CN108769586A - A kind of accurate monitoring system of monitoring - Google Patents
A kind of accurate monitoring system of monitoring Download PDFInfo
- Publication number
- CN108769586A CN108769586A CN201810542327.XA CN201810542327A CN108769586A CN 108769586 A CN108769586 A CN 108769586A CN 201810542327 A CN201810542327 A CN 201810542327A CN 108769586 A CN108769586 A CN 108769586A
- Authority
- CN
- China
- Prior art keywords
- image
- noise
- module
- video
- subsystem
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention provides a kind of accurate monitoring systems of monitoring, including smart home Monitor And Control Subsystem, safety monitoring subsystem and early warning subsystem, the smart home Monitor And Control Subsystem is used to acquire the operation data of smart home, and send it to early warning subsystem, the safety monitoring subsystem is for acquiring indoor monitor video and sending it to early warning subsystem, the early warning subsystem includes household warning module and security protection warning module, the normal operation data that the household warning module is used for the operation data according to the smart home received and prestores are compared, judge it whether normal operation, early warning is sent out if operation exception, the security protection warning module according to Indoor Video video for being monitored in real time, early warning is sent out when being abnormal.Beneficial effects of the present invention are：A kind of accurate monitoring system of monitoring is provided, by smart home data and indoor video image acquisition, realizing smart home and Indoor Video.
Description
Technical field
The present invention relates to monitoring technology fields, and in particular to a kind of accurate monitoring system of monitoring.
Background technology
Image procossing refers to the key technology that information is extracted from image, is had extensively in the various aspects such as industry and life
Application, such as agricultural production, oil exploration, biomedicine field.Image denoising is as the basic task in image procossing
Image analysis and understanding provide solid foundation.In image acquisition, compression, transmission stage, since environment, transmission channel etc. are more
The influence of kind factor, image can be interfered by noise, and image information is made to lose, and generate distortion.The image of distortion is carried out
Processing, will certainly influence image procossing as a result, reduces the accuracy of extraction information, and then interferes the various judgements made accordingly
And decision.Image denoising is to remove noise jamming from noise-containing picture signal, to recover image actual signal,
And then ensure the accuracy of further image processing and analysis result.
How core technology of the image procossing as monitoring system, treatment effect directly influence the performance of monitoring system.
Invention content
In view of the above-mentioned problems, the present invention is intended to provide a kind of accurate monitoring system of monitoring.
The purpose of the present invention is realized using following technical scheme：
Provide a kind of accurate monitoring system of monitoring, including smart home Monitor And Control Subsystem, safety monitoring subsystem and
Early warning subsystem, the smart home Monitor And Control Subsystem are used to acquire the operation data of smart home, and send it to early warning
Subsystem, the safety monitoring subsystem are described pre- for acquiring indoor monitor video and sending it to early warning subsystem
Alert subsystem includes household warning module and security protection warning module, and the household warning module is used for according to the intelligent family received
The operation data in residence and the normal operation data to prestore are compared, and judge that it whether normal operation, sends out if operation exception
Early warning, the security protection warning module send out early warning for being monitored in real time according to Indoor Video video when being abnormal.
Beneficial effects of the present invention are：Provide a kind of accurate monitoring system of monitoring, by smart home data and
Indoor video image acquisition, realizes smart home and Indoor Video.
Description of the drawings
Using attached drawing, the invention will be further described, but the embodiment in attached drawing does not constitute any limit to the present invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the structural schematic diagram of the present invention；
Reference numeral：
Smart home Monitor And Control Subsystem 1, safety monitoring subsystem 2, early warning subsystem 3.
Specific implementation mode
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of accurate monitoring system of monitoring of the present embodiment, including smart home Monitor And Control Subsystem 1, security protection
Monitor And Control Subsystem 2 and early warning subsystem 3, the smart home Monitor And Control Subsystem 1 are used to acquire the operation data of smart home, and
Early warning subsystem 3 is sent it to, the safety monitoring subsystem 2 is for acquiring indoor monitor video and sending it to pre-
Alert subsystem 3, the early warning subsystem 3 include household warning module and security protection warning module, and the household warning module 3 is used for
It is compared according to the operation data of the smart home received and the normal operation data to prestore, judges whether it normally transports
Row, sends out early warning if operation exception, and the security protection warning module occurs for being monitored in real time according to Indoor Video video
Early warning is sent out when abnormal.
A kind of accurate monitoring system of monitoring is present embodiments provided, by smart home data and indoor video image
Acquisition, realizes smart home and Indoor Video.
Preferably, the safety monitoring subsystem 2 includes off-the-air picture acquisition module, modeling module, denoising module, evaluation
Module and memory module, the off-the-air picture acquisition module is for obtaining indoor video image, and the modeling module is for establishing
Noise of video image model, the denoising module is for being removed noise of video image according to noise model, the evaluation
Module for evaluating the denoising effect of denoising module, the memory module be used for the video image after removal noise into
Row storage.
The modeling module is for establishing noise of video image model：
Noise of video image model is expressed as by each frame image in video sequence as an image block：CA=PL+
GW+M；
In above-mentioned formula, PL indicates the clean image array of not Noise, PL={ f1,f2,…,fl},fiIt indicates i-th
Clean image block, l indicate that number of image frames, i=1,2 ..., l, GW indicate impulsive noise matrix, GW={ n1,n2,…,nl, niTable
Show fiCorresponding impulsive noise, i=1,2 ..., l, M indicate Gaussian noise matrix, M={ m1,m2,…,ml, miIndicate fiIt is corresponding
Gaussian noise, i=1,2 ..., l, CA be noise-containing image array, CA={ h1,h2,…,hl, hiIndicate fiIt is corresponding
Noise-containing image, i=1,2 ..., l；
Video is the ordered sequence of several images, and the algorithm of existing removal impulsive noise is carried out both for single image
, the time redundancy that vision signal itself has is ignored, when this results in the impulsive noise in existing algorithm removal video
Inefficiency, this preferred embodiment modeling module using each image that inclines as an image block, and in video it is adjacent detect between
There is internal structure similitude again, constitute similar image block each other, modeling in this way does not have to the size for determining image block not only,
The measurement for also avoiding similitude, to help to reduce the interference of noise.
Preferably, the denoising module includes the first processing submodule and second processing submodule, the first processing
Module is used for for removing video image Gaussian noise, the second processing submodule to the video image after removal Gaussian noise
It is handled, removes video image impulsive noise；The first processing submodule is for removing video image Gaussian noise：To every
Frame image removes Gaussian noise, obtains the video image after removal Gaussian noise：KW=PL+GW；
In above-mentioned formula, KW is the only image array containing impulsive noise, KW={ s1,s2,…,sl, siIndicate fiIt is corresponding
The only image containing impulsive noise, i=1,2 ..., l；
The second processing submodule is used to handle the video image after removal Gaussian noise, removes video image
Impulsive noise：
Video sequence containing l frames is divided into l groups, to each frame image, centered on the image, front and back each n frames image
As the similar image block of the image, the similar image block is ranked sequentially composition matrix, the rank of matrix is minimized, obtains
One handling result of the image, since 2n+1 result can be carried out simple weighted average by every frame image by processing 2n+1 times
The result after impulsive noise is removed as the image；It seeks after all frame image removal impulsive noises as a result, obtaining removal arteries and veins
Rush the video image TZ after noise：TZ={ z1,z2,…,zl},ziIndicate that the image after i-th of removal impulsive noise, l indicate figure
As frame number, i=1,2 ..., l.
Structure is similar between adjacent image, this is the redundancy of time of video, if muting video image is formed
One matrix, then the matrix has low-rank.And the matrix that the video image with noise is constituted is exactly the low-rank matrix part
The matrix of the contaminated degeneration of element, removal video noise seek to recover low-rank matrix from the matrix of degeneration.This is preferably
Embodiment second processing submodule is for every frame image, by minimizing rank of matrix, and to handling result simply add
Weight average has obtained the video image after image removal impulsive noise, has handled all frame images, obtained removal arteries and veins
Rush the video image after noise.
Preferably, the evaluation module is for evaluating the denoising effect of denoising module：
Evaluation points are defined with following formula：
In above-mentioned formula, HX indicates evaluation points,The image z after removal salt-pepper noise is indicated respectivelyiWith without
The clean image f of noiseiAverage brightness,The image z after removal salt-pepper noise is indicated respectivelyiNot Noise
Clean image fiBrightness variance,Indicate the image z after removal salt-pepper noiseiThe not clean image f of Noisei's
Luminance standard is poor, and PSNR indicates the image z after removal salt-pepper noiseiThe not clean image f of NoiseiY-PSNR；Institute
It states that evaluation points are bigger, indicates that the denoising effect of described image denoising module is better.
Weigh whether denoising effect reaches expected, if noise remove is clean, if to cause fuzzy etc..Subjective assessment
In close relations with estimator itself, the possible otherness of evaluation conclusion that different observers obtains is very big.This preferred embodiment is logical
Definition evaluation points are crossed to evaluate denoising effect, fully considered denoising image Y-PSNR and denoising image with
The structural similarity of original image realizes the accurate evaluation of noise remove effect, and it is different to overcome estimator in subjective assessment
Caused evaluation difference.
Monitor accurate monitoring system using the present invention to be monitored, choose 5 families and tested, respectively family 1,
Family 2, family 3, family 4, family 5 count household early warning accuracy rate and security protection early warning accuracy rate, are compared with monitoring
System is compared, and generation has the beneficial effect that shown in table：
| Household early warning accuracy rate improves | Security protection early warning accuracy rate improves | |
| Family 1 | 29% | 27% |
| Family 2 | 27% | 26% |
| Family 3 | 26% | 26% |
| Family 4 | 25% | 24% |
| Family 5 | 24% | 22% |
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although being explained in detail to the present invention with reference to preferred embodiment, the ordinary skill family of this field answers
Work as understanding, technical scheme of the present invention can be modified or replaced equivalently, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of accurate monitoring system of monitoring, which is characterized in that including smart home Monitor And Control Subsystem, safety monitoring subsystem
With early warning subsystem, the smart home Monitor And Control Subsystem is used to acquire the operation data of smart home, and sends it to pre-
Alert subsystem, the safety monitoring subsystem are described for acquiring indoor monitor video and sending it to early warning subsystem
Early warning subsystem includes household warning module and security protection warning module, and the household warning module is used for according to the intelligence received
The operation data of household and the normal operation data to prestore are compared, and judge that it whether normal operation, sends out if operation exception
Go out early warning, the security protection warning module sends out early warning for being monitored in real time according to Indoor Video video when being abnormal.
2. the accurate monitoring system of monitoring according to claim 1, which is characterized in that the safety monitoring subsystem includes
Off-the-air picture acquisition module, modeling module, denoising module, evaluation module and memory module, the off-the-air picture acquisition module are used
In obtaining indoor video image, the modeling module is used for basis for establishing noise of video image model, the denoising module
Noise model is removed noise of video image, and the evaluation module is used to evaluate the denoising effect of denoising module,
The memory module is used to store the video image after removal noise.
3. the accurate monitoring system of monitoring according to claim 2, which is characterized in that the modeling module is regarded for establishing
Frequency image noise model：
Noise of video image model is expressed as by each frame image in video sequence as an image block：CA=PL+GW+
M；
In above-mentioned formula, PL indicates the clean image array of not Noise, PL={ f1, f2..., fl, fiIndicate i-th of clean figure
As block, l indicates that number of image frames, i=1,2 ..., l, GW indicate impulsive noise matrix, GW={ n1, n2..., nl, niIndicate fiIt is right
The impulsive noise answered, i=1,2 ..., l, M indicate Gaussian noise matrix, M={ m1, m2..., ml, miIndicate fiCorresponding Gauss
Noise, i=1,2 ..., l, CA are noise-containing image array, CA={ h1, h2..., hl, hiIndicate fiIt is corresponding containing making an uproar
The image of sound, i=1,2 ..., l.
4. the accurate monitoring system of monitoring according to claim 3, which is characterized in that the denoising module includes at first
Manage submodule and second processing submodule, the first processing submodule is for removing video image Gaussian noise, and described second
Processing submodule is used to handle the video image after removal Gaussian noise, removes video image impulsive noise；Described
One processing submodule is for removing video image Gaussian noise：Gaussian noise is removed to every frame image, obtains removal Gaussian noise
Video image afterwards：KW=PL+GW；
In above-mentioned formula, KW is the only image array containing impulsive noise, KW={ s1, s2..., sl, siIndicate fiIt is corresponding only
Image containing impulsive noise, i=1,2 ..., l.
5. the accurate monitoring system of monitoring according to claim 4, which is characterized in that the second processing submodule is used for
Video image after removal Gaussian noise is handled, video image impulsive noise is removed：
Video sequence containing l frames is divided into l groups, to each frame image, centered on the image, front and back each n frames image conduct
The similar image block is ranked sequentially composition matrix, minimizes the rank of matrix, obtain the figure by the similar image block of the image
One handling result of picture, due to every frame image can by processing 2n+1 time, using 2n+1 result progress simple weighted average as
The image removes the result after impulsive noise；It seeks after all frame images removal impulsive noises making an uproar as a result, obtaining removal pulse
Video image TZ after sound：TZ={ z1, z2..., zl, ziIndicate that the image after i-th of removal impulsive noise, l indicate picture frame
Number, i=1,2 ..., l.
6. the accurate monitoring system of monitoring according to claim 5, which is characterized in that the evaluation module is used for denoising
The denoising effect of module is evaluated：
Evaluation points are defined with following formula：
In above-mentioned formula, HX indicates evaluation points,The image z after removal salt-pepper noise is indicated respectivelyiNot Noise
Clean image fiAverage brightness,The image z after removal salt-pepper noise is indicated respectivelyiNoise is unclean
Image fiBrightness variance,Indicate the image z after removal salt-pepper noiseiThe not clean image f of NoiseiBrightness scale
Accurate poor, PSNR indicates the image z after removal salt-pepper noiseiThe not clean image f of NoiseiY-PSNR；The evaluation
The factor is bigger, indicates that the denoising effect of described image denoising module is better.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810542327.XA CN108769586A (en) | 2018-05-30 | 2018-05-30 | A kind of accurate monitoring system of monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810542327.XA CN108769586A (en) | 2018-05-30 | 2018-05-30 | A kind of accurate monitoring system of monitoring |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108769586A true CN108769586A (en) | 2018-11-06 |
Family
ID=64004445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810542327.XA Pending CN108769586A (en) | 2018-05-30 | 2018-05-30 | A kind of accurate monitoring system of monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108769586A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111444857A (en) * | 2020-03-30 | 2020-07-24 | 国网河北省电力有限公司沧州供电分公司 | Unmanned aerial vehicle inspection data processing method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140015921A1 (en) * | 2012-07-16 | 2014-01-16 | Noiseless Imaging Oy Ltd. | Methods and systems for suppressing noise in images |
| CN104754183A (en) * | 2015-04-10 | 2015-07-01 | 四川理工学院 | Real-time monitoring video adaptive filtering method and real-time monitoring video adaptive filtering system |
| CN106406115A (en) * | 2016-10-31 | 2017-02-15 | 安徽汇顿电子科技有限公司 | PLC-based intelligent household remote monitoring system |
| CN107040767A (en) * | 2017-05-18 | 2017-08-11 | 上海为然环保科技有限公司 | A kind of intelligent household security system |
| CN107241243A (en) * | 2017-06-07 | 2017-10-10 | 梧州市兴能农业科技有限公司 | Smart home safety monitoring system |
| CN107770498A (en) * | 2017-11-06 | 2018-03-06 | 龚土婷 | A kind of efficient security protection patrol device |
| CN107895503A (en) * | 2017-11-07 | 2018-04-10 | 钟永松 | A kind of unattended parking farm monitoring system |
-
2018
- 2018-05-30 CN CN201810542327.XA patent/CN108769586A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140015921A1 (en) * | 2012-07-16 | 2014-01-16 | Noiseless Imaging Oy Ltd. | Methods and systems for suppressing noise in images |
| CN104754183A (en) * | 2015-04-10 | 2015-07-01 | 四川理工学院 | Real-time monitoring video adaptive filtering method and real-time monitoring video adaptive filtering system |
| CN106406115A (en) * | 2016-10-31 | 2017-02-15 | 安徽汇顿电子科技有限公司 | PLC-based intelligent household remote monitoring system |
| CN107040767A (en) * | 2017-05-18 | 2017-08-11 | 上海为然环保科技有限公司 | A kind of intelligent household security system |
| CN107241243A (en) * | 2017-06-07 | 2017-10-10 | 梧州市兴能农业科技有限公司 | Smart home safety monitoring system |
| CN107770498A (en) * | 2017-11-06 | 2018-03-06 | 龚土婷 | A kind of efficient security protection patrol device |
| CN107895503A (en) * | 2017-11-07 | 2018-04-10 | 钟永松 | A kind of unattended parking farm monitoring system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111444857A (en) * | 2020-03-30 | 2020-07-24 | 国网河北省电力有限公司沧州供电分公司 | Unmanned aerial vehicle inspection data processing method |
| CN111444857B (en) * | 2020-03-30 | 2022-11-15 | 国网河北省电力有限公司沧州供电分公司 | Unmanned aerial vehicle inspection data processing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200118251A1 (en) | Moran's i for impulse noise detection and removal in color images | |
| Harikiran et al. | Impulse noise removal in digital images | |
| CN111199018B (en) | Abnormal data detection method and device, storage medium and electronic equipment | |
| DE102010024666A1 (en) | Method for optical self-diagnosis of a camera system and apparatus for carrying out such a method | |
| CN111654700B (en) | Privacy mask processing method and device, electronic equipment and monitoring system | |
| CN109670398A (en) | Pig image analysis method and pig image analysis equipment | |
| KR102101623B1 (en) | Method and apparatus for detecting informal situation using image | |
| JP4519323B2 (en) | Video signal quality analysis | |
| CN108830829B (en) | Non-reference quality evaluation algorithm combining multiple edge detection operators | |
| CN113963213A (en) | Method and system for removing antagonistic noise aiming at antagonistic sample of deep neural network | |
| Limshuebchuey et al. | Comparison of image denoising using traditional filter and deep learning methods | |
| CN108769586A (en) | A kind of accurate monitoring system of monitoring | |
| Freeman et al. | Dealing with non-equilibrium bias and survey effort in presence-only invasive Species Distribution Models (iSDM); Predicting the range of muntjac deer in Britain and Ireland | |
| CN110751667A (en) | Method for detecting infrared dim small target under complex background based on human visual system | |
| Bhateja et al. | Reduced reference IQA based on structural dissimilarity | |
| Anwar et al. | A neural network approach to edge detection using adaptive neuro-fuzzy inference system | |
| Bhateja et al. | A reduced reference distortion estimation measure for color images | |
| CN108694706A (en) | A kind of video image denoising system | |
| AKINTOYE et al. | COMPOSITE MEDIAN WIENER FILTER BASED TECHNIQUE FOR IMAGE ENHANCEMENT. | |
| Priego et al. | A cellular automata‐based filtering approach to multi‐temporal image denoising | |
| Tanaka et al. | A study on inter-frame differencing for compressed moving images | |
| Ghosh et al. | To Analysis and Implement Image De-Noising Using Fuzzy and Wiener Filter in Wavelet Domain | |
| CN117011288B (en) | Video quality diagnosis method and system | |
| CN108765348A (en) | A kind of pilotless automobile | |
| Li et al. | GRGAL: A Grey Relational Generative Adversarial Learning Method for Image Denoising. |
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 |
Application publication date: 20181106 |
|
| RJ01 | Rejection of invention patent application after publication |