CN103426181A - Automatic frame rate changing wire-mixing detection method - Google Patents
Automatic frame rate changing wire-mixing detection method Download PDFInfo
- Publication number
- CN103426181A CN103426181A CN2012101649176A CN201210164917A CN103426181A CN 103426181 A CN103426181 A CN 103426181A CN 2012101649176 A CN2012101649176 A CN 2012101649176A CN 201210164917 A CN201210164917 A CN 201210164917A CN 103426181 A CN103426181 A CN 103426181A
- Authority
- CN
- China
- Prior art keywords
- frame
- mixing
- wire
- frame rate
- frame per
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides an automatic frame rate changing wire-mixing detection method by which a wire-mixing detection speed can be substantially improved. The method comprises the following steps of: (1). processing picture frame generation, i.e., obtaining a picture frame by a fixation frame rate F first, obtaining frame interval time according to a current optimal frame rate, then calculating a time difference between current time and the last processing picture frame time, if the time difference is greater than the frame interval time, taking a current frame as a processing picture frame, or skipping the current frame without processing; (2). background generation and updating; (3). foreground detection and frame rate updating; (4). tracking and frame rate updating; and (5). wire-mixing result obtaining, i.e., for each generated locus, taking whether each locus passes a drawn wire-mixing strategy as a wire-mixing result for outputting. By using the automatic frame rate changing wire-mixing detection method, time consumed in wire-mixing detection can be reduced, and the effects are especially good for a video with sparse objects.
Description
Technical field
The present invention relates to a kind of line detecting method of mixing, especially a kind of automatic change frame per second mix line detecting method.
Background technology
In recent years, Video Supervision Technique is applied in safety-security area more and more, along with the continuous growth of monitor data amount, makes the monitor staff need to use up a large amount of time data are manually filtered, therefrom select useful video information, and work complicated, that repeat usually makes them unable to do what one wishes.The monitor staff in the urgent need to have a kind of work together lighter, be easier to the operation and the management product substitute original system.So intelligent video technology is arisen at the historic moment, enter people's life.
Intelligent video is that computer vision methods is incorporated in intelligent monitoring.This technology comprises by sequence of video images is moved or the content of the aspects such as detection, target classification and behavior understanding of static target automatically, purpose is to set up mapping relations between image and iamge description, thereby makes computing machine can analyze and understand the content in video pictures.
Mixing the line target detection technique is the important technology in intelligent video analysis, in the application such as intrusion detection, stream of people's statistics, public security case investigation, has broad application prospects.But especially the existing algorithm of the historical Video processing of magnanimity has the problem that efficiency is not high in actual applications.
To mix in order improving the efficiency that line detects, usually to use now high performance computing machine, but improved like this cost, and very sparse for most video content target, make a large amount of calculating all waste.
Summary of the invention
The invention provides a kind of line detecting method of mixing that can significantly promote the automatic change frame per second of mixing the speed that line detects.
Realize the object of the invention automatic change frame per second mix line detecting method, comprise the steps:
(1) processing picture frame generates: at first with fixing frame per second F, obtain picture frame; Then according to current optimum frame per second, obtain the frame period time; Calculate again current time and upper one mistiming of processing picture frame, if this mistiming be greater than the frame period time, just using present frame as the processing picture frame; Otherwise just skip, disregard;
(2) Background generation and renewal: ask for motionless zone according to frame-to-frame differences, these zones are carried out to the renewal of background;
(3) foreground detection with upgrade frame per second: computed image and background image poor, statistics maximum image block size, if be less than certain threshold value, just upgrade frame per second, and finish the processing of this frame;
(4) follow the tracks of and upgrade frame per second: the foreground blocks stable to continuous several frames forms target, the target corresponding at new frame to target is as the result of following the tracks of and formation track, to track statistics in present frame and previous frame image pitch from as speed, utilize maximal rate V in all tracks of this two field picture
maxDetermine the optimum frame per second of upgrading;
(5) whether whether mixing toe-in really obtains: to each track produced, depending on it, mix the line decision-making and really export as mixing toe-in by drawn.
The beneficial effect of mixing line detecting method of automatic change frame per second of the present invention is as follows:
Automatic change frame per second of the present invention mix line detecting method, reduced and mixed the time loss that line detects, especially for target, comparatively sparse video effect is good.
The accompanying drawing explanation
The process flow diagram of mixing line detecting method that Fig. 1 is automatic change frame per second of the present invention.
Embodiment
As shown in Figure 1, automatic change frame per second of the present invention mix line detecting method, comprise the steps:
(1) processing picture frame generates: at first with fixing frame per second F, obtain picture frame; Then according to current optimum frame per second, obtain the frame period time; Calculate again current time and upper one mistiming of processing picture frame, if this mistiming be greater than the frame period time, just using present frame as the processing picture frame; Otherwise just skip, disregard;
(2) Background generation and renewal: ask for motionless zone according to frame-to-frame differences, these zones are carried out to the renewal of background;
(3) foreground detection with upgrade frame per second: computed image and background image poor, statistics maximum image block size, if be less than certain threshold value, just upgrade frame per second, and finish the processing of this frame;
(4) follow the tracks of and upgrade frame per second: the foreground blocks stable to continuous several frames forms target, the target corresponding at new frame to target is as the result of following the tracks of and formation track, to track statistics in present frame and previous frame image pitch from as speed, utilize maximal rate V in all tracks of this two field picture
maxDetermine the optimum frame per second of upgrading;
(5) whether whether mixing toe-in really obtains: to each track produced, depending on it, mix the line decision-making and really export as mixing toe-in by drawn.
The specific embodiment of mixing line detecting method of automatic change frame per second of the present invention is as follows:
The processing picture frame generates, and at first with fixing frame per second F, obtains picture frame; Then obtain the frame period time (1/Fo) according to current optimum frame per second Fo; Calculate again the mistiming Td of current time and a upper processing picture frame, if Td>=1/Fo, just using present frame as processing picture frame; Otherwise just skip and disregard;
Background generation and renewal, ask for motionless zone according to frame-to-frame differences, these zones carried out to the renewal of background;
Foreground detection with upgrade frame per second, computed image and background image poor, add up the maximum image block size, if be less than certain threshold value, just upgrade frame per second and be: F
o=max (F
o* 0.9, F
min), and finish this frame and process;
Follow the tracks of and upgrade frame per second, the foreground blocks stable to continuous several frames forms target, to target, the target corresponding at new frame be as the result of following the tracks of with form track, to the track statistics in present frame and previous frame image pitch from as speed, utilize maximal rate V in all tracks of this two field picture
maxDetermine the optimum frame per second F upgraded
o=max (F
o, α V
max), α chooses as empirical parameter;
Mix toe-in and really obtain, to each track produced, depending on it, whether by drawn, mix the line decision-making and whether really export as mixing toe-in.
Embodiment recited above is described the preferred embodiment of the present invention; not scope of the present invention is limited; design under spiritual prerequisite not breaking away from the present invention; various distortion and improvement that the common engineering technical personnel in this area make technical solution of the present invention, all should fall in the definite protection domain of claims of the present invention.
Claims (1)
1. the line detecting method of mixing that automatically changes frame per second, comprise the steps:
(1) processing picture frame generates: at first with fixing frame per second F, obtain picture frame; Then according to current optimum frame per second, obtain the frame period time; Calculate again current time and upper one mistiming of processing picture frame, if this mistiming be greater than the frame period time, just using present frame as the processing picture frame; Otherwise just skip, disregard;
(2) Background generation and renewal: ask for motionless zone according to frame-to-frame differences, these zones are carried out to the renewal of background;
(3) foreground detection with upgrade frame per second: computed image and background image poor, statistics maximum image block size, if be less than certain threshold value, just upgrade frame per second, and finish the processing of this frame;
(4) follow the tracks of and upgrade frame per second: the foreground blocks stable to continuous several frames forms target, the target corresponding at new frame to target is as the result of following the tracks of and formation track, to track statistics in present frame and previous frame image pitch from as speed, utilize maximal rate V in all tracks of this two field picture
maxDetermine the optimum frame per second of upgrading;
(5) whether whether mixing toe-in really obtains: to each track produced, depending on it, mix the line decision-making and really export as mixing toe-in by drawn.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012101649176A CN103426181A (en) | 2012-05-25 | 2012-05-25 | Automatic frame rate changing wire-mixing detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012101649176A CN103426181A (en) | 2012-05-25 | 2012-05-25 | Automatic frame rate changing wire-mixing detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103426181A true CN103426181A (en) | 2013-12-04 |
Family
ID=49650871
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012101649176A Pending CN103426181A (en) | 2012-05-25 | 2012-05-25 | Automatic frame rate changing wire-mixing detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103426181A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105760132A (en) * | 2016-02-03 | 2016-07-13 | 广东欧珀移动通信有限公司 | Method, device and mobile device for achieving frame rate dynamic refreshing |
CN108881119A (en) * | 2017-05-12 | 2018-11-23 | 华为技术有限公司 | A kind of methods, devices and systems of video concentration |
CN110610514A (en) * | 2018-06-15 | 2019-12-24 | 株式会社日立制作所 | Method, device and electronic equipment for realizing multi-target tracking |
CN112200830A (en) * | 2020-09-11 | 2021-01-08 | 山东信通电子股份有限公司 | Target tracking method and device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101017573A (en) * | 2007-02-09 | 2007-08-15 | 南京大学 | Method for detecting and identifying moving target based on video monitoring |
CN101221663A (en) * | 2008-01-18 | 2008-07-16 | 电子科技大学中山学院 | Intelligent monitoring and alarming method based on movement object detection |
CN101266710A (en) * | 2007-03-14 | 2008-09-17 | 中国科学院自动化研究所 | An all-weather intelligent video analysis monitoring method based on a rule |
JP2009273023A (en) * | 2008-05-09 | 2009-11-19 | Fujifilm Corp | Imaging device, imaging method, focusing control method, and program |
JP2010088049A (en) * | 2008-10-02 | 2010-04-15 | Nikon Corp | Imaging apparatus and image recording method |
CN102096924A (en) * | 2010-11-18 | 2011-06-15 | 无锡中星微电子有限公司 | Method for adjusting detection frame rate |
-
2012
- 2012-05-25 CN CN2012101649176A patent/CN103426181A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101017573A (en) * | 2007-02-09 | 2007-08-15 | 南京大学 | Method for detecting and identifying moving target based on video monitoring |
CN101266710A (en) * | 2007-03-14 | 2008-09-17 | 中国科学院自动化研究所 | An all-weather intelligent video analysis monitoring method based on a rule |
CN101221663A (en) * | 2008-01-18 | 2008-07-16 | 电子科技大学中山学院 | Intelligent monitoring and alarming method based on movement object detection |
JP2009273023A (en) * | 2008-05-09 | 2009-11-19 | Fujifilm Corp | Imaging device, imaging method, focusing control method, and program |
JP2010088049A (en) * | 2008-10-02 | 2010-04-15 | Nikon Corp | Imaging apparatus and image recording method |
CN102096924A (en) * | 2010-11-18 | 2011-06-15 | 无锡中星微电子有限公司 | Method for adjusting detection frame rate |
Non-Patent Citations (1)
Title |
---|
黄孝建: "基于视频图像的绊线检测方法研究", 《计算机与现代化》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105760132A (en) * | 2016-02-03 | 2016-07-13 | 广东欧珀移动通信有限公司 | Method, device and mobile device for achieving frame rate dynamic refreshing |
CN105760132B (en) * | 2016-02-03 | 2018-11-20 | 广东欧珀移动通信有限公司 | Realize the method, apparatus and mobile device of frame per second dynamic refresh |
CN108881119A (en) * | 2017-05-12 | 2018-11-23 | 华为技术有限公司 | A kind of methods, devices and systems of video concentration |
CN108881119B (en) * | 2017-05-12 | 2021-02-12 | 华为技术有限公司 | Method, device and system for video concentration |
CN110610514A (en) * | 2018-06-15 | 2019-12-24 | 株式会社日立制作所 | Method, device and electronic equipment for realizing multi-target tracking |
CN110610514B (en) * | 2018-06-15 | 2023-09-19 | 株式会社日立制作所 | Method, device and electronic equipment for realizing multi-target tracking |
CN112200830A (en) * | 2020-09-11 | 2021-01-08 | 山东信通电子股份有限公司 | Target tracking method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11217088B2 (en) | Alert volume normalization in a video surveillance system | |
CN101236656B (en) | Movement target detection method based on block-dividing image | |
CN103077388B (en) | Fast text towards portable computing device sweeps the method for reading | |
CN107566781A (en) | Video frequency monitoring method and video monitoring equipment | |
CN104966304B (en) | Multi-target detection tracking based on Kalman filtering and nonparametric background model | |
CN103426181A (en) | Automatic frame rate changing wire-mixing detection method | |
CN103413444A (en) | Traffic flow surveying and handling method based on unmanned aerial vehicle high-definition video | |
US10878227B2 (en) | Unusual motion detection method and system | |
CN102426785B (en) | Traffic flow information perception method based on contour and local characteristic point and system thereof | |
CN101727672A (en) | Method for detecting, tracking and identifying object abandoning/stealing event | |
CN101216943B (en) | A method for video moving object subdivision | |
CN105160297A (en) | Masked man event automatic detection method based on skin color characteristics | |
CN104159088A (en) | System and method of remote monitoring of intelligent vehicle | |
Ling et al. | A background modeling and foreground segmentation approach based on the feedback of moving objects in traffic surveillance systems | |
CN102831472A (en) | People counting method based on video flowing image processing | |
CN103425960B (en) | Fast moving objects method for detecting in a kind of video | |
CN105578258A (en) | Method and device of video preprocessing and video playback | |
CN103049748A (en) | Behavior-monitoring method and behavior-monitoring system | |
Balu et al. | Smart traffic congestion control system | |
CN103425958A (en) | Method for detecting non-movable objects in video | |
CN101877135A (en) | Moving target detecting method based on background reconstruction | |
CN103426180B (en) | Video wire mixing detection method | |
CN107122285A (en) | A kind of multithread process control Dynamic Announce and intelligence change System and method for | |
CN111696142A (en) | Rapid face detection method and system | |
CN104754181B (en) | A kind of video noise estimation method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131204 |