CN107248160A - Video monitoring image distortion detection method and system - Google Patents
Video monitoring image distortion detection method and system Download PDFInfo
- Publication number
- CN107248160A CN107248160A CN201710400296.XA CN201710400296A CN107248160A CN 107248160 A CN107248160 A CN 107248160A CN 201710400296 A CN201710400296 A CN 201710400296A CN 107248160 A CN107248160 A CN 107248160A
- Authority
- CN
- China
- Prior art keywords
- picture
- video monitoring
- picture quality
- value
- quality value
- 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.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 58
- 238000001514 detection method Methods 0.000 title claims abstract description 43
- 101100316754 Arabidopsis thaliana VAL3 gene Proteins 0.000 claims description 11
- 101100316753 Arabidopsis thaliana VAL2 gene Proteins 0.000 claims description 7
- 101100316752 Arabidopsis thaliana VAL1 gene Proteins 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a kind of video monitoring image distortion detection method and system, its method comprises the following steps：Video monitoring image is periodically intercepted in the period setting；Truncated picture content is calculated into the first picture quality value by SOBEL modified operators；Transfer the second picture mass value of last interception video monitoring image；3rd picture quality value is tried to achieve according to the first picture quality value and second picture mass value；When the 3rd picture quality value is more than normal pictures mass value, then judge that video monitoring image is normal, same day detection terminates；When the 3rd picture quality value is less than normal pictures mass value, then number of times record is alerted once, and continue detection；Alarm number of times after detection is multiple has reached preset times, then present image distortion alarm status is set into alarm.Present invention aims at distortion detection is automatically performed, accuracy rate is high, and user only needs to set normal pictures mass value, is applicable to the video monitoring equipment with sectional drawing function.
Description
Technical field
The present invention relates to technical field of video monitoring, more particularly to a kind of video monitoring image distortion detection method and it is
System.
Background technology
In recent years, in order to adapt to the public security situation demands become increasingly complex, various regions government has carried forward vigorously video prison
System Construction is controlled, in the complicated place of public security, the multiple location of case, arterial street, emphasis critical position, critical junction, buckle etc.
Video surveillance point is set up in place, has been gradually formed the video surveillance network in the whole city of covering and small towns, has effectively been played monitoring
The social efficiency of system.With deepening continuously that monitoring system is applied, access device quantity is more and more, and scale is increasing,
Equipment fault occurs inevitable.But electronic monitoring wall can not show each road image simultaneously, some monitoring point discoveries are image blurring,
The phenomenons such as intentional shielded image can not be found in time.And the image blurring detection means that equipment manufacturer provides can not effectively be covered
The problem of covering other plant equipments.If monitoring system during public security application in actual combat because it is image blurring, deliberately block etc. reason
Zhao is irrecoverable into important image data, it is likely that directly affect the detection of important case together, or even socially triggers one
The no small public sentiment crisis in field.Therefore, the failure such as how to find to obscure, block in time with rejection image and having become video monitoring solution
The certainly new problem in scheme.
The content of the invention
The present invention provides a kind of video monitoring image distortion detection method and system, it is therefore intended that be automatically performed distortion inspection
Survey, accuracy rate is high, user only needs to set normal pictures mass value, is applicable to the video monitoring equipment with sectional drawing function.
To solve the above problems, the embodiment of the present invention provides a kind of video monitoring image distortion detection method, including it is following
Step：
Video monitoring image is periodically intercepted in the period setting；
Truncated picture content is calculated into the first picture quality value by SOBEL modified operators；
Transfer the second picture mass value of last interception video monitoring image；
The 3rd picture quality value is tried to achieve according to the first picture quality value and second picture mass value；
Judge whether video monitoring image is in distortion according to the 3rd picture quality value and default normal pictures mass value
State；
If the 3rd picture quality value is less than normal pictures mass value, alarm number of times record once, and continues detection；
Alarm number of times after detection is multiple has reached preset times, then is set to present image distortion alarm status
Alarm.
It is further comprising the steps of as a kind of embodiment：
If the 3rd picture quality value is more than normal pictures mass value, judge that video monitoring image is normal, same day detection knot
Beam, and the second picture mass value that the 3rd picture quality value is detected as next time.
It is described that 3rd picture matter is tried to achieve according to the first picture quality value and second picture mass value as a kind of embodiment
Value, specifically includes following steps：
The calculation formula of 3rd picture quality value is：
Wherein, VAL1 is expressed as the first picture quality value, and VAL2 is expressed as second picture mass value, and VAL3 is expressed as the 3rd
Picture quality value.
The embodiment of the present invention also provides a kind of video monitoring image distortion detection system, including interception unit, catalog unit,
Computing unit, comparing unit and warning count unit；
The sectional drawing unit, for setting regular interception video monitoring image in the period；
The catalog unit, the second picture mass value for transferring last interception video monitoring image；
The computing unit, for truncated picture content to be calculated into the first picture quality by SOBEL modified operators
Value, the 3rd picture quality value is tried to achieve according to the first picture quality value and second picture mass value；
The comparing unit, for judging video monitoring according to the 3rd picture quality value and default normal pictures mass value
Whether image is in distortion status, if the 3rd picture quality value is more than normal pictures mass value, is judging video monitoring image just
Often, same day detection terminates, and the second picture mass value that the 3rd picture quality value is detected as next time；
The warning count unit, for when the 3rd picture quality value is less than normal pictures mass value, then alerting number of times
Record once, and continues detection；Alarm number of times after detection is multiple has reached preset times, then accuses present image distortion
Alert state is set to alarm.
The present invention is compared to the beneficial effect of prior art：Distortion detection can be automatically performed, accuracy rate is high, user is only
Need to set normal pictures mass value, be applicable to the video monitoring equipment with sectional drawing function.
Brief description of the drawings
Fig. 1 is the flow chart of the video monitoring image distortion detection method of the present invention；
Fig. 2 is the structured flowchart of the video monitoring image distortion detection system of the present invention.
Accompanying drawing is marked：1st, interception unit；2nd, catalog unit；3rd, computing unit；4th, comparing unit；5th, warning count unit.
Embodiment
Below in conjunction with accompanying drawing, the technical characteristic above-mentioned and other to the present invention and advantage are clearly and completely described,
Obviously, described embodiment is only the section Example of the present invention, rather than whole embodiments.
As shown in figure 1, the embodiment of the present invention provides a kind of video monitoring image distortion detection method, comprise the following steps：
S101：Video monitoring image is periodically intercepted in the period setting；
S102：Truncated picture content is calculated into the first picture quality value by SOBEL modified operators；
S103：Transfer the second picture mass value of last interception video monitoring image；
S104：The 3rd picture quality value, the 3rd picture matter are tried to achieve according to the first picture quality value and second picture mass value
The calculation formula of value is：Wherein, VAL1 is expressed as the first picture quality value, and VAL2 is expressed as
Second picture mass value, VAL3 is expressed as the 3rd picture quality value；
S105：Judge whether video monitoring image is in default normal pictures mass value according to the 3rd picture quality value
Distortion status；
S106：If the 3rd picture quality value is less than normal pictures mass value, alarm number of times record once, and continues to visit
Survey；
S107：Alarm number of times after detection is multiple has reached preset times, then by present image distortion alarm status
It is set to alarm.
It is further comprising the steps of in addition to above-mentioned steps：
S108：If the 3rd picture quality value is more than normal pictures mass value, judge that video monitoring image is normal, the same day is visited
Survey terminates, and the second picture mass value that the 3rd picture quality value is detected as next time.
As shown in Fig. 2 a kind of video monitoring image distortion detection system, including interception unit 1, catalog unit 2, calculating list
Member 3, comparing unit 4 and warning count unit 5.Sectional drawing unit is used to set regular interception video monitoring figure in the period
Picture.Catalog unit 2 connects sectional drawing unit, the second picture mass value for transferring last interception video monitoring image.Calculate
Unit 3 connects catalog unit 2 and sectional drawing unit, for truncated picture content to be calculated into first by SOBEL modified operators
Picture quality value, and the 3rd picture quality value is tried to achieve according to the first picture quality value and second picture mass value.Comparing unit 4 connects
Computing unit 3 and warning count unit 5 are connect, for judging to regard according to the 3rd picture quality value and default normal pictures mass value
Whether frequency monitoring image is in distortion status, if the 3rd picture quality value is more than normal pictures mass value, judges video monitoring
Image is normal, and same day detection terminates, and the second picture mass value that the 3rd picture quality value is detected as next time；When the 3rd figure
When tablet quality value is less than normal pictures mass value, then number of times record is alerted once.Warning count unit 5 connects sectional drawing unit, when
When alarm number of times adds up to be less than preset times, triggering sectional drawing unit interception video monitoring image is detected again；Work as alarm
Number of times has reached preset times, then present image distortion alarm status is set into alarm, i.e. video monitoring image is in mistake
True state.
Embodiment one
When backstage detection service starts, periodic scanning camera, in scanning process, if system image analysis function is opened simultaneously
And system time is 9:00---16：Between 00, then the SDK provided by camera producer intercepts a video monitoring image simultaneously
It is saved under assigned catalogue；
By the image reading under assigned catalogue to internal memory, and this section of internal memory is created into flow object；
Picture material is calculated to the first picture quality value VAL1 for characterizing picture quality by SOBEL modified operators,
VAL1 values are higher to represent that picture quality is higher；
Transfer last detection grabgraf and calculate obtained second picture mass value VAL2, if being visited for the first time
Survey, then VAL2 is arranged to default value；
According to calculation formula：Try to achieve the 3rd picture quality value VAL3；
3rd picture quality value VAL3 is made comparisons with the normal pictures mass value VAL4 of user preset, if VAL3 is less than
VAL4, then it represents that video monitoring image is in distortion status, it is necessary to continue detection, while add 1 by alarm number of times, and by VAL3 and
Alarm number of times is saved in database, and VAL3 continues first step action as the VAL2 of detection next time；Until alarm number of times reach it is pre-
If during number of times (in the present embodiment, preset times are 3 times), then newest VAL3 and alarm number of times are preserved, and ought
Preceding image fault alarm status is set to alarm；
If VAL3 is more than VAL4, then it represents that video monitoring image is normal, and the detection on the same day terminates, and second of spy is not done
Survey, newest VAL3 is preserved and the VAL2 of detection next time is used as.
The present invention can be automatically performed distortion detection, and accuracy rate is high, and user only needs to set normal pictures mass value, applicable
In the video monitoring equipment with sectional drawing function.
Particular embodiments described above, has been carried out further to the purpose of the present invention, technical scheme and beneficial effect
Describe in detail, it will be appreciated that the foregoing is only the specific embodiment of the present invention, the protection being not intended to limit the present invention
Scope.Particularly point out, to those skilled in the art, within the spirit and principles of the invention, that is done any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.
Claims (4)
1. a kind of video monitoring image distortion detection method, it is characterised in that comprise the following steps：
Video monitoring image is periodically intercepted in the period setting；
Truncated picture content is calculated into the first picture quality value by SOBEL modified operators；
Transfer the second picture mass value of last interception video monitoring image；
The 3rd picture quality value is tried to achieve according to the first picture quality value and second picture mass value；
Judge whether video monitoring image is in distortion status according to the 3rd picture quality value and default normal pictures mass value；
If the 3rd picture quality value is less than normal pictures mass value, alarm number of times record once, and continues detection；
Alarm number of times after detection is multiple has reached preset times, then is set to present image distortion alarm status accuse
It is alert.
2. the video monitoring image distortion detection method according to claim 1, it is characterised in that also including following step
Suddenly：
If the 3rd picture quality value is more than normal pictures mass value, judge that video monitoring image is normal, same day detection terminates, and
The second picture mass value that 3rd picture quality value is detected as next time.
3. the video monitoring image distortion detection method according to claim 1, it is characterised in that described according to the first figure
Tablet quality value and second picture mass value try to achieve the 3rd picture quality value, specifically include following steps：
The calculation formula of 3rd picture quality value is：
Wherein, VAL1 is expressed as the first picture quality value, and VAL2 is expressed as second picture mass value, and VAL3 is expressed as the 3rd picture
Mass value.
4. a kind of video monitoring image distortion detection system, it is characterised in that including interception unit, catalog unit, computing unit,
Comparing unit and warning count unit；
The sectional drawing unit, for setting regular interception video monitoring image in the period；
The catalog unit, the second picture mass value for transferring last interception video monitoring image；
The computing unit, for truncated picture content to be calculated into the first picture quality value, root by SOBEL modified operators
The 3rd picture quality value is tried to achieve according to the first picture quality value and second picture mass value；
The comparing unit, for judging video monitoring image according to the 3rd picture quality value and default normal pictures mass value
Whether distortion status are in, if the 3rd picture quality value is more than normal pictures mass value, judge that video monitoring image is normal, when
Its detection terminates, and the second picture mass value that the 3rd picture quality value is detected as next time；
The warning count unit, for when the 3rd picture quality value is less than normal pictures mass value, then alerting number of times record
Once, and continue detection；Alarm number of times after detection is multiple has reached preset times, then present image distortion is alerted into shape
State is set to alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710400296.XA CN107248160B (en) | 2017-05-31 | 2017-05-31 | Video monitoring image distortion detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710400296.XA CN107248160B (en) | 2017-05-31 | 2017-05-31 | Video monitoring image distortion detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107248160A true CN107248160A (en) | 2017-10-13 |
| CN107248160B CN107248160B (en) | 2020-08-11 |
Family
ID=60018415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710400296.XA Active CN107248160B (en) | 2017-05-31 | 2017-05-31 | Video monitoring image distortion detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107248160B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102111532A (en) * | 2010-05-27 | 2011-06-29 | 周渝斌 | Camera lens occlusion detecting system and method |
| CN102740107A (en) * | 2011-04-11 | 2012-10-17 | 鸿富锦精密工业（深圳）有限公司 | Damage monitoring system of image surveillance equipment and method |
| CN103997622A (en) * | 2014-03-27 | 2014-08-20 | 上海海事大学 | Automatic cleaning method of unattended monitoring camera |
| CN104038666A (en) * | 2014-04-22 | 2014-09-10 | 深圳英飞拓科技股份有限公司 | Video shielding detection method and video shielding detection device |
| CN104079886A (en) * | 2014-07-09 | 2014-10-01 | 李任鸿 | Method for detecting whether monitoring camera shielded or disturbed |
| JP2015109058A (en) * | 2013-12-06 | 2015-06-11 | 三菱電機株式会社 | Tsunami monitoring system |
| CN105139016A (en) * | 2015-08-11 | 2015-12-09 | 豪威科技(上海)有限公司 | Interference detection system for surveillance camera and application method of interference detection system |
| CN105611188A (en) * | 2015-12-23 | 2016-05-25 | 北京奇虎科技有限公司 | Method and device for detecting shielding of camera based on automatic exposure |
| CN106454330A (en) * | 2016-11-02 | 2017-02-22 | 北京弘恒科技有限公司 | Fuzziness anomaly detection method for video signals |
| US20170094228A1 (en) * | 2015-06-29 | 2017-03-30 | Quantum IR Technologies, LLC | Methods and systems for hotspot detection |
-
2017
- 2017-05-31 CN CN201710400296.XA patent/CN107248160B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102111532A (en) * | 2010-05-27 | 2011-06-29 | 周渝斌 | Camera lens occlusion detecting system and method |
| CN102740107A (en) * | 2011-04-11 | 2012-10-17 | 鸿富锦精密工业（深圳）有限公司 | Damage monitoring system of image surveillance equipment and method |
| JP2015109058A (en) * | 2013-12-06 | 2015-06-11 | 三菱電機株式会社 | Tsunami monitoring system |
| CN103997622A (en) * | 2014-03-27 | 2014-08-20 | 上海海事大学 | Automatic cleaning method of unattended monitoring camera |
| CN104038666A (en) * | 2014-04-22 | 2014-09-10 | 深圳英飞拓科技股份有限公司 | Video shielding detection method and video shielding detection device |
| CN104079886A (en) * | 2014-07-09 | 2014-10-01 | 李任鸿 | Method for detecting whether monitoring camera shielded or disturbed |
| US20170094228A1 (en) * | 2015-06-29 | 2017-03-30 | Quantum IR Technologies, LLC | Methods and systems for hotspot detection |
| CN105139016A (en) * | 2015-08-11 | 2015-12-09 | 豪威科技(上海)有限公司 | Interference detection system for surveillance camera and application method of interference detection system |
| CN105611188A (en) * | 2015-12-23 | 2016-05-25 | 北京奇虎科技有限公司 | Method and device for detecting shielding of camera based on automatic exposure |
| CN106454330A (en) * | 2016-11-02 | 2017-02-22 | 北京弘恒科技有限公司 | Fuzziness anomaly detection method for video signals |
Non-Patent Citations (1)
| Title |
|---|
| 邬美银 等: "基于卷积神经网络的视频图像失真检测及分类", 《计算机应用研究》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107248160B (en) | 2020-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107770174A (en) | A kind of intrusion prevention system and method towards SDN | |
| CN106251568A (en) | A kind of fire alarm safety-protection system based on ultraviolet and image detecting technique and method | |
| CN108390856B (en) | DDoS attack detection method and device and electronic equipment | |
| JP5601255B2 (en) | Water level monitoring device, water level monitoring method, and water level monitoring program | |
| CN107221133A (en) | A kind of area monitoring warning system and alarm method | |
| CN105447139A (en) | Data acquisition statistical method, and system, terminal and service equipment thereof | |
| US9622048B2 (en) | SNS based incident management | |
| CN105427507B (en) | fire monitoring method and device | |
| EP2222099A1 (en) | A method, device and system of disaster recovery and handover control | |
| CN106131502B (en) | Video monitoring method and device for pipe gallery tunnel | |
| CN110619308A (en) | Aisle sundry detection method, device, system and equipment | |
| CN104243192B (en) | Fault handling method and system | |
| CN114937247B (en) | Transformer substation monitoring method and system based on deep learning and electronic equipment | |
| CN102651813A (en) | Intelligent video monitoring and advertising system | |
| CN114189361B (en) | Situation awareness method, device and system for defending threat | |
| JP2008193538A (en) | Attack monitoring device and attack trail management method to network | |
| CN107248160A (en) | Video monitoring image distortion detection method and system | |
| CN105959643A (en) | Monitoring method, device and system | |
| WO2022009356A1 (en) | Monitoring system | |
| CN117037065A (en) | Flame smoke concentration detection method, device, computer equipment and storage medium | |
| CN108877131A (en) | A kind of security alarm method and apparatus | |
| US10855633B2 (en) | Controlling asset messages | |
| CN112949359A (en) | Convolutional neural network-based abnormal behavior identification method and device | |
| JP2007233495A (en) | Distributed image processor | |
| CN112906651B (en) | Target detection method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: 13th Floor, Shanke Intelligent Building, No. 89 Qizhi Street, Xixing Street, Binjiang District, Hangzhou City, Zhejiang Province, 310000 Patentee after: ZHEJIANG YUANWANG INFORMATION Co.,Ltd. Address before: 15th Floor, Haiyue Building, No. 788 Danfeng Road, Binjiang District, Hangzhou City, Zhejiang Province, 310053 Patentee before: ZHEJIANG YUANWANG INFORMATION Co.,Ltd. |