CN106899828A - Intelligent prison system and method - Google Patents
Intelligent prison system and method Download PDFInfo
- Publication number
- CN106899828A CN106899828A CN201710020459.1A CN201710020459A CN106899828A CN 106899828 A CN106899828 A CN 106899828A CN 201710020459 A CN201710020459 A CN 201710020459A CN 106899828 A CN106899828 A CN 106899828A
- Authority
- CN
- China
- Prior art keywords
- prison
- custody
- personnel
- video image
- processor
- 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
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Psychiatry (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a kind of intelligent prison system and method, the system includes:The sound pick-up of the acoustic information in collection prison region;The filming apparatus of the video image information in collection prison region;Electrically connected with sound pick-up and filming apparatus, the sound and video image information are analyzed, detecting the processor that alarm signal is produced when there is abnormal behaviour by the personnel of taking into custody in prison region;And electrically connected with processor, the warning device of sound and/or light alarm is carried out according to alarm signal.The embodiment of the present invention is by monitoring the abnormal behaviour of the personnel that taken into custody using the sound and video image information in processor Treatment Analysis prison region, solve the problems, such as timely find to be taken into custody personnel's abnormal behaviour, and then ensured the safety and stabilization of the personnel that taken into custody.
Description
Technical field
The present invention relates to prison warning device field, more particularly to a kind of intelligent prison system and method.
Background technology
Prison is the place for putting in prison and transforming criminal, all the time, guarantee taken into custody the personal safety of personnel with it is steady
Surely it is the matter of utmost importance in prison.
However, the existing prison abnormal behaviour for going to find to be taken into custody personnel mostly artificial by taking personnel into custody, this
Artificial monitoring tends not to timely find the abnormal behaviour for being taken into custody personnel.
The content of the invention
Embodiment of the present invention technical problem to be solved is, there is provided a kind of intelligent prison system and method, to enable
The enough abnormal behaviour for finding to be taken into custody personnel in time.
In order to solve the above-mentioned technical problem, the embodiment of the present invention proposes a kind of intelligent prison system, including:Collection prison
The sound pick-up of the acoustic information in region;
The filming apparatus of the video image information in collection prison region;
Electrically connected with sound pick-up and filming apparatus, the sound and video image information are analyzed, detecting prison area
The processor for being occurred producing alarm signal during abnormal behaviour by the personnel of taking into custody in domain;And
Electrically connected with processor, the warning device of sound and/or light alarm is carried out according to alarm signal.
Correspondingly, the embodiment of the present invention additionally provides a kind of intelligent prison method, including:
Acquisition step:Sound and video image information in collection prison region;
Analysis judges step:Described information is analyzed, and determines whether abnormal behaviour occur;
Alarming step:If there is abnormal behaviour, then warning device is controlled to be alarmed, reminding correlation to take personnel into custody is carried out
Check.
By proposing a kind of intelligent prison system and method, the system includes sound pick-up, shoots dress the embodiment of the present invention
Put, processor and warning device, by being supervised using the sound and video image information in processor Treatment Analysis prison region
Survey is taken into custody the abnormal behaviour of personnel, solves the problems, such as timely find to be taken into custody personnel's abnormal behaviour, and then ensure
Taken into custody the safety and stabilization of personnel.
Brief description of the drawings
Fig. 1 is the structural representation of the intelligent prison system of the embodiment of the present invention.
Fig. 2 is the intelligent prison method flow schematic diagram of the embodiment of the present invention.
Drawing reference numeral explanation
Acquisition step S1
Analysis judges step S2
Alarming step S3.
Specific embodiment
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combine, the present invention is described in further detail with specific embodiment below in conjunction with the accompanying drawings.
If directional instruction (such as up, down, left, right, before and after ...) is only used for explaining at certain in the embodiment of the present invention
Relative position relation, motion conditions under one particular pose (as shown in drawings) between each part etc., if the particular pose is sent out
During raw change, then directionality indicates also correspondingly to change therewith.
If in addition, be related in the present invention " first ", " second " etc. description be only used for describe purpose, and it is not intended that
Indicate or imply its relative importance or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ",
At least one this feature can be expressed or be implicitly included to the feature of " second ".
Refer to Fig. 1, the intelligent prison system of the embodiment of the present invention mainly include sound pick-up, filming apparatus, processor and
Warning device.
Acoustic information in sound pick-up collection prison region.
Video image information in filming apparatus collection prison region.For example, filming apparatus can be imaged using IPC network
Machine, is electrically connected by netting twine with processor, completes the transmission of video image information.
Processor is electrically connected with sound pick-up and filming apparatus, and the sound and video image information are analyzed, and is being detected
Alarm signal is produced when there is abnormal behaviour by the personnel of taking into custody.For example, processor can be used at the DM3730 of Texas Instruments
Reason device.
Warning device is electrically connected with processor, and sound and/or light alarm are carried out according to alarm signal.Preferably, warning device
It is buzzer and/or LED alarm lamp.
Used as a kind of implementation method, intelligent prison system also includes one or more in illuminating lamp, fan and gate light, intelligence
Energy prison system also includes the clutch of the control illuminating lamp, fan and gate light ON/OFF, the illuminating lamp, fan and gate light
Switch is electrically connected with clutch, and the clutch is electrically connected with processor.Preferably, clutch can use STC15F2K60S2
Chip.Preferably, gate light is integrated tri coloured lantern, the state for indicating current prison.As a kind of implementation method, intelligence prison
House system also includes the alarm button electrically connected with clutch, is easy to related personnel when there are abnormal conditions, is reported manually
It is alert.
Used as a kind of implementation method, intelligent prison system also includes:On prison door, what is electrically connected with clutch passes through
The electronic lock that ID card controls are unlocked;And be connected with processor, for the writer to ID cards write-in correspondence unlocking information.Electronic lock
Correlation is facilitated to take personnel (people's police such as on duty) into custody when there is fire disaster emergency case, just can be rapid by an ID card
Open multiple prison doors in ground.Writer facilitates correlation to take the enabling authority that personnel change ID cards at any time into custody.
Used as a kind of implementation method, intelligent prison system also includes on prison door that what is electrically connected with clutch is used for
Detect the door sensor of prison door unusual switch.Door sensor detects the unusual switch of prison door, is easy to correlation to take the personnel (people such as on duty into custody
It is alert) find to be taken into custody the behavior of forcing open the door of personnel in time, and then there is situation about escaping from prison in strick precaution.
Used as a kind of implementation method, intelligent prison system also includes being electrically connected with processor, for taking personnel into custody and being seen
The video intercom panel of signature personnel's communication exchange.Video intercom panel is realized remotely propagandaing directed to communicate, and is easy to correlation to take personnel into custody and does sth. in advance to be situated between
Enter the disposal process of accident.
Used as a kind of implementation method, intelligent prison system also includes the PC ends being connected with processor.For example, PC ends are with wired
Mode or wireless mode are connected by network with processor, when there are abnormal conditions, processor by corresponding type of alarm,
The information such as room number are sent to PC ends, remind correlation to take personnel into custody.PC ends facilitate correlation to take personnel (people's police such as on duty) remotely prison into custody
Pipe prison, the alarm condition to occurring is checked, and the equipment such as clutch, processor are managed.
Fig. 2 is refer to, the intelligent prison method of the embodiment of the present invention includes:
Acquisition step S1:Sound and video image information in collection prison region;
Analysis judges step S2:Described information is analyzed, and determines whether abnormal behaviour occur;
Alarming step S3:If there is abnormal behaviour, then control warning device to be alarmed, remind correlation to take personnel into custody and enter
Row is checked.
Wherein, analysis judges that step S2 includes:
Phonetic analysis sub-step:Point the number of acoustic information is calculated, and is contrasted with default threshold value, when point a number
When meeting or exceeding the threshold value of setting, there is abnormal behaviour in judgement;And
Video image analysis sub-step:Calculate the event trace data for being taken into custody personnel in video image information, and with
Default threshold value is contrasted, and when data meet or exceed the threshold value of setting, abnormal behaviour occurs in judgement.
Video image analysis sub-step carries out calculating event trace data using following steps:
Step 1:Represent a certain pixel in certain time with K Gauss model each pixel in video image
State, it is assumed that XtIt is the pixel of t, then its probability function is:
Wherein, K is the number of mixed Gauss model, it is preferable that K values 3~5, wi,tIt is i-th Gauss model in t
Weights, η (Xt,ui,t,∑i,t) it is probability density function, ui,tIt is the mean vector of i-th Gauss model of t, ∑i,tFor
The covariance matrix of model, i=1,2 ..., K;
Step 2:Pixel value I (x, y) of present frame each point is matched with K Gaussian Profile, if meeting formula:
|I(x,y)-ui,t-1| < D × σi,t-1;
Then I (x, y) is matched with Gaussian Profile, is otherwise to mismatch, wherein, D is confidence parameter, it is preferable that D values are
2.5, ui,t-1It is i-th Gaussian Profile in the average at t-1 moment, σi,t-1It is i-th Gaussian Profile in the standard deviation at t-1 moment;
Step 3:If the match is successful, the parameter to matched Gaussian Profile is updated, and more new formula is such as
Under:
wi,t=(1- α) × wi,t-1+α;
ui,t=(1- ρ) × ui,t-1+ρ×Xt;
Wherein, α is learning rate, it is preferable that α values are 0.005, ρ=α × η (Xt,ui,t,∑i,t);
If matching is unsuccessful, a new Gauss model is set up, while removing the maximum Gaussian Profile of difference, other are high
This distribution average and variance inconvenience, weights are updated as follows:
wi,t=(1- α) × wi,t-1;
Step 4:Gaussian Profile is pressed the value descending arrangement of w/u, background mould of the preceding B distribution as Gaussian Profile is then taken
Type:
Wherein, T is global prior probability, and it represents the probability for appearing in and belonging to background pixel in pixel coverage, preferably
Ground, T=0.8;
Step 5:After choosing B Gauss model, by pixel value I (x, y) of present frame and the background model point chosen
Do not matched, if I (x, y) is mismatched with background model, then judged this pixel as the foreground point i.e. track of moving target,
Otherwise it is background dot.
In addition, one of ordinary skill in the art will appreciate that all or part of flow in realizing above-described embodiment method,
Program be can be by instruct the hardware of correlation to complete, described program can be stored in a computer-readable recording medium
In, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
Understanding can carry out various changes, modification, replacement to these embodiments without departing from the principles and spirit of the present invention
And modification, the scope of the present invention limits by appended claims and its equivalency range.
Claims (9)
1. a kind of intelligent prison system, it is characterised in that the system includes:
The sound pick-up of the acoustic information in collection prison region;
The filming apparatus of the video image information in collection prison region;
Electrically connected with sound pick-up and filming apparatus, the sound and video image information are analyzed, detected in prison region
The processor that alarm signal is produced when being occurred abnormal behaviour by the personnel of taking into custody;And
Electrically connected with processor, the warning device of sound and/or light alarm is carried out according to alarm signal.
2. intelligence prison system as claimed in claim 1, it is characterised in that the system also includes illuminating lamp, fan and door
One or more in lamp, the system also includes the clutch of the control illuminating lamp, fan and gate light ON/OFF, the photograph
Bright lamp, fan and door lamp switch are electrically connected with clutch, and the clutch is electrically connected with processor.
3. intelligence prison system as claimed in claim 2, it is characterised in that the system also includes:
On prison door, the electronic lock unlocked by ID card controls electrically connected with clutch;And
It is connected with processor, for the writer to ID cards write-in correspondence unlocking information.
4. intelligence prison system as claimed in claim 3, it is characterised in that the system also includes on prison door, with
The door sensor for detecting prison door unusual switch of clutch electrical connection.
5. intelligence prison system as claimed in claim 1, it is characterised in that the system also includes being electrically connected with processor,
For the video intercom panel for taking personnel into custody Yu taken into custody personnel's communication exchange.
6. intelligence prison system as claimed in claim 1, it is characterised in that the system also includes the PC being connected with processor
End.
7. a kind of intelligent prison method, it is characterised in that methods described includes:
Acquisition step:Sound and video image information in collection prison region;
Analysis judges step:Described information is analyzed, and determines whether abnormal behaviour occur;
Alarming step:If there is abnormal behaviour, then control warning device to be alarmed, remind correlation to take personnel into custody and looked into
See.
8. intelligence prison method as claimed in claim 7, it is characterised in that the analysis judges that step includes:
Phonetic analysis sub-step:Point the number of acoustic information is calculated, and is contrasted with default threshold value, when point a number reaches
Or during more than the threshold value for setting, there is abnormal behaviour in judgement;And
Video image analysis sub-step:Calculate the event trace data for being taken into custody personnel in video image information, and with it is default
Threshold value contrasted, when data meet or exceed the threshold value of setting, judgement there is abnormal behaviour.
9. intelligence prison method as claimed in claim 8, it is characterised in that the video image analysis sub-step is using as follows
Step carries out calculating event trace data:
Step 1:Shape of a certain pixel in certain time is represented with K Gauss model to each pixel in video image
State, it is assumed that XtIt is the pixel of t, then its probability function is:
Wherein, K is the number of mixed Gauss model, wi,tIt is i-th Gauss model in the weights of t, η (Xt,ui,t,∑i,t)
It is probability density function, ui,tIt is the mean vector of i-th Gauss model of t, ∑i,tIt is the covariance matrix of model, i=1,
2,…,K;
Step 2:Pixel value I (x, y) of present frame each point is matched with K Gaussian Profile, if meeting formula:
|I(x,y)-ui,t-1| < D × σi,t-1;
Then I (x, y) is matched with Gaussian Profile, otherwise to mismatch, wherein, D is confidence parameter, ui,t-1It is i-th Gaussian Profile
In the average at t-1 moment, σi,t-1It is i-th Gaussian Profile in the standard deviation at t-1 moment;
Step 3:If the match is successful, the parameter to matched Gaussian Profile is updated, and more new formula is as follows:
wi,t=(1- α) × wi,t-1+α;
ui,t=(1- ρ) × ui,t-1+ρ×Xt;
Wherein, α is learning rate, ρ=α × η (Xt,ui,t,∑i,t);
If matching is unsuccessful, a new Gauss model is set up, while removing the maximum Gaussian Profile of difference, other Gausses point
Cloth average and variance inconvenience, weights are updated as follows:
wi,t=(1- α) × wi,t-1;
Step 4:Gaussian Profile is pressed the value descending arrangement of w/u, background model of the preceding B distribution as Gaussian Profile is then taken:
Wherein, T is global prior probability, and it represents the probability for appearing in and belonging to background pixel in pixel coverage;
Step 5:After choosing B Gauss model, pixel value I (x, y) of present frame and the background model chosen are entered respectively
Row matching, if I (x, y) is mismatched with background model, then judges this pixel as the foreground point i.e. track of moving target, otherwise
It is background dot.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710020459.1A CN106899828A (en) | 2017-01-11 | 2017-01-11 | Intelligent prison system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710020459.1A CN106899828A (en) | 2017-01-11 | 2017-01-11 | Intelligent prison system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106899828A true CN106899828A (en) | 2017-06-27 |
Family
ID=59198674
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710020459.1A Pending CN106899828A (en) | 2017-01-11 | 2017-01-11 | Intelligent prison system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106899828A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107911653A (en) * | 2017-11-16 | 2018-04-13 | 王磊 | The module of intelligent video monitoring in institute, system, method and storage medium |
CN110751007A (en) * | 2018-07-24 | 2020-02-04 | 杭州海康威视数字技术股份有限公司 | Alarm method, alarm device, electronic equipment and storage medium |
CN111273232A (en) * | 2018-12-05 | 2020-06-12 | 杭州海康威视***技术有限公司 | Indoor abnormal condition judgment method and system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101364408A (en) * | 2008-10-07 | 2009-02-11 | 西安成峰科技有限公司 | Sound image combined monitoring method and system |
CN101394479A (en) * | 2008-09-25 | 2009-03-25 | 上海交通大学 | Teacher movement tracing method based on movement detection combining multi-channel fusion |
CN201315654Y (en) * | 2008-08-25 | 2009-09-23 | 云南正卓信息技术有限公司 | Special SkyEyes** intelligent monitoring system for prison |
CN201503601U (en) * | 2009-06-02 | 2010-06-09 | 中国科学院嘉兴无线传感网工程中心 | Intelligent prison management system |
CN201984337U (en) * | 2011-03-24 | 2011-09-21 | 南京敏求电子科技有限公司 | Integrated ward device for prison administration and integrated monitoring system |
CN102737480A (en) * | 2012-07-09 | 2012-10-17 | 广州市浩云安防科技股份有限公司 | Abnormal voice monitoring system and method based on intelligent video |
CN105025271A (en) * | 2015-07-28 | 2015-11-04 | 深圳英飞拓科技股份有限公司 | Behavior monitoring method and device |
-
2017
- 2017-01-11 CN CN201710020459.1A patent/CN106899828A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201315654Y (en) * | 2008-08-25 | 2009-09-23 | 云南正卓信息技术有限公司 | Special SkyEyes** intelligent monitoring system for prison |
CN101394479A (en) * | 2008-09-25 | 2009-03-25 | 上海交通大学 | Teacher movement tracing method based on movement detection combining multi-channel fusion |
CN101364408A (en) * | 2008-10-07 | 2009-02-11 | 西安成峰科技有限公司 | Sound image combined monitoring method and system |
CN201503601U (en) * | 2009-06-02 | 2010-06-09 | 中国科学院嘉兴无线传感网工程中心 | Intelligent prison management system |
CN201984337U (en) * | 2011-03-24 | 2011-09-21 | 南京敏求电子科技有限公司 | Integrated ward device for prison administration and integrated monitoring system |
CN102737480A (en) * | 2012-07-09 | 2012-10-17 | 广州市浩云安防科技股份有限公司 | Abnormal voice monitoring system and method based on intelligent video |
CN105025271A (en) * | 2015-07-28 | 2015-11-04 | 深圳英飞拓科技股份有限公司 | Behavior monitoring method and device |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107911653A (en) * | 2017-11-16 | 2018-04-13 | 王磊 | The module of intelligent video monitoring in institute, system, method and storage medium |
CN110751007A (en) * | 2018-07-24 | 2020-02-04 | 杭州海康威视数字技术股份有限公司 | Alarm method, alarm device, electronic equipment and storage medium |
CN110751007B (en) * | 2018-07-24 | 2023-03-10 | 杭州海康威视数字技术股份有限公司 | Alarm method, alarm device, electronic equipment and storage medium |
CN111273232A (en) * | 2018-12-05 | 2020-06-12 | 杭州海康威视***技术有限公司 | Indoor abnormal condition judgment method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108198292B (en) | Household monitoring method and system based on intelligent cloud lock | |
CN106412501B (en) | A kind of the construction safety behavior intelligent monitor system and its monitoring method of video | |
CN103839373B (en) | A kind of unexpected abnormality event Intelligent Recognition alarm device and warning system | |
CN103839346B (en) | A kind of intelligent door and window anti-intrusion device and system, intelligent access control system | |
CN107688884A (en) | Safety check centralized management system | |
CN103366506A (en) | Device and method for automatically monitoring telephone call behavior of driver when driving | |
CN106899828A (en) | Intelligent prison system and method | |
CN205080681U (en) | Register one's residence door electronic monitoring device | |
CN108009488A (en) | The street security joint defense system of Behavior-based control analysis | |
CN113971782B (en) | Comprehensive monitoring information management method and system | |
CN109657555A (en) | It is a kind of to get off the detection device and method of omission for school bus student | |
CN107064588A (en) | A kind of electricity anti-theft system and its application process | |
US12014271B2 (en) | Training image classifiers | |
CN206684875U (en) | A kind of real-time dynamic tracing and early warning system based on car plate and recognition of face | |
CN117119175A (en) | Underground coal mine air door AI video safety management control system | |
CN110415410A (en) | A kind of access control system of residential community based on safety technological guard engineering | |
CN108898717A (en) | A kind of intelligent safety defense monitoring system | |
CN113112744A (en) | Security management method and device, electronic equipment and storage medium | |
EP3109837A1 (en) | System and method of smart incident analysis in control system using floor maps | |
CA2933223A1 (en) | Method of implementing gps based extended chime and special escort mode in security panel | |
CN105451235A (en) | Wireless sensor network intrusion detection method based on background updating | |
CN111666780A (en) | Intelligent door control security method based on emotion recognition technology | |
CN205644854U (en) | Security alarm system | |
CN109640041A (en) | Intelligent video analysis system | |
CN105205966A (en) | Intelligent antitheft system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170627 |
|
RJ01 | Rejection of invention patent application after publication |