Industrial computer algorithm operating system for green, low-carbon and energy-efficient management
By performing multiple learning of the extreme learning machine neural network in the industrial computer algorithm operating system and combining parametric analysis and signal detection equipment, the problem of lack of intelligent prediction of inter-frame encoding effects in the prior art is solved, the functions of intelligent prediction and reference block selection are realized, and the intelligence and efficiency of image processing are improved.
Patent Information
- Application Number
- CN202411963282.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-04-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
There is a lack of a method in the prior art to solve the encoding effect of intelligent prediction using any concatenated peripheral block to perform inter-coding on the current image block.
In the industrial computer algorithm operating system, through multiple learning of the extreme learning machine neural network, an intelligent identification model is generated, and a parametric analysis device is used to select a parametric peripheral block from the forward frame of the current image frame, and a signal detection device is used to obtain multiple correlation parameters of the image block, and a difference identification agency is used to perform intelligent identification to predict the inter-frame encoding effect.
It realizes intelligent prediction of inter-coding effects in the industrial computer algorithm operating system, provides a basis for selecting inter-coding reference blocks, and improves the intelligence and efficiency of image processing.
Smart Images
Figure CN119784573A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer systems, and more specifically, to an industrial computer algorithm operating system for green and low-carbon energy efficiency management. Background Art
[0002] Green development is the fundamental solution to ecological and environmental problems, and an important way to build a high-quality modern economic system. With the proposal of carbon neutrality and carbon peak targets, all walks of life have embarked on the "dual carbon" path, and green and low-carbon have been further integrated into industrial production.
[0003] In the process of improving green and low-carbon energy efficiency, the capacity of the computer system is an important factor. The hardware of the computer system is mainly composed of the central processing unit, memory, input-output control system and various external devices. The central processing unit is the main component for high-speed computing and processing of information, and its processing speed can reach more than hundreds of millions of operations per second. The memory is used to store programs, data and files, and is often composed of fast internal memory (capacity can reach hundreds of megabytes or even several G bytes) and slow massive external memory (capacity can reach tens of G or hundreds of G or more). Various input-output external devices are information converters between humans and machines, and the information exchange between external devices and the main memory (central processing unit) is managed by the input-output control system.
[0004] Computer systems can perform various algorithmic operations. At present, there are still gaps in the application field of specific algorithmic operations that need to be filled. For example, it is hoped that the coding effect of using any co-located surrounding block to perform inter-frame coding on the current image block can be intelligently predicted, thereby providing a basis for selecting the inter-frame coding reference block required for performing inter-frame coding on the current image block. Obviously, there is a lack of corresponding solutions in the existing technology. Summary of the invention
[0005] In order to solve the technical problems in the prior art, the present invention provides an industrial computer algorithm operating system for green and low-carbon energy efficiency management, which can perform multiple learning on an extreme learning machine neural network in the industrial computer algorithm operating system to obtain an extreme learning machine neural network after completing multiple learning and output it as an intelligent identification model, and select any image block from each image block around the same-position image block in the forward frame of the current image frame that is at the same position as the current image block in the image as the same-position surrounding block, and detect the current image block of the current image frame to be inter-frame encoded to obtain the red channel numerical mean square error, green channel numerical mean square error, blue channel numerical mean square error, edge pixel point occupancy percentage and coordinate values of each edge pixel point of the current image block as multiple associated parameters of the current image block, and at the same time obtain the red channel numerical mean square error, green channel numerical mean square error, blue channel numerical mean square error, edge pixel point occupancy percentage and coordinate values of each edge pixel point of the same-position surrounding block as the same-position surrounding block The invention relates to a method for intelligently identifying the content difference between a reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks and the current image block, wherein the absolute value of the difference between the pixels at the same position of the reconstructed image block and the current image block is calculated to obtain the absolute values corresponding to the respective positions, and the accumulated value of the absolute values is used as the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks and the current image block, thereby completing the intelligent prediction of the coding effect of performing inter-frame coding on the current image block using any co-located surrounding block.
[0006] According to the present invention, an industrial computer algorithm operating system for green, low-carbon and energy efficiency management is provided, the system comprising: Directed establishment equipment, located in the industrial computer algorithm operating system, is used to perform multiple learning on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing multiple learning and output it as an intelligent identification model; A co-location analysis device, located in the industrial computer algorithm operating system, is used to select one image block from each image block surrounding the co-location image block in the forward frame of the current image frame and located at the same image position as the current image block and output it as the co-location surrounding block; A signal detection device is located in the industrial computer algorithm operating system and is connected to the co-location analysis device, and is used to detect a current image block of a current image frame to be inter-frame encoded, so as to obtain a red channel numerical mean square error, a green channel numerical mean square error, a blue channel numerical mean square error, an edge pixel point occupancy percentage, and a coordinate value of each edge pixel point of the current image block as multiple associated parameters of the current image block, and simultaneously obtain a red channel numerical mean square error, a green channel numerical mean square error, a blue channel numerical mean square error, an edge pixel point occupancy percentage, and a coordinate value of each edge pixel point of the co-location surrounding block as multiple associated parameters of the co-location surrounding block; a difference identification mechanism, connected to the orientation establishment device and the signal detection device respectively, for using the intelligent identification model to intelligently identify the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks and the current image block based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block, and multiple associated parameters of the co-located surrounding blocks; Wherein, the intelligent identification model is used to intelligently identify the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding block and the current image block based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block, and multiple associated parameters of the co-located surrounding block, including: performing an absolute value calculation on the difference between the pixels at the same position of the reconstructed image block and the current image block to obtain respective absolute values corresponding to respective positions, and taking the cumulative value of the respective absolute values as the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding block and the current image block; The directional establishment device is located in the industrial computer algorithm operating system and is used to perform multiple learning on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing multiple learning and output it as an intelligent identification model, including: the number of times the extreme learning machine neural network completes learning is inversely correlated with the number of background pixels of the current image frame; Among them, the co-location analysis device is located in the industrial computer algorithm operating system, and is used to select any image block from the image blocks surrounding the co-location image block in the forward frame of the current image frame that is in the same image position as the current image block as the co-location surrounding block output, including: the forward frame of the current image frame and the current image frame are in the same video sequence and the timestamp of the forward frame of the current image frame is before the timestamp of the current image frame.
[0007] It can be seen that the present invention has at least the following three beneficial technical effects: Technical effect 1: The extreme learning machine neural network is learned multiple times in the industrial computer algorithm operating system to obtain the extreme learning machine neural network after multiple learning and output it as an intelligent identification model, wherein the number of times the extreme learning machine neural network completes learning is inversely related to the number of background pixels of the current image frame to perform intelligent prediction of inter-frame coding effects, thereby achieving structural customization of different artificial intelligence models for different image contents; Technical effect 2: an image block is selected from each image block around the same-position image block as the current image block in the forward frame of the current image frame as the same position in the image, and the current image block of the current image frame to be inter-frame encoded is detected to obtain the red channel numerical mean square error, the green channel numerical mean square error, the blue channel numerical mean square error, the edge pixel point occupancy percentage and the coordinate value of each edge pixel point of the current image block as multiple associated parameters of the current image block, and at the same time, the red channel numerical mean square error, the green channel numerical mean square error, the blue channel numerical mean square error, the edge pixel point occupancy percentage and the coordinate value of each edge pixel point of the same-position surrounding block are obtained as multiple associated parameters of the same-position surrounding block, thereby obtaining various basic data for subsequent intelligent prediction of inter-frame encoding effect; Technical effect three: A difference identification mechanism is introduced into the algorithm operating system of an industrial computer to use an intelligent identification model to intelligently identify the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks and the current image block, based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block, and multiple associated parameters of the selected co-located surrounding blocks, wherein the absolute value of the difference between the pixels at the same position of the reconstructed image block and the current image block is calculated to obtain the absolute values corresponding to each position, and the accumulated value of the absolute values is used as the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks and the current image block, thereby completing the intelligent prediction of the coding effect of using any co-located surrounding block to perform inter-frame coding on the current image block.
[0008] The industrial computer algorithm operating system for green and low-carbon energy efficiency management of the present invention has stable operation and intelligent control. Since the artificial intelligence model with customized structure can be designed in the computer system, it can intelligently predict the coding effect of using any co-located surrounding block to perform inter-frame coding on the current image block, thereby providing a basis for selecting the inter-frame coding reference block required for performing inter-frame coding on the current image block. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] Those skilled in the art may better understand the numerous advantages of the present invention by referring to the accompanying drawings.
[0010] Figure 1 It is a schematic diagram of the internal structure of an industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to the first embodiment of the present invention.
[0011] Figure 2 It is a schematic diagram of the internal structure of an industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to the second embodiment of the present invention.
[0012] Figure 3 It is a schematic diagram of the internal structure of an industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to the third embodiment of the present invention. DETAILED DESCRIPTION
[0013] The implementation scheme of the industrial computer algorithm operating system for green and low-carbon energy efficiency management of the present invention will be described in detail below with reference to the accompanying drawings.
[0014] Figure 1 1 is a schematic diagram of the internal structure of an industrial computer algorithm operating system for green and low-carbon energy efficiency management according to a first embodiment of the present invention, the system comprising: Directed establishment equipment, located in the industrial computer algorithm operating system, is used to perform multiple learning on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing multiple learning and output it as an intelligent identification model; For example, the directional establishment device is located in the industrial computer algorithm operating system, and is used to perform multiple learning on the extreme learning machine neural network to obtain the extreme learning machine neural network after multiple learning and output it as the intelligent identification model, including: selecting an FPGA chip to implement the directional establishment device, which is located in the industrial computer algorithm operating system and is used to perform multiple learning on the extreme learning machine neural network to obtain the extreme learning machine neural network after multiple learning and output it as the intelligent identification model; A co-location analysis device, located in the industrial computer algorithm operating system, is used to select one image block from each image block surrounding the co-location image block in the forward frame of the current image frame and located at the same image position as the current image block and output it as the co-location surrounding block; A signal detection device is located in the industrial computer algorithm operating system and is connected to the co-location analysis device, and is used to detect a current image block of a current image frame to be inter-frame encoded, so as to obtain a red channel numerical mean square error, a green channel numerical mean square error, a blue channel numerical mean square error, an edge pixel point occupancy percentage, and a coordinate value of each edge pixel point of the current image block as multiple associated parameters of the current image block, and simultaneously obtain a red channel numerical mean square error, a green channel numerical mean square error, a blue channel numerical mean square error, an edge pixel point occupancy percentage, and a coordinate value of each edge pixel point of the co-location surrounding block as multiple associated parameters of the co-location surrounding block; a difference identification mechanism, connected to the orientation establishment device and the signal detection device respectively, for using the intelligent identification model to intelligently identify the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks and the current image block based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block, and multiple associated parameters of the co-located surrounding blocks; Wherein, the intelligent identification model is used to intelligently identify the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding block and the current image block based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block, and multiple associated parameters of the co-located surrounding block, including: performing an absolute value calculation on the difference between the pixels at the same position of the reconstructed image block and the current image block to obtain respective absolute values corresponding to respective positions, and taking the cumulative value of the respective absolute values as the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding block and the current image block; The directional establishment device is located in the industrial computer algorithm operating system and is used to perform multiple learning on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing multiple learning and output it as an intelligent identification model, including: the number of times the extreme learning machine neural network completes learning is inversely correlated with the number of background pixels of the current image frame; Wherein, the co-location analysis device is located in the industrial computer algorithm operating system, and is used to select one image block from each image block surrounding the co-location image block in the forward frame of the current image frame and located at the same image position as the current image block as the co-location surrounding block output, including: the forward frame of the current image frame and the current image frame are in the same video sequence and the timestamp of the forward frame of the current image frame is before the timestamp of the current image frame; Wherein, the co-location analysis device is located in the industrial computer algorithm operating system, and is used to select one image block from each image block surrounding the co-location image block in the previous frame of the current image frame and located at the same image position as the current image block as the co-location surrounding block output, and further includes: the position of the co-location image block in the previous frame of the current image frame is the same as the position of the current image block in the current image frame; Wherein, the co-location analysis device is located in the industrial computer algorithm operating system, and is used to select one image block from each image block surrounding the co-location image block in the forward frame of the current image frame and located at the same image position as the current image block as the co-location surrounding block output, and further includes: the sizes of the image blocks of various types are equal; Among them, the intelligent identification model is used to intelligently identify the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks based on the number of major noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks, and also includes: the major noise type of the current image frame refers to the noise type whose maximum amplitude in the current image frame is less than or equal to the set amplitude limit.
[0015] Figure 2 It is a schematic diagram of the internal structure of an industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to the second embodiment of the present invention.
[0016] and Figure 1 different, Figure 2 The industrial computer algorithm operating system for green and low-carbon energy efficiency management may also include the following components: A real-time display component, used for displaying in real time temporary data of the content difference between a reconstructed image block and the current image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks, using the intelligent identification model based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block, and multiple associated parameters of the co-located surrounding blocks; Wherein, the real-time display component is used for real-time displaying the temporary data of the content difference between the reconstructed image block and the current image block obtained by performing inter-frame coding on the current image block by the intelligent identification model based on the number of main noise types of the current image frame, the percentage of background pixels of the current image frame, the total number of pixels of the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks, and comprising: the real-time display component is an LED display array composed of multiple LED display units; Among them, the real-time display component is used to display in real time the temporary data of the content difference between the reconstructed image block and the current image block obtained by intelligently identifying the current image block by performing inter-frame encoding on the current image block using the intelligent identification model based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks, including: the real-time display component is an LCD display array composed of multiple LCD display units.
[0017] Figure 3 It is a schematic diagram of the internal structure of an industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to the third embodiment of the present invention.
[0018] and Figure 1 different, Figure 3 The industrial computer algorithm operating system for green and low-carbon energy efficiency management may also include the following components: A content processing component is used to collect in real time the amount of computation consumed by intelligently identifying the content difference between a reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks and the current image block based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block, and multiple associated parameters of the co-located surrounding blocks using the intelligent identification model; Wherein, the content processing component is used for real-time acquisition of the amount of computation consumed by the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block by the co-located surrounding blocks and the current image block based on the number of main noise types of the current image frame, the percentage of background pixels of the current image frame, the total number of pixels of the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks by the intelligent identification model, and includes: the content processing component is a programmable logic device; Among them, the content processing component is used for real-time acquisition of the amount of computation consumed by the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block by the co-located surrounding blocks and the current image block based on the number of main noise types of the current image frame, the percentage of background pixels of the current image frame, the total number of pixels of the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks by the intelligent identification model, and also includes: the programmable logic device is a field programmable gate array; And wherein, the content processing component is used to collect in real time the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks based on the intelligent identification model, and the amount of computation consumed by intelligently identifying the content difference between the reconstructed image block obtained by performing inter-frame encoding on the current image block by the co-located surrounding blocks and the current image block, and also includes: the programmable logic device has a built-in cache unit.
[0019] In addition, in the industrial computer algorithm operating system for green and low-carbon energy efficiency management, a device is established in a directional manner, located within the industrial computer algorithm operating system, for performing multiple learning on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing multiple learning and outputting it as an intelligent identification model, and also includes: using a numerical mapping formula to represent a numerical mapping relationship in which the number of times the extreme learning machine neural network completes learning is inversely correlated with the number of background pixels in the current image frame.
[0020] Many modifications and changes can be made to the techniques and data structures described and illustrated herein without departing from the spirit and scope of the claims. Therefore, it should be understood that the methods and devices described herein are exemplary only and are not intended to limit the claims.
Claims
1. An industrial computer algorithm operating system for green and low-carbon energy efficiency management, characterized in that: The system comprises: Directed establishment equipment, located in the industrial computer algorithm operating system, is used to perform multiple learning on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing multiple learning and output it as an intelligent identification model; A co-location analysis device, located in the industrial computer algorithm operating system, is used to select one image block from each image block surrounding the co-location image block in the forward frame of the current image frame and located at the same image position as the current image block and output it as the co-location surrounding block; A signal detection device is located in the industrial computer algorithm operating system and is connected to the co-location analysis device, and is used to detect a current image block of a current image frame to be inter-frame encoded, so as to obtain a red channel numerical mean square error, a green channel numerical mean square error, a blue channel numerical mean square error, an edge pixel point occupancy percentage, and a coordinate value of each edge pixel point of the current image block as multiple associated parameters of the current image block, and simultaneously obtain a red channel numerical mean square error, a green channel numerical mean square error, a blue channel numerical mean square error, an edge pixel point occupancy percentage, and a coordinate value of each edge pixel point of the co-location surrounding block as multiple associated parameters of the co-location surrounding block; a difference identification mechanism, connected to the orientation establishment device and the signal detection device respectively, for using the intelligent identification model to intelligently identify the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks and the current image block based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block, and multiple associated parameters of the co-located surrounding blocks; Wherein, the intelligent identification model is used to intelligently identify the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding block and the current image block based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block, and multiple associated parameters of the co-located surrounding block, including: performing an absolute value calculation on the difference between the pixels at the same position of the reconstructed image block and the current image block to obtain respective absolute values corresponding to respective positions, and taking the cumulative value of the respective absolute values as the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding block and the current image block; The directional establishment device is located in the industrial computer algorithm operating system and is used to perform multiple learning on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing multiple learning and output it as an intelligent identification model, including: the number of times the extreme learning machine neural network completes learning is inversely correlated with the number of background pixels of the current image frame; Among them, the co-location analysis device is located in the industrial computer algorithm operating system, and is used to select any image block from the image blocks surrounding the co-location image block in the forward frame of the current image frame that is in the same image position as the current image block as the co-location surrounding block output, including: the forward frame of the current image frame and the current image frame are in the same video sequence and the timestamp of the forward frame of the current image frame is before the timestamp of the current image frame.
2. The industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to claim 1, characterized in that: The co-location analysis device is located in the industrial computer algorithm operating system and is used to select one image block from each image block surrounding the co-location image block in the previous frame of the current image frame and located at the same image position as the current image block as the co-location surrounding block output, and further includes: the position of the co-location image block in the previous frame of the current image frame is the same as the position of the current image block in the current image frame; Wherein, the co-location analysis device is located in the industrial computer algorithm operating system, and is used to select one image block from each image block surrounding the co-location image block in the forward frame of the current image frame and located at the same image position as the current image block as the co-location surrounding block output, and further includes: the sizes of the image blocks of various types are equal; Among them, the intelligent identification model is used to intelligently identify the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks based on the number of major noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks, and also includes: the major noise type of the current image frame refers to the noise type whose maximum amplitude in the current image frame is less than or equal to the set amplitude limit.
3. The industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to claim 2, characterized in that: The computer system further comprises: A real-time display component is used to display in real time temporary data of the content difference between a reconstructed image block and the current image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks, using the intelligent identification model based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block, and multiple associated parameters of the co-located surrounding blocks.
4. The industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to claim 3, characterized in that: A real-time display component is used for displaying in real time temporary data of the content difference between a reconstructed image block and the current image block obtained by performing inter-frame coding on the current image block using the intelligent identification model based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks, including: the real-time display component is an LED display array composed of multiple LED display units.
5. The industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to claim 3, characterized in that: A real-time display component is used to display in real time temporary data of the content difference between a reconstructed image block and the current image block obtained by performing inter-frame coding on the current image block using the intelligent identification model based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks, including: the real-time display component is an LCD display array composed of multiple LCD display units.
6. The industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to claim 2, characterized in that: The system further comprises: The content processing component is used to collect in real time the amount of computation consumed by intelligently identifying the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks and the current image block based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks using the intelligent identification model.
7. The industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to claim 6, characterized in that: A content processing component is used for real-time acquisition of the amount of computation consumed by the intelligent identification model based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks, and intelligent identification of the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block by the co-located surrounding blocks and the current image block, including: the content processing component is a programmable logic device.
8. The industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to claim 7, characterized in that: A content processing component is used for real-time acquisition based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks using the intelligent identification model. The amount of computation consumed by intelligently identifying the content difference between the reconstructed image block obtained by performing inter-frame coding on the current image block using the co-located surrounding blocks and the current image block also includes: the programmable logic device is a field programmable gate array.
9. The industrial computer algorithm operating system for green, low-carbon and energy efficiency management according to claim 8, characterized in that: A content processing component is used for real-time acquisition based on the number of main noise types in the current image frame, the percentage of background pixels in the current image frame, the total number of pixels in the current image frame, multiple associated parameters of the current image block and multiple associated parameters of the co-located surrounding blocks using the intelligent identification model. The amount of computation consumed by intelligently identifying the content difference between the reconstructed image block obtained by performing inter-frame encoding on the current image block using the co-located surrounding blocks and the current image block also includes: a built-in cache unit in the programmable logic device.