 5 Display screen.

In addition, in order to further improve the image quality effect of the television device 5, the television image quality adjustment system in the embodiment of the present invention further includes a collection module 7, where the collection module 7 may be a sensor, and the sensor may be built into the display of the television device 5. On the screen, it can also be built into a portable device (such as a remote control). In addition, the collection module 7 can also use a mobile camera (such as a mobile phone camera), and send the collected current image quality parameters to the adjustment module 44 to communicate with the adjustment module. 44. The received image quality parameters sent by the cloud server 6 are compared, and the image quality parameters are revised according to the comparison result. At this time, the adjustment module 44 also loads the revised image quality parameters into the video frame data in the vertical blanking area, and The adjusted video frame data is displayed through the display module 45, which not only realizes the dynamic loading of the corresponding image quality parameters to the video frame data in different scenes, where different scenes can be the same source or different sources, but also improve This improves the image quality of TV equipment and improves user experience.

The embodiment of the present application also provides a computer-readable storage medium that stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to The foregoing method for adjusting the TV image quality is implemented. For specific implementation, please refer to the foregoing method embodiment, which will not be repeated here.

The television image quality adjustment method, device, system, and computer program product of television equipment provided by the embodiments of the present application include a computer-readable storage medium storing program code, and instructions included in the program code can be used to execute the foregoing method implementation For the specific implementation of the method described in the example, please refer to the method embodiment, which will not be repeated here.

Those skilled in the art can clearly understand that, for the convenience and conciseness of description, the specific working process of the system and device described above can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, they may be fixed connections or detachable connections. , Or integrally connected; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication between two components. For those of ordinary skill in the art, the specific meaning of the above-mentioned terms in the present invention can be understood in specific situations.

If the function is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present invention essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes. .

In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. The indicated orientation or positional relationship is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the pointed device or element must have a specific orientation or a specific orientation. The structure and operation cannot therefore be understood as a limitation of the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance.

Finally, it should be noted that the above-mentioned embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, but not to limit them. The protection scope of the present invention is not limited thereto, although referring to the foregoing The embodiments give a detailed description of the present invention, and those of ordinary skill in the art should understand that any person skilled in the art can still modify the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention. Or it can be easily conceived of changes, or equivalent replacements of some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be covered by the present invention Within the scope of protection. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

A television picture quality adjustment method, characterized in that the method is applied to a television device, and the television device is in communication connection with a cloud server, and the method includes:

Receiving a television signal, and decoding the television signal to obtain video frame data;

Applying a pre-trained deep learning model to perform feature extraction on the video frame data to obtain feature data; wherein the feature data is used to characterize scene information corresponding to the video frame data;

Sending the characteristic data to the cloud server to obtain image quality parameters returned by the cloud server based on the characteristic data;

Adjusting the video frame data by applying the image quality parameter;

Display the adjusted video frame data.
The method for adjusting TV picture quality according to claim 1, wherein the method further comprises:

Acquiring the current picture quality parameters displayed by the television device;

The current image quality parameter is compared with the image quality parameter, and the image quality parameter is revised according to the comparison result.
4. The television picture quality adjustment method according to claim 2, wherein the step of comparing the current picture quality parameter with the picture quality parameter, and revising the picture quality parameter according to the comparison result comprises:

Calculating the difference between the current image quality parameter and the image quality parameter;

Determine whether the difference is within a preset range;

If not, revise the image quality parameter.
The TV picture quality adjustment method according to claim 1, wherein the step of applying the picture quality parameter to adjust the video frame data comprises:

The image quality parameter is loaded into the video frame data according to a loading mode to adjust the video frame data; wherein the loading mode includes a frame image mode and a time axis mode.
The TV picture quality adjustment method according to claim 4, wherein if the loading mode is a frame picture mode, the picture quality parameters are loaded into the video frame data according to the loading mode to adjust all the picture quality parameters. The steps of describing the video frame data include:

The image quality parameters are sequentially loaded into the video frame data according to the preset number of frames to adjust the video frame data.
The TV image quality adjustment method according to claim 4, wherein if the loading mode is a time axis mode, the image quality parameters are loaded into the video frame data according to the loading mode to adjust all the image quality parameters. The steps of describing the video frame data include:

The image quality parameters are successively loaded according to the display time of the video frame data to adjust the video frame data.
The TV picture quality adjustment method according to claim 1, wherein the deep learning model is a model obtained based on neural network training, and the method further comprises:

Acquiring a pre-stored video frame data set, where the video frame data set includes an HDMI signal, an AV signal, a network video signal, a multimedia video signal, and a digital TV signal;

The video frame data set is input to a neural network for training to obtain the deep learning model.
The TV image quality adjustment method according to claim 1, wherein the image quality parameters include at least one of the following: color temperature, color, brightness, grayscale, sharpness, contrast, sharpness, and image scaling parameters.
A television picture quality adjustment device, characterized in that the device is provided in a television device, the television device is in communication connection with a cloud server, and the device includes:

The decoding module is used to receive a TV signal, and decode the TV signal to obtain video frame data;

An extraction module, configured to apply a pre-trained deep learning model to perform feature extraction on the video frame data to obtain feature data; wherein the feature data is used to characterize scene information corresponding to the video frame data;

An obtaining module, configured to send the characteristic data to the cloud server to obtain the image quality parameters returned by the cloud server based on the characteristic data;

An adjustment module for applying the image quality parameter to adjust the video frame data;

The display module is used to display the adjusted video frame data.
The television picture quality adjusting device according to claim 9, wherein:

The adjustment module is also used for:

Acquiring the current picture quality parameters displayed by the television device;

The current image quality parameter is compared with the image quality parameter, and the image quality parameter is revised according to the comparison result.
The television picture quality adjusting device according to claim 10, wherein:

The adjustment module is also used for:

Calculating the difference between the current image quality parameter and the image quality parameter;

Determine whether the difference is within a preset range;

If not, revise the image quality parameter.
The television picture quality adjustment device according to claim 9, wherein the adjustment module is further configured to:

The image quality parameter is loaded into the video frame data according to a loading mode to adjust the video frame data; wherein the loading mode includes a frame image mode and a time axis mode.
The television picture quality adjustment device according to claim 12, wherein the adjustment module is further configured to:

In response to the loading mode being the frame image mode, the image quality parameters are sequentially loaded into the video frame data according to the preset number of frames, so as to adjust the video frame data.
The television picture quality adjustment device according to claim 12, wherein the adjustment module is further configured to:

In response to the loading mode being the time axis mode, the image quality parameters are sequentially loaded according to the display time of the video frame data to adjust the video frame data.
The television image quality adjustment device according to claim 9, wherein the image quality parameters include at least one of the following: color temperature, color, brightness, grayscale, sharpness, contrast, sharpness, and image scaling parameters.
A television device includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to:

Receiving a television signal, and decoding the television signal to obtain video frame data;

Applying a pre-trained deep learning model to perform feature extraction on the video frame data to obtain feature data; wherein the feature data is used to characterize scene information corresponding to the video frame data;

Sending the characteristic data to a cloud server to obtain image quality parameters returned by the cloud server based on the characteristic data;

Adjusting the video frame data by applying the image quality parameter;

Display the adjusted video frame data.
The television device of claim 16, wherein the processor further executes the computer program to:

Acquiring the current picture quality parameters displayed by the television device;

The current image quality parameter is compared with the image quality parameter, and the image quality parameter is revised according to the comparison result.
18. The television device of claim 17, wherein the step of comparing the current image quality parameter with the image quality parameter, and revising the image quality parameter according to the comparison result comprises:

Calculating the difference between the current image quality parameter and the image quality parameter;

Determine whether the difference is within a preset range;

If not, revise the image quality parameter.
The television device of claim 16, wherein the step of applying the image quality parameter to adjust the video frame data comprises:

The image quality parameter is loaded into the video frame data according to a loading mode to adjust the video frame data; wherein the loading mode includes a frame image mode and a time axis mode.
The television device according to claim 19, wherein if the loading mode is a frame image mode, the image quality parameter is loaded into the video frame data according to the loading mode to adjust the video The steps of frame data include:

The image quality parameters are sequentially loaded into the video frame data according to the preset number of frames to adjust the video frame data.
The television device according to claim 19, wherein if the loading mode is a time axis mode, the image quality parameter is loaded into the video frame data according to the loading mode to adjust the video The steps of frame data include:

The image quality parameters are successively loaded according to the display time of the video frame data to adjust the video frame data.
The television device according to claim 16, wherein the image quality parameters comprise at least one of the following: color temperature, color, brightness, grayscale, sharpness, contrast, sharpness, and image scaling parameters. 23. The television device of claim 16, wherein the television device further comprises a sensor;

The sensor is used to collect the current picture quality parameters displayed by the television device.
A television picture quality adjustment system, characterized in that the system includes a television device and a cloud server communicatively connected with the television device;

The cloud server is configured to receive feature data sent by the television device, and obtain image quality parameters according to the feature data,

Wherein, the television device includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, and the processor executes the computer program to:

Receiving a television signal, and decoding the television signal to obtain video frame data;

Applying a pre-trained deep learning model to perform feature extraction on the video frame data to obtain feature data; wherein the feature data is used to characterize scene information corresponding to the video frame data;

Sending the characteristic data to a cloud server to obtain image quality parameters returned by the cloud server based on the characteristic data;

Adjusting the video frame data by applying the image quality parameter;

Display the adjusted video frame data. .
The TV picture quality adjustment system according to claim 24, wherein the cloud server is further configured to:

Performing recognition processing on the feature data to obtain scene information represented by the feature data;

The scene information is processed according to the pre-stored picture quality expert data to obtain picture quality parameters.