CN113850879A - Method for improving compression ratio of static background video based on background modeling technology - Google Patents

Method for improving compression ratio of static background video based on background modeling technology Download PDF

Info

Publication number
CN113850879A
CN113850879A CN202110609798.XA CN202110609798A CN113850879A CN 113850879 A CN113850879 A CN 113850879A CN 202110609798 A CN202110609798 A CN 202110609798A CN 113850879 A CN113850879 A CN 113850879A
Authority
CN
China
Prior art keywords
background
coding block
pixel point
image frame
rate control
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
Application number
CN202110609798.XA
Other languages
Chinese (zh)
Inventor
曹靖城
吕超
沈文琦
史国杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianyi Digital Life Technology Co Ltd
Original Assignee
Tianyi Smart Family Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianyi Smart Family Technology Co Ltd filed Critical Tianyi Smart Family Technology Co Ltd
Priority to CN202110609798.XA priority Critical patent/CN113850879A/en
Publication of CN113850879A publication Critical patent/CN113850879A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding
    • G06T9/001—Model-based coding, e.g. wire frame
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformation in the plane of the image
    • G06T3/40—Scaling the whole image or part thereof
    • G06T3/4053—Super resolution, i.e. output image resolution higher than sensor resolution

Abstract

The invention provides a method for improving the compression ratio of a static background video based on a background modeling technology. In the invention, background modeling is carried out on a video picture, and continuous differential coding is carried out according to the probability that each pixel point is judged as the background, so that the pixel points with high probability as the background tend to obtain codes with fewer bits in code rate control, thereby improving the compression rate. Because the probability function is continuous, the coding strategy can be continuously adjusted correspondingly, thereby eliminating the image quality difference feeling in vision and improving the user perception on the basis of ensuring the compression performance.

Description

Method for improving compression ratio of static background video based on background modeling technology
Technical Field
The invention relates to video coding, in particular to a method for improving the compression rate of a static background video based on a background modeling technology.
Background
The information amount acquired by human vision accounts for about 70% of the total information amount, and the video information has a series of advantages of intuition, credibility and the like. However, with the continuous expansion of the application range of video technology, such as the common application of a camera in a home scene, the amount of transmitted data is also increasing. However, the video coding compression technique is an effective solution because it is expensive and difficult to implement simply by increasing the memory capacity and increasing the transmission rate of the communication trunk.
Currently, mainstream video encoders are mainly divided into 3 series: VPx (VP8, VP9), h.26x (h.264, h.265, h.266), AVS (AVS1.0, AVS2.0), but they all propose only standards and specifications, and do not distinguish application scenarios. Therefore, in practical applications, in order to further improve the video compression efficiency, it is necessary to combine scene characteristics for improvement and depth optimization. For application scenes such as home cameras and road cameras with relatively static backgrounds and small changes, if only a mainstream video coding technology is used, the compression rate basically reaches the bottleneck, and only for video characteristics, an optimization scheme with better adaptability is adopted, so that the compression efficiency can be improved.
The patent "ROI-based video coding method and system and video transmission and coding system" (CN202010249206.3A) discloses a ROI-based video coding method, comprising: acquiring a video frame of a video to be coded, wherein the video frame comprises a plurality of coding blocks; dividing the video frame into ROI regions and non-ROI regions; generating a mask for the video frame, the mask distinguishing the ROI region from a non-ROI region; obtaining a difference value of quantization parameters of at least one channel of a color space of the video frame; for each coding block of the video frame, selecting a prediction mode of the at least one channel according to the mask; for each coding block of the video frame, according to the difference value of the quantization parameter of the at least one channel, and according to the fact that the coding block comprises an ROI area and/or a non-ROI area, adjusting the quantization parameter of the at least one channel; and encoding the video frame according to the prediction mode and the quantization parameter of the at least one channel.
The patent "ROI-based video coding method and video coding system" (CN202010366816.1A) discloses a ROI-based video coding method, comprising: s101: acquiring a video frame of a video to be coded; s102: extracting an ROI (region of interest) region of the video frame through a neural network model; s103: coding the ROI area of the video frame by adopting a first coding mode; and aiming at the non-ROI area of the video frame, coding by adopting a second coding mode, wherein the quality level of a coded image of the first coding mode is higher than that of the coded image of the second coding mode.
However, the above two schemes only divide the picture into two types of regions, namely, an ROI (region of interest) region and a non-ROI region, and performing the differential coding based on the piecewise function on the two regions makes the difference between the image quality of the two regions under the same picture obvious, thereby reducing the visual experience of the user in watching.
Therefore, how to improve the compression rate of videos with small background changes, such as home cameras, without affecting the subjective visual quality of the pictures is a problem worthy of further optimization.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
According to an embodiment of the present invention, there is provided a method for improving compression rate of a static background video based on a background modeling technology, including: establishing a background model by adopting a foreground extraction algorithm, wherein the background model is used for representing the characteristics of each pixel point in an image frame; initializing the established background model; updating the background model based on the acquired new image frame; performing foreground or background estimation on each pixel point in the new image frame; aiming at the probability that the pixel point in each coding block in the new image frame is determined as the background, adjusting a dynamic code rate control factor for each coding block; and performing differential coding on each coding block based on the dynamic code rate control factor aiming at each coding block.
According to another embodiment of the present invention, a system for improving the compression rate of a static background video based on a background modeling technology is provided, which includes a background modeling module and a dynamic encoding module. The background modeling module is configured to: establishing a background model by adopting a foreground extraction algorithm, wherein the background model is used for representing the characteristics of each pixel point in an image frame; initializing the established background model; updating the background model based on the acquired new image frame; and carrying out foreground or background estimation on each pixel point in the new image frame. The dynamic encoding module is configured to: aiming at the probability that the pixel point in each coding block in the new image frame is determined as the background, adjusting a dynamic code rate control factor for each coding block; and performing differential coding on each coding block based on the dynamic code rate control factor aiming at each coding block.
According to still another embodiment of the present invention, there is provided a computing device for super-resolution reconstruction of an image, including: a processor; a memory storing instructions that, when executed by the processor, are capable of performing the method as described above.
These and other features and advantages will become apparent upon reading the following detailed description and upon reference to the accompanying drawings. It is to be understood that both the foregoing general description and the following detailed description are explanatory only and are not restrictive of aspects as claimed.
Drawings
So that the manner in which the above recited features of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only some typical aspects of this invention and are therefore not to be considered limiting of its scope, for the description may admit to other equally effective aspects.
Fig. 1 shows a block diagram for a video coding system 100 based on background modeling techniques according to an embodiment of the invention;
FIG. 2 shows a flow diagram of a method 200 for video encoding based on background modeling techniques according to an embodiment of the invention;
FIG. 3 shows a block diagram of a computing device 300 that may be applied to the hardware devices of aspects of the invention, according to an embodiment of the invention.
Detailed Description
The present invention will be described in detail below with reference to the attached drawings, and the features of the present invention will be further apparent from the following detailed description.
The invention aims to combine with background modeling technology to obtain a compression ratio higher than that of mainstream codes (such as H.264, H.265 and the like) and improve the subjective visual quality of pictures. In the invention, background modeling is carried out on a video picture, and continuous differential coding is carried out according to the probability that each pixel point is judged as the background, so that the part with the high probability as the background tends to obtain codes with fewer bits in code rate control, thereby improving the compression rate. Because the probability function is continuous, the coding strategy can be continuously adjusted correspondingly, thereby eliminating the image quality difference feeling in vision and improving the user perception on the basis of ensuring the compression performance.
Fig. 1 shows a block diagram of a video coding system 100 for background modeling based techniques according to an embodiment of the invention. As shown in fig. 1, the system 100 is divided into modules, with communication and data exchange between the modules being performed in a manner known in the art. In the present invention, each module may be implemented by software or hardware or a combination thereof. The system 100 may include a background modeling module 101 and a dynamic encoding module 102.
In general, referring to fig. 1, the background modeling module 101 is configured to obtain the probability that a pixel belongs to the background based on background subtraction/foreground extraction of the background modeling method. According to one embodiment of the invention, background subtraction/foreground extraction based on background modeling mainly comprises: modeling the background environment of a video picture, extracting the picture foreground through background subtraction, and calculating the probability value of each pixel point which is judged as the background in the model.
The dynamic coding module 102 is configured for differential coding based on dynamic rate control. According to an embodiment of the present invention, the differential coding based on dynamic rate control mainly includes: based on the probability that the pixel points output by the background modeling module 101 are judged as the background, a dynamic code rate control strategy is adopted for the pixel points, so that the pixel points with the high probability as the background tend to obtain codes with fewer bits in code rate control, the visual quality is ensured, and the video compression rate is improved.
The invention is particularly suitable for application scenes with static backgrounds, such as application scenes adopting monitoring equipment such as a household camera, conference video equipment, a road camera and the like. Such monitoring devices can take pictures, capture images of scenes, store the acquired image data locally for processing (e.g., encoding), and transmit the processed data to remote devices (e.g., smart home control platforms, central control platforms, other computing devices, etc.) for subsequent processing (e.g., playing, editing, etc.) when needed. According to one embodiment of the invention, the background modeling module 101 and the dynamic encoding module 102 may be implemented in the monitoring device described above or in other computing devices 300 as described in FIG. 3.
Fig. 2 shows a flow diagram of a method 200 for video encoding based on background modeling techniques according to an embodiment of the invention. The method 200 generally includes two stages, a background modeling stage 201 and a dynamic encoding stage 202. According to an embodiment of the present invention, the background modeling phase 201 may be implemented by the background modeling module 101 shown in fig. 1, and the dynamic encoding phase 202 may be implemented by the dynamic encoding module 102 shown in fig. 1.
In the invention, different code rate control factors lambda are adopted for subsequent conventional coding (such as H.264, H.265 and the like) of the pixel points determined as the background and the pixel points determined as the foreground in the image frame, so that the pixel points with the background with high probability tend to obtain less bit codes in code rate control, thereby improving the integral compression rate of the image frame and reducing the storage pressure of equipment and the transmission pressure of a communication trunk line. Further details are described below with reference to fig. 2.
The background modeling stage 201 adopts a method of obtaining the probability that the pixel belongs to the background by using a background modeling method. In this stage 201, after the foreground is identified by using a background modeling method, the parameter that can represent the probability of the pixel point belonging to the background is obtained by using the relevant parameter of the background model, so that the adjustment function of the code rate control factor is continuous when the conventional coding (such as h.264, h.265, etc.) is subsequently adopted. As known to those skilled in the art, in conventional coding, a rate distortion optimization strategy is adopted to balance a code rate and image quality, that is, a cost function J ═ D + λ · R is obtained by using a lagrangian method, where D represents image distortion, R represents a code rate, and a lagrangian factor λ is also called a rate control factor, and is used to control a proportion between distortion and the code rate, where a larger λ is, a larger proportion of the code rate is, and a higher tendency is to sacrifice more video quality to obtain a smaller code rate during coding.
First, the background modeling phase 201 begins at step 201-1. In step 201-1, a foreground extraction algorithm is used to establish a background model, which is used to characterize the characteristics of each pixel in the image frame. Based on the general assumption that a background picture without an intrusive target can be described by using a statistical model, background modeling is performed on each pixel point in a picture, and the modeling method can refer to and is not limited to current mainstream foreground extraction algorithms, such as algorithms of GMM, ViBe, SACON, PBAS and the like. Of course, other types of foreground extraction algorithms are within the scope of the present invention.
Step 201-1 is illustrated using a Gaussian Mixture Model (GMM) as an example, according to one embodiment of the invention. As shown in equation (1), K gaussian mixture distribution models with weights w are used to characterize each pixel point in the image frame:
Figure BDA0003095235000000051
wherein X is the history value of any pixel point, and ω, μ, Σ are the weight, mean, and covariance of each gaussian distribution, respectively.
In step 201-2, the background model established in step 201-1 is initialized. Theoretically, if there is an image with only background and no foreground, the foreground object can be obtained by subtracting the background from the new image. In many cases, however, there is no such background image, and therefore the selected/created background model is typically initialized with the first frame or the first N frame images according to different algorithms.
Continuing with the example of the GMM model described above, in step 201-2, a background model is initialized with a first frame image, each gaussian distribution using the pixel values of the first frame as expected, the weights are all 1/K, and the standard deviations are all large, according to an embodiment of the present invention. Those skilled in the art will appreciate that the standard deviation represents the degree of dispersion of the data, and only one value is used for initialization, and the degree of dispersion cannot be calculated, so that it is assumed to be large, and when new data exists in the next frame, the next frame is updated accordingly.
In step 201-3, the background model is updated based on the acquired new image frame. According to one embodiment of the invention, when a new image frame is acquired, the model parameters are updated according to the update strategy of each model algorithm and the pixel values in the new image frame. Those skilled in the art will appreciate that the parameters used in the different models vary (such as thresholds used in the matching conditions, etc.), and there is no particular limitation on which parameters are updated.
The above example of using the GMM model is continued according to an embodiment of the present invention. In step 201-3, when a new image frame is acquired, the model parameters are updated according to the following update strategy:
ωi,t＝(1-α)ωi,t-1+αMi,t (2)
μi,t＝(1-ρ)μi,t-1+ρXt (3)
Figure BDA0003095235000000061
wherein the content of the first and second substances,
Figure BDA0003095235000000062
ρ＝αη(Xt|μi,t,σi,t) (6)
and α is the learning rate.
In step 201-4, foreground/background estimation is performed on each pixel point in the new image frame acquired in step 201-3. According to one embodiment of the invention, the current pixel value of each pixel point in the new image frame is matched with the corresponding background model (for example, the own GMM background model of each pixel point), and the pixel point with failed matching is classified as the foreground; and for the pixel point successfully matched, calculating the probability (p) that the pixel point belongs to the background according to the updated algorithm model parameters in the step 201-3. According to one embodiment of the invention, a matching threshold may be used in the matching described above.
The above example of using the GMM model is continued according to an embodiment of the present invention. In step 201-4, K Gaussian distributions are calculated
Figure BDA0003095235000000071
And (4) sorting, taking the first B Gaussian distributions as a current background model:
Figure BDA0003095235000000072
wherein T is the minimum proportion of the background in the picture. Equation (7) is to obtain the parameter B, and as mentioned above, the GMM model after being updated in step 201-3 takes the model formed by the first B gaussian distributions as the current background model. Matching the current pixel value of each pixel point with the current background model, and judging the pixel point as a foreground if the matching fails; otherwise, normalizing the B a values to obtain a', calculating a parameter p which can represent the probability size of the pixel point belonging to the background:
p＝a'(Xt-μ) (8)
after calculating the probability that the pixel is determined as the background, enter the dynamic encoding stage 202. The dynamic encoding stage 202 employs a method of adjusting an encoding strategy using the probability that a pixel belongs to the background. According to one embodiment of the invention, the dynamic encoding phase 202 is performed on a block-by-block basis. The following steps 202-1 to 202-2 are repeated for each coding block in the current image frame until all coding blocks are coded. It is fully understood by those skilled in the art that the division of the coding blocks of the image frame and the coding order of the coding blocks may be configured based on the specific coding scheme (such as h.264, h.265, etc.) used, and the specific division scheme and/or coding order are not within the scope of the present invention.
In this stage 202, based on the quality of the background picture acceptable by the user, a mapping relationship between a trade-off value between attenuation and a code rate and a probability that a pixel point is a background point in a rate-distortion optimization strategy is explored, and an adjustment strategy more conforming to the human eye attention mechanism is obtained.
In step 202-1, a dynamic rate control factor is adjusted for a current coding block based on a probability that a pixel point within the current coding block is determined to be background. According to an embodiment of the present invention, if all the pixels in the current coding block are background points, an average value p _ avg of p values of all the pixels in the coding block is taken, and a mapping relationship between the probability that the pixel belongs to the background and the background picture quality acceptable by a user is explored to obtain a code rate control factor λ ═ f (p _ avg) in a rate distortion optimization strategy, wherein f (·) represents a corresponding relationship between the trade-off between attenuation and the code rate in the rate distortion optimization strategy and the probability that the pixel belongs to the background, and the corresponding relationship is a continuous function instead of a discrete piecewise function in the prior art. For example, in a conventional x264 encoder, λ corresponds to a quantization parameter QP value, which is one of the inputs to the encoder and is an integer, and is found by looking up a table of QP values. Thus, the correspondence of λ to QP value in conventional coding is not a continuous function. In addition, in the invention, based on the corresponding relation between the trade-off between attenuation and code rate and the probability that the pixel point belongs to the background in the rate distortion optimization strategy, the probability that the pixel point belongs to the background is higher, the lambda is higher, and more video quality is likely to be sacrificed to obtain a smaller code rate during coding.
In step 202-2, the current coding block is differentially encoded using the dynamic rate control factor. According to an embodiment of the present invention, if the pixels in the current coding block contain or are all foreground, the coding is performed normally according to the original conventional coding mode (such as h.264, h.265, etc.); if all the pixels in the current coding block are background points, the coding is performed according to the lambda obtained in the step 202-1, and the background part of the video picture can be further compressed because the pixels with large p value can be coded by using a larger lambda.
In step 202-3, it is determined whether there are more coding blocks to be coded in the current image frame, if yes, the process returns to step 202-1, and if no, the process proceeds to step 203.
In step 203, it is determined whether there is a new image frame, if yes, the process returns to step 201-3 to continue to acquire a next new image frame, and if no, the process is ended. According to one embodiment of the invention, the image frames within the predetermined time period can be set to be acquired for encoding. According to another embodiment of the present invention, if the background changes significantly (such as the difference between the background of a new image frame and the background of a previous image frame reaches a certain threshold), the flow may be ended.
Compared with the prior art, the invention has the following advantages:
(1) the video compression rate is improved. On the premise of ensuring the quality of the foreground picture, the picture which is more likely to belong to the background in the video is further compressed, so that more code rates are saved, and the compression rate of the video is improved.
(2) The compression efficiency can be dynamically adjusted. The dynamic adjustment of the compression efficiency can be realized by modifying the parameters in the code rate control factor calculation formula according to the requirements of specific scenes.
(3) Improve the subjective visual quality of the picture. Based on the human eye attention mechanism, a more reasonable coding strategy is adopted to code and compress the part of the picture identified as the background according to the probability that the part is really the background point, so that the adjustment formula of the code rate control factor is a continuous function instead of a discrete piecewise function, and the image quality layering of the foreground and background areas in vision is avoided.
(4) High utility and easy implementation in a static context. For scenes with static or small change mostly, such as a home camera, a conference video, a road camera and the like, the method has the advantages of outstanding compression performance improvement and visual effect improvement.
FIG. 3 shows a block diagram 300 of an exemplary computing device, which is one example of a hardware device that may be applied to aspects of the present invention, according to one embodiment of the present invention.
With reference to FIG. 3, a computing device 300 will now be described, which is one example of a hardware device that may be applied to aspects of the present invention. Computing device 300 may be any machine that may be configured to implement processing and/or computing, and may be, but is not limited to, a workstation, a server, a desktop computer, a laptop computer, a tablet computer, a personal digital assistant, a smart phone, an on-board computer, a home camera, a conference recording device, a road camera, or any combination thereof. The various methods/apparatus/servers/client devices described above may be implemented in whole or at least in part by computing device 300 or similar devices or systems.
Computing device 300 may include components that may be connected or communicate via one or more interfaces and bus 302. For example, computing device 300 may include a bus 302, one or more processors 304, one or more input devices 306, and one or more output devices 308. The one or more processors 304 may be any type of processor and may include, but are not limited to, one or more general purpose processors and/or one or more special purpose processors (e.g., dedicated processing chips). Input device 306 may be any type of device capable of inputting information to a computing device and may include, but is not limited to, a mouse, a keyboard, a touch screen, a microphone, and/or a remote controller. Output device 308 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, a video/audio output terminal, a vibrator, and/or a printer. Computing device 300 may also include or be connected to non-transitory storage device 310, which may be any storage device that is non-transitory and that enables data storage, and which may include, but is not limited to, a disk drive, an optical storage device, a solid-state memory, a floppy disk, a flexible disk, a hard disk, a tape, or any other magnetic medium, an optical disk or any other optical medium, a ROM (read only memory), a RAM (random access memory), a cache memory, and/or any memory chip or cartridge, and/or any other medium from which a computer can read data, instructions, and/or code. The non-transitory storage device 310 may be detached from the interface. The non-transitory storage device 310 may have data/instructions/code for implementing the above-described methods and steps. Computing device 300 may also include a communication device 312. The communication device 312 may be any type of device or system capable of communicating with internal apparatus and/or with a network and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication device, and/or a chipset, such as a bluetooth device, an IEEE 1302.11 device, a WiFi device, a WiMax device, a cellular communication device, and/or the like.
The bus 302 may include, but is not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an enhanced ISA (eisa) bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.
Computing device 300 may also include a working memory 314, where working memory 314 may be any type of working memory capable of storing instructions and/or data that facilitate the operation of processor 304 and may include, but is not limited to, random access memory and/or read only memory devices.
Software components may be located in the working memory 314 including, but not limited to, an operating system 316, one or more application programs 318, drivers, and/or other data and code. Instructions for implementing the above-described methods and steps of the invention may be contained within the one or more applications 318, and the instructions of the one or more applications 318 may be read and executed by the processor 304 to implement the above-described method 200 of the invention.
It should also be appreciated that variations may be made according to particular needs. For example, customized hardware might also be used, and/or particular components might be implemented in hardware, software, firmware, middleware, microcode, hardware description speech, or any combination thereof. In addition, connections to other computing devices, such as network input/output devices and the like, may be employed. For example, some or all of the disclosed methods and apparatus can be implemented with logic and algorithms in accordance with the present invention through programming hardware (e.g., programmable logic circuitry including Field Programmable Gate Arrays (FPGAs) and/or Programmable Logic Arrays (PLAs)) having assembly language or hardware programming languages (e.g., VERILOG, VHDL, C + +).
Although the various aspects of the present invention have been described thus far with reference to the accompanying drawings, the above-described methods, systems, and apparatuses are merely examples, and the scope of the present invention is not limited to these aspects but only by the appended claims and equivalents thereof. Various components may be omitted or may be replaced with equivalent components. In addition, the steps may also be performed in a different order than described in the present invention. Further, the various components may be combined in various ways. It is also important that as technology develops that many of the described components can be replaced by equivalent components appearing later.

Claims (10)

1. A method for improving the compression ratio of a static background video based on a background modeling technology comprises the following steps:
establishing a background model by adopting a foreground extraction algorithm, wherein the background model is used for representing the characteristics of each pixel point in an image frame;
initializing the established background model;
updating the background model based on the acquired new image frame;
performing foreground or background estimation on each pixel point in the new image frame;
aiming at the probability that the pixel point in each coding block in the new image frame is determined as the background, adjusting a dynamic code rate control factor for each coding block; and
and carrying out differential coding on each coding block based on the dynamic code rate control factor aiming at each coding block.
2. The method of claim 1, wherein the foreground extraction algorithm comprises one of GMM, ViBe, SACON, or PBAS.
3. The method of claim 1, wherein initializing the established background model further comprises:
and initializing the background model by adopting the first frame image or the first N frame images.
4. The method of claim 1, wherein performing foreground or background estimation for each pixel point in the new image frame further comprises:
matching the current pixel value of each pixel point in the new image frame with the updated background model corresponding to the current pixel value;
if the matching fails, the pixel point is determined as a foreground;
and if the matching is successful, calculating the probability p that the pixel point belongs to the background according to the updated background model.
5. The method of claim 4, wherein adjusting a dynamic rate control factor for each coding block for a probability that a pixel point within each coding block in the new image frame is determined to be background further comprises:
if all the pixel points in the current coding block are determined as the background, taking the average value p _ avg of the p values of all the pixel points in the current coding block to obtain the code rate control factor lambda (f) (p _ avg) in the rate distortion optimization strategy.
6. The method of claim 5, wherein differentially encoding each coding block based on a dynamic rate control factor for each coding block further comprises:
and if all the pixel points in the current coding block are determined as the background, coding by using the code rate control factor lambda.
7. A system for improving the compression ratio of a static background video based on a background modeling technology comprises:
a background modeling module configured to:
establishing a background model by adopting a foreground extraction algorithm, wherein the background model is used for representing the characteristics of each pixel point in an image frame;
initializing the established background model;
updating the background model based on the acquired new image frame;
performing foreground or background estimation on each pixel point in the new image frame; and
a dynamic encoding module configured to:
aiming at the probability that the pixel point in each coding block in the new image frame is determined as the background, adjusting a dynamic code rate control factor for each coding block; and
and carrying out differential coding on each coding block based on the dynamic code rate control factor aiming at each coding block.
8. The system of claim 7, wherein performing foreground or background estimation for each pixel point in the new image frame further comprises:
matching the current pixel value of each pixel point in the new image frame with the updated background model corresponding to the current pixel value;
if the matching fails, the pixel point is determined as a foreground;
and if the matching is successful, calculating the probability p that the pixel point belongs to the background according to the updated background model.
9. The method of claim 8,
wherein adjusting the dynamic rate control factor for each coding block for the probability that a pixel within each coding block in the new image frame is determined to be background further comprises: if all the pixel points in the current coding block are determined as the background, taking the average value p _ avg of the p values of all the pixel points in the current coding block to obtain a code rate control factor lambda (f) (p _ avg) in a rate distortion optimization strategy;
wherein differentially encoding each coding block based on the dynamic rate control factor for each coding block further comprises: and if all the pixel points in the current coding block are determined as the background, coding by using the code rate control factor lambda.
10. A computing device for image super-resolution reconstruction, comprising:
a processor;
a memory storing instructions that, when executed by the processor, are capable of performing the method of claims 1-6.
CN202110609798.XA 2021-06-01 2021-06-01 Method for improving compression ratio of static background video based on background modeling technology Pending CN113850879A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110609798.XA CN113850879A (en) 2021-06-01 2021-06-01 Method for improving compression ratio of static background video based on background modeling technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110609798.XA CN113850879A (en) 2021-06-01 2021-06-01 Method for improving compression ratio of static background video based on background modeling technology

Publications (1)

Publication Number Publication Date
CN113850879A true CN113850879A (en) 2021-12-28

Family

ID=78972969

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110609798.XA Pending CN113850879A (en) 2021-06-01 2021-06-01 Method for improving compression ratio of static background video based on background modeling technology

Country Status (1)

Country Link
CN (1) CN113850879A (en)

Similar Documents

Publication Publication Date Title
Ki et al. Learning-based just-noticeable-quantization-distortion modeling for perceptual video coding
CN111182303A (en) Encoding method and device for shared screen, computer readable medium and electronic equipment
US11544606B2 (en) Machine learning based video compression
US20020051491A1 (en) Extraction of foreground information for video conference
US20220256140A1 (en) Video encoding method and apparatus, computer device, and storage medium
CN110149554B (en) Video image processing method and device, electronic equipment and storage medium
KR20140110008A (en) Object detection informed encoding
CN111131828B (en) Image compression method and device, electronic equipment and storage medium
WO2023016155A1 (en) Image processing method and apparatus, medium, and electronic device
CN112584119B (en) Self-adaptive panoramic video transmission method and system based on reinforcement learning
US11265528B2 (en) Methods and systems for color smoothing for point cloud compression
US10536696B2 (en) Image encoding device and image encoding method
CN111683244A (en) System and method for distortion removal across multiple quality levels
CN111970565A (en) Video data processing method and device, electronic equipment and storage medium
CN107818553B (en) Image gray value adjusting method and device
US20220067417A1 (en) Bandwidth limited context based adaptive acquisition of video frames and events for user defined tasks
CN112437301B (en) Code rate control method and device for visual analysis, storage medium and terminal
US20190052799A1 (en) Perception-based image processing apparatus and associated method
CN111385577B (en) Video transcoding method, device, computer equipment and computer readable storage medium
Menon et al. ETPS: Efficient Two-Pass Encoding Scheme for Adaptive Live Streaming
CN113850879A (en) Method for improving compression ratio of static background video based on background modeling technology
CN115567712A (en) Screen content video coding perception code rate control method and device based on just noticeable distortion by human eyes
US10764578B2 (en) Bit rate optimization system and method
CN113810692A (en) Method for framing changes and movements, image processing apparatus and program product
CN108933945B (en) GIF picture compression method, device 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
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20220207

Address after: Room 1423, No. 1256 and 1258, Wanrong Road, Jing'an District, Shanghai 200072

Applicant after: Tianyi Digital Life Technology Co.,Ltd.

Address before: 201702 3rd floor, 158 Shuanglian Road, Qingpu District, Shanghai

Applicant before: Tianyi Smart Family Technology Co.,Ltd.