CN106507037A - Intelligent control method and system that personnel invade/cross the border - Google Patents
Intelligent control method and system that personnel invade/cross the border Download PDFInfo
- Publication number
- CN106507037A CN106507037A CN201610875468.4A CN201610875468A CN106507037A CN 106507037 A CN106507037 A CN 106507037A CN 201610875468 A CN201610875468 A CN 201610875468A CN 106507037 A CN106507037 A CN 106507037A
- Authority
- CN
- China
- Prior art keywords
- personnel
- information
- video
- border
- barrier facility
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000004888 barrier function Effects 0.000 claims abstract description 129
- 238000012544 monitoring process Methods 0.000 claims abstract description 96
- 239000000284 extract Substances 0.000 claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 30
- 230000009545 invasion Effects 0.000 claims abstract description 30
- 230000000873 masking effect Effects 0.000 claims description 16
- 230000008447 perception Effects 0.000 claims description 14
- 230000007613 environmental effect Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000012546 transfer Methods 0.000 claims description 5
- 238000003556 assay Methods 0.000 claims description 4
- 239000003550 marker Substances 0.000 claims description 4
- 230000002093 peripheral effect Effects 0.000 claims description 2
- 230000002123 temporal effect Effects 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims 1
- 230000006399 behavior Effects 0.000 description 22
- 230000008569 process Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000002730 additional effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- 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
- G06V20/44—Event detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
- Burglar Alarm Systems (AREA)
Abstract
The invention provides a kind of personnel intelligent control method for invading/crossing the border and system, solve the problems, such as video and audio monitor mode of the prior art cannot invade to monitoring the personnel in video and audio/behavior of crossing the border carries out real-time, comprehensive analysis and judges.The intelligent control method that the personnel invade/cross the border includes：Real-time Collection video and audio monitoring data；The Barrier Facility information of Barrier Facility in extract real-time video and audio monitoring data；The characteristic information of the personnel of Barrier Facility is covered in extract real-time video and audio monitoring data；Barrier Facility information and personnel characteristics' information according to extract real-time judges that personnel, with the presence or absence of illegal invasion/behavior of crossing the border, if judgement personnel have illegal invasion/behavior of crossing the border, send a warning.
Description
Technical field
The present invention relates to video and audio monitoring technology field, and in particular to the intelligent control method that a kind of personnel invade/cross the border
And system.
Background technology
With the popularization of broadband network, the development of computer technology and the raising of image processing techniques, video and audio is monitored
Technology is just penetrating into the various fields such as education, government, amusement, medical treatment, hotel more and more widely.Especially in safety-security area, depending on
Voice Surveillance is to assist public safety department to fight crime, maintain the important means of social stability.But existing video and audio prison
Control analysis method remains in the low layer sub-level for carrying out manpower analysis afterwards based on the monitoring video and audio for being gathered, and fault rate
Higher, and the timely discovery and process for being unfavorable for personnel are invaded/crossed the border with behavior so that monitoring video and audio is led in security etc.
The using value in domain is not effectively played.Therefore, it is badly in need of a kind of people that can be analyzed in real time and judge in monitoring video and audio
Member invades/crosses the border the intelligent monitoring mode of behavior.
Content of the invention
In view of this, intelligent control method and system that a kind of personnel invade/cross the border is embodiments provided, is solved
Video and audio monitor mode of the prior art cannot be invaded to monitoring the personnel in video and audio/behavior of crossing the border carry out real-time, complete
The problem that the analysis in face judges.
The intelligent control method that a kind of personnel provided in an embodiment of the present invention invade/cross the border, including：Real-time Collection video and audio
Monitoring data；The Barrier Facility information of Barrier Facility in extract real-time video and audio monitoring data；Extract real-time video and audio monitors number
Characteristic information according to the personnel of middle masking Barrier Facility；Barrier Facility information and personnel characteristics' information according to extract real-time judges
Personnel, send a warning if judgement personnel have illegal invasion/behavior of crossing the border with the presence or absence of illegal invasion/behavior of crossing the border.
The intelligent monitor system that a kind of personnel provided in an embodiment of the present invention invade/cross the border, including：Environmental perception device,
For Real-time Collection video and audio monitoring data；Geographical sign analytical equipment, for gathered according to the environmental perception device
Video and audio monitoring data, the Barrier Facility information of extract real-time Barrier Facility；Characteristics of objects analytical equipment, for according to the ring
The video and audio monitoring data gathered by border sensing device, the characteristic information of the personnel of extract real-time masking Barrier Facility；And certainly
Plan device, for carrying according to the Barrier Facility information of geographical MARKER ASSAYS device extract real-time and characteristics of objects analytical equipment in real time
The personnel characteristics' information for taking judges personnel with the presence or absence of illegal invasion/behavior of crossing the border, if judgement personnel have illegal invasion/cross the border
Behavior, sends a warning.
Intelligent control method and system that personnel provided in an embodiment of the present invention invade/cross the border, Real-time Collection is regarding sound respectively
The characteristic information of the personnel of Barrier Facility information and masking Barrier Facility in frequency monitoring data, can based on the Barrier Facility information
Confirm the feature of Barrier Facility, based on the feature that personnel characteristics' information can confirm personnel, when the personnel of masking Barrier Facility are
During the Barrier Facility personnel that no thoroughfare, just can assert that personnel have carried out illegal invasion/behavior of crossing the border, it is achieved thereby that to prison
Real-time, the comprehensive analysis of the illegal invasion/behavior of crossing the border in control video and audio judges, and sends a warning, and is security
Work be smoothed out provide convenience.
Description of the drawings
The flow chart that Fig. 1 show the intelligent control method that a kind of personnel of one embodiment of the invention offer invade/cross the border.
Fig. 2 show the flow process of the intelligent control method that a kind of personnel of another embodiment of the present invention offer invade/cross the border
Figure.
Fig. 3 show the structure of the intelligent monitor system that a kind of personnel of one embodiment of the invention offer invade/cross the border and shows
It is intended to.
Fig. 4 show what a kind of personnel intelligent monitor system for invading/crossing the border of one embodiment of the invention offer was based on
Monitoring video/audio intelligent information model figure.
Specific embodiment
Accompanying drawing in below in conjunction with the embodiment of the present invention, to the embodiment of the present invention in technical scheme carry out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Based on this
Embodiment in invention, the every other reality obtained under the premise of creative work is not made by those of ordinary skill in the art
Example is applied, the scope of protection of the invention is belonged to.
Fig. 1 show the flow process of the intelligent control method that a kind of personnel of one embodiment of the invention offer invade/cross the border and shows
It is intended to.As shown in figure 1, the intelligent control method that the personnel invade/cross the border includes：
Step 101：Real-time Collection video and audio monitoring data.
Some essential informations that the video and audio monitoring data is directly collected for front end video and audio collecting device, directly make
For subsequently carrying out the basic resources data of further real-time intelligent analysis.In an embodiment of the present invention, Real-time Collection regarding sound
Frequency monitoring data also can directly be issued the monitoring personnel of Surveillance center and check so that monitoring personnel being capable of the whole personnel of real-time oversight
Invade/cross the border carrying out automatically for intelligent monitoring process.
In an embodiment of the present invention, the video and audio monitoring data of the Real-time Collection may include to monitor video and audio and following
One or more in several：Video and audio collection positional information and video and audio acquisition time information.Wherein monitoring video and audio be after
The continuous resource data for carrying out personnel characteristics' information and Barrier Facility information extraction, video and audio collection positional information and video and audio collection
Temporal information can be used for the when and where that clear and definite personnel invaded/crossed the border behavior generation as additional attribute information.
Step 102：The Barrier Facility information of Barrier Facility in extract real-time video and audio monitoring data.
Step 103：The characteristic information of the personnel of Barrier Facility is covered in extract real-time video and audio monitoring data.
In an embodiment of the present invention, Barrier Facility information may include one or more in following items：Barrier type
Information, barrier position information and barrier peripheral information, for the feature of further clear and definite Barrier Facility.Personnel characteristics' information can be wrapped
Include one or more in following items：Face characteristic, apparel characteristic, look feature, personnel pass through/attempt by Barrier Facility
Direction and time span, for the feature of further clear and definite personnel.
In an embodiment of the present invention, the extraction process of the Barrier Facility information and personnel characteristics' information can be based on to barrier
The pre-training model realization of facilities information and personnel characteristics' information.For example, generate that barrier type is corresponding with barrier structure closes in advance
The pre-training model of system, and the pre-training model of personnel identity and macroscopic features corresponding relation.When identifying that Barrier Facility is
The door that closes carry/periphery is when indicating printed words such as " warehouse important places, no admittance for non-working person ", can based on pre-training model
Judge that the Barrier Facility is non-working person's warehouse gate out-of-bounds；Barrier Facility is covered when identifying in monitoring video and audio
When personnel wear uniform, can judge substantially that the personnel are normal work personnel or Security Personnel based on pre-training model, but sometimes
Be also required to reference to personnel face feature and look feature judged, if it find that personnel nervous/gaze around or
When blocking face, even if he/her wears uniform, it is also possible to the non-working person unrelated with warehouse, nor Security Personnel.
Step 104：Barrier Facility information and personnel characteristics' information according to extract real-time judges personnel with the presence or absence of illegal
Behavior is invaded/crossed the border, if judgement personnel have illegal invasion/behavior of crossing the border, is sent a warning.
Based on the feature that the Barrier Facility information can confirm Barrier Facility, can confirm personnel's based on personnel characteristics' information
Feature, when identifying that Barrier Facility is certain Barrier Facility type that certain position forbids that unrelated person passes through, and covers barrier and sets
When the personnel for applying are identified as a suspect unrelated with the Barrier Facility, just can assert that the personnel have illegal invasion/cross the border
Behavior, sends a warning.
The intelligent control method provided using the present embodiment, the personnel's illegal invasion in the achievable video and audio to monitoring/
The real-time, comprehensive of behavior that cross the border analyzes judgement, while according to judging to send a warning in real time, timely beneficial to staff
Adopt an effective measure prevention illegal act, be safeguarding work be smoothed out provide convenience.
In an embodiment of the present invention, the personnel of the Barrier Facility information of Barrier Facility and masking barrier facility personnel are special
Reference breath can be conserved after being extracted, and being reviewed and being inquired about in order to follow-up.For example, can be believed with Barrier Facility receiving
After breath or personnel characteristics' information are for the query statement of querying condition, the personnel characteristics of all personnel for covering the Barrier Facility are transferred
Information, or transfer the Barrier Facility information of all Barrier Facilities that the personnel pass through/attempt to pass through, so as to realize for a certain can
The inquiry of record is invaded/crossed to the track record of doubtful personnel or a certain concrete Barrier Facility.
In an embodiment of the present invention, as related personnel normal through Barrier Facility and need not send alarm, therefore
If judgement personnel do not have illegal invasion/behavior of crossing the border, personnel characteristics' information corresponding with the personnel can not be preserved and which hides
The Barrier Facility information that covers, to improve the utilization ratio of hardware store resource.
Fig. 2 show the flow process of the intelligent control method that a kind of personnel of another embodiment of the present invention offer invade/cross the border
Schematic diagram.As shown in Fig. 2 the intelligent control method that the personnel invade/cross the border includes：
Step 201：Real-time Collection video and audio monitoring data.
Step 202：The region video and audio in region residing for the personnel of masking Barrier Facility is intercepted from video and audio monitoring data
Monitoring data.
By intercepting region video and audio monitoring data from video and audio monitoring data, remove unrelated with current monitor personnel
The video and audio monitoring data in region, reduces the amount of calculation of subsequent extracted Barrier Facility information and personnel characteristics' information, alleviates
The computation burden of hardware analysis resource.
It should be appreciated that the area size of the region video and audio monitoring data can be by developer according to the demand of actual scene
Depending on, the monitoring range of such as front end video and audio collecting device includes two enclosure walls, and monitoring personnel of interest be only wherein
An enclosure wall illegally cross situation, now just can intercept from video and audio monitoring data and to regard sound when the region of previous enclosure wall
Frequency monitoring data.
Step 203：Barrier Facility information is extracted from the video and audio monitoring data of region.
Step 204：The characteristic information of the personnel of masking Barrier Facility is extracted from the video and audio monitoring data of region.
The concrete extracting mode of Barrier Facility information and personnel characteristics' information can still pass through pre-training model realization, herein not
Repeat again.As original video and audio monitoring data has been truncated to region video and audio monitoring data, therefore Barrier Facility information
It is minimized with the amount of calculation of personnel characteristics' information extraction process, alleviates the computation burden of hardware analysis resource.
In an embodiment of the present invention, it is contemplated that the extraction of Barrier Facility information is concerned with monitoring the screen in video and audio
Barrier facility, the personnel extraction of personnel characteristics' information being concerned with monitoring video and audio, and personnel institute in monitoring video and audio
Often less than the region shared by Barrier Facility, therefore people can also be extracted only from the video and audio monitoring data of region in the region for accounting for
Member's characteristic information, and Barrier Facility information is still extracted from the video and audio monitoring data of acquired original.The present invention is to Barrier Facility
The extraction basis of information and personnel characteristics' information is simultaneously not specifically limited.
Step 205：Barrier Facility information and personnel characteristics' information generative semantics analysis result based on extract real-time.
For example, Barrier Facility information includes that the warehouse gate B in factory A, the characteristic information of personnel include that personnel C is inoperative
Personnel, the then semantic analysis result for being generated are represented by the warehouse gate B that non-working person C is invaded/attempt in invasion factory A.
One embodiment of the invention additionally provides a kind of querying method for interacting, when receiving with Barrier Facility information or people
When member's characteristic information is the query statement of querying condition, personnel characteristics' information of all personnel for covering the Barrier Facility is transferred,
Or transfer the Barrier Facility information of all Barrier Facilities that the personnel pass through/attempt to pass through.For example, if receiving with warehouse gate B
For querying condition query statement when, just may bring up and in current video and audio monitoring data, invade/attempt all of invasion warehouse gate B
The characteristic information of personnel.
Step 206：Semantic analysis result is based on, real-time judge personnel whether there is illegal invasion/behavior of crossing the border, if judging
Be present illegal invasion/behavior of crossing the border in personnel, send a warning.
It should be noted that the step numbering in the method for the invention is used only as the reference of the step, it is not offered as holding
Row order, because some actions can be protected according to the order different appearance with described herein and sign, application claims
Execution sequence institute not by these actions is limited by the subject content of shield.In addition, the description of abovementioned steps is not excluded for the method also
The additional step that may obtain additional effect can be included.It is also understood that described in different embodiments or flow process
Method and step can be mutually combined or replace.
Fig. 3 show the structure of the intelligent monitor system that a kind of personnel of one embodiment of the invention offer invade/cross the border and shows
It is intended to.As shown in figure 3, the intelligent monitor system that the personnel invade/cross the border includes：
Environmental perception device 301, for Real-time Collection video and audio monitoring data；
Geographical sign analytical equipment 302, for the video and audio monitoring data gathered according to environmental perception device 301, real
When extract Barrier Facility Barrier Facility information；
Characteristics of objects analytical equipment 303, for the video and audio monitoring data gathered according to environmental perception device 301, real
When extract masking Barrier Facility personnel characteristic information；And
Decision making device 304, special for the Barrier Facility information according to geographical 302 extract real-time of MARKER ASSAYS device and object
Personnel characteristics' information of 303 extract real-time of analytical equipment is levied, judgement personnel whether there is illegal invasion/behavior of crossing the border, if judging
There is illegal invasion/behavior of crossing the border, send a warning.
In an embodiment of the present invention, the intelligent monitor system that the personnel invade/cross the border is further included：Semantic analysis is filled
305 are put, for the Barrier Facility information based on 302 extract real-time of geographical sign analytical equipment and characteristics of objects analytical equipment 303
Personnel characteristics' information generative semantics analysis result of extract real-time；
Wherein, decision making device 304 is further used for：
Based on the semantic analysis result generated by semantic analysis device 305, real-time judge personnel with the presence or absence of illegal invasion/
Cross the border behavior, if judging there is illegal invasion/behavior of crossing the border, send a warning.
In an embodiment of the present invention, the decision making device 304 is further used for：
Receive the query statement with Barrier Facility information or personnel characteristics' information as querying condition；And transfer masking the screen
Personnel characteristics' information of all personnel of barrier facility, or the barrier for transferring all Barrier Facilities that the personnel pass through/attempt to pass through
Facilities information.
In an embodiment of the present invention, decision making device 304 is further used for：
If there is no illegal invasion/behavior of crossing the border in judgement personnel, do not preserve personnel characteristics' information corresponding with personnel and
Barrier Facility information.
In an embodiment of the present invention, the intelligent monitor system that the personnel invade/cross the border is further included：
Subject area extraction element 306, for intercepting in the video and audio monitoring data that gathered from environmental perception device 301
The region video and audio monitoring data in region residing for the personnel of masking Barrier Facility；
Wherein, characteristics of objects analytical equipment 303 is further used for：Personnel characteristics are extracted from the video and audio monitoring data of region
Information.
In an alternative embodiment of the invention, geographical sign analytical equipment 302 can also be further used for：Supervise from region video and audio
Control extracting data Barrier Facility information.
In an embodiment of the present invention, geographical sign analytical equipment 302 is further used for：Based on to Barrier Facility information
Pre-training model, extracts Barrier Facility information from video and audio monitoring data；And/or,
Characteristics of objects analytical equipment 303 is further used for：Based on the pre-training model to personnel characteristics' information, from video and audio
Personnel characteristics' information is extracted in monitoring data.
As can be seen here, the intelligent monitor system that the personnel provided by the embodiment of the present invention invade/cross the border substantially is based on one
Plant what monitoring video/audio intelligent information model was realized.Information flow in the monitoring video/audio intelligent information model can be divided into different
Aspect is extracted, and there is certain dependence between adjacent aspect.As shown in figure 4, gathering in environmental perception device 301
During video and audio monitoring data, by video and audio with live perception data (such as：The geographical position of camera, time, the sound that crosses
Sound, temperature, meteorology, camera pose etc.) environment sensing layer is stored in, these information are traditional video and audio monitoring and intelligent video and audio prison
Control provides the fundamental of monitoring scene, provides necessary support for top layer decision-making.During front-end processing, by acquired original
Video and audio monitoring data carry out preliminary treatment (including conventional pretreatment, and the front end based on statistical learning method be intelligently point
Analysis etc.), and the result of preliminary treatment is stored in geographical sign layer, characteristic layer and object layer, respectively correspondingly reason MARKER ASSAYS is filled
Put process and object that the process of 302 extraction Barrier Facility information, characteristics of objects analytical equipment 303 extract personnel characteristics' information
Region extracting device 306 intercepts the process of region video and audio monitoring data from the video and audio monitoring data of acquired original.Rear
In the processing procedure of end, by according to different application needs, comprehensive aforesaid accordingly each layer is analyzed using machine learning techniques
And process, related semantic analysis result is stored in semantic layer, the mistake of corresponding 305 generative semantics analysis result of semantic analysis device
Journey.For the semantic analysis result in semantic analysis device 305, the judgment models that is trained using machine learning techniques can be given
Different decision recommendations is referred to for monitoring personnel；Meanwhile, monitoring personnel can be to send instruction to system, with query monitor data
In corresponding content, these belong to decision-making/understand layer.Judgment models therein and the decision recommendation obtained by its judgement, with
And sent a warning according to decision recommendation, belong to decision-making category.Monitoring personnel sends certain to monitoring system during observation
Instruction is planted to inquire about the target for possessing certain category feature in a certain event, system is instructed to be construed to meet retouching for this structural model
Mode is stated, the data grasped by which enter line retrieval, belong to and understand category.
It should be appreciated that when the intelligent monitor system that personnel invade/cross the border includes that front end video and audio collecting device and rear end regard
During audio analysis equipment, environmental perception device 301 is may be provided in the video and audio collecting device of front end, and geographical sign analytical equipment
302nd, subject area extraction element 306, characteristics of objects analytical equipment 303, semantic analysis device 305, decision making device 304 can be distinguished
It is arranged in the video and audio collecting device of front end or is arranged in the video and audio analytical equipment of rear end.As long as the intelligence that personnel invade/cross the border
All devices in energy monitoring system can realize the progressively extraction of respective analysis abstraction function and information flow, finally to reach
Purpose to semantic decision-making.Before device in the intelligent monitor system that the present invention is invaded to personnel/crossed the border is specifically located at
Hold video and audio collecting device or rear end video and audio analytical equipment is not specifically limited.
It should be appreciated that can be implemented as a kind of computer of computer-readable recording medium according to the embodiment of the present invention
Program product, including computer program code, when computer program code is by computing device, its enable a processor to by
Method according to embodiment of the present invention is realizing intelligent control method that described personnel invade/cross the border.Computer-readable storage medium
Can be such as floppy disk, CD-ROM, DVD, even hard disk drive, any tangible media such as network medium.In addition, the present invention is implemented
The method or apparatus of mode can also be realized with the combining form of software, hardware or software and hardware.For example, it is possible to by
The semiconductor or such as field-programmable of super large-scale integration OR gate array, logic chip, transistor etc.
The hardware circuit of the programmable hardware device of gate array, programmable logic device etc. is realized, it is also possible to by various types of
The software that reason device is executed is realized, it is also possible to which the combination such as firmware by above-mentioned hardware circuit and software is realizing.
Presently preferred embodiments of the present invention is the foregoing is only, not in order to limit the present invention, all in essence of the invention
Within god and principle, any modification for being made, equivalent etc. should be included within the scope of the present invention.
Claims (15)
1. the intelligent control method that a kind of personnel invade/cross the border, it is characterised in that include：
Real-time Collection video and audio monitoring data；
The Barrier Facility information of Barrier Facility in extract real-time video and audio monitoring data；
The characteristic information of the personnel of Barrier Facility is covered in extract real-time video and audio monitoring data；
Barrier Facility information and personnel characteristics' information according to extract real-time judges personnel with the presence or absence of illegal invasion/cross the border row
For if judgement personnel have illegal invasion/behavior of crossing the border, sending a warning.
2. the intelligent control method that personnel according to claim 1 invade/cross the border, it is characterised in that further include：
Barrier Facility information and personnel characteristics' information generative semantics analysis result based on the extract real-time；
Wherein, the Barrier Facility information and personnel characteristics' information according to extract real-time judges that personnel whether there is illegally to enter
Invade/cross the border behavior, if there is illegal invasion/behavior of crossing the border in judgement personnel, send a warning including：
The semantic analysis result is based on, personnel described in real-time judge whether there is illegal invasion/behavior of crossing the border, if judging personnel
There is illegal invasion/behavior of crossing the border, send a warning.
3. the intelligent control method that personnel according to claim 1 invade/cross the border, it is characterised in that further include：
Preserve the characteristic information of the Barrier Facility information of the Barrier Facility and the personnel of masking Barrier Facility.
4. the intelligent control method that personnel according to claim 3 invade/cross the border, it is characterised in that further include：
Receive the query statement with Barrier Facility information or personnel characteristics' information as querying condition；And
Personnel characteristics' information of all personnel for covering the Barrier Facility is transferred, or transfers the personnel and pass through/attempt to pass through
All Barrier Facilities Barrier Facility information.
5. the intelligent control method that personnel according to claim 1 invade/cross the border, it is characterised in that
If judging there is no illegal invasion/behavior of crossing the border in the personnel, not preserve personnel characteristics' letter corresponding with the personnel
Breath and the Barrier Facility information of its masking.
6. the intelligent control method that personnel according to claim 1 invade/cross the border, it is characterised in that in extract real-time institute
Before the characteristic information of the personnel for stating Barrier Facility information in video and audio monitoring data and/or masking Barrier Facility, further wrap
Include：
The region video and audio monitoring in region residing for the personnel of the masking Barrier Facility is intercepted from the video and audio monitoring data
Data；
Wherein, in the extract real-time video and audio monitoring data, the Barrier Facility information of Barrier Facility includes：
The Barrier Facility information is extracted from the region video and audio monitoring data；And/or,
The characteristic information for covering the personnel of Barrier Facility in the extract real-time video and audio monitoring data includes：
Personnel characteristics' information is extracted from the region video and audio monitoring data.
7. the intelligent control method that personnel according to claim 1 invade/cross the border, it is characterised in that
In the extract real-time video and audio monitoring data, the Barrier Facility information of Barrier Facility includes：
Based on the pre-training model to the Barrier Facility information, from the video and audio monitoring data, extract the Barrier Facility
Information；And/or,
The characteristic information for covering the personnel of Barrier Facility in the extract real-time video and audio monitoring data includes：
Based on the pre-training model to personnel characteristics' information, from the video and audio monitoring data, extract the personnel characteristics
Information.
8. the intelligent control method that invades/cross the border according to arbitrary described personnel in claim 1 to 7, it is characterised in that described
Video and audio monitoring data includes monitoring one or more in video and audio and following items：Video and audio gathers positional information and regards
Audio collection temporal information；And/or,
The Barrier Facility information includes one or more in following items：Barrier type information, barrier position information and screen
Barrier peripheral information；And/or,
Personnel characteristics' information includes one or more in following items：Face characteristic, apparel characteristic, look feature, people
Member passes through/attempts the direction by Barrier Facility and time span.
9. the intelligent monitor system that a kind of personnel invade/cross the border, it is characterised in that include：
Environmental perception device, for Real-time Collection video and audio monitoring data；
Geographical sign analytical equipment, for the video and audio monitoring data gathered according to the environmental perception device, extract real-time
The Barrier Facility information of Barrier Facility；
Characteristics of objects analytical equipment, for the video and audio monitoring data gathered according to the environmental perception device, extract real-time
The characteristic information of the personnel of masking Barrier Facility；And
Decision making device, for the Barrier Facility information according to geographical MARKER ASSAYS device extract real-time and characteristics of objects analytical equipment
Personnel characteristics' information of extract real-time judges personnel with the presence or absence of illegal invasion/behavior of crossing the border, if judgement personnel exist illegally to enter
Behavior is invaded/crossed the border, is sent a warning.
10. the intelligent monitor system that personnel according to claim 9 invade/cross the border, it is characterised in that further include：
Semantic analysis device, for Barrier Facility information and characteristics of objects based on the geographical sign analytical equipment extract real-time
Personnel characteristics' information generative semantics analysis result of analytical equipment extract real-time；
Wherein, the decision making device is further used for：
Based on the semantic analysis result generated by the semantic analysis device, personnel described in real-time judge whether there is illegally to enter
Behavior is invaded/crossed the border, if judgement personnel have illegal invasion/behavior of crossing the border, is sent a warning.
The intelligent monitor system that 11. personnel according to claim 9 invade/cross the border, it is characterised in that the decision making device
It is further used for：
Query statement as querying condition is received with the Barrier Facility information or personnel characteristics' information；And
Personnel characteristics' information of all personnel for covering the Barrier Facility is transferred, or transfers the personnel and pass through/attempt to pass through
All Barrier Facilities Barrier Facility information.
The intelligent monitor system that 12. personnel according to claim 9 invade/cross the border, it is characterised in that the decision making device
It is further used for：
If judging there is no illegal invasion/behavior of crossing the border in the personnel, not preserve personnel characteristics' letter corresponding with the personnel
Breath and the Barrier Facility information of its masking.
The intelligent monitor system that 13. personnel according to claim 10 invade/cross the border, it is characterised in that further include：
Subject area extraction element, for intercepting the screening in the video and audio monitoring data that gathered from the environmental perception device
Cover the region video and audio monitoring data in region residing for the personnel of Barrier Facility；
Wherein, the geographical sign analytical equipment is further used for：The screen is extracted from the region video and audio monitoring data
Barrier facilities information；And/or,
The characteristics of objects analytical equipment is further used for：The personnel characteristics are extracted from the region video and audio monitoring data
Information.
The intelligent monitor system that 14. personnel according to claim 13 invade/cross the border, it is characterised in that the system bag
Include front end video and audio collecting device and rear end video and audio analytical equipment；
Wherein, the environmental perception device is arranged in the front end video and audio collecting device；
The geographical sign analytical equipment, subject area extraction element, characteristics of objects analytical equipment, semantic database, decision-making dress
Put and be separately positioned in the front end video and audio collecting device or be arranged in the rear end video and audio analytical equipment.
The intelligent monitor system that 15. personnel according to claim 9 invade/cross the border, it is characterised in that the geographical sign
Analytical equipment is further used for：Based on the pre-training model to the Barrier Facility information, from the video and audio monitoring data
Extract the Barrier Facility information；And/or,
The characteristics of objects analytical equipment is further used for：Based on the pre-training model to personnel characteristics' information, from described
Personnel characteristics' information is extracted in video and audio monitoring data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610875468.4A CN106507037A (en) | 2016-09-30 | 2016-09-30 | Intelligent control method and system that personnel invade/cross the border |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610875468.4A CN106507037A (en) | 2016-09-30 | 2016-09-30 | Intelligent control method and system that personnel invade/cross the border |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106507037A true CN106507037A (en) | 2017-03-15 |
Family
ID=58294872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610875468.4A Pending CN106507037A (en) | 2016-09-30 | 2016-09-30 | Intelligent control method and system that personnel invade/cross the border |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106507037A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145883A (en) * | 2018-10-10 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Method for safety monitoring, device, terminal and computer readable storage medium |
| CN110008928A (en) * | 2019-04-16 | 2019-07-12 | 杭州再灵云梯信息科技有限公司 | The analysis method to elevator accident based on deep learning method |
| CN111126317A (en) * | 2019-12-26 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Image processing method, device, server and storage medium |
| CN113537007A (en) * | 2021-07-02 | 2021-10-22 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Non-worker intrusion detection and alarm method and device applied to railway platform |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7446797B2 (en) * | 2003-02-10 | 2008-11-04 | Activeye, Inc. | User assisted customization of automated video surveillance systems |
| CN101496074A (en) * | 2006-05-31 | 2009-07-29 | 日本电气株式会社 | Device and method for detecting suspicious activity, program, and recording medium |
| CN103246869A (en) * | 2013-04-19 | 2013-08-14 | 福建亿榕信息技术有限公司 | Crime monitoring method based on face recognition technology and behavior and sound recognition |
| CN104239309A (en) * | 2013-06-08 | 2014-12-24 | 华为技术有限公司 | Video analysis retrieval service side, system and method |
| CN104268963A (en) * | 2014-08-06 | 2015-01-07 | 成都百威讯科技有限责任公司 | Intelligent door lock system, intelligent door lock and intelligent alarm door |
| CN104994334A (en) * | 2015-06-09 | 2015-10-21 | 海南电网有限责任公司 | Automatic substation monitoring method based on real-time video |
| CN105654647A (en) * | 2016-01-28 | 2016-06-08 | 中北大学 | Identification method for judging home invasion in real time |
-
2016
- 2016-09-30 CN CN201610875468.4A patent/CN106507037A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7446797B2 (en) * | 2003-02-10 | 2008-11-04 | Activeye, Inc. | User assisted customization of automated video surveillance systems |
| CN101496074A (en) * | 2006-05-31 | 2009-07-29 | 日本电气株式会社 | Device and method for detecting suspicious activity, program, and recording medium |
| CN103246869A (en) * | 2013-04-19 | 2013-08-14 | 福建亿榕信息技术有限公司 | Crime monitoring method based on face recognition technology and behavior and sound recognition |
| CN104239309A (en) * | 2013-06-08 | 2014-12-24 | 华为技术有限公司 | Video analysis retrieval service side, system and method |
| CN104268963A (en) * | 2014-08-06 | 2015-01-07 | 成都百威讯科技有限责任公司 | Intelligent door lock system, intelligent door lock and intelligent alarm door |
| CN104994334A (en) * | 2015-06-09 | 2015-10-21 | 海南电网有限责任公司 | Automatic substation monitoring method based on real-time video |
| CN105654647A (en) * | 2016-01-28 | 2016-06-08 | 中北大学 | Identification method for judging home invasion in real time |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145883A (en) * | 2018-10-10 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Method for safety monitoring, device, terminal and computer readable storage medium |
| CN109145883B (en) * | 2018-10-10 | 2019-10-22 | 百度在线网络技术（北京）有限公司 | Method for safety monitoring, device, terminal and computer readable storage medium |
| CN110008928A (en) * | 2019-04-16 | 2019-07-12 | 杭州再灵云梯信息科技有限公司 | The analysis method to elevator accident based on deep learning method |
| CN111126317A (en) * | 2019-12-26 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Image processing method, device, server and storage medium |
| CN113537007A (en) * | 2021-07-02 | 2021-10-22 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Non-worker intrusion detection and alarm method and device applied to railway platform |
| CN113537007B (en) * | 2021-07-02 | 2024-08-20 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Non-staff intrusion detection and alarm method and device applied to railway platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103581186B (en) | A kind of network security situational awareness method and system | |
| CN106507037A (en) | Intelligent control method and system that personnel invade/cross the border | |
| CN105574506A (en) | Intelligent face tracking system and method based on depth learning and large-scale clustering | |
| Muneer et al. | Cyber security event detection using machine learning technique | |
| CN109740411A (en) | Intelligent monitor system, monitoring method based on recognition of face and quickly go out alarm method | |
| CN110674761B (en) | Regional behavior early warning method and system | |
| CN110751080A (en) | Gathering early warning method and system for abnormal personnel and related device | |
| CN108710856A (en) | A kind of face identification method based on video flowing | |
| CN110909195A (en) | Picture labeling method and device based on block chain, storage medium and server | |
| CN111553264B (en) | Campus non-safety behavior detection and early warning method suitable for primary and secondary school students | |
| CN110689694B (en) | Intelligent monitoring system and method based on image processing | |
| Rafika et al. | An application of mask detector for prevent Covid-19 in public services area | |
| CN107920224A (en) | A kind of abnormality alarming method, equipment and video monitoring system | |
| CN108171187A (en) | A kind of abnormal behaviour automatic identifying method and device based on the extraction of bone point | |
| CN106454233A (en) | Intelligent crowd-gathering monitoring method and system | |
| CN110247888A (en) | A kind of computer network security Situation Awareness platform architecture | |
| CN106503618B (en) | Personnel based on video monitoring platform go around behavioral value method | |
| CN109039827A (en) | Location-based social software hot spot acquisition system and its method | |
| Prezioso et al. | Integrating Object Detection and Advanced Analytics for Smart City Crowd Management | |
| CN112766118A (en) | Object identification method, device, electronic equipment and medium | |
| Greene et al. | Can we trust computer with body-cam vidio? Police departments are being led to believe AI will help, but they should be wary | |
| Koneru et al. | A Real-Time Solution for Social Distance Detection in COVID-19 Pandemic | |
| CN116486339A (en) | Method and device for identifying suspicious personnel in data center park | |
| Sachan et al. | SOCIAL DISTANCING VIOLATION DETECTION MECHANISM USING OPENCV: A REVIEW | |
| Kumar et al. | An AI Powered Threat Detector for Banking Sector Using Intelligent Surveillance Cameras |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20171208 Address after: 519000 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105, -23898 (central office) Applicant after: Zhongxing Technology Co., Ltd. Address before: 100083 Haidian District, Xueyuan Road, No. 35, the world building, the second floor of the building on the ground floor, No. 16 Applicant before: Beijing Vimicro Corporation |
|
| TA01 | Transfer of patent application right | ||
| CB02 | Change of applicant information |
Address after: 519031 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105, -23898 (central office) Applicant after: Mid Star Technology Limited by Share Ltd Address before: 519000 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105, -23898 (central office) Applicant before: Zhongxing Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170315 |
|
| RJ01 | Rejection of invention patent application after publication |