CN112965922A - Method and system for enhancing AI performance of intelligent terminal - Google Patents
Method and system for enhancing AI performance of intelligent terminal Download PDFInfo
- Publication number
- CN112965922A CN112965922A CN202110235453.2A CN202110235453A CN112965922A CN 112965922 A CN112965922 A CN 112965922A CN 202110235453 A CN202110235453 A CN 202110235453A CN 112965922 A CN112965922 A CN 112965922A
- Authority
- CN
- China
- Prior art keywords
- chip
- processing chip
- content
- enhanced
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/14—Handling requests for interconnection or transfer
- G06F13/20—Handling requests for interconnection or transfer for access to input/output bus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/76—Architectures of general purpose stored program computers
- G06F15/78—Architectures of general purpose stored program computers comprising a single central processing unit
- G06F15/7807—System on chip, i.e. computer system on a single chip; System in package, i.e. computer system on one or more chips in a single package
- G06F15/7817—Specially adapted for signal processing, e.g. Harvard architectures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Microelectronics & Electronic Packaging (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention provides a method and a system for enhancing AI performance of an intelligent terminal, which undertake most AI enhancing tasks of the intelligent terminal through an independent AI processing chip, realize low image quality enhancement including but not limited to games and videos, low frame rate frame interpolation and the like, provide high-resolution and high-frame rate game and video effects and improve user experience; because the image fusion module is arranged in the AI processing chip, the fusion processing of real-time games, video contents and UI contents can be realized, complete output images and audio are obtained and displayed in real time through the display module without being transmitted back to the SOC chip for displaying, and therefore, ultra-low delay can be realized, and the user experience is not influenced.
Description
Technical Field
The invention relates to the technical field of AI chips, in particular to a method and a system for enhancing AI performance of an intelligent terminal.
Background
At present, mobile terminal devices such as mobile phones and the like on the market have AI computing capacity, can realize functions such as voice awakening, voiceprint unlocking, face recognition, photographing beautification and the like, and also has intelligent power consumption management and the like in the mobile phones. The realization method can adopt the CPU, GPU, DSP and other computing units in the SOC chip to cooperatively perform AI operation processing, and also can add a special neural network unit (NPU) in the SOC chip to perform AI operation processing.
The most typical AI application at present is AI photographing, and through image data obtained by a camera module and a certain AI algorithm added by a CPU/GPU/DSP/NPU module, face recognition/unlocking, face beautification/background blurring/scene recognition/special effect processing can be realized.
The AI computational power in the SOC chip is continuously improved, but the improvement of the computational power is limited all the time due to the limitation of the mobile terminal chip, and the AI computational power is only limited to voice and image processing and cannot be applied more and more strongly.
Disclosure of Invention
In order to overcome the technical defects, the invention aims to provide a method and a system for realizing AI game over-score, AI video over-score and AI video noise reduction by enhancing AI computing power.
The invention discloses a method for enhancing AI performance of an intelligent terminal, which comprises the following steps: receiving contents to be enhanced from an SOC chip of the intelligent terminal through an independent AI processing chip to perform AI processing so as to obtain primary AI enhanced contents; the AI processing chip also receives UI data from the SOC chip, wherein the UI data comprises interface data and interactive data, and the AI processing chip fuses the interface data and the interactive data with the primary AI enhanced content to acquire final AI enhanced content; and the AI processing chip directly outputs the final-stage AI enhancement content for display and transmits the final-stage AI enhancement content to the SOC chip for storage.
Preferably, the step of directly displaying the final-stage AI enhancement content output by the AI processing chip and transmitting the final-stage AI enhancement content output to the SOC chip for storage includes: the final-stage AI enhanced content is displayed through the AI processing chip and then transmitted to the SOC chip for storage; or the final-level AI enhanced content is transmitted to the SOC chip for storage through the AI processing chip and then displayed.
Preferably, the SOC chip controls the AI processing chip to operate in an AI enhanced mode or a through mode; when the AI processing chip carries out an AI enhancement mode, AI enhancement processing is carried out on the contents to be enhanced by the AI processing chip, and the contents are fused with the UI data and then output and displayed; and when the AI processing chip is in a direct-through mode, the AI processing chip receives the content to be enhanced from the SOC chip of the intelligent terminal and directly outputs and displays the content.
Preferably, the content to be enhanced includes video data and audio data, the final-level AI enhancement content includes a game data packet and a video data packet, and the game data packet and the video data packet include video data and audio data.
Preferably, a resolution parameter threshold, a frame rate parameter threshold, and an image quality parameter threshold are preset in the AI processing chip, and the SOC chip controls the AI processing chip to perform the AI enhancement mode operation or the through mode operation according to the resolution parameter threshold, the frame rate parameter threshold, and the image quality parameter threshold.
A system for enhancing AI performance of an intelligent terminal comprises an SOC chip and an AI processing chip, wherein the SOC chip and the AI processing chip are provided with a plurality of high-speed data interfaces, and the AI processing chip receives contents to be enhanced from the SOC chip through the high-speed data interfaces; the AI processing chip is provided with a first embedded neural network processor for carrying out AI processing on the content to be enhanced so as to obtain primary AI enhanced content; the AI processing chip is also provided with an image fusion module, receives UI data from the SOC chip through the high-speed data interface, the UI data comprises interface data and interactive data, and the AI processing chip fuses the interface data and the interactive data with the primary AI enhanced content to obtain final AI enhanced content; the display module is electrically connected with the SOC chip and/or the AI processing chip; and the AI processing chip outputs the final-stage AI enhancement content to the display module for display and transmits the final-stage AI enhancement content to the storage module of the SOC chip for storage.
Preferably, the display module is electrically connected with the SOC chip and the AI processing chip; the final-stage AI enhanced content is transmitted to the display module for display through the AI processing chip and then transmitted to the SOC chip for storage; or the final-level AI enhanced content is transmitted to the SOC chip for storage through the AI processing chip, and the display module acquires the final-level AI enhanced content through the SOC chip for display.
Preferably, the SOC chip controls the AI processing chip to operate in an AI enhanced mode or a through mode; when the AI processing chip carries out an AI enhancement mode, AI enhancement processing is carried out on the contents to be enhanced by the AI processing chip, and the contents are fused with the UI data and then output and displayed; when the AI processing chip is in a direct mode, the AI processing chip receives the content to be enhanced from the SOC chip of the intelligent terminal and directly outputs and displays the content; the SOC chip comprises a second embedded neural network processor, and the second embedded neural network processor works simultaneously with the first embedded neural network processor in the AI enhanced mode, or works or does not work when the AI processing chip is in the direct-through mode alone.
Preferably, a content transmission channel, a UI data transmission channel and an enhanced data backhaul transmission channel are included between the high-speed data interfaces of the SOC chip and the AI processing chip; the AI processing chip acquires the content to be enhanced from the SOC through the content transmission channel, acquires UI data from the SOC through the UI data transmission channel, and transmits the final-level AI enhanced content back to the SOC through the enhanced data transmission channel.
Preferably, the AI processing chip further comprises an AI performance analysis module, and a resolution parameter threshold, a frame rate parameter threshold and an image quality parameter threshold are preset in the AI performance analysis module; and the SOC controls the AI processing chip to carry out the AI enhancement mode work or the direct-through mode work according to a resolution parameter threshold, a frame rate parameter threshold and an image quality parameter threshold.
After the technical scheme is adopted, compared with the prior art, the method has the following beneficial effects:
1. the independent AI processing chip is used for bearing most AI enhancing tasks of the intelligent terminal, low image quality enhancement including but not limited to games and videos, frame insertion at a low frame rate and the like are realized, the effects of the games and videos with high resolution and high frame rate are provided, and the user experience is improved; the image fusion module is arranged in the AI processing chip, so that the fusion processing of real-time games and video contents and UI contents can be realized, complete output images and audio can be obtained, and the images and the audio can be displayed in real time through the display module without being transmitted back to the SOC chip for displaying, so that the ultra-low delay can be realized, and the user experience is not influenced;
2. under special conditions, the obtained final-level AI enhancement content needs to be stored, so that the final-level AI enhancement content is allowed to be transmitted to the SOC chip for storage through the AI processing chip and then displayed, and a certain delay is allowed at the moment;
3. the AI processing chip is controlled by the SOC chip, can be directly processed and displayed by the SOC chip in a general scene, and is controlled to be opened only when high-efficiency AI processing is needed, so that the power consumption is saved;
4. and the SOC carries out allocation according to various parameters of the AI performance analysis module to guide the AI processing chip to carry out an AI enhancement mode or a direct-through mode and share computing power for the second embedded neural network processor.
Drawings
Fig. 1 is a flowchart of a method for enhancing AI performance of an intelligent terminal according to the present invention;
fig. 2 is a block diagram illustrating a system for enhancing AI performance of an intelligent terminal according to the present invention.
Detailed Description
The advantages of the invention are further illustrated in the following description of specific embodiments in conjunction with the accompanying drawings.
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present disclosure. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention.
In the description of the present invention, unless otherwise specified and limited, it is to be noted that the terms "mounted," "connected," and "connected" are to be interpreted broadly, and may be, for example, a mechanical connection or an electrical connection, a communication between two elements, a direct connection, or an indirect connection via an intermediate medium, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no specific meaning in themselves. Thus, "module" and "component" may be used in a mixture.
Referring to fig. 1, the present invention discloses a method for enhancing AI performance of an intelligent terminal, comprising the steps of:
s1, receiving the content to be enhanced from the SOC chip of the intelligent terminal through the independent AI processing chip to perform AI processing so as to obtain primary AI enhanced content;
s2, the AI processing chip also receives UI data from the SOC chip, the UI data comprises interface data and interactive data, and the AI processing chip fuses the interface data and the interactive data with the primary AI enhanced content to obtain final AI enhanced content;
and S3, the AI processing chip directly displays the final-stage AI enhancement content output and transmits the final-stage AI enhancement content to the SOC chip for storage.
The invention shares most of AI enhancing tasks originally carried out by the SOC chip through the AI processing chip, has centralized functions, high efficiency and good effect, fuses game and video contents and UI contents in real time by the AI processing chip to obtain complete final-level AI enhancing contents for outputting images and audios, can directly display the final-level AI enhancing contents without transmitting the final-level AI enhancing contents back to the SOC chip for displaying, realizes ultralow time delay, and thus does not influence user experience while carrying out AI enhancing on the contents.
The invention is preferably applied to the mobile phone as the mobile phone is biased to the comprehensive function and the AI processing function is less prominent, and can also be applied to intelligent terminals such as tablets, game machines and the like with large computation and high requirements. The AI enhancements implemented by the present invention include, but are not limited to, AI game over-points, AI video noise reduction, and the like. For example, the video of 720p30fps can be promoted to 1080p60fps or higher through AI processing, so that better viewing experience and game experience can be realized.
Preferably, the final-level AI enhancement content is displayed in real time by the AI processing chip to reduce delay, and then transmitted to the SOC chip for storage. In special cases, the obtained final-level AI enhancement content needs to be saved first, so that it is preferable to allow the final-level AI enhancement content to be transmitted to the SOC chip for storage through the AI processing chip and then displayed so as to backup the final-level AI enhancement content.
Preferably, the SOC chip controls the AI processing chip to operate in an AI enhancement mode or a direct mode, and in a general scene, for a small-process AI enhancement task, when the SOC chip controls the AI processing chip to perform the direct mode, the AI processing chip receives contents to be enhanced from the SOC chip of the intelligent terminal to directly output and display the received contents, and only when efficient AI processing is required, the AI processing chip is controlled to perform the AI enhancement mode, that is, the contents to be enhanced of the AI processing chip are subjected to AI enhancement processing and output and display the fused contents with UI data, so as to reduce power consumption.
The content to be enhanced comprises image data and audio data, the final-level AI enhanced content comprises a game data packet and a video data packet, and the game data packet and the video data packet comprise the image data and the audio data. The game data packet can come from a local or network or cloud, and the video data packet can come from real-time shooting of the intelligent terminal, a local video or a network or cloud video.
Preferably, the AI processing chip is preset with a resolution parameter threshold, a frame rate parameter threshold and an image quality parameter threshold, and the SOC chip controls the AI processing chip to perform AI enhancement mode operation or direct mode operation according to the resolution parameter threshold, the frame rate parameter threshold and the image quality parameter threshold.
Referring to fig. 2, the present invention further provides a system for enhancing an AI performance of an intelligent terminal, which can be used to implement the above method for enhancing an AI performance of an intelligent terminal, including:
the SOC chip is used as a main chip of the intelligent terminal and is used for bearing the basic control function, the processing function and part of simple AI processing function of the intelligent terminal;
and the AI chip is used as a chip for enhancing the AI performance of the intelligent terminal and is used for carrying out complex AI operation, data fusion, data return and display output.
The SOC chip and the AI processing chip are provided with a plurality of high-speed data interfaces, and are in transmission connection with each other through the high-speed data interfaces, and the AI processing chip receives contents to be enhanced from the SOC chip through the high-speed data interfaces.
The AI Processing chip is provided with a first embedded Neural-Network Processing Unit (NPU) for performing AI Processing on the content to be enhanced to obtain primary AI enhanced content.
The AI processing chip is also provided with an image fusion module, receives UI data from the SOC chip through the high-speed data interface, the UI data comprises interface data and interactive data, and the AI processing chip fuses the interface data and the interactive data with primary AI enhanced content to obtain final AI enhanced content. Because the interface data and the interactive data are fused, the generated final-level AI enhanced content can be directly displayed, the time delay is small, a user can obtain game data and video data after AI enhancement in real time, and the experience is strong.
The system also comprises a display module which is a display screen and can be electrically connected with the SOC chip and the AI processing chip at the same time or designed to be electrically connected with only one of the SOC chip and the AI processing chip, and the connected chips play a role in outputting and displaying. In this embodiment, the display module is directly electrically connected to the AI processing chip, and the AI processing chip plays a role of outputting and displaying. The AI processing chip outputs the final-level AI enhancement content to the display module for display, and transmits the final-level AI enhancement content to the storage module of the SOC chip for storage.
Preferably, the display module is electrically connected with the SOC chip and the AI processing chip at the same time, the final-level AI enhancement content is transmitted to the SOC chip for storage through the AI processing chip, and the display module acquires the final-level AI enhancement content through the SOC chip for display so as to deal with a special situation that the acquired final-level AI enhancement content needs to be stored.
In this embodiment, the display module is only electrically connected to the AI processing chip, that is, the final-level AI enhancement content is directly obtained from the AI processing chip for display.
Preferably, the SOC chip includes a CPU module, a GPU module, a DSP module, and a second embedded neural network processor. The SOC controls the AI processing chip to work through an AI enhancement mode or a direct-through mode; when the AI processing chip carries out an AI enhancement mode, AI enhancement processing is carried out on the contents to be enhanced by the AI processing chip, and the contents are fused with UI data and then output and displayed; when the AI processing chip is in the direct-through mode, the AI processing chip receives the content to be enhanced from the SOC chip of the intelligent terminal and directly outputs and displays the content.
It should be noted that, the first embedded Neural network processor and the second embedded Neural network processor are both embedded Neural Network Processors (NPUs), and both of them may work separately or cooperatively, that is: the second embedded neural network processor may not operate, or operate simultaneously with the first embedded neural network processor in the AI enhancement mode, or operate alone in the through mode of the AI processing chip. The working states of the first embedded neural network processor and the second embedded neural network processor are distributed to deal with different application scenes, so that the calculation power is reduced integrally. The first embedded neural network processor and the second embedded neural network processor can apply the same algorithm and perform the same work content when cooperatively working, and can also respectively perform different work contents by adopting different algorithms, and the control is not limited here, and is specifically performed by an SOC chip.
The SOC chip is electrically connected with a camera module of the intelligent terminal to acquire image data, and is also electrically connected with a voice module to acquire audio data. The camera module is typically a camera and the speech module is typically a microphone.
Preferably, a content transmission channel, a UI data transmission channel and an enhanced data return transmission channel are included between the high-speed data interfaces of the SOC chip and the AI processing chip. The AI processing chip acquires the content to be enhanced from the SOC through the content transmission channel, acquires UI data from the SOC through the UI data transmission channel, and transmits the final-level AI enhanced content back to the SOC for storage through the enhanced data transmission channel.
Preferably, the AI processing chip further includes an AI performance analysis module, and a resolution parameter threshold, a frame rate parameter threshold and an image quality parameter threshold are preset in the AI performance analysis module. The SOC controls the AI processing chip to carry out AI enhancement mode work or direct-through mode work according to the resolution parameter threshold, the frame rate parameter threshold and the image quality parameter threshold.
As an optional application of the AI performance analysis module, the AI performance analysis module may further analyze that when the resolution of the final-level AI enhancement content reaches a preset resolution parameter, the final-level AI enhancement content is allowed to be output for display and storage; and when the resolution ratio does not reach the preset resolution ratio parameter, returning the final-stage AI enhanced content to the first embedded neural network processor for AI processing again until the preset resolution ratio is reached.
The smart terminal may be implemented in various forms. For example, the terminal described in the present invention may include an intelligent terminal such as a mobile phone, a smart phone, a notebook computer, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a navigation device, etc., and a fixed terminal such as a digital TV, a desktop computer, etc. In the following, it is assumed that the terminal is a smart terminal. However, it will be understood by those skilled in the art that the configuration according to the embodiment of the present invention can be applied to a fixed type terminal in addition to elements particularly used for moving purposes.
It should be noted that the embodiments of the present invention have been described in terms of preferred embodiments, and not by way of limitation, and that those skilled in the art can make modifications and variations of the embodiments described above without departing from the spirit of the invention.
Claims (10)
1. A method for enhancing AI performance of an intelligent terminal, comprising the steps of:
receiving contents to be enhanced from an SOC chip of the intelligent terminal through an independent AI processing chip to perform AI processing so as to obtain primary AI enhanced contents;
the AI processing chip also receives UI data from the SOC chip, wherein the UI data comprises interface data and interactive data, and the AI processing chip fuses the interface data and the interactive data with the primary AI enhanced content to acquire final AI enhanced content;
and the AI processing chip directly outputs the final-stage AI enhancement content for display and transmits the final-stage AI enhancement content to the SOC chip for storage.
2. The method of claim 1, wherein the AI processing chip directly displaying the final AI augmented content output and transmitting the final AI augmented content output to the SOC chip for storage comprises:
the final-stage AI enhanced content is displayed through the AI processing chip and then transmitted to the SOC chip for storage;
or the final-level AI enhanced content is transmitted to the SOC chip for storage through the AI processing chip and then displayed.
3. The method of claim 1, wherein the SOC chip controls the AI processing chip to operate in an AI enhanced mode or a pass-through mode;
when the AI processing chip carries out an AI enhancement mode, AI enhancement processing is carried out on the contents to be enhanced by the AI processing chip, and the contents are fused with the UI data and then output and displayed;
and when the AI processing chip is in a direct-through mode, the AI processing chip receives the content to be enhanced from the SOC chip of the intelligent terminal and directly outputs and displays the content.
4. The method of claim 1, wherein the content to be enhanced comprises video data and audio data, wherein the final AI enhancement content comprises game packets and video packets, and wherein the game packets and the video packets comprise video data and audio data.
5. The method according to claim 1, wherein a resolution parameter threshold, a frame rate parameter threshold, and an image quality parameter threshold are preset in the AI processing chip, and the SOC chip controls the AI processing chip to perform the AI enhancement mode operation or the through mode operation according to the resolution parameter threshold, the frame rate parameter threshold, and the image quality parameter threshold.
6. A system for enhancing AI performance of an intelligent terminal is characterized by comprising an SOC chip and an AI processing chip, wherein the SOC chip and the AI processing chip are provided with a plurality of high-speed data interfaces, and the AI processing chip receives contents to be enhanced from the SOC chip through the high-speed data interfaces;
the AI processing chip is provided with a first embedded neural network processor for carrying out AI processing on the content to be enhanced so as to obtain primary AI enhanced content;
the AI processing chip is also provided with an image fusion module, receives UI data from the SOC chip through the high-speed data interface, the UI data comprises interface data and interactive data, and the AI processing chip fuses the interface data and the interactive data with the primary AI enhanced content to obtain final AI enhanced content;
the display module is electrically connected with the SOC chip and/or the AI processing chip; and the AI processing chip outputs the final-stage AI enhancement content to the display module for display and transmits the final-stage AI enhancement content to the storage module of the SOC chip for storage.
7. The system of claim 6, wherein the display module is electrically connected with the SOC chip and the AI processing chip;
the final-stage AI enhanced content is transmitted to the display module for display through the AI processing chip and then transmitted to the SOC chip for storage;
or the final-level AI enhanced content is transmitted to the SOC chip for storage through the AI processing chip, and the display module acquires the final-level AI enhanced content through the SOC chip for display.
8. The system of claim 7, wherein the SOC chip controls the AI processing chip to operate in an AI enhanced mode or a pass-through mode;
when the AI processing chip carries out an AI enhancement mode, AI enhancement processing is carried out on the contents to be enhanced by the AI processing chip, and the contents are fused with the UI data and then output and displayed;
when the AI processing chip is in a direct mode, the AI processing chip receives the content to be enhanced from the SOC chip of the intelligent terminal and directly outputs and displays the content;
the SOC chip comprises a second embedded neural network processor, and the second embedded neural network processor works simultaneously with the first embedded neural network processor in the AI enhanced mode, or works or does not work when the AI processing chip is in the direct-through mode alone.
9. The system of claim 6, wherein the high-speed data interfaces of the SOC chip and the AI processing chip comprise a content transmission channel, a UI data transmission channel and an enhanced data backhaul transmission channel therebetween;
the AI processing chip acquires the content to be enhanced from the SOC through the content transmission channel, acquires UI data from the SOC through the UI data transmission channel, and transmits the final-level AI enhanced content back to the SOC through the enhanced data transmission channel.
10. The system of claim 6, wherein the AI processing chip further comprises an AI performance analysis module, and a resolution parameter threshold, a frame rate parameter threshold, and an image quality parameter threshold are preset in the AI performance analysis module;
and the SOC controls the AI processing chip to carry out the AI enhancement mode work or the direct-through mode work according to a resolution parameter threshold, a frame rate parameter threshold and an image quality parameter threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110235453.2A CN112965922A (en) | 2021-03-03 | 2021-03-03 | Method and system for enhancing AI performance of intelligent terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110235453.2A CN112965922A (en) | 2021-03-03 | 2021-03-03 | Method and system for enhancing AI performance of intelligent terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112965922A true CN112965922A (en) | 2021-06-15 |
Family
ID=76276327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110235453.2A Pending CN112965922A (en) | 2021-03-03 | 2021-03-03 | Method and system for enhancing AI performance of intelligent terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112965922A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116650958A (en) * | 2023-05-26 | 2023-08-29 | 启朔(深圳)科技有限公司 | Image quality enhancement method, terminal, computer device, and computer-readable storage medium |
| CN117437163A (en) * | 2023-10-31 | 2024-01-23 | 奕行智能科技(广州)有限公司 | Image enhancement method, image processing chip and image enhancement video system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040183760A1 (en) * | 2003-03-18 | 2004-09-23 | Kuei-Hsiung Chang | Image data transmission method and device |
| US20060146366A1 (en) * | 2004-12-30 | 2006-07-06 | Lg Electronics Inc. | Apparatus and method for enhancing image quality of a mobile communication terminal |
| CN107220208A (en) * | 2017-07-07 | 2017-09-29 | 深圳市图芯智能科技有限公司 | A kind of image processing system and method |
| CN108154494A (en) * | 2017-12-25 | 2018-06-12 | 北京航空航天大学 | A kind of image fusion system based on low-light and infrared sensor |
| CN109242757A (en) * | 2018-09-29 | 2019-01-18 | 南昌黑鲨科技有限公司 | intelligent terminal, image processing method and computer readable storage medium |
| CN110895788A (en) * | 2019-11-29 | 2020-03-20 | 上海众链科技有限公司 | System for enhancing graphic processing capability and external device |
-
2021
- 2021-03-03 CN CN202110235453.2A patent/CN112965922A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040183760A1 (en) * | 2003-03-18 | 2004-09-23 | Kuei-Hsiung Chang | Image data transmission method and device |
| US20060146366A1 (en) * | 2004-12-30 | 2006-07-06 | Lg Electronics Inc. | Apparatus and method for enhancing image quality of a mobile communication terminal |
| CN107220208A (en) * | 2017-07-07 | 2017-09-29 | 深圳市图芯智能科技有限公司 | A kind of image processing system and method |
| CN108154494A (en) * | 2017-12-25 | 2018-06-12 | 北京航空航天大学 | A kind of image fusion system based on low-light and infrared sensor |
| CN109242757A (en) * | 2018-09-29 | 2019-01-18 | 南昌黑鲨科技有限公司 | intelligent terminal, image processing method and computer readable storage medium |
| CN110895788A (en) * | 2019-11-29 | 2020-03-20 | 上海众链科技有限公司 | System for enhancing graphic processing capability and external device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116650958A (en) * | 2023-05-26 | 2023-08-29 | 启朔(深圳)科技有限公司 | Image quality enhancement method, terminal, computer device, and computer-readable storage medium |
| CN117437163A (en) * | 2023-10-31 | 2024-01-23 | 奕行智能科技(广州)有限公司 | Image enhancement method, image processing chip and image enhancement video system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8773498B2 (en) | Background compression and resolution enhancement technique for video telephony and video conferencing | |
| US9363473B2 (en) | Video encoder instances to encode video content via a scene change determination | |
| CN104780338A (en) | Method and electronic equipment for loading expression effect animation in instant video | |
| WO2013086734A1 (en) | Reduced image quality for video data background regions | |
| US20090096927A1 (en) | System and method for video coding using variable compression and object motion tracking | |
| CN106576158A (en) | Immersive video | |
| CN112965922A (en) | Method and system for enhancing AI performance of intelligent terminal | |
| CN112637517B (en) | Video processing method and device, electronic equipment and storage medium | |
| US11463270B2 (en) | System and method for operating an intelligent face framing management system for videoconferencing applications | |
| CN105979194A (en) | Video image processing apparatus and method | |
| US11985358B2 (en) | Artifact removal method and apparatus based on machine learning, and method and apparatus for training artifact removal model based on machine learning | |
| US10810462B2 (en) | Object detection with adaptive channel features | |
| US20220130023A1 (en) | Video denoising method and apparatus, terminal, and storage medium | |
| CN109168032B (en) | Video data processing method, terminal, server and storage medium | |
| CN116055786A (en) | Method for displaying multiple windows and electronic equipment | |
| CN114463470A (en) | Virtual space browsing method and device, electronic equipment and readable storage medium | |
| CN103929640A (en) | Techniques For Managing Video Streaming | |
| CN113315927B (en) | Video processing method and device, electronic equipment and storage medium | |
| US20220172440A1 (en) | Extended field of view generation for split-rendering for virtual reality streaming | |
| CN110807769A (en) | Image display control method and device | |
| CN112423139A (en) | Multi-machine live broadcast method, system, equipment and storage medium based on mobile terminal | |
| CN110604921B (en) | Display content switching method, server and storable medium | |
| CN114697731B (en) | Screen projection method, electronic equipment and storage medium | |
| CN113225613B (en) | Image recognition method, video live broadcast method and device | |
| CN115334349B (en) | Audio processing method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |