CN115393777A - Electric power video monitoring image edge calculation method and system based on compressed sensing - Google Patents
Electric power video monitoring image edge calculation method and system based on compressed sensing Download PDFInfo
- Publication number
- CN115393777A CN115393777A CN202211330614.7A CN202211330614A CN115393777A CN 115393777 A CN115393777 A CN 115393777A CN 202211330614 A CN202211330614 A CN 202211330614A CN 115393777 A CN115393777 A CN 115393777A
- Authority
- CN
- China
- Prior art keywords
- image
- image blocks
- compressed sensing
- blocks
- power video
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 39
- 238000004364 calculation method Methods 0.000 title claims description 9
- 239000011159 matrix material Substances 0.000 claims abstract description 50
- 238000005259 measurement Methods 0.000 claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 17
- 230000000903 blocking effect Effects 0.000 claims abstract description 13
- 239000013598 vector Substances 0.000 claims description 10
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 230000002596 correlated effect Effects 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims 1
- 230000005540 biological transmission Effects 0.000 description 13
- 230000000694 effects Effects 0.000 description 8
- 238000007906 compression Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000005070 sampling Methods 0.000 description 7
- 230000006835 compression Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The application belongs to the technical field of power systems, and particularly relates to a method and a system for calculating edges of power video monitoring images based on compressed sensing, wherein the method comprises the following steps: acquiring a power video monitoring image; the method comprises the steps of performing blocking processing on an obtained power video monitoring image to obtain a plurality of image blocks with the same size; extracting image features of the obtained image blocks, and classifying the image blocks according to the extracted image features; respectively constructing self-adaptive compressed sensing measurement matrixes and self-correlation matrixes of image blocks of different classes based on the classified image blocks; calculating an estimation factor of the image block according to the constructed measurement matrix and the autocorrelation matrix; and merging and reconstructing the image blocks according to the obtained estimation factors and measurement matrixes of the image blocks.
Description
Technical Field
The application belongs to the technical field of power systems, and particularly relates to a method and a system for calculating edges of power video monitoring images based on compressed sensing.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Based on modern information technologies such as mobile interconnection, artificial intelligence and the like and advanced communication technologies, all things interconnection and man-machine interaction in all links of a power system are achieved, and a ubiquitous power internet of things with comprehensive sensing of states, efficient information processing and convenient and flexible application is created. With the development of the ubiquitous power internet, various growing power terminal devices and service applications can generate massive data, and the processing of the massive data can cause huge pressure on a master station.
According to the knowledge of the inventor, in the process of power data transmission, the proportion of power video monitoring data is large; in order to further relieve the pressure of power communication transmission, data processing is carried out after power video monitoring data are obtained, and then communication uploading or transmission processing is carried out on the processed data; the data transmission quantity is reduced fundamentally so as to reduce the pressure of data processing on the main station.
Disclosure of Invention
In order to solve the problems, the application provides a method and a system for calculating the edge of an electric power video monitoring image based on compressed sensing, the edge of the electric power video monitoring image is calculated by using a compressed sensing theory of images, and the monitoring video image uploaded to a main station is compressed and sampled by an edge calculation node, so that the data volume transmitted by the main station is reduced, and the communication bandwidth utilization rate and the data transmission working efficiency are improved.
According to some embodiments, a first aspect of the present application provides a method for calculating an edge of an electric power video surveillance image based on compressed sensing, which adopts the following technical solutions:
a method for calculating the edge of a power video monitoring image based on compressed sensing comprises the following steps:
acquiring a power video monitoring image;
the method comprises the steps of performing blocking processing on an obtained power video monitoring image to obtain a plurality of image blocks with the same size;
extracting image features of the obtained image blocks, and classifying the image blocks according to the extracted image features;
respectively constructing self-adaptive compressed sensing measurement matrixes and self-correlation matrixes of image blocks of different classes based on the classified image blocks;
calculating an estimation factor of the image block according to the constructed measurement matrix and the autocorrelation matrix;
and combining and reconstructing the image blocks according to the obtained estimation factors and the measurement matrix of the image blocks.
As a further technical limitation, the size is obtained as
The power video monitors the video image of the image and carries out block processing on the image, and the size of each block is
The images may be divided into non-overlapping ones
Blocking the small image; where m denotes the number of rows of the size, n denotes the number of columns of the size,
。
as a further technical limitation, in the process of extracting image features of the obtained image blocks, the image blocks are divided into column vectors, the variance of the converted column vectors is calculated, and the image features are extracted.
As a further technical limitation, classification of image blocks
Wherein,
is as followsiThe column vector representation of the individual image blocks,
is a firstiThe variance of each image block is determined by the variance of each image block,
，
is the minimum value of the variance and is,
is the maximum value of the variance and is,
and
taking 0.1 and 0.3 respectively as threshold values according to experiments;
，
is the size of the image block,
is as followsiEach image blockjThe gray value of each pixel point is calculated,
is shown asiThe average value of all the pixel points of each image block,
。
as a further technical limitation, in the process of constructing the self-adaptive compressed sensing measurement matrix, the measurement rates of different types of image blocks are calculated according to the classified image blocks, the self-adaptive compressed sensing measurement matrix of the image blocks is constructed according to the obtained measurement rates, and the measurement matrix is stored and transmitted to the data center for storage.
As a further technical limitation, the autocorrelation matrix
Is composed of
(ii) a Wherein,
representing image blocks
To (1) akA plurality of pixels, each of which is a pixel,
representing image blocks
To (1) alA plurality of pixels, each of which is a pixel,
representing a pixel
The spatial position of (a) is determined,
representing a pixel
The spatial position of (a) of (b),
in order to be a coefficient of correlation,
in order to obtain the Euclidean distance,
the autocorrelation matrix is shown to follow an exponential distribution, i.e., the larger the euclidean distance, the less correlated.
And as a further technical limitation, according to the obtained estimation factor and measurement matrix of the image block, calculating an autocorrelation matrix by using the position information of the image block, solving a linear estimation factor according to the obtained autocorrelation matrix, correcting the obtained initial image block by combining the obtained linear estimation factor to obtain a reconstructed image, and finishing the monitoring analysis of the image.
According to some embodiments, a second aspect of the present application provides a system for calculating an edge of an electric power video surveillance image based on compressed sensing, which adopts the following technical solutions:
a compressed sensing-based power video surveillance image edge computing system, comprising:
an acquisition module configured to acquire a power video monitoring image;
the blocking module is configured to perform blocking processing on the acquired power video monitoring images to obtain a plurality of image blocks with the same size;
the classification module is configured to extract image features of the obtained image blocks and classify the image blocks according to the extracted image features;
the computing module is configured to respectively construct an adaptive compressed sensing measurement matrix and an autocorrelation matrix of image blocks of different categories based on the classified image blocks; calculating an estimation factor of the image block according to the constructed measurement matrix and the autocorrelation matrix;
and the reconstruction module is configured to carry out combined reconstruction on the image blocks according to the obtained estimation factors and the measurement matrix of the image blocks.
According to some embodiments, a third aspect of the present application provides a computer-readable storage medium, which adopts the following technical solutions:
a computer readable storage medium, on which a program is stored, which when executed by a processor, implements the steps in the method for calculating the edge of a monitored image based on compressed sensing in accordance with the first aspect of the present application.
According to some embodiments, a fourth aspect of the present application provides an electronic device, which adopts the following technical solutions:
an electronic device includes a memory, a processor and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for calculating the edge of the monitored image based on compressed sensing in the first aspect of the present application.
Compared with the prior art, the beneficial effects of this application do:
aiming at the problem that a coding and decoding algorithm is needed in the transmission process of a traditional video monitoring image, the method and the device fully utilize a compression sensing algorithm to carry out compression sampling on the video image, reduce the data dimension of image transmission to the maximum extent, reduce the calculation complexity in the compression process, centralize a large amount of image data processing work to a data center station or a user side, and improve the bandwidth utilization rate of a transmission channel.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a flowchart of a compressed sensing-based method for calculating an edge of an electric video surveillance image according to a first embodiment of the present application;
FIG. 2 (a) is a diagram of an image effect in the first embodiment of the present application;
FIG. 2 (b) is a diagram illustrating the effect of classifying image blocks in the first embodiment of the present application;
fig. 3 (a) is an effect diagram of an electric power video monitoring image in the first embodiment of the present application;
fig. 3 (b) is another effect diagram of the power video surveillance image in the first embodiment of the present application;
fig. 4 is a block diagram of a system for calculating an edge of a power video surveillance image based on compressed sensing according to a second embodiment of the present application.
Detailed Description
The present application will be further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
In the present application, terms such as "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "side", "bottom", and the like indicate orientations or positional relationships based on orientations or positional relationships shown in the drawings, and are only terms of relationships determined for convenience of describing structural relationships of components or elements of the present application, and are not intended to refer to any components or elements of the present application, and should not be construed as limiting the present application.
In the present application, terms such as "fixedly connected", "connected", and the like are to be understood in a broad sense, and mean either a fixed connection or an integrally connected or detachable connection; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present application can be determined according to specific situations by persons skilled in the relevant scientific research or technical field, and the terms cannot be understood as limiting the present application.
The embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Example one
The embodiment of the application introduces a method for calculating an edge of an electric power video monitoring image based on compressed sensing.
The embodiment performs compression processing on the video monitoring image, so that the data transmission quantity is reduced to a greater extent; meanwhile, the problem of low image distortion rate received by the master station can be solved, and the video monitoring service requirement of the master station is further met.
As shown in fig. 1, a method for calculating an edge of a power video surveillance image based on compressed sensing includes:
acquiring a power video monitoring image;
the method comprises the steps of performing blocking processing on an obtained power video monitoring image to obtain a plurality of image blocks with the same size;
extracting image features of the obtained image blocks, and classifying the image blocks according to the extracted image features;
respectively constructing self-adaptive compressed sensing measurement matrixes and self-correlation matrixes of image blocks of different classes based on the classified image blocks;
calculating an estimation factor of the image block according to the constructed measurement matrix and the autocorrelation matrix;
and combining and reconstructing the image blocks according to the obtained estimation factors and the measurement matrix of the image blocks.
In one or more embodiments, a video image of a size is read in, the size of the video image being
（mThe lines are represented as a result of,nrepresenting columns), extracting the gray value of the image, and carrying out block processing on the image, wherein the size of each block is
The images can be divided into non-overlapping
An image block of which
(ii) a Converting the image block into a column vector, calculating the variance of the column vector, and dividing the image into three types of flat, edge and texture by using a formula (1);
wherein,
is as followsiA column vector representation of the image block,
is as followsiThe variance of each image block is determined by the variance of each image block,
，
is the minimum value of the variance and is,
is the maximum value of the variance and is,
and
taking 0.1 and 0.3 respectively as threshold values according to experiments;
，
is the size of the image block,
is as followsiEach image blockjThe gray value of each pixel point is calculated,
is shown asiThe average value of all the pixel points of each image block,
(ii) a The image block is a matrix, and the elements in the image block are the gray values of the image; the variance of the image block is determined as a number, based on which
、
Determines the classification of the image block.
In this embodiment, the purpose of image blocking is to reduce unnecessary measurements. Experience shows that the texture block has the highest information content and the flat block has the lowest information content for the three types of blocks, namely the flat block, the edge block and the texture block, so that the measured value of the texture block is increased, the measured value of the flat block is reduced, the uniform sampling measurement reconstruction effect is better than that of the block which is not distinguished, and the calculated amount is less. The measurement of flat blocks is reduced, and the measurement of texture blocks is increased relatively, by determining the measurement rates of the different blocks. In the subsequent step, the category of the target block is known by the blocking process, and the measured value thereof is determined.
In the present embodiment, as shown in the image effect diagram of fig. 2 (a), and the image block classification effect diagram after blocking is shown in fig. 2 (b), hair areas with complex textures are all white, the edge areas are mostly gray, and for a flat face area, the black blocks are more concentrated.
As one or more embodiments, the measurement rates of different blocks are determined; to the pictureThe blocks are classified, assuming that a flat block is obtained
The edge block is
The texture block is
，
。
Assuming measured rate
(in the present embodiment, it is,rthe value is 0.2 according to experimental experience,Mis a measure of the whole image of the image,Nnumber of pixels for the entire image):
wherein,
is the rate of measurement of the flat block,
is the rate of measurement of the edge blocks,
is the measurement rate of texture blocks;
the measurement rate of different types of blocks can be obtained.
In one or more embodiments, the process of constructing the image block adaptive compressed sensing measurement matrix is as follows: random generation
Matrix array
Wherein each element obeys a standard Gaussian distribution; orthogonalizing a random matrix using Schmidt
Are mutually orthogonal; are respectively provided with
In random picking
、
、
Row, generate measurement matrix of flat, edge, texture block
、
And
。
and sampling the video image according to the previous steps, and then transmitting the observed quantity obtained by sampling to the master station, so that the transmitted data is greatly reduced, and the bandwidth pressure is well relieved.
As one or more embodiments, the master station reconstructs a video image by using the received sampling data, which comprises the following specific processes:
(1) using measurement matrices received by the master station
And of image blocksThe measured value reconstructs the image block to obtain an initial reconstructed imagey；
(2) Computing image blocks
Is self-correlation matrix of
Wherein,
representing image blocks
To (1) akThe number of the pixels is one, and the number of the pixels is one,
representing image blocks
To (1) alA plurality of pixels, each of which is a pixel,
representing a pixel
The spatial position of (a) of (b),
representing a pixel
The spatial position of (a) of (b),
in order to be a coefficient of correlation,
in order to obtain the Euclidean distance,
the autocorrelation matrix is expressed to obey exponential distribution, namely the larger the Euclidean distance is, the more uncorrelated is; flat block
Edge block
Texture block
。
(3) Calculating an estimation factor
Wherein,
a measurement matrix for the whole image, which may be composed of
The positions of the corresponding image blocks are combined.
In the traditional compressed sensing algorithm, image restoration is more than nonlinear estimation, but the reconstruction process comprises a large number of iterative algorithms. In the embodiment, the initial optimal image is obtained by utilizing a linear estimation algorithm based on the minimum mean square error, so that the calculated amount is reduced.
In the present embodiment, the obtained initial image blocks are paired by using linear estimation factorsyCorrecting to obtain the final reconstructed image
，
Is the final estimated image;xrepresenting an original image; so that the error of the reconstructed image from the original image is
(ii) a Thereby using the minimum mean square error method to solve
，
Solving when the derivative is equal to zero
。
(4) Calculate out
And a preliminary observed value y, by formula
And obtaining a linear estimation final image.
By adopting the calculation method provided by the embodiment, the power video monitoring image shown in fig. 3 (a) is reconstructed, and the reconstruction effect graph of the power video monitoring image shown in fig. 3 (b) is obtained, so that the algorithm of the embodiment can better reconstruct the power video monitoring image, the edge and texture information of the reconstructed image is rich, and meanwhile, the PSNR value (PSNR =31.2 dB) is higher, which fully indicates that the algorithm provided by the embodiment can meet the requirement of video monitoring analysis; in this embodiment, the PSNR represents a peak signal-to-noise ratio, which is a measure for image reconstruction quality, and it can be known through comparison that an image reconstructed by the reconstruction algorithm in this embodiment is valid. Through the remote sampling measurement, only the measured value is transmitted, the transmission data is greatly reduced, and the bandwidth is saved.
The embodiment aims at the problem that the traditional video monitoring image needs a coding and decoding algorithm in the transmission process, the application makes full use of the compression sensing algorithm to perform compression sampling on the video image, reduces the data dimensionality of image transmission to the maximum extent, reduces the calculation complexity in the compression process, concentrates a large amount of image data processing work to a data center station or a user side, and improves the bandwidth utilization rate of a transmission channel.
Example two
The second embodiment of the application introduces a power video monitoring image edge computing system based on compressed sensing.
A system for computing an edge of a power video surveillance image based on compressed sensing as shown in fig. 4 includes:
an acquisition module configured to acquire a power video monitoring image;
the blocking module is configured to perform blocking processing on the acquired power video monitoring images to obtain a plurality of image blocks with the same size;
the classification module is configured to extract image features of the obtained image blocks and classify the image blocks according to the extracted image features;
the computing module is configured to respectively construct an adaptive compressed sensing measurement matrix and an autocorrelation matrix of image blocks of different categories based on the classified image blocks; calculating an estimation factor of the image block according to the constructed measurement matrix and the autocorrelation matrix;
and the reconstruction module is configured to carry out combined reconstruction on the image blocks according to the obtained estimation factors and the measurement matrix of the image blocks.
The detailed steps are the same as those of the method for calculating the edge of the power video surveillance image based on compressed sensing provided in the first embodiment, and are not described herein again.
EXAMPLE III
The third embodiment of the application provides a computer-readable storage medium.
A computer readable storage medium, storing thereon a program, which when executed by a processor, implements the steps in the method for calculating the edge of the compressed sensing-based power video surveillance image according to the first embodiment of the present application.
The detailed steps are the same as those of the method for calculating the edge of the power video surveillance image based on compressed sensing provided in the first embodiment, and are not described herein again.
Example four
The fourth embodiment of the application provides electronic equipment.
An electronic device includes a memory, a processor, and a program stored in the memory and executable on the processor, where the processor executes the program to implement the steps in the method for calculating the edge of an electric power video surveillance image based on compressed sensing according to the first embodiment of the present application.
The detailed steps are the same as those of the method for calculating the edge of the power video surveillance image based on compressed sensing provided in the first embodiment, and are not described herein again.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Although the embodiments of the present application have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present application, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive effort by those skilled in the art.
Claims (10)
1. A method for calculating the edge of a power video monitoring image based on compressed sensing is characterized by comprising the following steps:
acquiring a power video monitoring image;
the method comprises the steps of performing blocking processing on an obtained power video monitoring image to obtain a plurality of image blocks with the same size;
extracting image features of the obtained image blocks, and classifying the image blocks according to the extracted image features;
respectively constructing self-adaptive compressed sensing measurement matrixes and self-correlation matrixes of image blocks of different classes based on the classified image blocks;
calculating an estimation factor of the image block according to the constructed measurement matrix and the autocorrelation matrix;
and merging and reconstructing the image blocks according to the obtained estimation factors and measurement matrixes of the image blocks.
2. The method as claimed in claim 1, wherein the size of the obtained edge is
The power video monitors the video image of the image and carries out block processing on the image, and the size of each block is
The images may be divided into non-overlapping ones
Blocking the small image; where m denotes the number of rows of dimensions, n denotes the number of columns of dimensions,
。
3. the method for calculating the edge of the power video surveillance image based on the compressed sensing as claimed in claim 1, wherein during the image feature extraction process of the obtained image blocks, the image blocks are divided into column vectors, the column vectors are converted, the variance of the converted column vectors is calculated, and the image features are extracted.
4. The method as claimed in claim 1, wherein the classification of the image blocks is based on the edge calculation of the power video surveillance image based on compressed sensing
Wherein,
is a firstiA column vector representation of the image block,
is as followsiThe variance of each image block is determined by the variance of each image block,
，
is the minimum value of the variance and is,
is the maximum value of the variance and is,
and
as a threshold, 0.1 and 0.3 are respectively taken according to experiments;
，
is the size of the image block,
is as followsiEach image blockjThe gray value of each pixel point is calculated,
is shown asiThe average value of all the pixel points of each image block,
。
5. the method as claimed in claim 1, wherein in the process of constructing the adaptive compressed sensing measurement matrix, the measurement rates of different types of image blocks are calculated according to the classified image blocks, the adaptive compressed sensing measurement matrix of the image blocks is constructed according to the obtained measurement rates, and the measurement matrix is stored and transmitted to the data center for storage.
6. The method as claimed in claim 1, wherein the autocorrelation matrix is a matrix of a compressed sensing-based edge calculation method for an electric video surveillance image
Is composed of
(ii) a Wherein,
representing image blocks
To (1) akA plurality of pixels, each of which is a pixel,
representing image blocks
To (1) alA plurality of pixels, each of which is a pixel,
representing a pixel
The spatial position of (a) of (b),
representing a pixel
The spatial position of (a) is determined,
in order to be a coefficient of correlation,
in order to obtain the Euclidean distance,
the autocorrelation matrix is shown to follow an exponential distribution, i.e., the larger the euclidean distance, the less correlated.
7. The power video monitoring image edge calculation method based on compressed sensing as claimed in claim 1, wherein an autocorrelation matrix is calculated by using image block position information according to the obtained estimation factors and measurement matrix of the image block, a linear estimation factor is solved according to the obtained autocorrelation matrix, the obtained initial image block is corrected by combining the obtained linear estimation factor to obtain a reconstructed image, and monitoring analysis of the image is completed.
8. A system for calculating the edge of a power video surveillance image based on compressed sensing is characterized by comprising the following components:
an acquisition module configured to acquire a power video monitoring image;
the blocking module is configured to perform blocking processing on the acquired power video monitoring images to obtain a plurality of image blocks with the same size;
the classification module is configured to extract image features of the obtained image blocks and classify the image blocks according to the extracted image features;
the computing module is configured to respectively construct an adaptive compressed sensing measurement matrix and an autocorrelation matrix of image blocks of different categories based on the classified image blocks; calculating an estimation factor of the image block according to the constructed measurement matrix and the autocorrelation matrix;
and the reconstruction module is configured to carry out merging reconstruction on the image blocks according to the obtained estimation factors and the measurement matrix of the image blocks.
9. A computer-readable storage medium, on which a program is stored, which, when being executed by a processor, carries out the steps of the method for calculating the edge of a compressed sensing-based power video surveillance image according to any one of claims 1 to 7.
10. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor implements the steps of the method for calculating the edge of an image for power video surveillance based on compressed sensing according to any one of claims 1-7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211330614.7A CN115393777A (en) | 2022-10-28 | 2022-10-28 | Electric power video monitoring image edge calculation method and system based on compressed sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211330614.7A CN115393777A (en) | 2022-10-28 | 2022-10-28 | Electric power video monitoring image edge calculation method and system based on compressed sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115393777A true CN115393777A (en) | 2022-11-25 |
Family
ID=84115004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211330614.7A Pending CN115393777A (en) | 2022-10-28 | 2022-10-28 | Electric power video monitoring image edge calculation method and system based on compressed sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115393777A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102568016A (en) * | 2012-01-03 | 2012-07-11 | 西安电子科技大学 | Compressive sensing image target reconstruction method based on visual attention |
| CN103338363A (en) * | 2013-03-06 | 2013-10-02 | 西安电子科技大学 | System and method for video compression sensing and encoding based on measurement domain block classification |
| CN104952039A (en) * | 2015-06-14 | 2015-09-30 | 中国电子科技集团公司第十研究所 | Distributed compressive sensing reconstruction method for images |
| CN105451019A (en) * | 2015-11-25 | 2016-03-30 | 中国地质大学（武汉） | Image compression transmission method facing wireless video sensor network |
| CN108521573A (en) * | 2018-04-16 | 2018-09-11 | 广东技术师范学院 | A kind of distributed video compressed sensing decoding method |
| CN110149516A (en) * | 2019-05-29 | 2019-08-20 | 东北石油大学 | A kind of compression sensing method of image, apparatus and system |
| CN114025118A (en) * | 2022-01-06 | 2022-02-08 | 广东电网有限责任公司中山供电局 | Low-bit-rate video reconstruction method and system, electronic equipment and storage medium |
| CN114143551A (en) * | 2021-12-01 | 2022-03-04 | 北京邮电大学 | Video safe and efficient transmission system applied to video sensor network |
-
2022
- 2022-10-28 CN CN202211330614.7A patent/CN115393777A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102568016A (en) * | 2012-01-03 | 2012-07-11 | 西安电子科技大学 | Compressive sensing image target reconstruction method based on visual attention |
| CN103338363A (en) * | 2013-03-06 | 2013-10-02 | 西安电子科技大学 | System and method for video compression sensing and encoding based on measurement domain block classification |
| CN104952039A (en) * | 2015-06-14 | 2015-09-30 | 中国电子科技集团公司第十研究所 | Distributed compressive sensing reconstruction method for images |
| CN105451019A (en) * | 2015-11-25 | 2016-03-30 | 中国地质大学（武汉） | Image compression transmission method facing wireless video sensor network |
| CN108521573A (en) * | 2018-04-16 | 2018-09-11 | 广东技术师范学院 | A kind of distributed video compressed sensing decoding method |
| CN110149516A (en) * | 2019-05-29 | 2019-08-20 | 东北石油大学 | A kind of compression sensing method of image, apparatus and system |
| CN114143551A (en) * | 2021-12-01 | 2022-03-04 | 北京邮电大学 | Video safe and efficient transmission system applied to video sensor network |
| CN114025118A (en) * | 2022-01-06 | 2022-02-08 | 广东电网有限责任公司中山供电局 | Low-bit-rate video reconstruction method and system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105451019B (en) | A kind of image compression transmission method towards wireless video sensor network | |
| CN115294409B (en) | Video processing method, system and medium for security monitoring | |
| CN107481293B (en) | Differential image compressed sensing reconstruction method based on multi-hypothesis weighting and intelligent terminal | |
| CN112365554A (en) | Compressed sensing image reconstruction method based on multi-scale residual error neural network | |
| CN104159003A (en) | Method and system of video denoising based on 3D cooperative filtering and low-rank matrix reconstruction | |
| CN112465727A (en) | Low-illumination image enhancement method without normal illumination reference based on HSV color space and Retinex theory | |
| CN107133992B (en) | Based on spectrum correlation adaptive grouping high spectrum image distributed associating compression method | |
| CN107085835B (en) | Color image filtering method based on quaternary number Weighted Kernel Norm minimum | |
| CN110827198A (en) | Multi-camera panoramic image construction method based on compressed sensing and super-resolution reconstruction | |
| CN106952317A (en) | Based on the high spectrum image method for reconstructing that structure is sparse | |
| Shen et al. | Joint sparse representation model for multi-channel image based on reduced geometric algebra | |
| CN108573509B (en) | Self-adaptive compressed sensing image coding method based on measurement domain significance detection model | |
| CN109003247B (en) | Method for removing color image mixed noise | |
| CN115393777A (en) | Electric power video monitoring image edge calculation method and system based on compressed sensing | |
| CN108521573A (en) | A kind of distributed video compressed sensing decoding method | |
| CN107707917B (en) | A kind of video adaptive sample rate setting method based on comentropy | |
| CN105160664B (en) | Compressed sensing video reconstruction method based on low-rank model | |
| Yuan-Yuan et al. | Discrete cosine transform optimization in image compression based on genetic algorithm | |
| CN115802038A (en) | Quantization parameter determination method and device and video coding method and device | |
| CN109934882A (en) | Based on the video compress sensing reconstructing methods for dynamically selecting more hypothesis match blocks | |
| Monika et al. | Perceptual variance weight matrix based adaptive block compressed sensing for marine image compression | |
| CN114926348A (en) | Device and method for removing low-illumination video noise | |
| CN111510719A (en) | Distributed compressed sensing coding and decoding method for video | |
| Feng et al. | Improvement of BM3D algorithm based on wavelet and directed diffusion | |
| CN102769751A (en) | Image encoding method based on directional block compressed sensing |
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: 20221125 |