CN110765932B - Scene change sensing method - Google Patents
Scene change sensing method Download PDFInfo
- Publication number
- CN110765932B CN110765932B CN201911005224.0A CN201911005224A CN110765932B CN 110765932 B CN110765932 B CN 110765932B CN 201911005224 A CN201911005224 A CN 201911005224A CN 110765932 B CN110765932 B CN 110765932B
- Authority
- CN
- China
- Prior art keywords
- video
- picture
- pictures
- memory
- video 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention provides a scene change sensing method, which comprises the steps of firstly, initializing a message queue and setting original pictures; step two, capturing video pictures according to a preset time period; cutting the intercepted video picture, and comparing and analyzing the cut video picture with the original picture; step four, if the picture is found to be the same as the original picture, feeding back the picture to the system without any processing; if the video pictures are different, storing the cut video pictures into a memory, and continuously executing the step five; step five, after waiting for a preset time period, intercepting the video picture again; step six, cutting the video pictures obtained in the step five, and comparing and analyzing the video pictures with the video pictures stored in the memory; step seven, if the video picture is found to be the same as the video picture stored in the memory, feeding back the video picture to the system execution return preset position; if the video pictures are different, storing the cut video pictures in the step six into a memory, replacing the video pictures stored originally, and continuously executing the step five.
Description
Technical Field
The invention relates to a video image analysis method, in particular to a scene change perception method.
Background
With the continuous updating of security industry standards, the promotion of AI algorithms, artificial intelligence and the like. Automation and intellectualization have become trends in security and related industries. The security, automation and intellectualization updating promotes the compatibility and intellectualization requirements of the national security industry platform. Along with the continuous expansion of the intelligent security range, the application of video analysis algorithm-based video analysis algorithm has become the development direction of security industry.
At present, only pictures are compared in the field, and the pictures are not actually used in scenes. The scene change sensing method provided by the invention can effectively judge whether the scene monitored by the front end meets the analysis requirement, further accurately position and lock the monitored scene, and improve the accuracy of automated law enforcement.
Disclosure of Invention
In order to solve the above problems, the present invention proposes a scene change sensing method.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a scene change awareness method comprising the steps of:
step one: initializing a message queue, a real-time monitoring service and a coding library, initializing monitoring area setting and further obtaining original pictures of the monitoring area;
step two: acquiring a monitoring video in real time through a camera, and intercepting video pictures according to a preset time interval period;
step three: cutting the intercepted video picture, reserving a picture corresponding to the initial monitoring area, and comparing and analyzing the picture with the original picture;
step four: if the image is found to be the same as the original image, feeding back the image to the system without any processing; if the video picture is found to be different from the original picture, storing the cut video picture in the third step into a memory, and continuously executing the fifth step;
step five: continuously waiting for a preset time interval period, and then intercepting video pictures again;
step six: cutting the video pictures obtained in the step five, reserving the pictures corresponding to the video pictures stored in the memory, and comparing and analyzing the pictures with the video pictures stored in the memory;
step seven: if the video picture is found to be the same as the video picture stored in the memory, feeding back a command for returning to a preset position to the system; if the video picture is found to be different from the video picture stored in the memory, storing the video picture cut in the step six into the memory, replacing the video picture stored in the memory in advance, and continuing to execute the step five.
Preferably, the image comparison analysis adopts a convolutional neural network method to perform feature comparison.
Preferably, the preset time interval period is 5min.
Preferably, the preset position in the step seven refers to a position where the camera acquires an original picture of the monitoring area.
Preferably, the camera is a high-definition camera with more than 200 ten thousand pixels, and can be a high-definition ball machine, a dynamic ball gun machine or a high-point ball machine.
The method and the device can accurately position the change problem of the preset position, solve the problem that the analysis result of the video image is different due to the influence of the pixels of the front-end camera, effectively judge whether the scene monitored by the front end meets the analysis requirement, further accurately position and lock the monitored scene, and improve the accuracy of automatic law enforcement.
Drawings
The accompanying drawings are included to provide a further understanding of the invention.
In the drawings:
fig. 1 is a block diagram of a scene change awareness method according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, a scene change sensing method includes the following steps:
step one: initializing a message queue, a real-time monitoring service and a coding library, initializing monitoring area setting so as to acquire original pictures of the monitoring area, and preparing other environments;
step two: acquiring a monitoring video in real time through a camera, and intercepting video pictures according to a preset time interval period which is 5min; the camera is a high-definition camera with more than 200 ten thousand pixels and can be a high-definition ball machine, a dynamic ball gun machine or a high-point ball machine;
step three: cutting the intercepted video picture by an image processing technology, reserving a picture corresponding to an initial monitoring area, comparing and analyzing the picture with an original picture, and comparing the features by adopting a convolutional neural network method;
step four: if the image is found to be the same as the original image, feeding back the image to the system without any processing; if the video picture is found to be different from the original picture, storing the cut video picture in the third step into a memory, and continuously executing the fifth step;
step five: continuously waiting for a preset time interval period, and then intercepting video pictures again;
step six: cutting the video pictures obtained in the step five, reserving the pictures corresponding to the video pictures stored in the memory, and comparing and analyzing the pictures with the video pictures stored in the memory;
step seven: if the video picture is found to be the same as the video picture stored in the memory, feeding back a command for returning to a preset position to the system; if the video picture is found to be different from the video picture stored in the memory, storing the video picture cut in the step six into the memory, replacing the video picture stored in the memory in advance, and continuing to execute the step five. The preset position refers to the position of the camera for acquiring the original picture of the monitoring area.
The invention provides a quick linear tracking method for us through a neural network comparison method, and simultaneously lays a certain foundation for subsequent video processing.
The general process of the image contrast analysis is as follows: selecting an image which does not generate change in the original image as a reference object, marking a specific position, selecting an image corresponding to the four sides of the display screen of the monitoring system as a reference mark, cutting and acquiring a new image corresponding to the four sides of the display screen through the image when performing image comparison analysis, matching the new image with the image corresponding to the four sides of the original display screen, if matching is successful, indicating that the shooting scene of the camera is not changed, and if matching is unsuccessful, indicating that the shooting scene of the camera is changed.
The technical scheme adopted by the invention is as follows: and pre-analyzing the code stream, extracting pictures from the video stream according to frames, and setting the immovable position of the marked pictures. After the program is started, pictures are extracted from the video stream at regular intervals of 5 minutes, gray values of the pictures are compared with marked patterns, the pictures are identified as the same scene with consistency of more than 75%, the scene is judged to be unchanged, and otherwise, the scene is judged to be changed. And finally informing the application of the scheduling algorithm of the result of the research and judgment, and releasing all resources.
Setting original pictures and partial areas in the pictures according to preset bits, carrying out round inspection and monitoring according to set time intervals, and comparing the pictures with the original pictures after cutting the pictures, wherein the comparison results are the same, the description scenes are the same, and the algorithm informs the system (namely the video monitoring system) that no change exists. If the comparison results are different, the scene change is indicated, in order to prevent the scene from still changing, the algorithm does not immediately inform the system to return to the preset position, the existing picture is temporarily stored, after waiting for the next round of inspection, the picture is compared with the temporarily stored picture after being cut, and if the picture is the same, a command for returning to the preset position is fed back to the system. If the comparison is different, the picture is cut again, the existing temporary picture is replaced, and the polling operation is repeated.
Although the present invention has been described with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described, or equivalents may be substituted for elements thereof, and any modifications, equivalents, improvements and changes may be made without departing from the spirit and principles of the present invention.
Claims (5)
1. A scene change awareness method, characterized by: the method comprises the following steps:
step one: initializing a message queue, a real-time monitoring service and a coding library, initializing monitoring area setting and further obtaining original pictures of the monitoring area;
step two: acquiring a monitoring video in real time through a camera, and intercepting video pictures according to a preset time interval period;
step three: cutting the intercepted video picture, reserving a picture corresponding to the initial monitoring area, and comparing and analyzing the picture with the original picture;
step four: if the image is found to be the same as the original image, feeding back the image to the system without any processing; if the video picture is found to be different from the original picture, storing the cut video picture in the third step into a memory, and continuously executing the fifth step;
step five: continuously waiting for a preset time interval period, and then intercepting video pictures again;
step six: cutting the video pictures obtained in the step five, reserving the pictures corresponding to the video pictures stored in the memory, and comparing and analyzing the pictures with the video pictures stored in the memory;
step seven: if the video picture is found to be the same as the video picture stored in the memory, feeding back a command for returning to a preset position to the system; if the video picture is found to be different from the video picture stored in the memory, storing the video picture cut in the step six into the memory, replacing the video picture stored in the memory in advance, and continuing to execute the step five.
2. A method of scene change awareness according to claim 1, wherein: and the image comparison and analysis adopts a convolutional neural network method to perform characteristic comparison.
3. A method of scene change awareness according to claim 1, wherein: the preset time interval period is 5min.
4. A method of scene change awareness according to claim 1, wherein: the preset position in the step seven refers to the position of the camera for acquiring the original picture of the monitoring area.
5. A method of scene change awareness according to claim 1, wherein: the camera is a high-definition camera with more than 200 ten thousand pixels and can be a high-definition ball machine, a dynamic ball gun machine or a high-point ball machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911005224.0A CN110765932B (en) | 2019-10-22 | 2019-10-22 | Scene change sensing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911005224.0A CN110765932B (en) | 2019-10-22 | 2019-10-22 | Scene change sensing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110765932A CN110765932A (en) | 2020-02-07 |
| CN110765932B true CN110765932B (en) | 2023-06-23 |
Family
ID=69332568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911005224.0A Active CN110765932B (en) | 2019-10-22 | 2019-10-22 | Scene change sensing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110765932B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114422848A (en) * | 2022-01-19 | 2022-04-29 | 腾讯科技（深圳）有限公司 | Video segmentation method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103561243A (en) * | 2013-11-13 | 2014-02-05 | 太仓太乙信息工程有限公司 | Camera condition monitoring system and method |
| CN104537664A (en) * | 2014-12-25 | 2015-04-22 | 合肥寰景信息技术有限公司 | Method for distinguishing abnormal conditions of monitoring camera on basis of background comparison |
| CN104811586A (en) * | 2015-04-24 | 2015-07-29 | 福建星网锐捷安防科技有限公司 | Scene change video intelligent analyzing method, device, network camera and monitoring system |
| CN105352604A (en) * | 2015-11-02 | 2016-02-24 | 上海电力学院 | Infrared temperature measurement system holder position calibration method based on visible light image registration |
| CN105761261A (en) * | 2016-02-17 | 2016-07-13 | 南京工程学院 | Method for detecting artificial malicious damage to camera |
| CN106454282A (en) * | 2016-12-09 | 2017-02-22 | 南京创维信息技术研究院有限公司 | Security and protection monitoring method, apparatus and system |
| CN107564062A (en) * | 2017-08-16 | 2018-01-09 | 清华大学 | Pose method for detecting abnormality and device |
| CN109902633A (en) * | 2019-03-04 | 2019-06-18 | 南京小网科技有限责任公司 | Accident detection method and device based on the camera supervised video of fixed bit |
-
2019
- 2019-10-22 CN CN201911005224.0A patent/CN110765932B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103561243A (en) * | 2013-11-13 | 2014-02-05 | 太仓太乙信息工程有限公司 | Camera condition monitoring system and method |
| CN104537664A (en) * | 2014-12-25 | 2015-04-22 | 合肥寰景信息技术有限公司 | Method for distinguishing abnormal conditions of monitoring camera on basis of background comparison |
| CN104811586A (en) * | 2015-04-24 | 2015-07-29 | 福建星网锐捷安防科技有限公司 | Scene change video intelligent analyzing method, device, network camera and monitoring system |
| CN105352604A (en) * | 2015-11-02 | 2016-02-24 | 上海电力学院 | Infrared temperature measurement system holder position calibration method based on visible light image registration |
| CN105761261A (en) * | 2016-02-17 | 2016-07-13 | 南京工程学院 | Method for detecting artificial malicious damage to camera |
| CN106454282A (en) * | 2016-12-09 | 2017-02-22 | 南京创维信息技术研究院有限公司 | Security and protection monitoring method, apparatus and system |
| CN107564062A (en) * | 2017-08-16 | 2018-01-09 | 清华大学 | Pose method for detecting abnormality and device |
| CN109902633A (en) * | 2019-03-04 | 2019-06-18 | 南京小网科技有限责任公司 | Accident detection method and device based on the camera supervised video of fixed bit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110765932A (en) | 2020-02-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921105B (en) | Method and device for identifying target number and computer readable storage medium | |
| CN110096945B (en) | Indoor monitoring video key frame real-time extraction method based on machine learning | |
| US20160239769A1 (en) | Methods for determining manufacturing waste to optimize productivity and devices thereof | |
| CN110765932B (en) | Scene change sensing method | |
| CN105260716A (en) | Fault indicator state identification method and fault indicator state identification device | |
| CN112163468A (en) | Image processing method and device based on multiple threads | |
| CN111814776B (en) | Image processing method, device, server and storage medium | |
| CN115035088A (en) | Helmet wearing detection method based on yolov5 and posture estimation | |
| CN111325773A (en) | Method, device and equipment for detecting moving target and readable storage medium | |
| CN111464790A (en) | Industrial environment monitoring video processing method and system based on deep learning | |
| CN108900895B (en) | Method and device for shielding target area of video stream | |
| CN114359594A (en) | Scene matching method and device, electronic equipment and storage medium | |
| CN108198226B (en) | Ceramic color identification method, electronic equipment, storage medium and device | |
| CN111353507B (en) | Image recognition method and device for oil stains on surface of transformer substation device | |
| CN115937218B (en) | Surface defect detection method and system for cold stamping part | |
| CN109544514B (en) | Sawn timber identity identification method, device and equipment integrating apparent features | |
| CN109886963B (en) | Image processing method and system | |
| CN110322391A (en) | Visual alarm affair analytical method based on multithreading | |
| CN110798618A (en) | Camera resource scheduling method and device in dynamic tracking | |
| CN115526859A (en) | Method for identifying production defects, distributed processing platform, equipment and storage medium | |
| CN104754248A (en) | Method and device for acquiring target snapshot | |
| CN111553408B (en) | Automatic test method for video recognition software | |
| CN114897766A (en) | Code stream anomaly detection method and device and computer readable storage medium | |
| CN113850795A (en) | Test triggering method, device to be tested and computer readable storage medium | |
| CN114387564A (en) | Head-knocking engine-off pumping-stopping detection method based on YOLOv5 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |