CN106131545A - A kind of picture quality inspection device and method - Google Patents
A kind of picture quality inspection device and method Download PDFInfo
- Publication number
- CN106131545A CN106131545A CN201610648120.1A CN201610648120A CN106131545A CN 106131545 A CN106131545 A CN 106131545A CN 201610648120 A CN201610648120 A CN 201610648120A CN 106131545 A CN106131545 A CN 106131545A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- picture quality
- controller
- dvr
- 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
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/04—Diagnosis, testing or measuring for television systems or their details for receivers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to monitoring field, disclose a kind of picture quality inspection device, including DVR, video server, controller, Web server and data base, DVR connects video server, video server connects controller, and controller connects Web server, and Web server connects data base, controller includes dispatching scheduler module and analysis process module, and analysis process module includes that colour cast module, image definition evaluation module, image block module and picture noise detection module.Technique scheme is used to be made for a kind of picture quality inspection device that can monitor in real time.Picture quality inspection device and method can be arranged the distinct device in network by demand, and select the passage in equipment to be monitored.Can accomplish arrange the different number of times of detection every day or key scenes carries out uninterruptedly detection in 7x24 hour for monitor task.
Description
Technical field
The present invention relates to monitoring field, particularly to a kind of picture quality inspection device and method.
Background technology
Along with the high speed development of computer, multimedia and data communication technology, Digital Image Processing has obtained pole in recent years
Big attention and significant progress, and achieve in safety, commercial production, health care, Edutainment, management and communication aspects
It is widely applied.Field is used for DVR (i.e. DVR) to the overwhelming majority, IP images first-class digital monitoring device.
But how to ensure that these monitoring devices are properly functioning and DVR disk can have sufficient space to preserve video file, become urgently
Problem to be solved.Present bank and national treasury Surveillance center use the mode of manpower monitoring, allow monitoring personnel in the face of timing for cutting
Change the video wall of picture, check in the way of naked eyes, but in the face of the monitored picture day by day increased, cannot by perusal
Tackle the change of multi-channel video simultaneously, and manpower also cannot accomplish continuous monitoring in 24 hours.
Summary of the invention
In order to solve the problems referred to above, the present invention provides a kind of picture quality inspection device that can monitor in real time and side
Method.
A kind of picture quality inspection device in the present invention, including DVR, video server, controller, Web clothes
Business device and data base, described DVR connects video server, and described video server connects controller, described controller
Connecting Web server, described Web server connects data base, and described controller includes dispatching scheduler module and analysis process mould
Block, described analysis process module includes that colour cast module, image definition evaluation module, image block module and picture noise detection
Module.
In such scheme, also including photographic head, described photographic head connects DVR.
A kind of method of picture quality inspection device, comprises the following steps:
S1:Web server arranges parameter；
The content of S2: photographic head production is stored in DVR；
S3: controller issues instructions to video server by scheduling scheduler module, transfers the hard disk record of predetermined amount of time
The content of camera；
S4: video enters analysis process module and carries out image procossing and judgement；
S5: judge that image is whether normal, be to turn S6, non-turns S7；
S6: video enters Web server, turns S8；
S7: send early warning, turns S6；
S8: video enters database purchase.
In such scheme, described S5 carries out colour cast process, it is judged that image colour cast degree.
In such scheme, described S5 carries out image definition process, it is judged that image is the most clear.
In such scheme, described S5 carries out image and blocks process, it is judged that whether image is blocked.
In such scheme, described S5 carries out picture noise detection, it is judged that whether image has noise.
In such scheme, the detection of described picture noise comprises the following steps:
The pretreatment of S10: target image；
The filtration of S11: continuous profile；
S12: calculate Local standard deviation；
S13: based on histogrammic Noise Variance Estimation.
Advantages of the present invention and having the beneficial effects that: the present invention provides a kind of picture quality that can monitor in real time to patrol and examine dress
Put and method.Picture quality inspection device and method can be arranged the distinct device in network by demand, and select equipment
In passage be monitored.Can accomplish arrange the different number of times of detection every day or key scenes is carried out for monitor task
Uninterruptedly detection in 7x24 hour.Picture freeze, brightness that video image can be occurred by system according to setting prediction scheme are abnormal, signal lacks
The multiple abnormal shape such as mistake, video displacement, snow, video shelter, banding ripple, shake, roll screen, fuzzy, colour cast, scene change
State diagnoses automatically；Several duties such as the network condition of video equipment, Disk State are carried out detection analyze.Decrease
Artificially judge equipment state and the human cost of picture quality and time.It is applicable to any containing multiple video storaging equipments
Network, wide market.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, also may be used
To obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the system block diagram of the present invention；
Fig. 2 is the flow chart of the present invention.
In figure: 1, DVR 2, video server 3, controller 31, scheduling scheduler module 32, analysis process mould
Block 321, colour cast module 322, image definition evaluation module 323, image block module 324, picture noise detection module
4, Web server 5, data base 6, photographic head
Detailed description of the invention
Below in conjunction with the accompanying drawings and embodiment, the detailed description of the invention of the present invention is further described.Following example are only
For technical scheme is clearly described, and can not limit the scope of the invention with this.
As it is shown in figure 1, the present invention is a kind of picture quality inspection device, including DVR 1, video server 2, control
Device 3 processed, Web server 4 and data base 5, DVR 1 connects video server 2, and video server 2 connects controller 3,
Controller 3 connects Web server 4, and Web server 4 connects data base 5, controller 3 include dispatching scheduler module 31 and analyze into
Journey module 32, analysis process module 32 includes that colour cast module 321, image definition evaluation module 322, image block module 323
With picture noise detection module 324.Also include that photographic head 6, photographic head 6 connect DVR.
As in figure 2 it is shown, a kind of method of picture quality inspection device, comprise the following steps:
S1:Web server arranges parameter；
The content of S2: photographic head production is stored in DVR；
S3: controller issues instructions to video server by scheduling scheduler module, transfers the hard disk record of predetermined amount of time
The content of camera；
S4: video enters analysis process module and carries out image procossing and judgement；
S5: judge that image is whether normal, be to turn S6, non-turns S7；
S6: video enters Web server, turns S8；
S7: send early warning, turns S6；
S8: video enters database purchase.
Wherein, S5 can make the following judgment: 1, carries out colour cast process, it is judged that image colour cast degree；This algorithm uses CIE
LAB color space replaces RGB color to add up image chroma, and the RGB color of image is that one is the simplest
Single color space, being limited in that when portraying the difference between two kinds of colors by Euclidean distance of its maximum, calculated
Between the two kinds of colors gone out away from the real difference that cannot correctly characterize between people's both colors of being perceived of reality.Adopt
With CIE Lab color space, the distance between the color that this space is calculated is basic with the difference in human eye actual perceived
Unanimously.Colour cast image can be carried out under CIE Lab with objective direct reflection image colour cast degree by histogrammic statistics
Automatically detection is the most reasonable.
2, image definition process is carried out, it is judged that image is the most clear；In the quality evaluation of non-reference picture, image
Definition is to weigh the important indicator that picture quality is good and bad, and it can be preferably corresponding with the subjective feeling of people, image clear
Clear degree is the highest shows the fuzzy of image.
Algorithm uses 4 kinds of sharpness evaluation functions to differentiate image is the fuzzyyest: Tenengrad evaluation function,
Laplacian evaluation function, SMD2 (gray variance product) evaluation function, EAV point acutance evaluation function, by from the ladder of image
Degree, rate of gray level, and the mode that energy 3 aspect is comprehensive, provide corresponding testing result to image is the fuzzyyest.
3, carry out image and block process, it is judged that whether image is blocked；Blocking is the universal phenomenon in real life, when one
When individual object is at least partially obscured, the object that is blocked is difficult to be detected.For solving to change situation, algorithm have employed image block and calculates
Method, in this method, target is represented as the set of feature and correspondence position (referred to as topology).Local is tied by this algorithm with entirety
Close, it is possible to more effectively solve the situation that partial occlusion cannot detect.
4, picture noise detection is carried out, it is judged that whether image has noise.Snow noise be a kind of common picture noise it
One.It is, in general, that isolate single fall analysis function and noise function from an image having fall analysis function and noise function
Being unlikely that, therefore picture noise is estimated by algorithm by following four step:
The pretreatment of S10: target image, respectively at x, it is basic that y direction uses that simple gradient operator removes in image
Information and leave profile information and noise information；
The filtration of S11: continuous profile, in order to remove the continuous part in residual information, uses connected graph method to continuous print
Side information is tracked, and the profile information in image and marginal information are successfully carried out by suitable contour following algorithm of sampling
Filter；
S12: calculate Local standard deviation, after above-mentioned process, remaining mainly noise information and the most discrete
" residual error " information, can obtain the local variance of original image for this, and concrete grammar is to be carried out once by a template and image
Process of convolution is additionally, due to zones of different average gray difference is different, even if the overall average gray value of target image is zero also
The Noise Estimation of image is produced bigger error, therefore when estimating noise variance, will carry out for the local pixel in image
Individually consider；
S13: based on histogrammic Noise Variance Estimation, histogram treatment occupies an important position in image procossing.Warp
Obtain a distribution about picture noise estimated value after crossing above-mentioned steps, it include noise figure to maximum noise value and
The frequency occurred.Thus can accurately estimate the accounting of noise in image.S5 can also be as required to above 4 kinds
Judge be optionally combined and then judge.
System hardware is based on X86-based, and for the existing scheme analyzed based on DSP, hardware performance is with the obvious advantage,
The concurrent quantity that can simultaneously support is more, and can upgrade algorithm in time thus obtain the lifting of performance.And it is right
The equipment such as DVR, the IPC in current main flow, X86 scheme can based on mainstream vendor provide SDK develop, the efficiency of exploitation
Height is wanted with the compatibility relatively DSP scheme of hardware.
The picture freeze of video image appearance, brightness exception, signal deletion, video can be moved by system according to setting prediction scheme
The multiple abnormality such as position, snow, video shelter, banding ripple, shake, roll screen, fuzzy, colour cast, scene change is carried out certainly
Dynamic diagnosis；Several duties such as the network condition of video equipment, Disk State are carried out detection analyze.Decrease and artificially sentence
Disconnected equipment state and the human cost of picture quality and time.It is applicable to any network containing multiple video storaging equipments, city
Field has a extensive future.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all essences in the present invention
Within god and principle, any modification, equivalent substitution and improvement etc. made, should be included within the scope of the present invention.
Claims (8)
1. a picture quality inspection device, it is characterised in that include that DVR, video server, controller, Web take
Business device and data base, described DVR connects video server, and described video server connects controller, described controller
Connecting Web server, described Web server connects data base, and described controller includes dispatching scheduler module and analysis process mould
Block, described analysis process module includes that colour cast module, image definition evaluation module, image block module and picture noise detection
Module.
A kind of picture quality inspection device the most according to claim 1, it is characterised in that also include photographic head, described in take the photograph
As head connects DVR.
The method of a kind of picture quality inspection device the most according to claim 2, it is characterised in that comprise the following steps:
S1:Web server arranges parameter；
The content of S2: photographic head production is stored in DVR；
S3: controller issues instructions to video server by scheduling scheduler module, transfers the DVR of predetermined amount of time
Content；
S4: video enters analysis process module and carries out image procossing and judgement；
S5: judge that image is whether normal, be to turn S6, non-turns S7；
S6: video enters Web server, turns S8；
S7: send early warning, turns S6；
S8: video enters database purchase.
A kind of picture quality method for inspecting the most according to claim 3, it is characterised in that described S5 carries out colour cast process,
Judge image colour cast degree.
A kind of picture quality method for inspecting the most according to claim 3, it is characterised in that described S5 carries out image definition
Process, it is judged that image is the most clear.
A kind of picture quality method for inspecting the most according to claim 3, it is characterised in that described S5 carries out image and blocks place
Reason, it is judged that whether image is blocked.
A kind of picture quality method for inspecting the most according to claim 3, it is characterised in that described S5 carries out picture noise inspection
Survey, it is judged that whether image has noise.
A kind of picture quality method for inspecting the most according to claim 7, it is characterised in that the detection of described picture noise includes
Following steps:
The pretreatment of S10: target image；
The filtration of S11: continuous profile；
S12: calculate Local standard deviation；
S13: based on histogrammic Noise Variance Estimation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610648120.1A CN106131545A (en) | 2016-08-09 | 2016-08-09 | A kind of picture quality inspection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610648120.1A CN106131545A (en) | 2016-08-09 | 2016-08-09 | A kind of picture quality inspection device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106131545A true CN106131545A (en) | 2016-11-16 |
Family
ID=57257480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610648120.1A Pending CN106131545A (en) | 2016-08-09 | 2016-08-09 | A kind of picture quality inspection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106131545A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819015A (en) * | 2021-02-04 | 2021-05-18 | 西南科技大学 | Image quality evaluation method based on feature fusion |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103260049A (en) * | 2013-04-23 | 2013-08-21 | 四川天翼网络服务有限公司 | Intelligent skynet video quality diagnostic system |
| CN105323565A (en) * | 2015-12-11 | 2016-02-10 | 国网浙江桐乡市供电公司 | Intelligent video fault analysis and pre-warning system of transformer substation |
| CN105610642A (en) * | 2015-12-22 | 2016-05-25 | 海南电网有限责任公司 | Intelligent scheduling and fault result displaying method for video quality diagnosis of transformer substation |
-
2016
- 2016-08-09 CN CN201610648120.1A patent/CN106131545A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103260049A (en) * | 2013-04-23 | 2013-08-21 | 四川天翼网络服务有限公司 | Intelligent skynet video quality diagnostic system |
| CN105323565A (en) * | 2015-12-11 | 2016-02-10 | 国网浙江桐乡市供电公司 | Intelligent video fault analysis and pre-warning system of transformer substation |
| CN105610642A (en) * | 2015-12-22 | 2016-05-25 | 海南电网有限责任公司 | Intelligent scheduling and fault result displaying method for video quality diagnosis of transformer substation |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819015A (en) * | 2021-02-04 | 2021-05-18 | 西南科技大学 | Image quality evaluation method based on feature fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100596192C (en) | An intelligent digital system based on video and its processing method | |
| US8712149B2 (en) | Apparatus and method for foreground detection | |
| CN102348128B (en) | Surveillance camera system having camera malfunction detection function | |
| CN106373123B (en) | Industrial component detection method of surface flaw based on k_tSL central cluster algorithm | |
| CN102413356B (en) | Detecting system for video definition and detecting method thereof | |
| CN109670441A (en) | A kind of realization safety cap wearing knows method for distinguishing, system, terminal and computer readable storage medium | |
| CN104394377B (en) | A kind of fuzzy abnormal recognition methods of monitoring image and device | |
| CN102176758A (en) | Video quality diagnosis system and realization method thereof | |
| CN111898486B (en) | Monitoring picture abnormality detection method, device and storage medium | |
| CN102740121B (en) | Be applied to video quality diagnostic control system and the method for video surveillance network | |
| JP5087112B2 (en) | Self-monitoring camera device | |
| CN110348343A (en) | A kind of act of violence monitoring method, device, storage medium and terminal device | |
| CN101420593A (en) | Image comparison method detects the method for operating state of cloud platform video camera | |
| CN109509190A (en) | Video monitoring image screening technique, device, system and storage medium | |
| CN110826522A (en) | Method and system for monitoring abnormal human behavior, storage medium and monitoring equipment | |
| CN109151463B (en) | Video quality diagnosis system and video quality analysis method | |
| CN105554494B (en) | Snow point image detecting method and device and video quality detection device and system | |
| CN111223011A (en) | Food safety supervision method and system for catering enterprises based on video analysis | |
| CN108460319A (en) | Abnormal face detecting method and device | |
| CN106131545A (en) | A kind of picture quality inspection device and method | |
| KR102040562B1 (en) | Method to estimate visibility distance using image information | |
| CN109255793B (en) | A kind of monitoring early-warning system of view-based access control model feature | |
| CN206364953U (en) | A kind of picture quality inspection device | |
| CN107085845A (en) | Image blurring detection method and device | |
| CN106101696B (en) | Video quality diagnosis system and video quality analysis algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161116 |
|
| RJ01 | Rejection of invention patent application after publication |