CN114025118A - Low-bit-rate video reconstruction method and system, electronic equipment and storage medium - Google Patents
Low-bit-rate video reconstruction method and system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114025118A CN114025118A CN202210007865.5A CN202210007865A CN114025118A CN 114025118 A CN114025118 A CN 114025118A CN 202210007865 A CN202210007865 A CN 202210007865A CN 114025118 A CN114025118 A CN 114025118A
- Authority
- CN
- China
- Prior art keywords
- image
- reconstructed
- reconstruction
- network
- matrix
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/01—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/01—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level
- H04N7/0117—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level involving conversion of the spatial resolution of the incoming video signal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/01—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level
- H04N7/0127—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level by changing the field or frame frequency of the incoming video signal, e.g. frame rate converter
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Graphics (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention relates to the technical field of image processing, and discloses a low-bit-rate video reconstruction method, a system, electronic equipment and a storage medium, wherein the method comprises the steps of performing de-framing processing on a video to be reconstructed to obtain a plurality of frames of images to be reconstructed, performing segmentation processing on each image to be reconstructed based on a block sampling network to obtain a plurality of image blocks, measuring the plurality of image blocks by adopting a uniform measurement matrix to obtain corresponding observed value vectors, forming a total observation matrix of the images to be reconstructed by the measurement matrices of the plurality of image blocks, greatly reducing the calculated amount, improving the video reconstruction efficiency, performing linear fusion by adopting an MMSE linear estimation algorithm to obtain an initial reconstructed image, extracting a feature map in the initial reconstructed image by a characteristic extraction network, and performing feature reconstruction on the feature map by sequentially passing through a residual error network and a convolution reconstruction network, so as to obtain a reconstructed image and improve the video code rate effect after reconstruction.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a low-bit-rate video reconstruction method, a low-bit-rate video reconstruction system, electronic equipment and a storage medium.
Background
At present, the field safety supervision work of electric power operation is mostly carried out by adopting a remote video monitoring mode in the electric power industry. Because the operation sites are widely distributed and the operation amount is frequent, the operation site monitoring system in the power industry is exposed to huge data transmission pressure. In order to reduce the pressure of network transmission, the video must be compressed and transmitted.
At present, the traditional compressed sensing reconstruction algorithm solves the defects in image reconstruction to a certain extent, such as: the method has the advantages of being poor in anti-jamming capability, high in complexity, resource wasting and the like, but the traditional compressed sensing reconstruction algorithm is large in calculation amount, so that the video reconstruction efficiency is low, and meanwhile, the effect of the reconstructed video code rate is still poor.
Disclosure of Invention
The invention provides a low-bit-rate video reconstruction method, a low-bit-rate video reconstruction system, electronic equipment and a storage medium, and solves the technical problems of low video reconstruction efficiency and poor reconstructed video bit rate effect.
In view of the above, a first aspect of the present invention provides a low bitrate video reconstruction method, including the following steps:
performing de-framing processing on a video to be reconstructed to obtain a plurality of frames of images to be reconstructed, thereby forming an image sequence set to be reconstructed;
based on a block sampling network, carrying out segmentation processing on each image to be reconstructed in the image sequence set to be reconstructed to obtain a plurality of image blocks, measuring the plurality of image blocks by adopting a uniform measurement matrix to obtain corresponding observed value vectors, and forming a total observation matrix of the image to be reconstructed by the measurement matrices of the plurality of image blocks;
linearly fusing the observation value vector and the total observation matrix by adopting an MMSE linear estimation algorithm so as to obtain an initial reconstruction image;
extracting the characteristics of the initial reconstruction image based on a characteristic extraction network to obtain a characteristic diagram;
carrying out down-sampling operation on the feature map through a residual error network to obtain a down-sampled feature map;
and performing feature reconstruction on the down-sampled feature map through a convolution reconstruction network to obtain a reconstructed image.
Preferably, the step of segmenting each image to be reconstructed in the image sequence set to be reconstructed based on a block sampling network to obtain a plurality of image blocks, measuring the plurality of image blocks by using a uniform measurement matrix to obtain corresponding observed value vectors, and forming a total observation matrix of the image to be reconstructed by using the measurement matrices of the plurality of image blocks specifically includes:
based on the block sampling network, each image to be reconstructed in the image sequence set to be reconstructed is segmented to obtain
Image blocks, each of which has a uniform size and is not overlapped;
measuring a plurality of image blocks by adopting a uniform measurement matrix to obtain corresponding observed value vectors which are recorded as
Then, there are:
in the formula (I), the compound is shown in the specification,
representing a measurement matrix, adopting a binary sparse matrix as the measurement matrix,
a column vector representing the image block,
n represents the total number of pixels of the image to be reconstructed;
by passing
The measurement matrix of each image block forms the total observation matrix of the image to be reconstructed
Comprises the following steps:
preferably, the initial reconstructed image is represented as:
in the formula (I), the compound is shown in the specification,
wherein, in the step (A),
for inputting the autocorrelation function of the image to be reconstructed, the calculation process of the autocorrelation function is as follows:
calculating the difference between each pixel of the image to be reconstructed and the average value of 4 pixels with the distance of m, and obtaining:
in the formula (I), the compound is shown in the specification,
representing the difference between the current pixel and the average of 4 pixels whose distance is m,
a coordinate value representing the current pixel is set,
、
、
and
respectively representing the coordinate values of the pixels with the current pixel distance of m;
will be provided with
Multiplying by the average of its 4 neighboring pixel values to obtain an autocorrelation function
Comprises the following steps:
in the formula (I), the compound is shown in the specification,
is a set of coordinates of pixels in the image to be reconstructed, which are at a mutual distance of m.
Preferably, the signature extraction network comprises a convolutional layer and an active layer, wherein the convolutional layer comprises 64 convolutional layers
And the large and small convolution kernels are formed, and the active layer adopts a PReLU active function.
Preferably, the residual network is composed of a plurality of residual blocks, each of which is composed of a convolutional layer and an active layer, wherein the convolutional layer is composed of 64 convolutional kernels with 3 × 3 sizes, and the active layer adopts a LeakReLU nonlinear activation function.
Preferably, the convolutional reconstruction network consists of one convolutional layer and one active layer, wherein the convolutional layer consists of 2 convolutional layers
And the large and small convolution kernels are formed, and the activation layer adopts a Tanh activation function.
Preferably, the method further comprises:
and calculating the loss value of the convolution reconstruction network by utilizing the mean square error loss function, thereby optimizing the convolution reconstruction network.
In a second aspect, the present invention further provides a low bit rate video reconstruction system, including:
the device comprises a frame decoding module, a frame decoding module and a frame decoding module, wherein the frame decoding module is used for decoding a video to be reconstructed so as to obtain a plurality of frames of images to be reconstructed, and thus an image sequence set to be reconstructed is formed;
the block sampling module is used for carrying out segmentation processing on each image to be reconstructed in the image sequence set to be reconstructed based on a block sampling network to obtain a plurality of image blocks, measuring the image blocks by adopting a uniform measurement matrix to obtain corresponding observed value vectors, and forming a total observation matrix of the image to be reconstructed by the measurement matrix of the image blocks;
the linear fusion module is used for performing linear fusion on the observation value vector and the total observation matrix by adopting an MMSE linear estimation algorithm so as to obtain an initial reconstruction image;
the characteristic extraction module is used for extracting the characteristics of the initial reconstruction image based on a characteristic extraction network so as to obtain a characteristic diagram;
the residual error module is used for carrying out downsampling operation on the feature map through a residual error network to obtain a downsampled feature map;
and the convolution reconstruction module is used for performing feature reconstruction on the downsampled feature map through a convolution reconstruction network so as to obtain a reconstructed image.
In a third aspect, the present invention also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of the above method when executing the computer program.
In a fourth aspect, the invention also provides a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method as described above.
According to the technical scheme, the invention has the following advantages:
the method comprises the steps of performing de-framing processing on a video to be reconstructed to obtain a plurality of frames of images to be reconstructed, performing segmentation processing on each image to be reconstructed based on a block sampling network to obtain a plurality of image blocks, measuring the plurality of image blocks by adopting a uniform measurement matrix to obtain corresponding observed value vectors, forming a total observation matrix of the images to be reconstructed by adopting the measurement matrices of the plurality of image blocks, greatly reducing the calculated amount and improving the video reconstruction efficiency, performing linear fusion by adopting an MMSE linear estimation algorithm to obtain an initial reconstructed image, extracting a feature map in the initial reconstructed image by adopting a feature extraction network, and performing feature reconstruction on the feature map sequentially through a residual error network and a convolution reconstruction network to obtain a reconstructed image so as to improve the video code rate effect after reconstruction.
Drawings
Fig. 1 is a flowchart of a low bit rate video reconstruction method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a low bit rate video reconstruction system according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
For easy understanding, please refer to fig. 1, the present invention provides a low bit rate video reconstruction method, which includes the following steps:
s100, performing frame decoding processing on the video to be reconstructed to obtain a plurality of frames of images to be reconstructed, and forming an image sequence set to be reconstructed.
The image sequence set to be reconstructed is constructed by sequencing the time frame sizes of a plurality of frames of images to be reconstructed.
S200, based on a block sampling network, dividing each image to be reconstructed in the image sequence set to be reconstructed to obtain a plurality of image blocks, measuring the image blocks by adopting a uniform measurement matrix to obtain corresponding observed value vectors, and forming a total observation matrix of the image to be reconstructed by the measurement matrices of the image blocks.
It should be noted that, in this embodiment, a block sampling network is used to perform compression sampling on an image to be reconstructed. The block sampling network divides the image into sub-blocks with the same size and without overlap, and through division processing, a smaller observation matrix can be used for observing the block image, so that the calculation amount is greatly reduced.
S300, carrying out linear fusion on the observation value vector and the total observation matrix by adopting an MMSE linear estimation algorithm, thereby obtaining an initial reconstruction image.
It should be noted that, an MMSE linear estimation algorithm, that is, a minimum mean square error linear estimation algorithm, is used to predict the observation value vector and the total observation matrix, so as to obtain an initial reconstructed image.
And S400, extracting the characteristics of the initial reconstructed image based on the characteristic extraction network so as to obtain a characteristic diagram.
The feature map can be a shallow feature map, a deep feature map or a feature map formed by fusing the shallow feature map and the deep feature map.
In this embodiment, the feature extraction network comprises a convolutional layer and an active layer, wherein the convolutional layer comprises 64 convolutional layers
And the large and small convolution kernels are formed, and the active layer adopts a PReLU active function.
And S500, performing downsampling operation on the feature map through a residual error network to obtain the downsampled feature map.
In this embodiment, the residual network is composed of a plurality of residual blocks, each of which is composed of a convolutional layer and an active layer, wherein the convolutional layer is composed of 64 convolutional kernels with 3 × 3 sizes, and the active layer adopts a LeakReLU nonlinear activation function.
The residual error network fuses the extracted features of the two convolutional layers by adopting element-by-element addition and outputs the feature map to the next residual error block until the feature map is output by the last residual error block.
And S600, performing feature reconstruction on the down-sampled feature map through a convolution reconstruction network to obtain a reconstructed image.
In this embodiment, the convolutional reconstruction network consists of one convolutional layer and one active layer, wherein the convolutional layer consists of 2 convolutional layers
And the large and small convolution kernels are formed, and the activation layer adopts a Tanh activation function.
The embodiment provides a low-bit-rate video reconstruction method, which performs the de-framing processing on the video to be reconstructed, thereby obtaining a plurality of frames of images to be reconstructed, segmenting each image to be reconstructed based on the block sampling network to obtain a plurality of image blocks, measuring the image blocks by using a uniform measurement matrix to obtain corresponding observed value vectors, forming a total observation matrix of the image to be reconstructed by using the measurement matrices of the image blocks, thereby greatly reducing the calculated amount, improving the video reconstruction efficiency, and also adopting MMSE linear estimation algorithm to carry out linear fusion to obtain an initial reconstruction image, and extracting a characteristic graph in the initial reconstructed image through a characteristic extraction network, and sequentially performing characteristic reconstruction on the characteristic graph through a residual error network and a convolution reconstruction network to obtain a reconstructed image so as to improve the video code rate effect after reconstruction.
In this embodiment, step S200 specifically includes:
s201, based on the block sampling network, carrying out segmentation processing on each image to be reconstructed in the image sequence set to be reconstructed to obtain
Image blocks, each of which has a uniform size and is not overlapped;
measuring a plurality of image blocks by adopting a uniform measurement matrix to obtain corresponding observed value vectors which are recorded as
Then, there are:
in the formula (I), the compound is shown in the specification,
representing a measurement matrix, adopting a binary sparse matrix as the measurement matrix,
a column vector representing the image block,
n represents the total number of pixels of the image to be reconstructed;
s202, passing
The measurement matrix of each image block forms the total observation matrix of the image to be reconstructed
Comprises the following steps:
wherein, by block sampling, only the observation matrix needs to be stored
Due to the fact that
The size of the image compression sampling device is far smaller than an observation matrix when the whole image is directly compressed and sampled, so that the calculated amount and the storage space are effectively reduced, and the compression sampling efficiency is greatly improved.
In the present embodiment, the initial reconstructed image is represented as:
in the formula (I), the compound is shown in the specification,
wherein, in the step (A),
for inputting the autocorrelation function of the image to be reconstructed, the calculation process of the autocorrelation function is as follows:
calculating the difference between each pixel of the image to be reconstructed and the average value of 4 pixels with the distance of m, and obtaining:
in the formula (I), the compound is shown in the specification,
representing the difference between the current pixel and the average of 4 pixels whose distance is m,
a coordinate value representing the current pixel is set,
、
、
and
respectively representing the coordinate values of the pixels with the current pixel distance of m;
will be provided with
Multiplying by the average of its 4 neighboring pixel values to obtain an autocorrelation function
Comprises the following steps:
in the formula (I), the compound is shown in the specification,
is a set of coordinates of pixels in the image to be reconstructed, which are at a mutual distance of m.
In this embodiment, the method further includes:
and calculating the loss value of the convolution reconstruction network by using the mean square error loss function, thereby optimizing the convolution reconstruction network.
The above is a detailed description of an embodiment of a low bit rate video reconstruction method provided by the present invention, and the following is a detailed description of an embodiment of a low bit rate video reconstruction system provided by the present invention.
For easy understanding, please refer to fig. 2, the present invention provides a low bitrate video reconstruction system, including:
the device comprises a frame decoding module 100, a frame decoding module and a frame decoding module, wherein the frame decoding module is used for performing frame decoding processing on a video to be reconstructed so as to obtain a plurality of frames of images to be reconstructed, and thus an image sequence set to be reconstructed is formed;
the block sampling module 200 is configured to segment each image to be reconstructed in the image sequence set to be reconstructed based on a block sampling network to obtain a plurality of image blocks, measure the plurality of image blocks by using a uniform measurement matrix to obtain corresponding observation value vectors, and form a total observation matrix of the image to be reconstructed by using the measurement matrices of the plurality of image blocks;
a linear fusion module 300, configured to perform linear fusion on the observation value vector and the total observation matrix by using an MMSE linear estimation algorithm, so as to obtain an initial reconstructed image;
a feature extraction module 400, configured to perform feature extraction on the initial reconstructed image based on a feature extraction network, so as to obtain a feature map;
a residual error module 500, configured to perform downsampling on the feature map through a residual error network to obtain a downsampled feature map;
and a convolution reconstruction module 600, configured to perform feature reconstruction on the downsampled feature map through a convolution reconstruction network, so as to obtain a reconstructed image.
The invention also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of the method when executing the computer program.
The invention also provides a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method as described above.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for executing all or part of the steps of the method according to the embodiments of the present invention through a computer device (which may be a personal computer, a server, or a network device). And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A low bit rate video reconstruction method is characterized by comprising the following steps:
performing de-framing processing on a video to be reconstructed to obtain a plurality of frames of images to be reconstructed, thereby forming an image sequence set to be reconstructed;
based on a block sampling network, carrying out segmentation processing on each image to be reconstructed in the image sequence set to be reconstructed to obtain a plurality of image blocks, measuring the plurality of image blocks by adopting a uniform measurement matrix to obtain corresponding observed value vectors, and forming a total observation matrix of the image to be reconstructed by the measurement matrices of the plurality of image blocks;
linearly fusing the observation value vector and the total observation matrix by adopting an MMSE linear estimation algorithm so as to obtain an initial reconstruction image;
extracting the characteristics of the initial reconstruction image based on a characteristic extraction network to obtain a characteristic diagram;
carrying out down-sampling operation on the feature map through a residual error network to obtain a down-sampled feature map;
and performing feature reconstruction on the down-sampled feature map through a convolution reconstruction network to obtain a reconstructed image.
2. The low bit rate video reconstruction method according to claim 1, wherein the step of segmenting each image to be reconstructed in the image sequence set to be reconstructed based on a block sampling network to obtain a plurality of image blocks, measuring the plurality of image blocks by using a uniform measurement matrix to obtain corresponding observation value vectors, and forming a total observation matrix of the image to be reconstructed by using the measurement matrices of the plurality of image blocks specifically comprises:
based on the block sampling network, each image to be reconstructed in the image sequence set to be reconstructed is segmented to obtain
Image blocks, each of which has a uniform size and is not overlapped;
measuring a plurality of image blocks by adopting a uniform measurement matrix to obtain corresponding observed value vectors which are recorded as
Then, there are:
in the formula (I), the compound is shown in the specification,
representing a measurement matrix, adopting a binary sparse matrix as the measurement matrix,
a column vector representing the image block,
n represents the total number of pixels of the image to be reconstructed;
by passing
The measurement matrix of each image block forms the total observation matrix of the image to be reconstructed
Comprises the following steps:
3. the low bit rate video reconstruction method of claim 2, wherein the initial reconstructed image is represented as:
in the formula (I), the compound is shown in the specification,
wherein, in the step (A),
for inputting the autocorrelation function of the image to be reconstructed, the calculation process of the autocorrelation function is as follows:
calculating the difference between each pixel of the image to be reconstructed and the average value of 4 pixels with the distance of m, and obtaining:
in the formula (I), the compound is shown in the specification,
representing the difference between the current pixel and the average of 4 pixels whose distance is m,
a coordinate value representing the current pixel is set,
、
、
and
respectively representing the coordinate values of the pixels with the current pixel distance of m;
will be provided with
Multiplying by the average of its 4 neighboring pixel values to obtain an autocorrelation function
Comprises the following steps:
in the formula (I), the compound is shown in the specification,
is a set of coordinates of pixels in the image to be reconstructed, which are at a mutual distance of m.
4. The method of claim 1, wherein the extraction network comprises a convolutional layer and an active layer, and the convolutional layer comprises 64 convolutional layers
And the large and small convolution kernels are formed, and the active layer adopts a PReLU active function.
5. The method of claim 1, wherein the residual network comprises a plurality of residual blocks, each of the residual blocks comprises a convolutional layer and an active layer, wherein the convolutional layer comprises 64 convolutional kernels of 3 × 3 size, and the active layer uses a LeakReLU nonlinear activation function.
6. The method of claim 1, wherein the convolutional reconstruction network comprises of a convolutional layer and an active layer, wherein the convolutional layer comprises of 2 convolutional layers
And the large and small convolution kernels are formed, and the activation layer adopts a Tanh activation function.
7. The method for reconstructing low bitrate video according to claim 1, further comprising:
and calculating the loss value of the convolution reconstruction network by utilizing the mean square error loss function, thereby optimizing the convolution reconstruction network.
8. A low rate video reconstruction system, comprising:
the device comprises a frame decoding module, a frame decoding module and a frame decoding module, wherein the frame decoding module is used for decoding a video to be reconstructed so as to obtain a plurality of frames of images to be reconstructed, and thus an image sequence set to be reconstructed is formed;
the block sampling module is used for carrying out segmentation processing on each image to be reconstructed in the image sequence set to be reconstructed based on a block sampling network to obtain a plurality of image blocks, measuring the image blocks by adopting a uniform measurement matrix to obtain corresponding observed value vectors, and forming a total observation matrix of the image to be reconstructed by the measurement matrix of the image blocks;
the linear fusion module is used for performing linear fusion on the observation value vector and the total observation matrix by adopting an MMSE linear estimation algorithm so as to obtain an initial reconstruction image;
the characteristic extraction module is used for extracting the characteristics of the initial reconstruction image based on a characteristic extraction network so as to obtain a characteristic diagram;
the residual error module is used for carrying out downsampling operation on the feature map through a residual error network to obtain a downsampled feature map;
and the convolution reconstruction module is used for performing feature reconstruction on the downsampled feature map through a convolution reconstruction network so as to obtain a reconstructed image.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210007865.5A CN114025118A (en) | 2022-01-06 | 2022-01-06 | Low-bit-rate video reconstruction method and system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210007865.5A CN114025118A (en) | 2022-01-06 | 2022-01-06 | Low-bit-rate video reconstruction method and system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114025118A true CN114025118A (en) | 2022-02-08 |
Family
ID=80069779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210007865.5A Pending CN114025118A (en) | 2022-01-06 | 2022-01-06 | Low-bit-rate video reconstruction method and system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114025118A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115393777A (en) * | 2022-10-28 | 2022-11-25 | 国网山东省电力公司青岛供电公司 | Electric power video monitoring image edge calculation method and system based on compressed sensing |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105992009A (en) * | 2015-02-05 | 2016-10-05 | 袁琳琳 | Motion-compensation-and-block-based video compressed sensing processing method |
| CN109920013A (en) * | 2019-01-30 | 2019-06-21 | 北京交通大学 | Image reconstructing method and device based on gradual convolution measurement network |
| CN110276721A (en) * | 2019-04-28 | 2019-09-24 | 天津大学 | Image super-resolution rebuilding method based on cascade residual error convolutional neural networks |
| CN111553867A (en) * | 2020-05-15 | 2020-08-18 | 润联软件系统(深圳)有限公司 | Image deblurring method and device, computer equipment and storage medium |
| CN111951164A (en) * | 2020-08-11 | 2020-11-17 | 哈尔滨理工大学 | Image super-resolution reconstruction network structure and image reconstruction effect analysis method |
| CN112116601A (en) * | 2020-08-18 | 2020-12-22 | 河南大学 | Compressive sensing sampling reconstruction method and system based on linear sampling network and generation countermeasure residual error network |
| CN113793263A (en) * | 2021-08-23 | 2021-12-14 | 电子科技大学 | Parallel residual error network high-resolution image reconstruction method for multi-scale cavity convolution |
-
2022
- 2022-01-06 CN CN202210007865.5A patent/CN114025118A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105992009A (en) * | 2015-02-05 | 2016-10-05 | 袁琳琳 | Motion-compensation-and-block-based video compressed sensing processing method |
| CN109920013A (en) * | 2019-01-30 | 2019-06-21 | 北京交通大学 | Image reconstructing method and device based on gradual convolution measurement network |
| CN110276721A (en) * | 2019-04-28 | 2019-09-24 | 天津大学 | Image super-resolution rebuilding method based on cascade residual error convolutional neural networks |
| CN111553867A (en) * | 2020-05-15 | 2020-08-18 | 润联软件系统(深圳)有限公司 | Image deblurring method and device, computer equipment and storage medium |
| CN111951164A (en) * | 2020-08-11 | 2020-11-17 | 哈尔滨理工大学 | Image super-resolution reconstruction network structure and image reconstruction effect analysis method |
| CN112116601A (en) * | 2020-08-18 | 2020-12-22 | 河南大学 | Compressive sensing sampling reconstruction method and system based on linear sampling network and generation countermeasure residual error network |
| CN113793263A (en) * | 2021-08-23 | 2021-12-14 | 电子科技大学 | Parallel residual error network high-resolution image reconstruction method for multi-scale cavity convolution |
Non-Patent Citations (4)
| Title |
|---|
| 王克奇等: "基于分形理论的木材纹理特征研究", 《林业机械与木工设备》 * |
| 王华等: "基于自相关函数的自然纹理图像分形维数的估计", 《北京航空航天大学学报》 * |
| 范晓维等: "分块可压缩传感的图像重构模型", 《计算机工程与应用》 * |
| 谢永华等: "基于小波分解与分形维的木材纹理分类", 《东北林业大学学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115393777A (en) * | 2022-10-28 | 2022-11-25 | 国网山东省电力公司青岛供电公司 | Electric power video monitoring image edge calculation method and system based on compressed sensing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111105352A (en) | Super-resolution image reconstruction method, system, computer device and storage medium | |
| CN112862877B (en) | Method and apparatus for training an image processing network and image processing | |
| CN111445418A (en) | Image defogging method and device and computer equipment | |
| CN113570606B (en) | Target segmentation method and device and electronic equipment | |
| CN115358932B (en) | Multi-scale feature fusion face super-resolution reconstruction method and system | |
| CN114025118A (en) | Low-bit-rate video reconstruction method and system, electronic equipment and storage medium | |
| CN113538235A (en) | Training method and device of image processing model, electronic equipment and storage medium | |
| CN112907448A (en) | Method, system, equipment and storage medium for super-resolution of any-ratio image | |
| CN111083478A (en) | Video frame reconstruction method and device and terminal equipment | |
| US20230260211A1 (en) | Three-Dimensional Point Cloud Generation Method, Apparatus and Electronic Device | |
| CN116708807A (en) | Compression reconstruction method and compression reconstruction device for monitoring video | |
| CN111083494A (en) | Video coding method and device and terminal equipment | |
| CN113177483B (en) | Video object segmentation method, device, equipment and storage medium | |
| Rodríguez et al. | Video background modeling under impulse noise | |
| CN114501029B (en) | Image encoding method, image decoding method, image encoding device, image decoding device, computer device, and storage medium | |
| CN112258394B (en) | Data processing method, ship tracking method, device, equipment and storage medium | |
| CN111932466B (en) | Image defogging method, electronic equipment and storage medium | |
| CN114842066A (en) | Image depth recognition model training method, image depth recognition method and device | |
| CN115423697A (en) | Image restoration method, terminal and computer storage medium | |
| CN113628338A (en) | Sampling reconstruction method and device, computer equipment and storage medium | |
| CN112990046A (en) | Difference information acquisition method, related device and computer program product | |
| CN111861897A (en) | Image processing method and device | |
| CN113099231B (en) | Method and device for determining sub-pixel interpolation position, electronic equipment and storage medium | |
| JP7372487B2 (en) | Object segmentation method, object segmentation device and electronic equipment | |
| CN111275692B (en) | Infrared small target detection method based on generation countermeasure network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220208 |