CN106971520B - A kind of smart home joint defense system - Google Patents
A kind of smart home joint defense system Download PDFInfo
- Publication number
- CN106971520B CN106971520B CN201710353919.2A CN201710353919A CN106971520B CN 106971520 B CN106971520 B CN 106971520B CN 201710353919 A CN201710353919 A CN 201710353919A CN 106971520 B CN106971520 B CN 106971520B
- Authority
- CN
- China
- Prior art keywords
- household
- video image
- background model
- moment
- gray value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/10—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using wireless transmission systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
Abstract
The present invention provides a kind of smart home joint defense system, including monitoring modular, identification module, wireless transport module and joint defence user terminal, the monitoring modular is used to monitor the exception information of household；The identification module obtains the recognition result of household exception information for carrying out identification judgement to household exception information；The wireless transport module is used to the recognition result of household exception information being sent to the joint defence user terminal.The present invention solves household abnormal conditions by the way of joint defence, can solve in time the household abnormal conditions of the family using other joint defence users when the unmanned house for abnormal conditions occur is in, ensure the personal safety as well as the property safety of the user.
Description
Technical field
The present invention relates to Smart Home technical fields, and in particular to a kind of smart home joint defense system.
Background technique
Smart home is to build platform with house, by installing smart home system indoors come the house to improve people
Safety, convenience are provided, the smart home system for the purpose of improving house safety performance is usually taken in the prior art
Method is in premises security cameras, and with the situation in monitoring room, once indoor generation safety accident, user can be by checking
Monitoring video searches cause of accident, but the disadvantage of this house system is exactly that can not usually prevent the generation of accident,
It not can avoid user in other words to sustain a loss, if to accomplish to further increase the security performance for wanting user's residence, need
The situation that user is indoor by the concern of camera moment is wanted, but this is very also unrealistic, it is therefore desirable to which one kind can occur in accident
The more intelligent house system of prevention accident generation can be reached before.
Summary of the invention
In view of the above-mentioned problems, the present invention is intended to provide a kind of smart home joint defense system.
The purpose of the present invention is realized using following technical scheme:
A kind of smart home joint defense system, including monitoring modular, identification module, wireless transport module and joint defence user are whole
End, the monitoring modular are used to monitor the exception information of household；The identification module is for identifying household exception information
Judgement, obtains the recognition result of household exception information；The wireless transport module is used for the recognition result of household exception information
It is sent to the joint defence user terminal.
The invention has the benefit that the present invention solves household abnormal conditions by the way of joint defence, it can be different in appearance
When the unmanned house of reason condition is in, solves the household abnormal conditions of the family in time using other joint defence users, ensure the use
The personal safety as well as the property safety at family, and user can usually be notified to take measures to prevent peace before accident will occur
The generation of full accident, the function of having prevention house safety accident to occur, greatly improves the security performance of user's residence.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is frame construction drawing of the invention；
Fig. 2 is the frame construction drawing of monitoring modular of the invention.
Appended drawing reference:
Monitoring modular 1, identification module 2, wireless transport module 3, joint defence user terminal 4, sense signals module 11, video prison
Submodule 12, carbon monoxide transducer 111, smoke sensor device 112, humidity sensor 113, vibrating sensor 114, background is surveyed to know
Other unit 121, refresh unit 122 and goer detection unit 123.
Specific embodiment
In conjunction with following application scenarios, the invention will be further described.
Referring to Fig. 1, a kind of smart home joint defense system of the present embodiment, including monitoring modular 1, identification module 2, wireless biography
Defeated module 3 and joint defence user terminal 4, the monitoring modular 1 are used to monitor the exception information of household；The identification module 2 is used for
Identification judgement is carried out to household exception information, obtains the recognition result of household exception information；The wireless transport module 3 is used for will
The recognition result of household exception information is sent to the joint defence user terminal 4.
Preferably, as shown in Fig. 2, the monitoring modular 1 includes sense signals module 11 and video surveillance submodule 12, institute
Stating sense signals module 11 includes carbon monoxide transducer 111, smoke sensor device 112, humidity sensor 113 and vibrating sensor
114, for monitor whether have in household gas leakage, fire, leak infiltration and judder exception information；The video prison
Surveying submodule 12 includes Background Recognition unit 121, refresh unit 122 and goer detection unit 123, is for monitoring in household
It is no to have the exception information that stranger swarms into.
Preferably, the joint defence user terminal 4 is pc client or cell phone client, for receiving household exception information
Recognition result, when the user for being abnormal situation cannot solve in time this abnormal conditions, other can solve this abnormal feelings
The joint defence user of condition can receive the household exception information of the user.
The above embodiment of the present invention solves household abnormal conditions by the way of joint defence, abnormal conditions can occurring
When unmanned house is in, solves the household abnormal conditions of the family in time using other joint defence users, ensure the person of the user
Property safety, and user can usually be notified to take measures to prevent safety accident before accident will occur
Occur, the function of having prevention house safety accident to occur greatly improves the security performance of user's residence.
Preferably, the Background Recognition unit identifies the static background in household, first according to household video figure
The data of picture initialize each Gaussian Background model important parameter, by each pixel position in N frame household video image
Initial mean value and initial variance as each single Gaussian Background model of average gray value and variance, and set initial weight,
Specifically:
In formula, T indicates Gaussian Background model, ψ2(m, n) indicates the gray value side at household video image positional (m, n)
Difference, K (m, n) are the gray value at household video image positional (m, n), and ω (m, n) is indicated at household video image positional (m, n)
Gray value mean value, ηl,0Indicate that the initial weight of first of Gaussian Background model, L are the number of Gaussian Background model, ωl,0(m,
N) initial mean value of the gray value in first of Gaussian Background model at household video image positional (m, n) is indicated,Indicate the initial variance of the gray value in first of Gaussian Background model at household video image positional (m, n), N
For initial window width (unit: frame)；
Then the gray value of each pixel of household video image and Gaussian Background model are subjected to matching judgment again, in τ
Moment, by the gray value of the pixel of household video image at position (m, n) with L Gaussian Background model one by one according to customized
Matching judgment formula is judged, wherein the customized matching formula used are as follows:
In formula, Kτ(m, n) is the gray value at τ moment household video image positional (m, n), ωl,τ-1When (m, n) is τ -1
Carve the mean value in first of Gaussian Background model at household video image positional (m, n), ψl,τ-1(m, n) is that τ -1 moment is first high
Variance in this background model at household video image positional (m, n).
The above embodiment of the present invention after being initialized according to the data of household video image to Gaussian Background model, is led to
Customized matching judgment formula is crossed, by the gray value and Gaussian Background model of the pixel at household video image positional (m, n)
It is matched, the indoor static background of user's residence is distinguished with dynamic object image, is conducive to this smart home joint defence system
The accurate detection united to goer facilitates identification of the identification module to goer, improves the attention rate to goer, when
There is stranger to find in time when swarming into user's residence.
Preferably, mean value, variance, power of the refresh unit to first of Gaussian Background model of household video image τ moment
It is updated again, specifically:
In formula, ωl,τ(m, n) is equal at household video image positional (m, n) in first of Gaussian Background model of τ moment
Value, ωl,τ-1(m, n) is the mean value in first of Gaussian Background model of τ -1 moment at household video image positional (m, n), Kτ(m,
It n) is the gray value at τ moment household video image positional (m, n),Indicate first of Gaussian Background model of τ moment
Variance at middle household video image positional (m, n),Indicate household in first of Gaussian Background model of τ -1 moment
Variance at video image positional (m, n),For the mean value of Gaussian Background model and the turnover rate of variance,It is set as 0.01；
ηl,τ(m, n) indicates that the initial weight of first of Gaussian Background model of τ moment, ζ are weight turnover rate, and ζ is set as
0.02, L is the number of Gaussian Background model.
The above embodiment of the present invention quickly updates the parameter in household video image, is conducive to household video
The pixel changed in image is quickly detected, and guarantees that movement slowly will not be all detected with mobile very rapid goer
It surveys and omits, be conducive to the timely discovery to indoor goer, greatly improve the anti-theft security performance of this smart home joint defense system.
Preferably, the goer detection unit is first to all weight η for having completed parameter updatel,τ(m, n) is carried out
Normalized then calculates the ω after normalizedl,τ(m, n) withRatioAnd according to from greatly to
Small sequence is ranked up, and X meet model characterization background before choosing, and the stability then calculated in household video image refers to
Mark, last computational stability metrics-thresholds simultaneously judge dynamic object image, specifically:
(1) X value, the calculation formula of use are calculated are as follows:
In formula,Function representation, which takes, meets ∑X=1ηl,τX minimum value when (m, n) >=μ, μ are that weight judges threshold
Value；
(2) it calculates the Stability index of pixel in household video image and filters out its maximum and minimum value, use
Stability index calculation formula are as follows:
In formula, Q (m, n) indicates the Stability index function at position (m, n), and G is the frame number slided backward, Kτ(m,n)
For the gray value at τ moment household video image positional (m, n)；
(3) computational stability metrics-thresholds, the calculation formula of use are as follows:
In formula, Q ' expression Stability index threshold value, QmaxFor maximum stable degree index value, QminFor minimum Stability index
Value；
Stability index Q (m, n) > Q ' of the continuous F frame image in the moment position household video image τ (m, n) if it exists, then
The pixel for judging the household video image moment position τ (m, n) is goer pixel, is otherwise static household background, works as inspection
It surveys in household when there is goer, the identification module identifies goer, if recognition result is when having stranger to swarm into,
It sends and warns to the joint defence user terminal immediately.
The above embodiment of the present invention accurately distinguishes goer in household video image by the calculating to Stability index
With indoor static background, goer image slices vegetarian refreshments is advantageously reduced by the probability of background model erroneous matching, increases dynamic
The discrimination of object and indoor static background enhances algorithm robustness, while improving the accuracy of the detection and tracking to goer,
It is accurately judged to dynamic object image, so that identification module determines whether this goer constitutes a threat to user's house security.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (3)
1. a kind of smart home joint defense system, characterized in that including monitoring modular, identification module, wireless transport module and joint defence
User terminal, the monitoring modular are used to monitor the exception information of household；The identification module be used for household exception information into
Row identification judgement, obtains the recognition result of household exception information；The wireless transport module is used for the knowledge of household exception information
Other result is sent to the joint defence user terminal；
The monitoring modular includes sense signals module and video surveillance submodule, and the sense signals module includes carbon monoxide
Whether sensor, smoke sensor device, humidity sensor and vibrating sensor have gas leakage, fire, leakage for monitoring in household
The exception information of water infiltration and judder；The video surveillance submodule includes Background Recognition unit, refresh unit and dynamic
Analyte detection unit, for monitoring the exception information for whether thering is stranger to swarm into household；
The joint defence user terminal is pc client or cell phone client, for receiving the recognition result of household exception information,
When the user for being abnormal situation cannot solve in time this abnormal conditions, other can solve the joint defence user of this abnormal conditions
The household exception information of the user can be received；
The Background Recognition unit identifies the static background in household, first according to the data of household video image to each
Gaussian Background model important parameter is initialized, by the average gray value of each pixel position in N frame household video image
Initial mean value and initial variance with variance as each single Gaussian Background model, and initial weight is set, specifically:
In formula, T indicates Gaussian Background model, ψ2Gray value variance at (m, n) expression household video image positional (m, n), K (m,
It n) is the gray value at household video image positional (m, n), ω (m, n) indicates the gray scale at household video image positional (m, n)
It is worth mean value, ηl,0Indicate that the initial weight of first of Gaussian Background model, L are the number of Gaussian Background model, ωl,0(m, n) is indicated
The initial mean value of gray value in first of Gaussian Background model at household video image positional (m, n),It indicates
The initial variance of gray value in first of Gaussian Background model at household video image positional (m, n), N are initial window
Width (unit: frame)；
Then the gray value of each pixel of household video image and Gaussian Background model are subjected to matching judgment again, at the τ moment,
By the gray value of the pixel of household video image at position (m, n) and L Gaussian Background model one by one according to customized matching
Judgment formula is judged, wherein the customized matching judgment formula used are as follows:
In formula, Kτ(m, n) is the gray value at τ moment household video image positional (m, n), ωl,τ-1(m, n) is τ -1 moment l
The mean value of gray value in a Gaussian Background model at household video image positional (m, n), ψl,τ-1(m, n) is first of τ -1 moment
The variance of gray value in Gaussian Background model at household video image positional (m, n).
2. a kind of smart home joint defense system according to claim 1, characterized in that the refresh unit is to household video
Image τ the moment mean value, variance, weight of first of Gaussian Background model are updated, specifically:
In formula, ωl,τ(m, n) is the gray value in first of Gaussian Background model of τ moment at household video image positional (m, n)
Mean value, ωl,τ-1(m, n) is the gray value in first of Gaussian Background model of τ -1 moment at household video image positional (m, n)
Mean value, Kτ(m, n) is the gray value at τ moment household video image positional (m, n),Indicate first of Gauss of τ moment
The variance of gray value in background model at household video image positional (m, n),Indicate that τ -1 moment is first high
The variance of gray value in this background model at household video image positional (m, n),For the mean value and variance of Gaussian Background model
Turnover rate；
ηl,τ(m, n) indicates that the initial weight of first of Gaussian Background model of τ moment, ζ are weight turnover rate, and ζ ∈ [0,1], L are height
The number of this background model.
3. a kind of smart home joint defense system according to claim 2, characterized in that the goer detection unit is used for
The real household background for determining the τ moment, to all weight η for having completed parameter updatel,τ(m, n) is normalized, with
The ω after normalized is calculated afterwardsl,τ(m, n) withRatioAnd it is carried out according to sequence from big to small
Sequence, X meet model characterization background before choosing, specifically:
(1) X value, the calculation formula of use are calculated are as follows:
In formula,Function representation, which takes, meets ∑X=1ηl,τX minimum value when (m, n) >=μ, μ are weight judgment threshold；
(2) it calculates the Stability index of pixel in household video image and filters out its maximum and minimum value, the stabilization of use
Spend index calculation formula are as follows:
In formula, Q (m, n) indicates the Stability index function at position (m, n), and G is the frame number slided backward, KτWhen (m, n) is τ
Carve the gray value at household video image positional (m, n)；
(3) computational stability metrics-thresholds, the calculation formula of use are as follows:
In formula, Q ' expression Stability index threshold value, QmaxFor maximum stable degree index value, QminFor minimum Stability index value；
Stability index Q (m, n) > Q ' of the continuous F frame image in the moment position household video image τ (m, n) if it exists, then judge house
The pixel for occupying the video image moment position τ (m, n) is goer pixel, is otherwise static household background, when detection household
When inside there is goer, the identification module identifies goer, if recognition result is when having stranger to swarm into, immediately to
The joint defence user terminal sends warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710353919.2A CN106971520B (en) | 2017-05-18 | 2017-05-18 | A kind of smart home joint defense system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710353919.2A CN106971520B (en) | 2017-05-18 | 2017-05-18 | A kind of smart home joint defense system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106971520A CN106971520A (en) | 2017-07-21 |
| CN106971520B true CN106971520B (en) | 2019-07-23 |
Family
ID=59327254
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710353919.2A Active CN106971520B (en) | 2017-05-18 | 2017-05-18 | A kind of smart home joint defense system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106971520B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102355391A (en) * | 2011-08-18 | 2012-02-15 | 广东工业大学 | Household security system |
| CN102509078A (en) * | 2011-10-28 | 2012-06-20 | 北京安控科技股份有限公司 | Fire detection device based on video analysis |
| CN103632158A (en) * | 2013-11-20 | 2014-03-12 | 北京环境特性研究所 | Forest fire prevention monitor method and forest fire prevention monitor system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5793665B1 (en) * | 2014-03-20 | 2015-10-14 | パナソニックＩｐマネジメント株式会社 | Monitoring system |
-
2017
- 2017-05-18 CN CN201710353919.2A patent/CN106971520B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102355391A (en) * | 2011-08-18 | 2012-02-15 | 广东工业大学 | Household security system |
| CN102509078A (en) * | 2011-10-28 | 2012-06-20 | 北京安控科技股份有限公司 | Fire detection device based on video analysis |
| CN103632158A (en) * | 2013-11-20 | 2014-03-12 | 北京环境特性研究所 | Forest fire prevention monitor method and forest fire prevention monitor system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106971520A (en) | 2017-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200402378A1 (en) | Gunshot Detection System with Location Tracking | |
| US11735018B2 (en) | Security system with face recognition | |
| KR101644443B1 (en) | Warning method and system using prompt situation information data | |
| Mohammadmoradi et al. | Measuring people-flow through doorways using easy-to-install ir array sensors | |
| CN106781165A (en) | A kind of indoor multi-cam intelligent linkage supervising device based on depth sensing | |
| TWI753023B (en) | Computer-implemented method for detecting a person in publicly accessible location, method for controlling loitering in unsecured location, and physical security system | |
| JPWO2020152851A1 (en) | Digital search security systems, methods and programs | |
| US20170053504A1 (en) | Motion detection system based on user feedback | |
| CN108073577A (en) | A kind of alarm method and system based on recognition of face | |
| US11854357B2 (en) | Object tracking using disparate monitoring systems | |
| JP7162412B2 (en) | detection recognition system | |
| US10706699B1 (en) | Projector assisted monitoring system | |
| JP5388829B2 (en) | Intruder detection device | |
| WO2021082112A1 (en) | Neural network training method, skeleton diagram construction method, and abnormal behavior monitoring method and system | |
| KR20160074208A (en) | System and method for providing safety service using beacon signals | |
| CN114913663A (en) | Anomaly detection method and device, computer equipment and storage medium | |
| US20220070414A1 (en) | System For Generating Drone Video Feed Overlays Based On Property Monitoring System Data | |
| CN106971520B (en) | A kind of smart home joint defense system | |
| US20210020022A1 (en) | Notifications for camera tampering | |
| CN112381053B (en) | Environment-friendly monitoring system with image tracking function | |
| CN111339879B (en) | Weapon room single person room entering monitoring method and device | |
| CA3138671A1 (en) | System and method of a concealed threat detection system in objects | |
| CN113091202A (en) | Air conditioner, monitoring terminal and security control method of air conditioner | |
| CN111462227A (en) | Indoor personnel positioning device and method | |
| CN114157526B (en) | Digital image recognition-based home security remote monitoring method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190618 Address after: Room 901, No. 6, 600 Lane, Yunling West Road, Putuo District, Shanghai, 2003 Applicant after: Shanghai Industrial Control Safety Innovation Technology Co., Ltd. Address before: 518000 five, Third South Oil fourth industrial zone, Nanshan Avenue, Nanshan street, Nanshan District, Shenzhen, Guangdong, China, 1124 Applicant before: Shenzhen Li Li Power Technology Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |