CN106327791A - Exceptional event real-time alarm method and system - Google Patents
Exceptional event real-time alarm method and system Download PDFInfo
- Publication number
- CN106327791A CN106327791A CN201610794078.4A CN201610794078A CN106327791A CN 106327791 A CN106327791 A CN 106327791A CN 201610794078 A CN201610794078 A CN 201610794078A CN 106327791 A CN106327791 A CN 106327791A
- Authority
- CN
- China
- Prior art keywords
- region
- anomalous event
- sport foreground
- monitored
- unit
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0297—Robbery alarms, e.g. hold-up alarms, bag snatching alarms
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses an exceptional event real-time alarm method and system. According to the scheme, whether an exceptional event occurs in a monitored area can be accurately detected through an exceptional event detection algorithm, exceptional measures can be taken in time, the reliability is high, the false alarm rate is low, and the alarm is given in time; besides, the detection algorithm can be directly written into an intelligent terminal, compared with the fact that the detection algorithm conventionally operates at a background server, the transmission time of network video streams is greatly saved, the cost is low, and timeliness is realized.
Description
Technical field
The present invention relates to intelligent monitoring technology field, particularly relate to a kind of anomalous event Realtime Alerts method and system.
Background technology
At present, the anomalous event in society, such as, fight, the behavior such as robbery emerges in an endless stream, in particular in ATM's
Robbery crime behavior, mainly by Security Personnel is round-the-clock, traditional video monitoring checks that video monitoring determines whether to plunder row
For, consume a large amount of manpower and materials, and when checking monitoring is recorded a video, miss the best period stoping crime afterwards.The most academic
Boundary is related to the research of accident detections such as robbing, but algorithm is the most complicated, and speed is the slowest, it is impossible to reach wanting of real-time
Ask.
Summary of the invention
It is an object of the invention to provide a kind of anomalous event Realtime Alerts method and system, there is low cost, high reliability
Advantage.
It is an object of the invention to be achieved through the following technical solutions:
A kind of anomalous event real-time alarm system, including:
Video acquisition unit, for the ambient image of Real-time Collection area to be monitored；
Abnormality detecting unit, for utilizing accident detection algorithm that the ambient image of area to be monitored is processed,
To determine whether anomalous event；
Information process unit, for when determining generation anomalous event, sending warning information；And check finger receiving
After order, view data during event that exception will occur is sent out；
Video display unit, after being used for receiving warning information, sends to information process unit and checks instruction, and show letter
View data during the generation anomalous event that breath processing unit is sent.
Described video acquisition unit is intelligent terminal, is fixedly installed on the precalculated position of area to be monitored；Described abnormal inspection
Survey unit to be arranged in described intelligent terminal；Described information process unit is web server, by the way of wired or wireless with
Video acquisition unit and abnormality detecting unit carry out data communication；Described video display unit is to be arranged on the intelligence of Control Room eventually
End, with information process unit row data communication by the way of wired or wireless.
Described utilize accident detection algorithm that the ambient image of area to be monitored is processed, to determine whether to occur
Anomalous event includes:
Acquiring motion area: to arbitrary neighborhood two two field picture collected, uses mixture Gaussian background model algorithm, will the back of the body
Scape separates with sport foreground, it is thus achieved that sport foreground region is moving target；
Sport foreground regional processing: use dense optical flow algorithm, the light stream of each pixel in calculating sport foreground region
Vector, after having calculated, sets up statistic histogram；It is divided into N number of bin by 0-360 °, adds up the amplitude on each bin, from
And obtained the weighting direction histogram based on amplitude intensity in sport foreground region；
Unusual checking: use the computational methods of Region Entropy, for described weighting direction Histogram based on amplitude intensity
Figure carries out Region Entropy calculating, the most unordered confusion of moving in Region Entropy the biggest explanation region；When Region Entropy is more than threshold value T set
Time, then judge that sport foreground region has Deviant Behavior to occur；
Abnormal event alarming: when all detecting that Deviant Behavior occurs in the continuous print S time, then confirm anomalous event,
And to information process unit alert.
A kind of anomalous event Realtime Alerts method, including:
The ambient image of Real-time Collection area to be monitored；
Utilize accident detection algorithm that the ambient image of area to be monitored is processed, to determine whether to occur extremely
Event；
When determining generation anomalous event, send warning information；And after receiving and checking instruction, thing that exception will occur
View data during part is sent out.
The method also includes: after receiving warning information, sends and checks instruction, and when showing described generation anomalous event
View data.
Described utilize accident detection algorithm that the ambient image of area to be monitored is processed, to determine whether to occur
Anomalous event includes:
Acquiring motion area: to arbitrary neighborhood two two field picture collected, uses mixture Gaussian background model algorithm, will the back of the body
Scape separates with sport foreground, it is thus achieved that sport foreground region is moving target；
Sport foreground regional processing: use dense optical flow algorithm, the light stream of each pixel in calculating sport foreground region
Vector, after having calculated, sets up statistic histogram；It is divided into N number of bin by 0-360 °, adds up the amplitude on each bin, from
And obtained the weighting direction histogram based on amplitude intensity in sport foreground region；
Unusual checking: use the computational methods of Region Entropy, for described weighting direction Histogram based on amplitude intensity
Figure carries out Region Entropy calculating, the most unordered confusion of moving in Region Entropy the biggest explanation region；When Region Entropy is more than threshold value T set
Time, then judge that sport foreground region has Deviant Behavior to occur；
Abnormal event alarming: when all detecting that Deviant Behavior occurs in the continuous print S time, then confirm anomalous event,
And to information process unit alert.
As seen from the above technical solution provided by the invention, by accident detection algorithm, can accurately detect
Whether area to be monitored there is anomalous event, and can take abnormal measure in time, has that reliability is high, rate of false alarm is low, reports to the police
The feature such as in time；Write direct detection algorithm intelligent terminal simultaneously, than ever detection algorithm is operated in background server mutually,
Present invention eliminates the substantial amounts of Internet video streaming time, there is the advantage such as low cost and real-time.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, required use in embodiment being described below
Accompanying drawing be briefly described, it should be apparent that, below describe in accompanying drawing be only some embodiments of the present invention, for this
From the point of view of the those of ordinary skill in field, on the premise of not paying creative work, it is also possible to obtain other according to these accompanying drawings
Accompanying drawing.
The schematic diagram of the anomalous event real-time alarm system that Fig. 1 provides for the embodiment of the present invention；
The schematic diagram of anomalous event is there is for the monitoring ATM that the embodiment of the present invention provides in Fig. 2 when withdrawing the money；
Fig. 3 for the embodiment of the present invention provide realize abnormal event alarming by submodule, signal that picture/video supervises
Figure；
The flow chart of the abnormality detecting unit detection anomalous event that Fig. 4 provides for the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground describes, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments.Based on this
Inventive embodiment, the every other enforcement that those of ordinary skill in the art are obtained under not making creative work premise
Example, broadly falls into protection scope of the present invention.
The embodiment of the present invention provides a kind of anomalous event real-time alarm system.As it is shown in figure 1, this system specifically includes that
Video acquisition unit, for the ambient image of Real-time Collection area to be monitored；
Abnormality detecting unit, for utilizing accident detection algorithm that the ambient image of area to be monitored is processed,
To determine whether anomalous event；
Information process unit, for when determining generation anomalous event, sending warning information；And check finger receiving
After order, view data during event that exception will occur is sent out；
Video display unit, after being used for receiving warning information, sends to information process unit and checks instruction, and show letter
View data during the generation anomalous event that breath processing unit is sent.
It will be understood by those skilled in the art that image described in literary composition includes the picture of video image and single frames, concrete
Can set according to practical situation.
In the embodiment of the present invention, described anomalous event includes events such as plundering, fight；Area to be monitored can also be according to need
Ask and select, for example, it is possible to be used for monitoring the robbery occurred when ATM is withdrawn the money, the anomalous event such as fight, or bank other
Region, and the robbery in the region such as hotel, office block, residential building, the anomalous event such as fight.
In the embodiment of the present invention, described video acquisition unit is intelligent terminal, is fixedly installed on the predetermined of area to be monitored
Position.Such as, intelligent terminal can be Android mobile phone, when for monitoring the robbery occurred when ATM is withdrawn the money, fighting and wait exception
During behavior, put in can after the shell of Android mobile phone and screen can be removed, it is simple to protection, then be fixed on a visual field relatively
Good position.Android mobile phone is provided with video acquisition app, the Real-time Collection of image can be carried out.
In the embodiment of the present invention, abnormality detecting unit can be arranged in described intelligent terminal.Such as, by abnormality detection list
Unit's algorithm to be performed writes direct in the microprocessor in intelligent terminal；Adopt in this way, image transmitting can be avoided
The spent time.
In the embodiment of the present invention, information process unit can be web server, and it mainly realizes two functions: to outgoing
Send warning information, and view data when being sent out occurring anomalous event.Wherein, the triggering bar of warning information it is sent out
Part is, abnormality detecting unit detects anomalous event；The trigger condition sending view data when there is anomalous event is, receives
Check instruction to what video display unit sent, afterwards, the image that will collect from video acquisition unit intercepts corresponding figure
Picture.Certainly, information process unit be also not limited to send anomalous event time view data, it is also possible to send real-time image,
Concrete will illustrate when introducing video display unit.It is to say, structurally, information process unit needs with abnormal
Detector unit, video acquisition unit, video display unit connect, to realize the two function.Concrete connected mode does not limit
System, can be wired or wirelessly.
In the embodiment of the present invention, described video display unit is the intelligent terminal being arranged on Control Room.For example, it is possible to for pacifying
Zhuo Shouji；It possesses transmission and checks instruction, and checks the function of respective image；Described video display unit can a period of time in office
Carving and check instruction described in sending, when being not limited in receiving warning information, such as, monitoring personnel do not have at video display unit
When receiving warning information, it is desirable to the image of viewing area to be monitored, it is also possible to by checking instruction, show video acquisition unit
The image that Real-time Collection arrives.Additionally, the Control Room described in the embodiment of the present invention can be bank, hotel, office block, residential building
The Control Room that sets of management personnel, after receiving warning information, report a case to the security authorities to public security part or make corresponding process and arrange
Execute；Certainly, Control Room can also be set by public security department, after receiving warning information, can directly make corresponding process
Measure；Or, it is also possible to it is the Control Room of third party's security unit setting；Concrete can set according to practical situation, this
This is not made restriction by invention.
As in figure 2 it is shown, the robbery that occurred when withdrawing the money by monitoring ATM, the schematic diagram of the anomalous event such as fight, by respectively
The collaborative work of individual unit, it is achieved anomalous event Realtime Alerts.Additionally, in order to realize previously described various functions, can be by
Unit divides there is corresponding submodule；As it is shown on figure 3, after abnormality detecting unit detects anomalous event, can pass through
Its internal abnormal alarm module sends warning message (seeing Fig. 3 a) to information process unit.Meanwhile, image as mentioned before
Can be video can also be picture, accordingly, information process unit can arrange picture and supervise module and video and supervise mould
Block, in order to according to query statement, check that unit feeds back corresponding picture and video (seeing Fig. 3 b～Fig. 3 c) to video.
In the embodiment of the present invention, it is achieved the basis of anomalous event Realtime Alerts is for detecting anomalous event accurately.Its mistake
Journey as shown in Figure 4, mainly comprises the steps:
Acquiring motion area: to arbitrary neighborhood two two field picture collected, uses mixture Gaussian background model algorithm, will the back of the body
Scape separates with sport foreground, it is thus achieved that sport foreground region is moving target；
Sport foreground regional processing: use dense optical flow algorithm, the light stream of each pixel in calculating sport foreground region
Vector, after having calculated, sets up statistic histogram；It is divided into N number of bin by 0-360 °, adds up the amplitude on each bin, from
And obtained the weighting direction histogram based on amplitude intensity in sport foreground region；
Unusual checking: use the computational methods of Region Entropy, for described weighting direction Histogram based on amplitude intensity
Figure carries out Region Entropy calculating, the most unordered confusion of moving in Region Entropy the biggest explanation region；When Region Entropy is more than threshold value T set
Time, then judge that sport foreground region has Deviant Behavior to occur, otherwise, Deviant Behavior does not occur；
Abnormal event alarming: in order to reduce the situation of erroneous judgement, needs to repeat above 3 steps, when the continuous print S time
Interior (such as, in 3 seconds) all detects that Deviant Behavior occurs, then confirm anomalous event, and send report to information process unit
Alarming information；Otherwise it is assumed that be erroneous judgement, do not process.
In the such scheme of the embodiment of the present invention, by accident detection algorithm, can accurately detect area to be monitored
Whether anomalous event occurs, and abnormal measure can be taked in time that there is the features such as reliability is high, rate of false alarm is low, warning is timely；
Write direct detection algorithm intelligent terminal simultaneously, mutually detection algorithm operates in background server than ever, and the present invention saves
Substantial amounts of Internet video streaming time, there is the advantage such as low cost and real-time.
Those skilled in the art is it can be understood that arrive, for convenience and simplicity of description, only with above-mentioned each function
The division of module is illustrated, and in actual application, can distribute above-mentioned functions by different function moulds as desired
Block completes, and the internal structure of system will be divided into different functional modules, to complete all or part of merit described above
Energy.
Another embodiment of the present invention, also provides for a kind of anomalous event Realtime Alerts method, and the method can be by aforementioned
The claimed system of embodiment realizes, and the method specifically includes that
The ambient image of Real-time Collection area to be monitored；
Utilize accident detection algorithm that the ambient image of area to be monitored is processed, to determine whether to occur extremely
Event；
When determining generation anomalous event, send warning information；And after receiving and checking instruction, thing that exception will occur
View data during part is sent out.
Additionally, the method also includes: after receiving warning information, send and check instruction, and show described generation extremely
View data during event.
Described utilize accident detection algorithm that the ambient image of area to be monitored is processed, to determine whether to occur
Anomalous event includes:
Acquiring motion area: to arbitrary neighborhood two two field picture collected, uses mixture Gaussian background model algorithm, will the back of the body
Scape separates with sport foreground, it is thus achieved that sport foreground region is moving target；
Sport foreground regional processing: use dense optical flow algorithm, the light stream of each pixel in calculating sport foreground region
Vector, after having calculated, sets up statistic histogram；It is divided into N number of bin by 0-360 °, adds up the amplitude on each bin, from
And obtained the weighting direction histogram based on amplitude intensity in sport foreground region；
Unusual checking: use the computational methods of Region Entropy, for described weighting direction Histogram based on amplitude intensity
Figure carries out Region Entropy calculating, the most unordered confusion of moving in Region Entropy the biggest explanation region；When Region Entropy is more than threshold value T set
Time, then judge that sport foreground region has Deviant Behavior to occur；
Abnormal event alarming: when all detecting that Deviant Behavior occurs in the continuous print S time, then confirm anomalous event,
And to information process unit alert.
It should be noted that said method specific implementation has had a detailed description in embodiment above, therefore
Here repeat no more.
Through the above description of the embodiments, those skilled in the art it can be understood that to above-described embodiment can
To be realized by software, it is also possible to the mode adding necessary general hardware platform by software realizes.Based on such understanding,
The technical scheme of above-described embodiment can embody with the form of software product, this software product can be stored in one non-easily
The property lost storage medium (can be CD-ROM, USB flash disk, portable hard drive etc.) in, including some instructions with so that a computer sets
Standby (can be personal computer, server, or the network equipment etc.) performs the method described in each embodiment of the present invention.
The above, the only present invention preferably detailed description of the invention, but protection scope of the present invention is not limited thereto,
Any those familiar with the art in the technical scope of present disclosure, the change that can readily occur in or replacement,
All should contain within protection scope of the present invention.Therefore, protection scope of the present invention should be with the protection model of claims
Enclose and be as the criterion.
Claims (6)
1. an anomalous event real-time alarm system, it is characterised in that including:
Video acquisition unit, for the ambient image of Real-time Collection area to be monitored；
Abnormality detecting unit, for utilizing accident detection algorithm to process the ambient image of area to be monitored, with really
Determine whether anomalous event occurs；
Information process unit, for when determining generation anomalous event, sending warning information；And check instruction receiving
After, view data during event that exception will occur is sent out；
Video display unit, after being used for receiving warning information, sends to information process unit and checks instruction, and show at information
View data during the generation anomalous event that reason unit is sent.
System the most according to claim 1, it is characterised in that described video acquisition unit is intelligent terminal, is fixedly installed
Precalculated position in area to be monitored；Described abnormality detecting unit is arranged in described intelligent terminal；Described information process unit
For web server, by the way of wired or wireless, carry out data communication with video acquisition unit and abnormality detecting unit；Described
Video display unit is the intelligent terminal being arranged on Control Room, with information process unit row data by the way of wired or wireless
Communication.
System the most according to claim 1, it is characterised in that described utilize accident detection algorithm to area to be monitored
Ambient image process, with determine whether occur anomalous event include:
Acquiring motion area: to arbitrary neighborhood two two field picture collected, uses mixture Gaussian background model algorithm, by background with
Sport foreground separates, it is thus achieved that sport foreground region is moving target；
Sport foreground regional processing: use dense optical flow algorithm, the light stream vectors of each pixel in calculating sport foreground region,
After calculating completes, set up statistic histogram；It is being divided into N number of bin by 0-360 °, is adding up the amplitude on each bin, thus obtain
The weighting direction histogram based on amplitude intensity in sport foreground region；
Unusual checking: use the computational methods of Region Entropy, described weighting direction histogram based on amplitude intensity is entered
Row Region Entropy calculates, the most unordered confusion of moving in Region Entropy the biggest explanation region；When Region Entropy is more than threshold value T set, then
Judge that sport foreground region has Deviant Behavior to occur；
Abnormal event alarming: when all detecting that Deviant Behavior occurs in the continuous print S time, then confirmation generation anomalous event, and to
Information process unit alert.
4. an anomalous event Realtime Alerts method, it is characterised in that including:
The ambient image of Real-time Collection area to be monitored；
Utilize accident detection algorithm that the ambient image of area to be monitored is processed, to determine whether abnormal thing
Part；
When determining generation anomalous event, send warning information；And after receiving and checking instruction, during event that exception will occur
View data be sent out.
Method the most according to claim 4, it is characterised in that the method also includes: after receiving warning information, sends
Check instruction, and view data when showing described generation anomalous event.
System the most according to claim 1, it is characterised in that described utilize accident detection algorithm to area to be monitored
Ambient image process, with determine whether occur anomalous event include:
Acquiring motion area: to arbitrary neighborhood two two field picture collected, uses mixture Gaussian background model algorithm, by background with
Sport foreground separates, it is thus achieved that sport foreground region is moving target；
Sport foreground regional processing: use dense optical flow algorithm, the light stream vectors of each pixel in calculating sport foreground region,
After calculating completes, set up statistic histogram；It is being divided into N number of bin by 0-360 °, is adding up the amplitude on each bin, thus obtain
The weighting direction histogram based on amplitude intensity in sport foreground region；
Unusual checking: use the computational methods of Region Entropy, described weighting direction histogram based on amplitude intensity is entered
Row Region Entropy calculates, the most unordered confusion of moving in Region Entropy the biggest explanation region；When Region Entropy is more than threshold value T set, then
Judge that sport foreground region has Deviant Behavior to occur；
Abnormal event alarming: when all detecting that Deviant Behavior occurs in the continuous print S time, then confirmation generation anomalous event, and to
Information process unit alert.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610794078.4A CN106327791A (en) | 2016-08-31 | 2016-08-31 | Exceptional event real-time alarm method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610794078.4A CN106327791A (en) | 2016-08-31 | 2016-08-31 | Exceptional event real-time alarm method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106327791A true CN106327791A (en) | 2017-01-11 |
Family
ID=57786359
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610794078.4A Pending CN106327791A (en) | 2016-08-31 | 2016-08-31 | Exceptional event real-time alarm method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106327791A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107609498A (en) * | 2017-09-01 | 2018-01-19 | 湖州师范学院 | A kind of data processing method of computer supervisory control system |
| CN107807403A (en) * | 2017-12-05 | 2018-03-16 | 中磊电子（苏州）有限公司 | For reducing the moving sensing method and moving sensing device of false alarm |
| CN109756666A (en) * | 2017-11-06 | 2019-05-14 | 京瓷办公信息系统株式会社 | monitoring system |
| CN111860030A (en) * | 2019-04-24 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Behavior detection method, behavior detection device, behavior detection equipment and storage medium |
| CN112364680A (en) * | 2020-09-18 | 2021-02-12 | 西安工程大学 | Abnormal behavior detection method based on optical flow algorithm |
| CN112380905A (en) * | 2020-10-15 | 2021-02-19 | 西安工程大学 | Abnormal behavior detection method based on histogram and entropy of surveillance video |
| CN113034826A (en) * | 2021-03-10 | 2021-06-25 | 深圳市兴海物联科技有限公司 | Video-based abnormal event warning method and system, equipment and storage medium thereof |
| CN113115003A (en) * | 2021-04-14 | 2021-07-13 | 武汉畅途网络科技有限公司 | Hotel daily management safety online monitoring method based on image acquisition and analysis technology and Internet of things |
-
2016
- 2016-08-31 CN CN201610794078.4A patent/CN106327791A/en active Pending
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107609498A (en) * | 2017-09-01 | 2018-01-19 | 湖州师范学院 | A kind of data processing method of computer supervisory control system |
| CN107609498B (en) * | 2017-09-01 | 2020-08-18 | 湖州师范学院 | Data processing method of computer monitoring system |
| CN109756666A (en) * | 2017-11-06 | 2019-05-14 | 京瓷办公信息系统株式会社 | monitoring system |
| CN107807403A (en) * | 2017-12-05 | 2018-03-16 | 中磊电子（苏州）有限公司 | For reducing the moving sensing method and moving sensing device of false alarm |
| CN107807403B (en) * | 2017-12-05 | 2020-02-14 | 中磊电子（苏州）有限公司 | Motion sensing method and motion sensor for reducing false alarms |
| CN111860030A (en) * | 2019-04-24 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Behavior detection method, behavior detection device, behavior detection equipment and storage medium |
| CN112364680A (en) * | 2020-09-18 | 2021-02-12 | 西安工程大学 | Abnormal behavior detection method based on optical flow algorithm |
| CN112364680B (en) * | 2020-09-18 | 2024-03-05 | 西安工程大学 | Abnormal behavior detection method based on optical flow algorithm |
| CN112380905A (en) * | 2020-10-15 | 2021-02-19 | 西安工程大学 | Abnormal behavior detection method based on histogram and entropy of surveillance video |
| CN112380905B (en) * | 2020-10-15 | 2024-03-08 | 西安工程大学 | Abnormal behavior detection method based on histogram combination entropy of monitoring video |
| CN113034826A (en) * | 2021-03-10 | 2021-06-25 | 深圳市兴海物联科技有限公司 | Video-based abnormal event warning method and system, equipment and storage medium thereof |
| CN113115003A (en) * | 2021-04-14 | 2021-07-13 | 武汉畅途网络科技有限公司 | Hotel daily management safety online monitoring method based on image acquisition and analysis technology and Internet of things |
| CN113115003B (en) * | 2021-04-14 | 2022-11-25 | 深圳市长泰传媒有限公司 | Hotel daily management safety online monitoring method based on image acquisition and analysis technology and Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106327791A (en) | Exceptional event real-time alarm method and system | |
| CN107071342B (en) | A kind of anomalous event automatic push and monitoring method and system based on historical operation | |
| CN206894809U (en) | Electric power safety operation and O＆M intelligent monitoring system | |
| CN110555964B (en) | Multi-data fusion key area early warning system and method | |
| CN204129891U (en) | A kind of high ferro anti-intrusion system along the line | |
| CN102081844A (en) | Traffic video behavior analyzing and alarming server | |
| CN100527178C (en) | Automatic tracking display system for warn | |
| CN201114536Y (en) | A video monitoring system | |
| CN207117828U (en) | A kind of intelligent behavior analysis system | |
| CN106529401A (en) | Vehicle anti-tracking method, vehicle anti-tracking device and vehicle anti-tracking system | |
| WO2018232846A1 (en) | Large-scale peripheral security monitoring method and system | |
| CN104454011A (en) | Coal face rock burst alarming method based on images | |
| KR102358773B1 (en) | Smart guide device for guiding objects, system and method including the device | |
| CN107221133A (en) | A kind of area monitoring warning system and alarm method | |
| CN202816112U (en) | Radioactive object transportation monitoring system | |
| CN110928305A (en) | Patrol method and system for railway passenger station patrol robot | |
| CN103093579B (en) | Debris flow or landslide alarm system based on videos | |
| CN110300280A (en) | A kind of scenic spot passenger flow monitoring system | |
| CN106097666A (en) | A kind of Chemical Manufacture distributed monitoring system based on GPRS network | |
| CN117978969A (en) | AI video management platform applied to aquaculture | |
| CN201717988U (en) | All-in-one machine with intelligent office monitoring system | |
| CN202472805U (en) | ATM safety prevention and control device | |
| CN201830395U (en) | Oil well monitoring system | |
| CN203722747U (en) | Monitor signal acquisition device and monitor signal real-time alarm system | |
| CN104767969A (en) | Intelligent operation safety monitoring system and method for railway crossing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170111 |