CN106385580A - Video jittering detection method based on image gray distribution characteristics - Google Patents
Video jittering detection method based on image gray distribution characteristics Download PDFInfo
- Publication number
- CN106385580A CN106385580A CN201610873192.6A CN201610873192A CN106385580A CN 106385580 A CN106385580 A CN 106385580A CN 201610873192 A CN201610873192 A CN 201610873192A CN 106385580 A CN106385580 A CN 106385580A
- Authority
- CN
- China
- Prior art keywords
- row
- row gray
- gray
- video
- 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
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
- H04N5/144—Movement detection
-
- 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
Abstract
The invention relates to a video jittering detection method based on image gray distribution characteristics. The video jittering detection method comprises the steps that step one, statistics of row gray values and column gray values is performed respectively, and the expectation and the variance of the row gray values and the expectation and the variance of the column gray values are calculated; step two, hypothesis testing is performed in the row direction, and jittering in the vertical direction is judged; and step three, hypothesis testing is performed in the column direction, and jittering in the horizontal direction is judged. Movement of a apart of objects and video jittering can be distinguished in judgment of jittering of videos so that the calculation amount is low, the detection efficiency is high, the detection accuracy is high and the algorithm real-time performance is great.
Description
Technical field
The present invention relates to a kind of detection method of monitor video shake, it is based on gradation of image distribution characteristics particularly to a kind of
Video jitter detection method.
Background technology
Video monitoring system as the important component part of vision Internet of Things, be widely used in urban safety, intelligent transportation,
In the application of each field such as wisdom environmental protection, border security, the contradiction that its regular maintenance is patrolled and examined is growing more intense.According to statistics, domestic at present
In the monitoring system run, the ratio of the video camera that can normally use is less than 60%, and the video monitoring system of substantial amounts
Operation and maintenance work majority manually detect and process.How to improve the efficiency of video monitoring system operation maintenance work,
Understand the ruuning situation of head end video equipment in time, building intelligentized video monitoring quality diagnosis system becomes video monitoring neck
Domain practical problem in the urgent need to address.
Video image dithering is video monitoring equipment recurrent picture quality anomaly.Under normal circumstances, move
Between the continuous multiple frames of image sequence, transition is smooth, and picture correlation is more continuous, but if the correlation between them
Great fluctuation process in property, and video arises that the situation of shake.In video monitoring, camera is typically all fixed on certain position
Put, mainly have the reason thus result in video pictures jitter phenomenon：1) camera is disturbed (such as high wind) to occur by environment
Regular swing is thus cause the upper and lower of image or left and right shake；2) camera is moved by people, causes float.Appoint
A kind of what situation, all can lead to picture periodicity chatter or irregular distortion, can mean that camera work occurs in that different
Often, badly influence the work effectiveness of video monitoring system, accordingly, it would be desirable to intelligence is carried out to the video image of video monitoring system
Analysis detection, finds video jitter failure problems in time, realizes instant alarming and reparation.
In the research related to video jitter, Niu Yaoyao, Hong Danfeng are in paper《A kind of Traffic Surveillance Video based on HGPC
Shake method for detecting abnormality》Propose a kind of Gray Projection correlation coefficient process (Hierarchical Gray based on classification
Project Correlation, HGPC).This algorithm mainly coincideing by the row Gray scale projection curve of two field pictures in front and back
Degree judges to have or not in vertical direction to shake, then is judged by the goodness of fit of the row Gray scale projection curve of two field pictures in front and back
Horizontal direction has or not shakes, thus judge that whole video has or not shaking.
We experimentally found that the ranks grey value profile feature of the video image of shake and normal video image is poor
Different obvious, based on this, it is proposed that a kind of video jitter detection method based on gray distribution features.The method Detection accuracy
Height, algorithm real-time is good.
Content of the invention
It is an object of the invention to provide a kind of video jitter detection method based on gradation of image distribution characteristics.This invention according to
Meet normal distribution according to normal video image ranks gray value, and the ranks gray value shaking video image does not meet normal state and divides
Cloth, using this distribution characteristics difference, by the ranks gray value of in front and back's frame of video, constructs the system that APPROXIMATE DISTRIBUTION is normal distribution
Metering, calculates the ranks gray scale inspection factor, to weigh continuity and the correlation of before and after's two field pictures, and then to judge that this video is
No there occurs shake.
The technical step of the present invention is as follows：
Based on the video jitter detection method of gradation of image distribution characteristics, step is as follows：
Step 1：Adjacent two field pictures before and after intercepting in video.
Step 2：The two field pictures of intercepting are transformed into gray space.
Step 3：The often row gray value of statistics previous frame image and each column gray value, calculate trip gray average and row gray scale
Variance yields and row gray average and row gray variance value.
Step 4：The often row gray value of statistics a later frame image and each column gray value, calculate trip gray average and row gray scale
Variance yields and row gray average and row gray variance value.
Step 5：Before and after calculated to step 3 and step 4, the row gray average of two field pictures and row gray variance do
One row hypothesis testing, obtains a performing check factor.
Step 6：Before and after calculated to step 3 and step 4, the row gray average of two frames and row gray variance do one
Row hypothesis testing, obtains a row inspection factor.
Step 7：By step 5 and the step 6 calculated performing check factor and the row inspection factor respectively with given threshold value
Compare, if one of exceed threshold value, judge previous frame image as shake frame.
Step 8：Counting in whole video, the ratio shared by shake frame, if it exceeds setting dithering threshold, then judging that this regards
Frequency is shake.
Further, in step 3, row gray value, row gray average and row gray variance computational methods are as follows：
Row gray value
Row gray average
Row gray variance
Wherein f (i, j) is the gray value of each pixel in gray level image, and A is picturedeep, and B is picturewide.
Row gray value, row gray average and row gray variance computational methods are as follows：
Row gray value
Row gray average
Row gray variance
Further in steps of 5, the computational methods of the performing check factor are as follows：
The performing check factor
Wherein,sx 2 1It is row gray average and the row gray variance of previous frame image respectively,sx 2 2One after being respectively
The row gray average of two field picture and row gray variance.
Further, in step 6, the computational methods of the row inspection factor are as follows：
The row inspection factor
Wherein,sy 2 1It is row gray average and the row gray variance of previous frame image respectively,sy 2 2One after being respectively
The row gray average of frame and row gray variance.
Further, in step 7, the threshold value of the performing check factor and the row inspection factor is set to α, if θx>α or θy>α has one
Set up, then judge previous frame image as shake frame.
Further, in step 8, the value of the shake frame number according to step 7 statistics, calculates the ratio that shake frame number accounts for totalframes
Example k, if dithering threshold is β, if k>β sets up, then judge that this video is shaken.
Beneficial effects of the present invention：
The present invention detects respectively to the ranks of image, can detect the shake of different directions.Amount of calculation is little, detection effect
Rate is high.Whether the video of monitor video or other equipment shooting, effectively can be detected with this algorithm, detection
The degree of accuracy reaches more than 90%.
Brief description
Fig. 1 is the algorithm flow chart of the present invention.
Specific embodiment
Below according to accompanying drawing, contain the video detection process of 101 frame of video to this in conjunction with a size for 1280*720
Invention is described in detail, and specific implementation step is as follows：
Step 1：Adjacent two field pictures before and after intercepting in video successively, intercept 100 times altogether.
Step 2：The two field pictures of intercepting are transformed into gray space.
Step 3：The often row gray value of statistics former frame and each column gray value, calculate trip gray average and row gray variance
Value and row gray average and row gray variance.
Step 4：The often row gray value of statistics a later frame and each column gray value, calculate trip gray average and row gray variance
Value and row gray average and row gray variance.
Step 5：Do one using step 3 and step 4 counted the row gray average of two field pictures and row gray variance in front and back
Individual row hypothesis testing, obtains a performing check factor.
Step 6：Do one using step 3 and step 4 counted the row gray average of two field pictures and row gray variance in front and back
Individual row hypothesis testing, obtains a row inspection factor.
Step 7：Compared with given threshold value using step 5 and the step 6 counted performing check factor and the row inspection factor,
If wherein there being one to exceed threshold value, judging former frame as shake frame.
Step 8：Count in whole video, the ratio shared by shake frame, if it exceeds the threshold, then judge that this video there occurs
Shake.
Further, in step 3, row gray average and row gray variance computational methods are as follows：
Row gray value
Row gray average
Row gray variance
Wherein f (i, j) is the gray value of each pixel in gray level image, and A is the line number of image, and B is the columns of image.
Further, in step 3, row gray average and row gray variance computational methods are as follows：
Row gray value
Row gray average
Row gray variance
Further in steps of 5, the computational methods of the performing check factor are as follows：
The performing check factor
Wherein,sx 2 1It is row gray average and the row gray variance of former frame respectively,sx 2 2It is a later frame respectively
Row gray average and row gray variance.
Further in step 6, the computational methods of the row inspection factor are as follows：
The performing check factor
Wherein,sy 2 1It is row gray average and the row gray variance of former frame respectively,sy 2 2It is a later frame respectively
Row gray average and row gray variance.
Further, in step 7, the threshold value of the performing check factor and the row inspection factor is set to 0.2, if θx>0.2 or θy>0.2
There is an establishment, then judge previous frame image as shake frame.
Further, in step 8, value m of the shake frame number according to step 7 statistics, calculate shake frame number accounts for totalframes
Ratio k, whereinIf threshold value is 60%, if k>60% establishment, then judge that this video is shaken.
Claims (7)
1. the video jitter detection method based on gradation of image distribution characteristics is it is characterised in that comprise the steps：
Step 1：Adjacent two field pictures before and after intercepting in video；
Step 2：The two field pictures of intercepting are transformed into gray space；
Step 3：The often row gray value of statistics previous frame image and each column gray value, calculate trip gray average and row gray variance
Value and row gray average and row gray variance value；
Step 4：The often row gray value of statistics a later frame image and each column gray value, calculate trip gray average and row gray variance
Value and row gray average and row gray variance value；
Step 5：Before and after calculated to step 3 and step 4, the row gray average of two field pictures and row gray variance do one
Row hypothesis testing, obtains a performing check factor；
Step 6：Before and after calculated to step 3 and step 4, the row gray average of two frames and row gray variance do a row vacation
If inspection, obtain a row inspection factor；
Step 7：Step 5 and the step 6 calculated performing check factor and the row inspection factor are done ratio with given threshold value respectively
Relatively, if one of exceed threshold value, judge previous frame image as shake frame；
Step 8：Counting in whole video, the ratio shared by shake frame, if it exceeds setting dithering threshold, then judging that this video is sent out
Raw shake.
2. the video jitter detection method based on gradation of image distribution characteristics according to claim 1 is it is characterised in that walk
In rapid 3, row gray value, row gray average and row gray variance computational methods are as follows：
Row gray value
Row gray average
Row gray variance
Wherein f (i, j) is the gray value of each pixel of gray level image, and A is the line number of image, and B is picturewide.
3. the video jitter detection method based on gradation of image distribution characteristics according to claim 1 is it is characterised in that walk
In rapid 3, row gray value, row gray average and row gray variance computational methods are as follows：
Row gray value
Row gray average
Row gray variance
4. the video jitter detection method based on gradation of image distribution characteristics according to claim 1 is it is characterised in that walk
In rapid 5, the computational methods of the performing check factor are as follows：
The performing check factor
Wherein,sx 2 1It is row gray average and the row gray variance of previous frame image respectively,sx 2 2It is a later frame figure respectively
The row gray average of picture and row gray variance.
5. the video jitter detection method based on gradation of image distribution characteristics according to claim 1 is it is characterised in that walk
In rapid 6, the computational methods of the row inspection factor are as follows：
The row inspection factor
Wherein,sy 2 1It is row gray average and the row gray variance of previous frame image respectively,sy 2 2It is a later frame respectively
Row gray average and row gray variance.
6. the video jitter detection method based on gradation of image distribution characteristics according to claim 1 is it is characterised in that walk
In rapid 7, the threshold value of the performing check factor and the row inspection factor is set to α, if θx>α or θy>α has an establishment, then judge former frame figure
As for shaking frame.
7. the video jitter detection method based on gradation of image distribution characteristics according to claim 1 is it is characterised in that walk
In rapid 8, the value of the shake frame number according to step 7 statistics, calculate ratio k that shake frame number accounts for totalframes, if dithering threshold is β,
If k>β sets up, then judge that this video is shaken.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610873192.6A CN106385580B (en) | 2016-09-30 | 2016-09-30 | Video jitter detection method based on gradation of image distribution characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610873192.6A CN106385580B (en) | 2016-09-30 | 2016-09-30 | Video jitter detection method based on gradation of image distribution characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106385580A true CN106385580A (en) | 2017-02-08 |
| CN106385580B CN106385580B (en) | 2018-02-06 |
Family
ID=57937234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610873192.6A Active CN106385580B (en) | 2016-09-30 | 2016-09-30 | Video jitter detection method based on gradation of image distribution characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106385580B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040189814A1 (en) * | 2003-03-28 | 2004-09-30 | Hidehiro Katoh | Video camera |
| CN101009769A (en) * | 2007-02-09 | 2007-08-01 | 于中 | Jitter-prevention processing method of TV image |
| CN103067741A (en) * | 2013-01-24 | 2013-04-24 | 浙江理工大学 | Shaking detection algorithm based on multi-feature fusion |
| CN103679750A (en) * | 2013-11-25 | 2014-03-26 | 武汉东智科技有限公司 | Camera shake detecting method based on videos |
| CN104301712A (en) * | 2014-08-25 | 2015-01-21 | 浙江工业大学 | Monitoring camera shaking detection method based on video analysis |
| CN105681663A (en) * | 2016-02-26 | 2016-06-15 | 北京理工大学 | Video jitter detection method based on inter-frame motion geometric smoothness |
-
2016
- 2016-09-30 CN CN201610873192.6A patent/CN106385580B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040189814A1 (en) * | 2003-03-28 | 2004-09-30 | Hidehiro Katoh | Video camera |
| CN101009769A (en) * | 2007-02-09 | 2007-08-01 | 于中 | Jitter-prevention processing method of TV image |
| CN103067741A (en) * | 2013-01-24 | 2013-04-24 | 浙江理工大学 | Shaking detection algorithm based on multi-feature fusion |
| CN103679750A (en) * | 2013-11-25 | 2014-03-26 | 武汉东智科技有限公司 | Camera shake detecting method based on videos |
| CN104301712A (en) * | 2014-08-25 | 2015-01-21 | 浙江工业大学 | Monitoring camera shaking detection method based on video analysis |
| CN105681663A (en) * | 2016-02-26 | 2016-06-15 | 北京理工大学 | Video jitter detection method based on inter-frame motion geometric smoothness |
Non-Patent Citations (1)
| Title |
|---|
| 牛瑶瑶等: "《一种基于HGPC的交通监控视频抖动异常检测方法》", 《青岛大学学报（自然科学版）》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106385580B (en) | 2018-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11102417B2 (en) | Target object capturing method and device, and video monitoring device | |
| CN111160125B (en) | Railway foreign matter intrusion detection method based on railway monitoring | |
| US7982774B2 (en) | Image processing apparatus and image processing method | |
| CN104410855A (en) | Jitter detection method of monitoring video | |
| CN104966304B (en) | Multi-target detection tracking based on Kalman filtering and nonparametric background model | |
| EP3104327A2 (en) | Anomalous pixel detection | |
| CN103096121B (en) | A kind of camera movement detection method and device | |
| CN103903008B (en) | A kind of method and system of the mist grade based on image recognition transmission line of electricity | |
| CN103927520A (en) | Method for detecting human face under backlighting environment | |
| CN104394377B (en) | A kind of fuzzy abnormal recognition methods of monitoring image and device | |
| CN105740792B (en) | Object detection method and device | |
| CN109598706A (en) | A kind of camera lens occlusion detection method and system | |
| CN109905670A (en) | A kind of multi-stage platform monitoring system | |
| CN104539899A (en) | Method for distinguishing monitoring camera abnormal situation through video signal | |
| CN108364282A (en) | Image-mosaics detection method, image-mosaics detecting system | |
| JP2009140307A (en) | Person detector | |
| CN105554494B (en) | Snow point image detecting method and device and video quality detection device and system | |
| US20120092501A1 (en) | Computing device and method for adjusting resolutions of internet protocol cameras | |
| CN105530406B (en) | A kind of intelligent Enhancement Method based on historical frames image statistics value | |
| CN114638808A (en) | Multi-scene video jitter detection method based on video monitoring | |
| CN103095966A (en) | Video jitter quantization method and video jitter quantization device | |
| JP2015158796A (en) | Object detection device | |
| CN105844671B (en) | A kind of fast background relief method under the conditions of change illumination | |
| CN106385580B (en) | Video jitter detection method based on gradation of image distribution characteristics | |
| CN112329515A (en) | High-point video monitoring congestion event detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |