CN103428406B - Monitoring video analysis method and device - Google Patents
Monitoring video analysis method and device Download PDFInfo
- Publication number
- CN103428406B CN103428406B CN201210162170.0A CN201210162170A CN103428406B CN 103428406 B CN103428406 B CN 103428406B CN 201210162170 A CN201210162170 A CN 201210162170A CN 103428406 B CN103428406 B CN 103428406B
- Authority
- CN
- China
- Prior art keywords
- time point
- monitoring video
- curve
- amplitude
- picture
- 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.)
- Active
Links
Abstract
The invention provides a kind of monitoring video analysis method and device.It is related to field of video processing;Solve monitoring video and be not easy to the problem of user searches the video content needed.This method includes:Continuous image sequence is extracted from monitoring video, described image sequence includes the plurality of pictures of different time points;Calculate the difference that corresponding picture and previous picture are sometime put in described image sequence;Extract the sound variation amplitude at the time point;According to the difference and the sound variation amplitude of the time point corresponding picture and previous picture, the video situation of change at the time point is judged.The technical scheme that the present invention is provided is positioned suitable for monitoring video, realizes the identification to monitoring video content change.
Description
Technical field
The present invention relates to field of video processing, more particularly to a kind of monitoring video analysis method and device.
Background technology
The need for due to both privately and publicly owned's property safety, video monitoring is widely used.On airport, subway, wide
Etc. public place, there is provided numerous monitoring devices with strengthen to public sphere safety control and prevention ability.In addition, handing over
The field video monitorings such as logical, bank, big chain store, residential building have also obtained widely available.Video monitoring service can be
Locally preserve a large amount of monitoring videos and browsed for user and checked.Intellectual analysis is carried out to monitoring video using computer, can be effective
Mitigation user workload, improve time monitoring efficiency.
Video Analysis Technology generally carries out the detection of image change using background separation technology.Its thinking is to frame of video
It is compared with reference background picture, the pixel or regional change of same position are then considered the region changed, to these
Region is further processed, tracks, recognized, obtains including the fundamental forms such as target location, size, shape, speed, residence time
State information and multidate information, complete tracking and the behavior understanding of target.
Prior art can detect the moving object in monitor video.Using sub-block of pixels as minimum detection unit, pass through system
Pixel difference is converted into sub-block of pixels difference by meter method, and it is set on the basis of background modeling, using Background difference when
Image to be detected, is then divided into overlapped sub-block of pixels by statistical noise level on sky, using background as reference frame, leads to
Each pixel in statistical pixel sub-block is crossed with brightness, gradient and the gradient direction difference with reference to background corresponding pixel points to judge
It whether there is moving target in the sub-block of pixels.
Some monitor video analytical technologies are used for specific occasion, such as can be counted in traffic monitoring by prison
Control the number of vehicles of scope, car speed, the information such as time passed through.Basic thinking is to extract the static of monitoring scene first
Background, then extracts the object moved in video by the comparison with background, and calculates the speed of object of which movement, by calculating
The quantity of moving object, can obtain the number by vehicle.The people in monitor video can be realized with reference to more complicated algorithm
Physical examination survey, event count, target following, abnormal alarm etc. function.
Above is referred to intelligent analysis method, can to monitoring video carry out calculating analysis, draw the result that user wants,
But user needs to check in person and browses original monitoring video in most cases.Compared with multimedia recreation video, monitoring
The angle shot of recording a video and scene are mostly single, may be shot for a long time in the range of camera view less than abnormal conditions, so
It is the unconcerned still frame of user to cause quite a few video in the monitoring video shot, is not easy to user and searches what is needed
Video content.
The content of the invention
The invention provides a kind of monitoring video analysis method and device, solve monitoring video and be not easy to user's lookup need
The problem of video content wanted.
A kind of monitoring video analysis method, including:
Continuous image sequence is extracted from monitoring video, described image sequence includes the plurality of pictures of different time points;
Calculate the difference that corresponding picture and previous picture are sometime put in described image sequence;
Extract the sound variation amplitude at the time point;
According to the difference and the sound variation amplitude of the time point corresponding picture and previous picture, the time is judged
Video situation of change at point.
It is preferred that, it is described according to the time point corresponding picture and the difference of previous picture and institute in the image sequence
Sound variation amplitude is stated, judges that the video situation of change at the time point is specially:
Time point corresponding picture and the difference of previous picture are bigger, then judge that time point epigraph change is got over
Greatly;
The sound variation amplitude at the time point is bigger, then judges that the time point upper sound variation is bigger.
It is preferred that, it is described according to the time point corresponding picture and the difference of previous picture and institute in the image sequence
Sound variation amplitude is stated, after the step of judging the video situation of change at the time point, in addition to:
It regard the difference of the time point corresponding picture and its previous picture in described image sequence as image curve
The amplitude at the time point;
Using the sound variation amplitude at the time point as audio curve the time point amplitude;
Using the time as transverse axis, the image curve and audio curve of the monitoring video are drawn.
It is preferred that, it is described to calculate the difference bag that corresponding picture and previous picture are sometime put in described image sequence
Include:
The image-region of the monitoring video is divided into multiple block of pixels, take the time point corresponding picture with it is previous
The color average of each block of pixels of picture;
Picture corresponding to the time point and the color average of the correspondence position block of pixels of previous picture take difference
Absolute value;
The absolute value of the color average difference of whole block of pixels is added, obtained result is the time point correspondence
Picture and previous picture difference.
It is preferred that, extracting the sound variation amplitude at the time point is specially:
The sound size for calculating the time point is used as the sound variation amplitude at the time point.
It is preferred that, extracting the sound variation amplitude at the time point is specially:
It regard amplitude of the audio volume control figure of the audio-frequency information of the monitoring video on the time point as the time point
On sound variation amplitude.
It is preferred that, it is described using the time as transverse axis, the step of drawing image curve and the audio curve of the monitoring video it
Afterwards, in addition to:
Described image curve, the time shaft of audio curve are aligned with the time shaft of the monitoring video, simultaneous display.
Present invention also offers a kind of monitoring video analytical equipment, including:
Image sequence provides module, and for extracting continuous image sequence from monitoring video, described image sequence includes
The plurality of pictures of different time points;
Picture difference calculating module, corresponding picture and previous picture are sometime put for calculating in described image sequence
Difference;
Sound variation computing module, for extracting the sound variation amplitude at the time point;
Video changes judge module, for the difference and the sound according to the time point corresponding picture and previous picture
Sound amplitude of variation, judges the video situation of change at the time point.
It is preferred that, above-mentioned monitoring video analytical equipment also includes:
Image curve amplitude acquisition module, for by the time point corresponding picture and its in described image sequence before
The difference of one picture as image curve the amplitude at the time point;
Audio curve amplitude acquisition module, for using the sound variation amplitude at the time point as audio curve this when
Between the amplitude put;
Drawing of Curve module, image curve and audio curve for using the time as transverse axis, drawing the monitoring video.
It is preferred that, above-mentioned monitoring video analytical equipment also includes:
Display module, for by the time shaft pair of described image curve, the time shaft of audio curve and the monitoring video
Standard, simultaneous display.
The invention provides a kind of monitoring video analysis method and device, continuous image sequence is extracted from monitoring video
Row, described image sequence include plurality of pictures, calculate described image sequence in adjacent image difference as image curve amplitude,
Audio-frequency information is provided from the monitoring video, using sound variation amplitude as the amplitude of audio curve, using the time as transverse axis, is painted
The image curve and audio curve of the monitoring video are made, image in monitoring video is embodied by image curve and audio curve
With the change of sound, reference is provided to search the content in big section monitoring video, monitoring video is solved and is not easy to user and look into
The problem of looking for the video content of needs.
Brief description of the drawings
Fig. 1 is a kind of flow chart for monitoring video analysis method that embodiments of the invention one are provided;
Fig. 2 is the particular flow sheet of step 102 in Fig. 1;
Fig. 3 is video recording analysis curve synoptic diagram;
Fig. 4 is a kind of structural representation for monitoring video analytical equipment that embodiments of the invention two are provided;
Fig. 5 is the structural representation for another monitoring video analytical equipment that embodiments of the invention two are provided;
Fig. 6 is the structural representation for another monitoring video analytical equipment that embodiments of the invention two are provided;
Fig. 7 is a kind of flow chart for monitoring video analysis method that embodiments of the invention three are provided.
Embodiment
Existing monitoring video intelligent analysis method, can carry out calculating analysis to monitoring video, draw what user wanted
As a result, user, which needs to check in person, but in most cases browses original monitoring video.Compared with multimedia recreation video,
The angle and scene that monitoring video is shot are mostly single, may be shot for a long time less than abnormal conditions in the range of camera view,
It is the unconcerned still frame of user so to cause quite a few video in the monitoring video shot.
, can be with auxiliary the embodiments of the invention provide a kind of monitoring video analysis method and device in order to solve the above problems
User is helped when browsing monitoring video, situation static and dynamic in video recording, normal and abnormal is distinguished so that user checks video recording
When it is more targeted.
Embodiments of the invention are described in detail below in conjunction with accompanying drawing.It should be noted that not conflicting
In the case of, the feature in embodiment and embodiment in the application can be mutually combined.
First with reference to accompanying drawing, embodiments of the invention one are illustrated.
The embodiments of the invention provide a kind of monitoring video analysis method, the flow analyzed using this method video recording
As shown in figure 1, including:
Step 101, extract continuous image sequence from monitoring video, described image sequence includes many of different time points
Pictures;
In this step, continuous picture is extracted from one section of monitoring video according to sampling interval, an image sequence is constituted.Can
Extracted according to a fixed time interval, according to monitoring demand, the length at selection time interval.
The difference of corresponding picture and previous picture is sometime put in step 102, calculating described image sequence;
This step it is specific as shown in Fig. 2 including:
Step 1021, the image-region of the monitoring video is divided into multiple block of pixels, takes the time point corresponding
Picture and the color average of each block of pixels of previous picture;
In this step, the image-region of monitoring video is divided into the block of pixels of n*n pixels.Respectively in sequence of computed images
The color average of each block of pixels of each picture.
Step 1022, the color average to the time point corresponding picture and the correspondence position block of pixels of previous picture
Take the absolute value of difference;
In this step, the color average in block of pixels is asked for, is then made the difference in units of block with adjacent picture, difference is taken
Absolute value, can so avoid error caused by the trickle change of image, and mutually supporting between positive negative difference will not be introduced
Disappear.
Step 1023, the absolute value addition by the color average difference of whole block of pixels, obtained result is described
The difference of time point corresponding picture and previous picture;
It is preferred that, can also be using single pixel as computing unit, by the color value of each pixel of adjacent two width picture
Take the computing of absolute difference, then the time point corresponding picture is obtained with before to the absolute difference summation of whole pixels
The difference of one picture.
Step 103, the sound variation amplitude at the extraction time point;
In this step, the sound size at the time point can be calculated as the sound variation amplitude at the time point, also may be used
To regard amplitude of the audio volume control figure of the audio-frequency information of the monitoring video on the time point as the sound on the time point
Sound amplitude of variation.
Step 104, using the time as transverse axis, draw the image curve and audio curve of the monitoring video;
In this step, the difference of the time point corresponding picture and its previous picture in described image sequence is made
For the amplitude at the time point of image curve, using the sound variation amplitude at the time point as audio curve at the time point
Amplitude, according to the image curve amplitude and audio curve amplitude of the picture of each in image sequence, drawing image curve and audio
Curve.
Image curve and audio curve can separately be drawn, using the time as transverse axis, using picture amplitude value as the longitudinal axis, drawn
The image curve of the monitoring video, using the time as transverse axis, using the amplitude of audio curve as the longitudinal axis, draws the monitoring video
Audio curve.
Image curve and audio curve can also be drawn in same reference axis, using the time as transverse axis, with picture amplitude
Value is the longitudinal axis of image curve, using the amplitude of audio curve as the longitudinal axis of audio curve, and the image for drawing the monitoring video is bent
Line and audio curve, video recording analysis curve is collectively formed by image curve and audio curve.
The auxiliary recorded a video as user's checking monitoring, video recording analysis curve can be placed on video player time schedule axle
Lower section, see Fig. 3.Video recording analysis curve is two curves comprising image and sound variation, wherein transverse axis in two-dimensional coordinate
For the time shaft of monitoring video, the longitudinal axis is the amplitude of variation of video image and sound.The transverse axis and monitoring video for analyzing curve are broadcast
Put the time overlapping of axles and correspondingly of device.
Step 105, described image curve, the time shaft of audio curve be aligned with the time shaft of the monitoring video, together
Step display;
In this step, the monitoring video information that can be shown according to image curve and audio curve, to select viewing to supervise
The part of video recording is controlled, such as when not having mobile object in camera view, i.e., when video frames are static, image curve is shown as
The straight line overlapped with time shaft convergence.Conversely, such as there are personnel to pass through when there are objects moving in camera view, there is garage to cross
When, what the picture of monitoring video was continually changing, at this time image curve can be shown as according to the size of change away from transverse axis
The curve of cyclical fluctuations.Similarly, when not having sound in monitoring range, audio curve shows as the straight line that amplitude convergence is 0, instead
Show as the curve of cyclical fluctuations with certain amplitude.The transient change of image and sound is bigger, and the amplitude of curve and fluctuation are bigger.
User can infer the change of video and sound in video recording according to the fluctuation situation of analysis curve, it is possible to drag player progress
Bar checks corresponding monitoring video to time shaft position interested.
Below in conjunction with the accompanying drawings, embodiments of the invention two are illustrated.
The problem of user searches the video content needed is not easy in order to solve monitoring video, the embodiment of the present invention is provided
A kind of monitoring video analytical equipment, its structure as shown in figure 4, including:
Image sequence provides module 401, for extracting continuous image sequence, described image sequence bag from monitoring video
Include the plurality of pictures of different time points;
Picture difference calculating module 402, for calculate sometime put in described image sequence corresponding picture with it is previous
The difference of picture;
Sound variation computing module 403, for extracting the sound variation amplitude at the time point;
Video changes judge module 404, for the difference according to the time point corresponding picture and previous picture and institute
Sound variation amplitude is stated, the video situation of change at the time point is judged.
It is preferred that, above-mentioned monitoring video analytical equipment is as shown in figure 5, also include:
Image curve amplitude acquisition module 405, for by the time point corresponding picture and its in described image sequence
In previous picture difference as image curve the amplitude at the time point;
Audio curve amplitude acquisition module 406, for the sound variation amplitude at the time point to be existed as audio curve
The amplitude at the time point;
Drawing of Curve module 407, the image curve and audio for using the time as transverse axis, drawing the monitoring video is bent
Line.
It is preferred that, above-mentioned monitoring video analytical equipment is as shown in fig. 6, also include:
Display module 408, for by the time shaft of described image curve, the time shaft of audio curve and the monitoring video
Alignment, simultaneous display.
Below in conjunction with the accompanying drawings, embodiments of the invention three are illustrated.
The embodiment of the present invention proposes a kind of monitoring video analysis method based on image and sound variation, is regarded according to monitoring
The change curve of frequency drawing image and sound, describes dynamic change situation of the monitoring video with the time.The embodiment of the present invention is carried
The monitoring video analysis method of confession, the event during active analysis or statistics are not recorded a video, but provided for the video recording of user's checking monitoring
With reference to and auxiliary.
The flow such as Fig. 7 institutes analyzed using monitoring video analysis method provided in an embodiment of the present invention monitoring video
Show, including:
Step 701, loading monitoring video.Load and can play after monitoring video, video recording analysis curve can be used in addition
One thread is calculated.
Step 702, calculating video recording analysis curve.Continuous image sequence is extracted from monitoring video, if can be at interval of
Dry millisecond takes a picture, it is to avoid amount of calculation is excessive.Each picture is divided into the block of n*n pixels, and asks for each pixel
The color average of block, the adjacent corresponding block of pixels of picture is made the difference, and difference is taken absolute value, then by all pixels block
The range value that difference is summed as the video curve point.Video curve is generated according to the method.
Step 703, calculating audio curve.Audio-frequency information is extracted from monitoring video, the sound before and after some time point is calculated
Sound size corresponds to the amplitude of the audio curve at time point as sonic profile, or is directly used as audio bent the oscillogram of audio
Line.
Step 704, show below the time schedule axle of player video recording analysis curve.By settings button, video recording is bent
Line can show or hide according to the hobby of user, increase the flexibility that user uses.
Step 705, according to video recording analysis curve dragging checking monitoring video recording.The transverse axis time of video recording curve plays with video recording
Time correspondence, the video recording situation that can directly instruct user to check at homologous thread.When user is fluctuated for some curve
During violent area interest, playing progress rate can be directly dragged at the time, the situation that checking monitoring video recording occurs.
Step 706, end.
The embodiments of the invention provide a kind of monitoring video analysis method and device, continuous figure is extracted from monitoring video
As sequence, described image sequence includes plurality of pictures, calculates adjacent image difference in described image sequence and is used as image curve
Amplitude, audio-frequency information is provided from the monitoring video, using sound variation amplitude as audio curve amplitude, using the time as horizontal stroke
Axle, draws the image curve and audio curve of the monitoring video, monitoring video is embodied by image curve and audio curve
The change of middle image and sound, provides reference to search the content in big section monitoring video, solves monitoring video and be not easy to
The problem of user searches the video content needed.
Compared with prior art, content of the technical scheme provided in an embodiment of the present invention not to monitoring video carries out intelligence point
Analysis draws an analysis result, but the analysis curve auxiliary user of generation video recording is monitored checking for video recording and browsed.Video
The video and multimedia recreation video of monitoring make a big difference, because camera is regarded in fixed angle shot for a long time
Frequently, the scene of shooting be also possible to the most of the time be it is static, so monitoring video may have be greatly user not
Static video recording interested.By browsing video recording analysis curve, which period video recording user can be very easily determined in
It is the stationary video without abnormal information, by user's abnormal conditions interested in which period.Similarly, it can be determined which
There is no sound in one period, have abnormal acoustic information period in which.In a cell, abnormal conditions very may be used
Can be that situations such as not clear personnel or vehicle pass through is occurred in that in monitoring visual field, the fluctuation of this when of analysis curve can violent one
A bit.By the auxiliary for analysis curve of recording a video, user can be absorbed in abnormal conditions interested as far as possible, big without spending
The amount time in the stationary video without actual information, effectively improves the efficiency of user.
One of ordinary skill in the art will appreciate that all or part of step of above-described embodiment can use computer journey
Sequence flow realizes that the computer program can be stored in a computer-readable recording medium, the computer program exists
(such as system, unit, device) is performed on corresponding hardware platform, upon execution, including the step of embodiment of the method it
One or its combination.
Alternatively, all or part of step of above-described embodiment can also use integrated circuit to realize, these steps can
To be fabricated to integrated circuit modules one by one respectively, or the multiple modules or step in them are fabricated to single integrated electricity
Road module is realized.So, the present invention is not restricted to any specific hardware and software combination.
Each device/functional module/functional unit in above-described embodiment can be realized using general computing device, it
Can concentrate on single computing device, can also be distributed on the network that multiple computing devices are constituted.
Each device/functional module/functional unit in above-described embodiment realized using in the form of software function module and as
Independent production marketing in use, can be stored in a computer read/write memory medium.Computer mentioned above
Read/write memory medium can be read-only storage, disk or CD etc..
Any one skilled in the art the invention discloses technical scope in, can readily occur in change or
Replace, should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with the guarantor described in claim
Shield scope is defined.
Claims (8)
1. a kind of monitoring video analysis method, it is characterised in that including:
Continuous image sequence is extracted from monitoring video, described image sequence includes the plurality of pictures of different time points;
Calculate the difference that corresponding picture and previous picture are sometime put in described image sequence;
Extract the sound variation amplitude at the time point;
According to the difference and the sound variation amplitude of the time point corresponding picture and previous picture, judge at the time point
Video situation of change;
The difference of the time point corresponding picture and its previous picture in described image sequence is existed as image curve
The amplitude at the time point;
Using the sound variation amplitude at the time point as audio curve the time point amplitude;
Using the time as transverse axis, the image curve and audio curve of the monitoring video are drawn.
2. monitoring video analysis method according to claim 1, it is characterised in that described corresponding according to the time point
Picture and the difference of previous picture and the sound variation amplitude in the image sequence, judge the video change at the time point
Situation is specially:
Time point corresponding picture and the difference of previous picture are bigger, then judge that time point epigraph change is bigger;
The sound variation amplitude at the time point is bigger, then judges that the time point upper sound variation is bigger.
3. monitoring video analysis method according to claim 1, it is characterised in that certain in the calculating described image sequence
One time point corresponding picture includes with the difference of previous picture:
The image-region of the monitoring video is divided into multiple block of pixels, the time point corresponding picture and previous picture is taken
Each block of pixels color average;
Picture corresponding to the time point and the color average of the correspondence position block of pixels of previous picture take the absolute of difference
Value;
The absolute value of the color average difference of whole block of pixels is added, obtained result is the time point corresponding figure
The difference of piece and previous picture.
4. monitoring video analysis method according to claim 1, it is characterised in that extract the sound at the time point and become
Change amplitude is specially:
The sound size for calculating the time point is used as the sound variation amplitude at the time point.
5. monitoring video analysis method according to claim 1, it is characterised in that extract the sound at the time point and become
Change amplitude is specially:
Using amplitude of the audio volume control figure of the audio-frequency information of the monitoring video on the time point as on the time point
Sound variation amplitude.
6. monitoring video analysis method according to claim 1, it is characterised in that described using the time as transverse axis, draws institute
After the step of stating image curve and the audio curve of monitoring video, in addition to:
Described image curve, the time shaft of audio curve are aligned with the time shaft of the monitoring video, simultaneous display.
7. a kind of monitoring video analytical equipment, it is characterised in that including:
Image sequence provides module, and for extracting continuous image sequence from monitoring video, described image sequence includes difference
The plurality of pictures at time point;
Picture difference calculating module, the difference of corresponding picture and previous picture is sometime put for calculating in described image sequence
Value;
Sound variation computing module, for extracting the sound variation amplitude at the time point;
Video changes judge module, becomes for the difference and the sound according to the time point corresponding picture and previous picture
Change amplitude, judges the video situation of change at the time point;
Image curve amplitude acquisition module, for by the time point corresponding picture and its previous figure in described image sequence
The difference of piece as image curve the amplitude at the time point;
Audio curve amplitude acquisition module, for using the sound variation amplitude at the time point as audio curve in the time
The amplitude of point;
Drawing of Curve module, image curve and audio curve for using the time as transverse axis, drawing the monitoring video.
8. monitoring video analytical equipment according to claim 7, it is characterised in that the device also includes:
Display module, for described image curve, the time shaft of audio curve to be aligned with the time shaft of the monitoring video, together
Step display.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210162170.0A CN103428406B (en) | 2012-05-23 | 2012-05-23 | Monitoring video analysis method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210162170.0A CN103428406B (en) | 2012-05-23 | 2012-05-23 | Monitoring video analysis method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103428406A CN103428406A (en) | 2013-12-04 |
CN103428406B true CN103428406B (en) | 2017-11-07 |
Family
ID=49652540
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210162170.0A Active CN103428406B (en) | 2012-05-23 | 2012-05-23 | Monitoring video analysis method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103428406B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105302701B (en) * | 2014-06-23 | 2020-02-28 | 中兴通讯股份有限公司 | Method, device and equipment for testing reaction time of terminal user interface |
JP6063971B2 (en) * | 2015-01-29 | 2017-01-18 | 京セラドキュメントソリューションズ株式会社 | Image processing device |
CN106338711A (en) * | 2016-08-30 | 2017-01-18 | 康佳集团股份有限公司 | Voice directing method and system based on intelligent equipment |
CN107146372A (en) * | 2017-04-11 | 2017-09-08 | 深圳市粮食集团有限公司 | A kind of method and system by video identification production line working condition |
CN108712671A (en) * | 2018-04-26 | 2018-10-26 | 国政通科技股份有限公司 | Monitor video document play-back method, device and terminal device |
CN108769572A (en) * | 2018-04-26 | 2018-11-06 | 国政通科技股份有限公司 | Monitor video file generated, device and terminal device |
CN112399069B (en) * | 2019-08-16 | 2022-06-07 | RealMe重庆移动通信有限公司 | Image encoding method and apparatus, storage medium, and electronic device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5099322A (en) * | 1990-02-27 | 1992-03-24 | Texas Instruments Incorporated | Scene change detection system and method |
CN1687929A (en) * | 2005-05-13 | 2005-10-26 | 北京工业大学 | Video searching method based on video characteristic curve |
CN101539925A (en) * | 2008-03-20 | 2009-09-23 | 中国科学院计算技术研究所 | Audio/video file-abstracting method based on attention-degree analysis |
CN101556727A (en) * | 2008-04-10 | 2009-10-14 | 上海宇嵌电子科技有限公司 | Electronic device for energy-saving and environment-protecting regulation and control and safe preservation to household environment |
CN101577114A (en) * | 2009-06-18 | 2009-11-11 | 北京中星微电子有限公司 | Method and device for implementing audio visualization |
CN102025970A (en) * | 2010-12-15 | 2011-04-20 | 广东威创视讯科技股份有限公司 | Method and system for automatically adjusting display mode of video conference |
CN102033707A (en) * | 2010-12-15 | 2011-04-27 | 广东威创视讯科技股份有限公司 | System and method for processing audio/video data in multi-window display |
-
2012
- 2012-05-23 CN CN201210162170.0A patent/CN103428406B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5099322A (en) * | 1990-02-27 | 1992-03-24 | Texas Instruments Incorporated | Scene change detection system and method |
CN1687929A (en) * | 2005-05-13 | 2005-10-26 | 北京工业大学 | Video searching method based on video characteristic curve |
CN101539925A (en) * | 2008-03-20 | 2009-09-23 | 中国科学院计算技术研究所 | Audio/video file-abstracting method based on attention-degree analysis |
CN101556727A (en) * | 2008-04-10 | 2009-10-14 | 上海宇嵌电子科技有限公司 | Electronic device for energy-saving and environment-protecting regulation and control and safe preservation to household environment |
CN101577114A (en) * | 2009-06-18 | 2009-11-11 | 北京中星微电子有限公司 | Method and device for implementing audio visualization |
CN102025970A (en) * | 2010-12-15 | 2011-04-20 | 广东威创视讯科技股份有限公司 | Method and system for automatically adjusting display mode of video conference |
CN102033707A (en) * | 2010-12-15 | 2011-04-27 | 广东威创视讯科技股份有限公司 | System and method for processing audio/video data in multi-window display |
Also Published As
Publication number | Publication date |
---|---|
CN103428406A (en) | 2013-12-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103428406B (en) | Monitoring video analysis method and device | |
JP6801760B2 (en) | Image processing equipment, surveillance systems, image processing methods, and programs | |
CN110049206B (en) | Image processing method, image processing apparatus, and computer-readable storage medium | |
EP3343435A1 (en) | Multi-camera object tracking | |
Sharif et al. | An entropy approach for abnormal activities detection in video streams | |
CN103700087B (en) | mobile detection method and device | |
CN102156880B (en) | Method for detecting abnormal crowd behavior based on improved social force model | |
US8310542B2 (en) | Segmenting time based on the geographic distribution of activity in sensor data | |
Mancas et al. | Abnormal motion selection in crowds using bottom-up saliency | |
JP4705090B2 (en) | Smoke sensing device and method | |
US20180039601A1 (en) | Event signal processing method and apparatus | |
US20120314907A1 (en) | System and method for predicting object location | |
US20200363903A1 (en) | Engagement analytic system and display system responsive to interaction and/or position of users | |
CN106778688B (en) | Method for detecting crowd flow abnormal event in monitoring video in crowded scene | |
CN104717457A (en) | Video condensing method and device | |
CN101321269A (en) | Passenger flow volume detection method and system based on computer vision | |
CN104933412A (en) | Abnormal state detection method of medium and high density crowd | |
Zhao et al. | Crowd instability analysis using velocity-field based social force model | |
US9082042B2 (en) | System and method for classification of moving object during video surveillance | |
CN107480653A (en) | passenger flow volume detection method based on computer vision | |
CN110020618A (en) | A kind of crowd's abnormal behaviour monitoring method can be used for more shooting angle | |
CN105245817B (en) | Video recording playback method and its device | |
CN101984451A (en) | Video-based shielded flame detecting method and device | |
Lyu et al. | Violence detection algorithm based on local spatio-temporal features and optical flow | |
Lee et al. | Crowd behavior representation using motion influence matrix for anomaly detection |
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 |