CN103024361A - Method and device for verifying capture images of video - Google Patents

Method and device for verifying capture images of video Download PDF

Info

Publication number
CN103024361A
CN103024361A CN2012105866745A CN201210586674A CN103024361A CN 103024361 A CN103024361 A CN 103024361A CN 2012105866745 A CN2012105866745 A CN 2012105866745A CN 201210586674 A CN201210586674 A CN 201210586674A CN 103024361 A CN103024361 A CN 103024361A
Authority
CN
China
Prior art keywords
video
key images
result
field picture
command information
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
Application number
CN2012105866745A
Other languages
Chinese (zh)
Other versions
CN103024361B (en
Inventor
苏聪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
TIANJIN AIDIER SOFTWARE DEVELOPMENT Co Ltd
Original Assignee
TIANJIN AIDIER SOFTWARE DEVELOPMENT Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by TIANJIN AIDIER SOFTWARE DEVELOPMENT Co Ltd filed Critical TIANJIN AIDIER SOFTWARE DEVELOPMENT Co Ltd
Priority to CN201210586674.5A priority Critical patent/CN103024361B/en
Publication of CN103024361A publication Critical patent/CN103024361A/en
Application granted granted Critical
Publication of CN103024361B publication Critical patent/CN103024361B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Closed-Circuit Television Systems (AREA)

Abstract

The invention provides a method for verifying capture images of a video. The method includes acquiring the real-time video; determining critical images in the real-time video; acquiring instruction information from the critical images; capturing lower n critical images from the critical images of the captured video; and acquiring instruction information from the lower n critical images, and judging whether the instruction information is correct or not according to a mode that the instruction information is correct if {nX(a result of the n<th> image)+(n-1)X[a result of the (n-1)<th> image)]+...+1X(a result of the first image)}/(n+n-1+...+1) is larger than or equal to 0.5, and the instruction information is incorrect if {nX(the result of the n<th> image)+(n-1)X[the result of the (n-1)<th> image]+...+1X(the result of the first image)}/n+n-1+...+1 is smaller than 0.5. The method has the advantages that whether the capture images are effective or not can be judged within a short time, the possibility of false alarms is further reduced, the method for verifying the capture images of the video is simple and flexible and is high in accuracy, and the like.

Description

A kind of method of calibration and device to the video capture image
Technical field
The invention belongs to field of video image processing, especially relate to a kind of method of calibration to the video capture image and device.
Background technology
Video monitoring is the important component part of safety and protection system, and it is the stronger integrated system of a kind of prevention ability.Video monitoring is directly perceived with it, accurately, in time and the information content abundant and be widely used in many occasions.In recent years, along with computer, network and image are processed, the develop rapidly of transmission technology, Video Supervision Technique has also had significant progress.
In video monitoring, owing to be subjected to the impact of various objective condition, only voucher width of cloth image is judged the various wrongheaded situations of as easy as rolling off a log appearance, the situation of various wrong reports occurs for the identification result of image.
Summary of the invention
The problem to be solved in the present invention provides method and device, especially is fit to fast consecutive image be judged.
For solving the problems of the technologies described above, the technical solution used in the present invention is:
A kind of method of calibration to the video capture image comprises:
1) obtains instant video;
2) from instant video, determine key images;
3) from key images, obtain command information;
4) descend n frame key images in the key images in the seizure video;
5) from lower n frame key images, obtain command information;
6) whether correct according to following manner decision instruction information:
N*(n two field picture result)+(n-1) * (n-1 two field picture result)+... 1*(the 1st two field picture result)/n+n-1+ ... + 1 〉=0.5 command information is errorless;
N*(n two field picture result)+(n-1) * (n-1 two field picture result)+... 1*(the 1st two field picture result)/n+n-1+ ... + 1<0.5 command information is incorrect.
According to a further aspect in the invention, also proposed a kind of calibration equipment to the video capture image, having comprised:
The video monitoring unit is in order to obtain the video of surrounding road condition;
Image acquisition unit is in order to the resulting video acquisition key images from the video monitoring unit;
Graphics processing unit is in order to obtain command information from key images;
And verification unit, in order to the command information of each frame key images of integrated treatment verification, and draw final result.
Further, described calibration equipment also comprises reminding unit, in order to final result is informed the user.
Advantage and good effect that the present invention has are: owing to adopt technique scheme, can whether effective to catching image at short notice, and further reduced the possibility of wrong report, this method of calibration has simply, flexible, high accuracy for examination.
Description of drawings
Fig. 1 is schematic flow sheet of the present invention
Embodiment
The invention will be further elaborated below in conjunction with drawings and Examples, the video monitoring unit of native system is in work always, in order to catch the real-time change of video, image data unit is carried out sampling processing according to the frequency of setting to video image, this frequency can be set as the case may be, can take 1hz or higher frequency, its arrangement is the two field picture at certain hour interval, and judging whether to belong to the predefined key images of system according to the content in the two field picture, key images refers to comprise sets the visible image of multi view such as object of which movement.Graphics processing unit is processed the key images that previous step obtains, with extracting such as figures such as objects in the key images, and with memory in the image of pre-stored compare, if comparison meets, send reminding unit to then with its record, and with these information, reminding unit passes through voice-output unit, above-mentioned information exchange is crossed speech play to the staff, for staff's reference.
In practical work process, because the restriction of other conditions such as distance and light, be difficult to only just can obtain corresponding information by a width of cloth key images, also be provided with in the present invention an authentication unit, this authentication unit is after graphics processing unit gets access to command information first, the frequency that image data unit is set is changed, with frequency modification to 3 ~ 5Hz, in order to the follow-up key images of continuous acquisition, processing subsequently and described above to obtain the command information process similar, to compare from the command information of rear a few frame key images and the command information of the first frame key images again, if command information is identical, then send these information to reminding unit in order to inform the staff.If not identical with the command information of the first frame key images from the command information of follow-up key images, then calculate according to following manner:
N*(n two field picture result)+(n-1) (n-1 two field picture result)+... 1(the first two field picture result)/n+n-1+ ... + 1 〉=0.5 confirms that command information is errorless
N*(n two field picture result)+(n-1) (n-1 two field picture result)+... 1(the first two field picture result)/n+n-1+ ... + 1<0.5 command information is incorrect
Wherein, described image result be judged as be labeled as 1, be judged as and no be not labeled as 0.
Can whether accurate through the comprehensive decision instruction information of continuous a few frame key images according to above-mentioned method, further improved the accuracy rate of advance notice, reduced the probability of wrong report.
More than one embodiment of the present of invention are had been described in detail, but described content only is preferred embodiment of the present invention, can not be considered to be used to limiting practical range of the present invention.All equalizations of doing according to the present patent application scope change and improve etc., all should still belong within the patent covering scope of the present invention.

Claims (3)

1. method of calibration to the video capture image comprises:
1) obtains instant video;
2) from instant video, determine key images;
3) from key images, obtain command information;
4) descend n frame key images in the key images in the seizure video;
5) from lower n frame key images, obtain command information;
6) whether correct according to following manner decision instruction information:
N*(n two field picture result)+(n-1) * (n-1 two field picture result)+... 1*(the 1st two field picture result)/n+n-1+ ... + 1 〉=0.5 command information is errorless;
N*(n two field picture result)+(n-1) * (n-1 two field picture result)+... 1*(the 1st two field picture result)/n+n-1+ ... + 1<0.5 command information is incorrect.
2. the calibration equipment of a method of calibration according to claim 1 comprises:
The video monitoring unit is in order to obtain the video of surrounding road condition;
Image acquisition unit is in order to the resulting video acquisition key images from the video monitoring unit;
Graphics processing unit is in order to obtain command information from key images;
And
Verification unit in order to the command information of each frame key images of integrated treatment verification, and draws final result.
3. calibration equipment according to claim 2, it is characterized in that: described calibration equipment also comprises reminding unit, in order to final result is informed the user.
CN201210586674.5A 2012-12-28 2012-12-28 A kind of method of calibration to video capture image and device Active CN103024361B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210586674.5A CN103024361B (en) 2012-12-28 2012-12-28 A kind of method of calibration to video capture image and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210586674.5A CN103024361B (en) 2012-12-28 2012-12-28 A kind of method of calibration to video capture image and device

Publications (2)

Publication Number Publication Date
CN103024361A true CN103024361A (en) 2013-04-03
CN103024361B CN103024361B (en) 2015-10-14

Family

ID=47972440

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210586674.5A Active CN103024361B (en) 2012-12-28 2012-12-28 A kind of method of calibration to video capture image and device

Country Status (1)

Country Link
CN (1) CN103024361B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101295405A (en) * 2008-06-13 2008-10-29 西北工业大学 Portrait and vehicle recognition alarming and tracing method
CN101626489A (en) * 2008-07-10 2010-01-13 苏国政 Method and system for intelligently identifying and automatically tracking objects under unattended condition
CN101715111A (en) * 2009-11-16 2010-05-26 南京邮电大学 Method for automatically searching abandoned object in video monitoring
CN102842211A (en) * 2012-09-07 2012-12-26 嘉兴电力局 Monitoring and early warning system and monitoring and early warning method for prevention of external force of transmission line based on image recognition

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101295405A (en) * 2008-06-13 2008-10-29 西北工业大学 Portrait and vehicle recognition alarming and tracing method
CN101626489A (en) * 2008-07-10 2010-01-13 苏国政 Method and system for intelligently identifying and automatically tracking objects under unattended condition
CN101715111A (en) * 2009-11-16 2010-05-26 南京邮电大学 Method for automatically searching abandoned object in video monitoring
CN102842211A (en) * 2012-09-07 2012-12-26 嘉兴电力局 Monitoring and early warning system and monitoring and early warning method for prevention of external force of transmission line based on image recognition

Also Published As

Publication number Publication date
CN103024361B (en) 2015-10-14

Similar Documents

Publication Publication Date Title
CN110287923B (en) Human body posture acquisition method, device, computer equipment and storage medium
KR101309366B1 (en) System and Method for Monitoring Emergency Motion based Image
US11132887B2 (en) Eyeglasses-type wearable terminal, control method thereof, and control program
CN107679471B (en) Indoor personnel air post detection method based on video monitoring platform
US20190332856A1 (en) Person&#39;s behavior monitoring device and person&#39;s behavior monitoring system
WO2010079921A3 (en) Video signal processing method and apparatus using depth information
WO2007070738A3 (en) Methods and systems for enabling depth and direction detection when interfacing with a computer program
US20070229663A1 (en) Image processing apparatus, monitoring camera, and image monitoring system
WO2008056229A3 (en) Eye opening detection system and method of detecting eye opening
CN102262727A (en) Method for monitoring face image quality at client acquisition terminal in real time
WO2015133195A1 (en) Information processing device, information processing method, and program
CA2795896A1 (en) Method and system for security system tampering detection
WO2007143642A3 (en) Method and system for the detection of removed objects in video images
CN105957300B (en) A kind of wisdom gold eyeball identification is suspicious to put up masking alarm method and device
KR20140110484A (en) Risk behavior detection method using image information
CN113191293B (en) Advertisement detection method, device, electronic equipment, system and readable storage medium
US20110280442A1 (en) Object monitoring system and method
CN113223046A (en) Method and system for identifying prisoner behaviors
JP2014007498A (en) Disaster detection system
CN105354552A (en) Human face identification and expression analysis based online monitoring system and method
JP5115763B2 (en) Image processing apparatus, content distribution system, image processing method, and program
CN103024361A (en) Method and device for verifying capture images of video
Dong et al. Fall alarm and inactivity detection system design and implementation on raspberry pi
KR20130094488A (en) System and method for monitoring emergency motion based image
JP2020095651A (en) Productivity evaluation system, productivity evaluation device, productivity evaluation method, and program

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant