CN103198595A - Intelligent door and window anti-invasion system - Google Patents

Abstract

The invention discloses an intelligent door and window anti-invasion system which comprises a video collecting module, an audio collecting module, a heat releasing infrared detecting and alarming module, a vibration detecting module, a glass crushing detecting module, a door magnetic detecting module, a signal processing module, an alarming transmitting module and a power supply managing module. According to the intelligent door and window anti-invasion system, possible illegal invasion behaviors in door and window areas are found through a multi-dimensional detecting manner. Illegal invasions or guest visiting or normal coming in and going out by the head of a household can be accurately recognized. Pictures of visiting of a guest are sent to terminals like a cellphone of a host at home or real-time and intuitional alarming signals with audio and video or pictures as carriers are sent to alarming receiving and processing terminals such as the cellphone of the head of the household, a residential area monitoring computer and the like. Meanwhile, alarm lamps and alarm signals are linked so as to achieve sound-light alarming in a field where an incident happens, or other relevant devices are linked. In addition, the intelligent door and window anti-invasion system is arranged outdoors so that illegal invasions are wiped out to the largest degree before the illegal invasions actually happen.

Description

The intelligent door and window anti-intrusion system

Technical field

The present invention relates to a kind of burglary-resisting system, be specifically related to a kind of intelligent door and window anti-intrusion system.

Background technology

We know, in order to avoid theft, generally can locate to install the anti-theft device of camera and so in residential quarter or outdoor corridor etc., a kind of monitoring and warning system of swarming into based on the indoor occupant of intelligent video for example, mainly be by the intellectual analysis to camera image, realization is to the analysis of indoor place moving target, breaking in of personnel reached timely discovery and warning, ignore the motion that is safe from danger simultaneously, reduce false-alarm, also have a kind of home furnishings intelligent burglary-resisting system, it is made of antitheft door, mechanical lockset, window, terrace and balcony door at least.By being installed in: the door net sensor on (1) antitheft door, antitheft door Magnetic Sensor, (2) be installed in dead bolt sensor, key on the lockset and insert/extract sensor, the pellet shot from a slingshot sensor of beating, (3) be installed in the interior handling position sensor of outer handle subassembly, arrange simultaneously from terrace and enter balcony path detecting area the balcony door passage, enter window path detecting area the passage in room from window, realize owner in the identification at home automatically and robber's Smart Home burglary-resisting system.

There is following shortcoming in existing door and window anti-intrusion system:

1. there is defective separately in single anti-Intrusion Detection Technique, in some cases can't operate as normal, in case can't operate as normal, whole detection system is in paralyzed state, the poor stability of system.As: intelligent video analysis detects the interference that may be subjected to irrelevant motions such as ambient light variation, minute surface reflection, causes a large amount of wrong reports; Rpyroelectric infrared detects the interference that is subject to temperature, high light, circumstance complication motion; Vibration detection is vulnerable to the interference that external force such as wind causes that the door and window vibration produces; The broken detection of glass is vulnerable to the interference of external environment noise; Door magnetic detects needs door and window strict closed, can't use under the indoor situation that needs to ventilate, and as the summer of sweltering heat, the user often needs the ventilation of windowing.

2. the ability that anticipation is carried out in the behavior of setting foot-point before traditional anti-intrusion system can't be committed a crime to the robber, the pre-alerting ability of system is poor;

3. need after the robber enters the room, could trigger warning, report to the police and can not trigger in the very first time of implementing crime, reduce the promptness of reporting to the police;

4. relate to a large amount of various sensors, Installation and Debugging are very complicated, and warning message is not directly perceived simultaneously, can't learn field condition;

5. traditional warning system can't be worked under the situation of cutting off external power supply, gives illegal invasion person with opportunity.

Summary of the invention

The object of the present invention is to provide a kind of intelligent door and window anti-intrusion system, solved existing anti-theft measure function singleness, rate of false alarm height, the untimely and easy out-of-work problem of reporting to the police.

For solving above-mentioned technical matters, the present invention by the following technical solutions:

A kind of intelligent door and window anti-intrusion system comprises:

Video acquisition module adopts video sensor to gather video stream signal, finishes the digitizing of picture signal, and the pre-service of picture signal is met the digital video signal of signal processing module requirement and exports to signal processing module;

The audio collection module is finished the digital-to-analog conversion of voice signal, and the sample code of voice signal and filtering are handled, and is met the digital audio and video signals of signal processing module requirement and exports to signal processing module;

Heat discharges the infrared detection alarm module, the difference of the temperature of inducing moving objects and background object, and heat is released the infrared different information that can sense human body temperature and ambient temperature when human body moves, and converts the output of voltage signal backward signal processing module to;

The vibration detection module produces extraneous vibration deformation or is subjected to force information to change voltage signal into, exports to signal processing module;

The broken detection module of glass and door magnetic detection module are transformed into voltage signal by the wired or wireless communication mode with corresponding information and export to signal processing module;

Signal processing module, collect heat and discharge the signal that infrared detection alarm module, vibration detection module, video acquisition module and audio collection module transmit, differentiate intrusion behavior or guest visiting, send alerting signal or send visitor's photo to the owner that is in to the warning sending module respectively;

The warning sending module adopts the wired or wireless communication mode, is used for receiving alerting signal that signal processing module sends and to sending warning message to householder's mobile phone or cell management center;

Power management module connects external power supply and accumulator, when the external power supply normal power supply, entire product is used external power supply, when extraneous power cut-off, inner standby battery is enabled automatically, guarantees that above-mentioned each module continues operate as normal after external power interruption.

Further technical scheme is that the present invention is arranged on the cartridge type light fixture, described heat discharges the outward flange that infrared detection alarm module, vibration detection module, video acquisition module, audio collection module and warning sending module are installed in the cartridge type light fixture, and the switch lamp control module of described signal processing module, power management module and cartridge type light fixture itself is installed in the middle part of cartridge type light fixture.

Further technical scheme is above-mentioned signal processing module, main process chip adopts main core processor and the double-core architecture mode of being combined from core processor, described main core processor is mainly finished the collection of digital video signal and word sound signal, audio/video coding, collect the signal of heat release infrared detection alarm module output and the signal of vibration detection module output, receive the signal that the broken detection module of glass and door magnetic detection module send, the multi-source signal is sent to from core processor together with audio, video data; Described judgement and the householder's authentication of carrying out intrusion behavior from core processor, wherein invasion should be judgement and mainly comprises operation audio-video intelligent analysis algorithm, judge whether to exist intrusion behavior by video and sound, the signal of the signal of exporting in conjunction with heat release infrared detection alarm module, the signal of vibration detection module output, the broken detection module of glass and the transmission of door magnetic detection module forms final decision signal simultaneously.

Further technical scheme is that above-mentioned householder's identity judgement comprises recognition of face or at user mobile phone the WIFI communication software is installed, video acquisition module is communicated by letter by WIFI with user mobile phone and is carried out identity validation, and the method for wherein said recognition of face mainly comprises with the lower part:

The front face photo of same individual's different angles is gathered in the registration of people's face, finds the position of people's face in image by people's face location, and standardization people face size, people's face angle and illumination, the feature of extraction standardization facial image, typing registered user database;

Recognition of face, adopt the HAAR feature to realize that in conjunction with the adaboost algorithm people's face detects realization people face location, adopted two-layer human eye steady arm, all be to obtain the human eye location by the adaboost algorithm, utilize people's face positioning result by the image rotation eyes to be proofreaied and correct and be the standardization of level realization people face, carry out feature extraction by two-dimensional Gabor filter, utilize the covariance between vector to mate the tolerance mode apart from conduct, realize the facial image of inquiry and the coupling of database facial image by the arest neighbors classification.

Further technical scheme is above-mentioned signal processing module

Be connected with memory module;

Be connected with external power supply and battery by power management module;

Be connected with the internal memory for the master cpu operation;

Be connected with the flash memory for storage system start-up routine, configuration parameter, log information;

Be connected with by external warning lamp, the warning signal interlocking equipment is realized local sound and light alarm, or controls the interlink warning module of other associate device.

Further technical scheme is that the detection method of above-mentioned video acquisition module mainly is divided into background modeling and motion detection, goal verification, and target following and behavioural analysis four parts, wherein

Described background modeling and motion detection are that the mode that has adopted multiple image to be averaging obtains background mean value, and the variance of background is initialized as a constant, pass through formula

$f(x,y)=\left\{\begin{array}{cc}1& |f(x,y)-\mathrm{\μ}(x,y)|>N\×\mathrm{\σ}(x,y)\\ 0& \mathrm{else}\end{array}\right.$

With background pixels and prospect pixel separation, wherein 1 represents the prospect pixel with foreground detection, 0 expression background pixels.F (x, y) in the presentation video (x y) locates the gray-scale value of pixel, μ (x, y) the corresponding background mean value of expression, σ (x, the y) variance of the corresponding background of expression,

Described goal verification, by the foreground area of target size wave filter according to cun requirement of the discontented full size of the size filtering of setting, by the highlighted target filter foreground area highlighted according to the setting threshold filtering, by time domain filtering motion continuity, motion conspicuousness and area change continuity are carried out filtering respectively

The tracking of described target, according to present frame and before the location estimation target of target in the position of next frame, pass through formula $v_t^x=\frac{\underset{n=0}{\overset{N-2}{\mathrm{\Σ}}}(x_{t-n}-x_{t-n-1})}{N-1}$ With $v_t^y=\frac{\underset{n=0}{\overset{N-2}{\mathrm{\Σ}}}(y_{t-n}-y_{t-n-1})}{N-1}$ Estimating target speed is realized target prodiction, wherein

With

Target is in the speed of x direction and y direction constantly to represent t respectively, and N is time window.x _T-nAnd y _T-nRepresent t-n horizontal ordinate and the ordinate at the extraneous rectangle frame of target center, in like manner x constantly respectively _T-n-1And y _T-n-1Represent t-n-1 horizontal ordinate and the ordinate at the extraneous rectangle frame of target center constantly respectively;

The judgement of alarm region and corresponding rule realization specific behavior is set in described behavioural analysis by the user.

Further technical scheme is the detection method of above-mentioned audio collection module,

Intrusion detection flow process based on sound is as shown below, the sound signal that obtains by audio collecting device, at first carry out pre-service, mainly comprise pre-emphasis, divide frame and windowing, satisfy the needs of follow-up spectrum analysis and identification, next adopt mixed Gauss model to set up the background sound model, after finishing, modeling begins sound detection, when occurring being different from the abnormal noise of background sound in detecting scene, warning intensity begins to add up, if warning intensity is greater than setting threshold, illustrate to have intrusion behavior, trigger and report to the police.

Obtain the power spectrum density of sound signal, the sampling rate of establishing sound signal X (t) is f _s, X (t) is passed through pre-emphasis successively, divide frame and windowing process, before handling, signal at first removes average, adopt the period map method in the Classical Spectrum estimation, use Fast Fourier Transform (FFT) FFT to realize, finally obtain normalized power spectrum X ^(t)(f _n), n ∈ [1, N] wherein, N is sampling number, t represents sampling instant, adopts the sub belt energy ratio Describe power spectrum density, utilize formula

Calculate the sub belt energy ratio

Be defined as the ratio of sub belt energy and gross energy, wherein coboundary and the lower boundary of U (i) and L (i) expression subband i are M subband according to logarithm with frequency band division here;

Based on mixed Gaussian background modeling and the sound detection of sub belt energy ratio, the probability distribution that mixed Gaussian background modeling hypothesis signal changes can be used K Gaussian distribution match, and the probability distribution of sound signal is expressed as

Each Gaussian distribution η in the model _i(x, μ _i, σ _i) all give a weights omega _i, μ wherein _iAnd σ _iAverage and the standard deviation of representing Gaussian distribution respectively, a plurality of Gaussian distribution obtain the probability distribution of signal by linear combination, and with preceding B Gaussian distribution model as a setting, remaining Gaussian distribution is as foreground model, wherein

Current demand signal amplitude and a preceding B Gaussian distribution are mated, and if wherein any one Gaussian distribution the match is successful then this signal is background, otherwise be foreground signal, utilization | I (x, t)-μ _i(x, t-1) |＜c * σ _i(x t-1) mates.

Further technical scheme is, the anti-intrusion method of intelligent door and window anti-intrusion system is as follows:

The first step, discharging the infrared detection alarm module by heat collects the external heat temperature information and changes voltage signal into, collecting extraneous vibration by the vibration detection module produces the information of deformation or stressed transformation and changes voltage signal into, collecting the broken and door magnetic variation information of glass by the broken detection module of glass and a door magnetic detection module closes and changes voltage signal into, collect digital video signal by video acquisition module, collect digital audio and video signals by the audio collection module;

Second step, signal processing module receives the voltage signal that heat discharges infrared detection alarm module, vibration detection module, the broken detection module of glass and door magnetic detection module, and in conjunction with audio-video intelligent analysis, differentiate intrusion behavior or guest visiting, send alerting signal or send information such as visitor's photo to the owner that is in to the warning sending module respectively;

In the 3rd step, the warning sending module is received alerting signal, and the receiver, video acquisition module is collected digital video signal and collected digital audio and video signals by the audio collection module simultaneously, and is transferred to external management terminal or handheld terminal by wired or wireless mode.

Further technical scheme is, this intelligent door and window anti-intrusion system is as follows as the method for visual entrance guard:

The first step, collect digital video signal by video acquisition module, collect digital audio and video signals by the audio collection module, discharging the infrared detection alarm module by heat collects the external heat temperature information and changes voltage signal into, collect extraneous vibration by the vibration detection module and produce the information of deformation or stressed transformation and change voltage signal into, collect the broken and door magnetic variation information of glass by the broken detection module of glass and a door magnetic detection module and close and change voltage signal into;

Second step, signal processing module receives the voltage signal that heat discharges infrared detection alarm module, vibration detection module, the broken detection module of glass and door magnetic detection module, and judge whether to be guest visiting in conjunction with audio-video intelligent analysis, if there is the visit generation of behavior of guest, then by wireless mode the visitor is sent to mobile or fixed terminals such as the indoor master cellular phone of being in automatically at outdoors video or photographic intelligence, and activated terminals provides ring, vibrations or voice suggestion.

Compared with prior art, the invention has the beneficial effects as follows: intelligent door and window anti-intrusion system of the present invention adopts rpyroelectric infrared to detect, vibration detection, audio detection, glass is broken to be detected and door magnetic detection technique, find the illegal invasion behavior that the door and window zone may exist by the multidimensional detection mode, can accurately tell is illegal invasion, guest's visiting still householder is come in and gone out normally, with audio frequency and video or picture be carrier in real time, alerting signal directly perceived is by the wired or wireless communication means, the very first time is sent to the mobile phone such as the householder, cell monitoring computing machines etc. are reported to the police and are received and processing terminal, warning lamp simultaneously also links, warning signal realizes site of the accident sound and light alarm, and other associate device perhaps links; Native system is installed on outdoorly in addition, can at utmost illegal invasion be eliminated before its actual generation; Than traditional warning system, the present invention also carries standby power supply, can still can finish anti-intrusion detection in the sensitization time section for self powering 2-24 hour under the situation of cutting off external power supply.

Description of drawings

Fig. 1 is the connection diagram of an embodiment of intelligent door and window anti-intrusion system of the present invention.

Fig. 2 is the hardware connection diagram of intelligent door and window anti-intrusion system of the present invention.

Fig. 3 is the software architecture diagram of the wise energy of the present invention door and window anti-intrusion system.

Fig. 4 is primary processor end schematic flow sheet in the signal processing module of intelligent door and window anti-intrusion system of the present invention.

Fig. 5 is from processor end schematic flow sheet in the signal processing module of intelligent door and window anti-intrusion system of the present invention.

Fig. 6 is the registration of people's face and the recognition of face schematic flow sheet of intelligent door and window anti-intrusion system of the present invention.

Fig. 7 is the moving object detection and tracking schematic flow sheet based on video of intelligent door and window anti-intrusion system of the present invention.

Fig. 8 is the audio detection schematic flow sheet of intelligent door and window anti-intrusion system of the present invention.

Fig. 9 analyzes synoptic diagram to accessing facial image during for people's face standardization of intelligent door and window anti-intrusion system of the present invention.

Embodiment

In order to make purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explaining the present invention, and be not used in restriction the present invention.

Fig. 1 shows an embodiment of a kind of intelligent door and window anti-intrusion system of the present invention: a kind of intelligent door and window anti-intrusion system comprises

Video acquisition module, adopt video sensor to gather video stream signal, finish the digitizing of picture signal, the pre-service of picture signal, being met the digital video signal of signal processing module requirement and exporting its concrete detection mode to signal processing module can be domain mode or curtain mode;

The audio collection module is finished the digital-to-analog conversion of voice signal, and the sample code of voice signal and filtering are handled, and is met the digital audio and video signals of signal processing module requirement and exports to signal processing module;

Heat discharges the infrared detection alarm module, the difference of the temperature of inducing moving objects and background object, and heat is released the infrared different information that can sense human body temperature and ambient temperature when human body moves, and converts the output of voltage signal backward signal processing module to;

The vibration detection module produces extraneous vibration deformation or is subjected to force information to change voltage signal into, exports to signal processing module;

The broken detection module of glass and door magnetic detection module are transformed into voltage signal by the wired or wireless communication mode with corresponding information and export to signal processing module;

Signal processing module, collect heat and discharge the signal that infrared detection alarm module, vibration detection module, video acquisition module and audio collection module transmit, carry out analysis-by-synthesis, differentiate illegal invasion or guest visiting, send alerting signal or send visitor's information such as photo to the owner that is in to the warning sending module respectively;

The warning sending module, adopt the wired or wireless communication mode, be mainly used in receiving alerting signal that signal processing module sends and send warning message to householder's mobile phone or cell management center, can adopt one of wired, 3G, WIFI, Zigbee, Bluetooth or other communication;

Power management module, connect external power supply and accumulator, when the external power supply normal power supply, entire product is used external power supply, when extraneous power cut-off, inner standby battery is enabled automatically, guarantees that above-mentioned each module continues operate as normal after external power interruption, guarantees that preferably video camera worked on after external power interruption 2-24 hour.

In Fig. 1, as can be seen, invention is arranged on the cartridge type light fixture, described heat discharges the outward flange that infrared detection alarm module, vibration detection module, video acquisition module, audio collection module and warning sending module are installed in the cartridge type light fixture, and the switch lamp control module of described signal processing module, power management module and cartridge type light fixture itself is installed in the middle part of cartridge type light fixture.Described switch lamp control module can be in conjunction with vibration, sound, and the infrared signal that waits judges whether that the someone enters, if there is the people to enter, the turn on lights optical illumination is for the subsequent video analysis provides ambient lighting.We are the appearance that total system are made into similar illuminating lamp, the mutual set of system and lamp, native system well can not only be stashed, prevent that the lawless person from destroying this intelligent door and window anti-intrusion system, can also carry out light filling to the camera of video acquisition module in the system, make the video information of collection more clear, when ambient light illumination is not enough, provide secondary light source to video acquisition module, guarantee that it still can collect effective view data under the environment of low-light (level).

Fig. 2 shows a preferred embodiment of a kind of intelligent door and window anti-intrusion system of the present invention, signal processing module, and main process chip adopts main core processor and the double-core architecture mode of being combined from core processor.Main core processor is mainly finished the collection of digital video signal and word sound signal, audio/video coding, collect the signal of heat release infrared detection alarm module output and the signal of vibration detection module output, receive the signal that the broken detection module of glass and door magnetic detection module send, the multi-source signal is sent to from core processor together with audio, video data; Main core processor carries out judgement and householder's authentication of intrusion behavior, wherein invasion should be judgement and mainly comprises operation audio-video intelligent analysis algorithm, judge whether to exist intrusion behavior by video and sound, the signal of the signal of exporting in conjunction with heat release infrared detection alarm module, the signal of vibration detection module output, the broken detection module of glass and the transmission of door magnetic detection module forms final decision signal simultaneously.

As shown in Figure 3, software is mainly by signals collecting, and signal analysis, warning send and interlock control three parts are formed.Signals collecting and the transmission of reporting to the police operate in main nuclear end for process, and signal analysis operates in from the nuclear end for process.The signals collecting interface has comprised the audio-video collection module, rpyroelectric infrared alerting signal acquisition module, vibration alarming signal acquisition module and wireless alarm signal acquisition module.Main nuclear end for process is finished the collection of switching value alerting signal and is delayed time synchronously, is sent to from the nuclear end for process together with audio-video signal.Finish intelligent audio frequency and video analysis from the nuclear end for process, multi-source alert information fusion and decision-making, finish the affirmation of householder's identity by recognition of face mode or wireless WIFI mode, if user identification confirmation is failed then sent warning/early warning signal to the main end for process of examining when detecting intrusion behavior, the main end for process of examining sends warning and interlock control information by the warning sending module to exterior terminal.

As shown in Figure 4, main nuclear end for process software flow:

After system powers on, at first finish the initialization that the master chip master examines end for process, next finish peripheral collecting device, the communication facilities initialization starts main nuclear handling procedure.Create audio-video collection thread, rpyroelectric infrared detection thread, wireless receiving thread, communication thread, warning transmission thread.

Audio-video collection thread: combination one frame multi-source data after receiving audio, video data, comprise the sign whether video data, voice data, various sensor warning intensity and user mobile phone exist, putting into FrameBuffer calls for communication thread, finish pre-recording of audio frequency and video simultaneously, in order to warning message is provided.

The alerting signal collecting thread: receive the switching value alarm signal A i of the alarm sensor of various wired or wireless accesses, wherein Ai can be the rpyroelectric infrared alerting signal, vibration alarming signal, the broken alerting signal of glass, door magnetic alerting signal etc.

Communication thread: receive the alerting signal of sending from the core processor end, notice is reported to the police and is sent thread.If there is a frame multi-source data among the FrameBuffer, then these data are sent to the DSP end.

Report to the police and send thread: after receiving alerting signal, the warning message that tissue is relevant, as the audio frequency and video of pre-recording, pictures etc. send to exterior terminal.

As shown in Figure 5, from core processor end software flow:

At first main core processor end is loaded into multitask kernel and application program from the core processor internal memory after starting, and finishes a series of initialization from core processor, creates communication thread and recognition of face thread automatically.Communication thread at first judges whether to need to send warning/early warning signal, if then send warning/early warning signal to main end for process, otherwise judge whether to receive a frame multi-source information, wherein multi-source information comprises: audio, video data, the sign whether various sensor alerting signals and user mobile phone exist, multi-source information is put into frame buffer FrameBuffer, send the confirmation of receipt signal to main end for process simultaneously, show from end for process working properly.The recognition of face thread takes out video data and finishes recognition of face from FrameBuffer, if recognition of face success, the then sign of set identity validation.The intrusion detection thread reads frame data from FrameBuffer, by audio analysis, and vibration information, infrared information judges whether that the someone will enter guarded region, if then open illumination, for ensuing video analysis provides ambient lighting, make things convenient for the householder to open the door simultaneously.Open illumination back setting in motion and detect, owing to only be concerned about this behavior of entering, judge so need carry out direction of motion, when being judged as when entering direction, target is followed the tracks of.When target life period during greater than setting-up time, be illustrated as a suspect, system can cooperate with on one's own initiative by voice suggestion and carry out recognition of face if WIFI mode identity validation is failed, and triggers intrusion behavior if authentication is failed and reports to the police, and sends warning/early warning signal to the ARM end.

Fig. 6 shows another preferred embodiment of a kind of intelligent door and window anti-intrusion system of the present invention, the judgement of householder's identity comprises recognition of face or at user mobile phone the WIFI communication software is installed, video acquisition module is communicated by letter by WIFI with user mobile phone and is carried out identity validation, and the method for wherein said recognition of face mainly comprises with the lower part:

The front face photo of same individual's different angles is gathered in the registration of people's face, finds the position of people's face in image by people's face location, and standardization people face size, people's face angle and illumination, the feature of extraction standardization facial image, typing registered user database;

Recognition of face, adopt the HAAR feature to realize that in conjunction with the adaboost algorithm people's face detects realization people face location, adopted two-layer human eye steady arm, all be to obtain the human eye location by the adaboost algorithm, utilize people's face positioning result by the image rotation eyes to be proofreaied and correct and be the standardization of level realization people face, carry out feature extraction by two-dimensional Gabor filter, utilize the covariance between vector to mate the tolerance mode apart from conduct, realize the facial image of inquiry and the coupling of database facial image by the arest neighbors classification.Wherein the Weak Classifier that the Adaboost algorithm is general with a large amount of classification capacities is combined as a strong classifier according to the mode that the training error index descends.And HAAR is characterized as the weak typing feature that the adaboost algorithm provides magnanimity, has guaranteed that the adaboost algorithm totally finds the weak typing of excellent performance.Detect in the implementation process at people's face, the use of integration histogram and cascade classifier greatly reduces the processing time when guaranteeing than high measurement accuracy; Human eye generally is divided into two-layer location during the location, and wherein ground floor is coarse positioning, and locating area has selected to comprise most of ocular of eyes eyebrows, and the second layer is accurately to locate, and locating area only comprises ocular.The coarse positioning device than precise localizer owing to comprised area information more, therefore the stability of location is higher, substantially do not have bigger position deviation, and precise localizer can realize the accurate location of human eye, but the interference that is subjected to eyebrow, canthus easily causes the location mistake.On the basis of coarse positioning, determine the approximate location scope of human eye by the geometric proportion relation, in this scope, use precise localizer to realize the accurate location of human eye.By having reduced eyebrow, canthus etc. to location influence by thick to smart locator meams, improved the accuracy of location; And the standardization of people's face is very crucial in a recognition of face step, and standardization result's quality has directly influenced the precision of recognition of face.Geometry correction and the gamma correction of facial image mainly finished in the standardization of people's face.The result who utilizes the previous step human eye to locate is easy to realize the geometry correction of facial image, at first by the image rotation eyes is proofreaied and correct to be level, intercepts apart from the facial image of d by eyes.As shown in Figure 9, wherein scale the images to the 80x80 pixel at last.

Gamma correction mainly is to eliminate uneven illumination to a certain extent to the influence of follow-up identification.Mainly comprise the plane of illumination match, the deduction plane of illumination, histogram equalization and gray-scale value normalize to zero-mean, unit variance.Here suppose that plane of illumination is a plane.Point on the plane of illumination satisfies following formula: IP (x, y)=to be write as matrix form be x=Np to ax+by+c, the column vector lined up of the picture element gray-scale value of x presentation video wherein, N represents the coordinate of picture element correspondence, horizontal ordinate is shown in first tabulation, secondary series is represented ordinate, and the 3rd row are filled 1, p=[a b c] ^TPlane parameter a, b, c can try to achieve by the mode of linear regression, i.e. p=(N ^TN) ^-1N ^TX.

Can select the Gabor wavelet character, the Gabor conversion has excellent performance aspect the analysis image regional area texture.Two-dimensional Gabor filter Can be expressed as:

$\mathrm{\ψ}\left(\stackrel{\→}{x}\right)=\frac{\left|\right|\stackrel{\→}{k}\left|\right|}{{\mathrm{\σ}}^2}\exp (-\frac{{\left|\right|\stackrel{\→}{k}\left|\right|}^2{\left|\right|\stackrel{\→}{x}\left|\right|}^2}{2{\mathrm{\σ}}^2})[\exp \left(i\stackrel{\→}{k}\stackrel{\→}{x}\right)-\exp (-\frac{{\mathrm{\σ}}^2}{2})]$

Wherein Be image coordinate, Be the centre frequency of wave filter, k _xAnd k _yExpression respectively

In the projection of transverse axis and the longitudinal axis,

Be the direction of wave filter, u and the different value of v representative,

Be Gaussian envelope, Be the complex values plane wave.Two-dimensional Gabor filter realizes by the sinusoidal wave plane of two-dimensional Gaussian function modulation characteristic frequency and direction, the analysis that the frequency by changing sinusoidal wave plane and direction realize different scale and different directions image texture.

Obtained the facial image of 80x80 size by the standardization of people's face, here 5 wave filter yardsticks have been selected, 8 filtering directions, obtain the Gabor wave filter of 40 different directions and frequency, a facial image is obtained 40 magnitude image behind the Gabor wavelet transformation after by the wave filter convolution, and the Gabor intrinsic dimensionality that obtains at last is 163840.Can reduce the speed of discriminator in the proper vector of such higher-dimension greatly, therefore need carry out dimensionality reduction to proper vector.Here adopt 4x4 evenly to realize the feature dimensionality reduction to down-sampling.

Adopt the arest neighbors classification to realize the facial image of inquiry and the coupling of database facial image, the covariance between the employing vector simultaneously can be by covariance apart from weighing the confidence level of finally mating apart from conduct coupling tolerance mode.

Another preferred embodiment of a kind of intelligent door and window anti-intrusion system according to the present invention, signal processing module

Be connected with memory module (Storage), at different applicable cases, can use dissimilar storage mediums, SD and TF cartoon are crossed SDIO and are controlled, and the storage medium of this type is convenient for changing; Nand controls by Nandflash, this type integrated level height, but be not easy to change storage medium; SSD is by PCI-E or the control of SATA interface, and this type storage space can be accomplished very big;

Be provided with Ethernet interface (RJ45);

Be connected with external power supply (DC IN) and battery (Battery) by power management module (Power manager);

Be connected with the internal memory (DDR) for the master cpu operation;

Be connected with the flash memory (Flash) for storage system start-up routine, configuration parameter, log information;

Be connected with wireless module (3G, WIFI), be used for the transmission of audio, video data and remote control signal;

Be connected with wireless module (zigbee, Blue tooth or other wireless modules), be used for receiving the alerting signal that the distributed alarming device sends, as the broken signal of glass and door magnetic opening signal, also can send control information to miscellaneous equipment.

Be connected with by external warning lamp, the warning signal interlocking equipment is realized local sound and light alarm, or controls the interlink warning module of other associate device.

Fig. 7 shows another preferred embodiment of a kind of intelligent door and window anti-intrusion system of the present invention, and the detection method of video acquisition module mainly is divided into background modeling and motion detection, goal verification, and target following and behavioural analysis four parts, wherein

Described background modeling and motion detection are that the mode that has adopted multiple image to be averaging obtains background mean value, and the variance of background is initialized as a constant, pass through formula

$f(x,y)=\left\{\begin{array}{cc}1& |f(x,y)-\mathrm{\μ}(x,y)|>N\×\mathrm{\σ}(x,y)\\ 0& \mathrm{else}\end{array}\right.$

With background pixels and prospect pixel separation, wherein 1 represents the prospect pixel with foreground detection, 0 expression background pixels.F (x, y) in the presentation video (x y) locates the gray-scale value of pixel, μ (x, y) the corresponding background mean value of expression, σ (x, the y) variance of the corresponding background of expression,

If detect large tracts of land prospect pixel then system thinks that variation may take place scene, at this moment close follow-up analysis, if all detect large tracts of land prospect pixel for a long time then system thinks that variation has taken place scene really, at this moment restarts background modeling.

The context update strategy that the renewal of the background of native system has been adopted the based target aspect and combined based on the pixel aspect.When picture element is detected as background dot, adopt the context update based on the pixel aspect, adopt single Gaussian Background update method here, comprise the renewal of background mean value and the renewal of background variance, shown in the following formula:

μ _t(x,y)＝(1-α)×μ _t-1(x,y)+f _t(x,y)×α

${\mathrm{\σ}}_t^2(x,y)=\max (\mathrm{\Δ},(1-\mathrm{\α})\×{\mathrm{\σ}}_{t-1}^2(x,y)+{(f_t(x,y)-{\mathrm{\μ}}_t(x,y))}^2\×\mathrm{\α})$

Wherein subscript t represents t constantly, and α generally is a very little value, as 0.01 for upgrading the factor.Here clamper the minimum value of variance be Δ, prevent that model from too restraining, cause the model noise resisting ability to weaken, the value of Δ is 36 here.

When picture element is detected as the foreground point, if cut apart by target and to judge that picture element is not target pixel point then adopts context update based on the pixel aspect, if namely this picture element at a fixed time long-time the detection be the prospect picture element then be updated in the background picture element is disposable; If cut apart by target and to judge that picture element is target pixel point then adopts the background update method of based target aspect, namely have only the judgement target when not moving for a long time, just can be with disposable being updated in the background of regional picture element at target place.

Described goal verification, by the foreground area of target size wave filter according to cun requirement of the discontented full size of the size filtering of setting, by the highlighted target filter foreground area highlighted according to the setting threshold filtering, by time domain filtering motion continuity, motion conspicuousness and area change continuity are carried out filtering respectively.Highlighted target filter wherein: the foreground area that filtering is highlighted, these foreground area may be interference such as light source or reflective medium.The determination methods of highlighted foreground area: if the ratio of highlighted pixel surpasses setting threshold in the foreground area, think that then this foreground area is highlighted foreground area; Time domain filtering: time-domain filtering is based on the filtering of target aspect, need be by the target following technology.Comprise: motion continuity filtering, the filtering of motion conspicuousness, the filtering of area change continuity.Motion continuity filtering: the occupied zone of hypothetical target two frames in front and back is that large tracts of land is overlapping, and namely can not undergo mutation in the position of target.The filtering of motion conspicuousness: the motion of hypothetical target is that certain directivity is arranged, namely the vector of a period of time internal object displacement add and add with the scalar of displacement of targets and ratio should be greater than certain threshold value.The filtering of area change continuity: the area of hypothetical target is metastable, can not undergo mutation.

The tracking of described target, the target following based on motion detection has been adopted in employing, target association by interframe on the basis of motion detection, form the movement locus of target, for the succeeding target behavioural analysis provides foundation, according to present frame and before the location estimation target of target in the position of next frame, pass through formula $v_t^x=\frac{\underset{n=0}{\overset{N-2}{\mathrm{\Σ}}}(x_{t-n}-x_{t-n-1})}{N-1}$ With $v_t^y=\frac{\underset{n=0}{\overset{N-2}{\mathrm{\Σ}}}(y_{t-n}-y_{t-n-1})}{N-1}$ Estimating target speed is realized target prodiction, wherein With

Target is in the speed of x direction and y direction constantly to represent t respectively, and N is time window, x _T-nAnd y _T-nRepresent t-n horizontal ordinate and the ordinate at the extraneous rectangle frame of target center, in like manner x constantly respectively _T-n-1And y _T-n-1Represent t-n-1 horizontal ordinate and the ordinate at the extraneous rectangle frame of target center constantly respectively.The feature selecting aspect has been selected two features of center C of relatively stable reliable target area S and target boundary rectangle frame here, and the target association coupling just can find the former frame target in the position of present frame, realizes the location of target.According to the correlation tracking principle, as long as guarantee under the situation of enough image sampling rates, the change in location of same target between adjacent two frames is not too large, therefore the hunting zone of target can be limited to a less distance range, also greatly reduces the risk of mistake coupling simultaneously.Utilize

Formula, the present frame target With target to be matched

Just carry out characteristic matching when satisfying following formula, wherein γ is the detection range threshold value, need determine according to actual scene.

The criterion of coupling, shown in the following formula:

$\arg \min (\mathrm{\&omega;}\&times;\left(\frac{\mathrm{dist}\left(O_t^j\right\{C\},O_{t-1}^i\{C\left\}\right)}{\mathrm{\&gamma;}}\right)+(1-\mathrm{\&omega;})\&times;\frac{\left|o_t^j\right\{S\}-O_{t-1}^i\{S\left\}\right|}{O_{t-1}^i\left\{S\right\}})<T$

Wherein ω is the weight factor of feature, gets 0.5 here, is provided with the error upper limit T of coupling here, prevents the mistake coupling, gets 0.4 here.

The renewal of target signature all adopts the single order smooth mode to upgrade, shown in the following formula:

$O_t^i\left\{F\right\}=\mathrm{\&alpha;}\&times;O_{t-1}^i\left\{F\right\}+(1-\mathrm{\&alpha;})\&times;O_t^i\left\{F\right\},F=\{S,C\}$

Wherein α gets 0.2 here for upgrading the factor.

The judgement of alarm region and corresponding rule realization specific behavior is set in described behavioural analysis by the user.For example can be set to a region by alarm region, surpass setting value then think possible intrusion behavior if enter this regional people's residence time, trigger and report to the police.Big zone that also can the door place is set to the surveyed area of pacing up and down, and surpasses setting value then thinks the possible behavior of setting foot-point if enter this regional people's residence time, triggers early warning.

Fig. 8 shows another preferred embodiment of a kind of intelligent door and window anti-intrusion system of the present invention, the detection method of audio collection module,

Intrusion detection flow process based on sound is as shown below, the sound signal that obtains by audio collecting device, at first carry out pre-service, mainly comprise pre-emphasis, divide frame and windowing, satisfy the needs of follow-up spectrum analysis and identification, next adopt mixed Gauss model to set up the background sound model, begin sound detection after modeling is finished, when in detecting scene, occurring being different from the abnormal noise of background sound, warning intensity begins to add up, there is intrusion behavior if warning intensity greater than setting threshold, illustrates, triggers and report to the police, specific as follows

Obtain the power spectrum density of sound signal, the sampling rate of establishing sound signal X (t) is f _s(for example getting 48kHz) passes through pre-emphasis successively with X (t), divides frame and windowing process, (frame length is 48K sampled point, frame moves and is 24K sampled point, and window function is selected Hanning window), before handling, signal at first removes average, avoid DC component that near the spectral line ω=0 place is exerted an influence, adopt the period map method in the Classical Spectrum estimation, use Fast Fourier Transform (FFT) FFT to realize, finally obtain normalized power spectrum X ^(t)(f _n), n ∈ [1, N] wherein, N is sampling number, t represents sampling instant, (when sampling rate is f _s=48kHz, the value of N is 48000, calculated amount is bigger for subsequent analysis), adopt the sub belt energy ratio A _i ^(t)Describe power spectrum density, utilize formula

Calculate the sub belt energy ratio A _i ^(t)Be defined as the ratio of sub belt energy and gross energy, wherein coboundary and the lower boundary of U (i) and L (i) expression subband i are that M subband (worked as M=10, f according to logarithm with frequency band division here _sThe subband border of correspondence is 0.023kHz during=48kHz, 0.046kHz, 0.093kHz, 0.187kHz, 0.375kHz, 0.750kHz, 1.5kHz, 3kHz, 6kHz, 12kHz and 24kHz);

Based on mixed Gaussian background modeling and the sound detection of sub belt energy ratio, the probability distribution that mixed Gaussian background modeling hypothesis signal changes can be used K Gaussian distribution match, and the probability distribution of sound signal is expressed as

Each Gaussian distribution η in the model _i(x, μ _i, σ _i) all give a weights omega _i, μ wherein _iAnd σ _iAverage and the standard deviation of representing Gaussian distribution respectively, a plurality of Gaussian distribution obtain the probability distribution of signal, ω by linear combination _iEmbodied the attention degree of model for i Gaussian distribution, when the amplitude of signal in a period of time drops in this Gaussian distribution, ω _iValue can increase gradually, otherwise ω _iCan reduce gradually.σ has reflected the convergence of Gaussian distribution, and for a Gaussian distribution that is tending towards restraining, amplitude should be less around the fluctuation of average, and σ is also less, and such Gaussian distribution just is fit to describe the variation of background.K Gaussian distribution arranged forward Gaussian distribution and can be represented the distribution of background according to the descending sort of ω/σ, and with preceding B Gaussian distribution model as a setting, remaining Gaussian distribution is as foreground model, wherein

Current demand signal amplitude and a preceding B Gaussian distribution are mated, and if wherein any one Gaussian distribution the match is successful then this signal is background, otherwise be foreground signal, utilization | I (x, t)-μ _i(x, t-1) |＜c * σ _i(x t-1) mates.

Another embodiment of a kind of intelligent door and window anti-intrusion system according to the present invention, the anti-intrusion method of intelligent door and window anti-intrusion system, step is as follows:

The first step, collect digital video signal by video acquisition module, collect digital audio and video signals by the audio collection module, discharging the infrared detection alarm module by heat collects the external heat temperature information and changes voltage signal into, collect extraneous vibration by the vibration detection module and produce the information of deformation or stressed transformation and change voltage signal into, collect the broken and door magnetic variation information of glass by the broken detection module of glass and a door magnetic detection module and close and change voltage signal into;

Second step, signal processing module receives the voltage signal that heat discharges infrared detection alarm module, vibration detection module, the broken detection module of glass and door magnetic detection module, and in conjunction with audio-video intelligent analysis, mastership identification checking, the generation of synthetic determination intrusion behavior, when having intrusion behavior, send alerting signal;

In the 3rd step, the warning sending module is received alerting signal, and the receiver, video acquisition module is collected digital video signal and collected digital audio and video signals by the audio collection module simultaneously, and is transferred to external management terminal or handheld terminal by wired or wireless mode.

Another embodiment of a kind of intelligent door and window anti-intrusion system according to the present invention, its method as visual entrance guard of intelligent door and window anti-intrusion system is as follows:

The first step, collect digital video signal by video acquisition module, collect digital audio and video signals by the audio collection module, discharging the infrared detection alarm module by heat collects the external heat temperature information and changes voltage signal into, collect extraneous vibration by the vibration detection module and produce the information of deformation or stressed transformation and change voltage signal into, collect the broken and door magnetic variation information of glass by the broken detection module of glass and a door magnetic detection module and close and change voltage signal into;

Second step, signal processing module receives the voltage signal that heat discharges infrared detection alarm module, vibration detection module, the broken detection module of glass and door magnetic detection module, and judge whether to be guest visiting in conjunction with audio-video intelligent analysis, if there is the visit generation of behavior of guest, then by wireless mode the visitor is sent to mobile or fixed terminals such as the indoor master cellular phone of being in automatically at outdoors video or photographic intelligence, and activated terminals provides ring, vibrations or voice suggestion.

In the present invention:

The intelligent video analysis technology that video acquisition module is utilized, namely adopt computing machine, Embedded Double core processor etc. from video by computing and analysis, extract a technology of useful information in the video.This technology is carried out high speed analysis by the powerful data-handling capacity of various processors to the mass data in the video pictures, filters out the unconcerned information of user, only provides the key message of usefulness for the user.

The rpyroelectric infrared detection technique that the infrared detection alarm module utilizes, namely passive infrared detection is a kind of, the difference of the temperature of inducing moving objects and background object.In the guarded region, when no human body moves, the just ambient temperature that pyroelectric infrared sensor is sensed, when human body entered the zone, the infrared ray of human body emission gathered on the pyroelectric infrared sensor after strengthening by Fresnel Lenses, and the pyroelectricity element senses in the rpyroelectric infrared is to the difference of human body temperature and ambient temperature, temperature changes, lose charge balance, outwards discharge electric charge, subsequent conditioning circuit detects handles back generation alerting signal.

The vibration burglar alarm technology that the vibration detection module is utilized: adopt the piezoelectric type potsherd as sensor, extraneous vibration is produced deformation or the stressed voltage signal that changes into, finish the transmission of alerting signal and stop by follow-up auxiliary circuit.

The broken detection technique of glass that the broken detection of glass detection module utilizes: utilize the piezoelectric effect of piezoelectric ceramic piece, can make the broken intrusion detector of glass.To the broken sound of the glass of high frequency (10k～15kHZ) effectively detect, and the voice signal below the 10kHZ (as speaking, walk sound) is had stronger inhibiting effect.Usually just acoustic control is surveyed two kinds of technical combinations together with vibrations, has only the high-frequency sound signal that sends when detecting the glass fragmentation simultaneously and knocks the vibrations that glass causes, just output alarm signal.

The door magnetic detection technique that door magnetic detection module utilizes: formed by two parts: the tongue tube of permanent magnet and open type, permanent magnet is used for producing constant magnetic field, when permanent magnet and tongue tube lean on very closely, door status sensor is in the work stand-by state, after permanent magnet leaves the tongue tube certain distance, be in normally open, trigger and report to the police.

The native system workflow is:

The user can open or close warning function as required, the mode that detects can select video detection, audio detection, rpyroelectric infrared to detect, vibration detection, glass is broken to be detected, during door magnetic detects one or more, adopt rpyroelectric infrared detection, vibration detection, the broken detection of glass, door magnetic to detect as window area, the door region adopts video detection, audio detection, rpyroelectric infrared detection, vibration detection, a magnetic to detect.Warning message can be video, one or more in audio frequency or the picture.

(1) after system powered on or resets, signal processing module is load operation system and application program from FLASH, finishes the initialization of main process chip and the configuration of peripheral hardware, next finishes the initialization to each subsystem, enters normal operating conditions at last.

(2) audio-video signal and the heat at the continuous acquisition monitoring of the primary processor end scene of main process chip are released infrared detection signal, receive the alerting signal of other distributed alarming sensor simultaneously by wireless receiving module, multi-source data sent into from the processor end analyze, carry out audio frequency and video simultaneously and pre-record.If receive warning or early warning signal from the processor end, then with the audio frequency and video of pre-recording, send on cell monitoring center or householder's the mobile phone by the alerting signal sending module together with the photo of capturing.

(3) main process chip moves intelligent audio frequency and video analytical algorithm and intrusion behavior judgement from the processor end.By audio analysis, vibration information, infrared information judge whether that the someone will enter guarded region, if then open illumination, for ensuing video analysis provides ambient lighting, make things convenient for the householder to open the door simultaneously.Open illumination back setting in motion and detect, owing to only be concerned about this behavior of entering, judge so need carry out direction of motion, when being judged as when entering direction, target is followed the tracks of.When target life period during greater than setting-up time, be illustrated as a suspect, system can cooperate with on one's own initiative by voice suggestion and carry out recognition of face if WIFI mode identity validation is failed, and triggers intrusion behavior if authentication is failed and reports to the police, and sends warning/early warning signal to the primary processor end.

(4) after Surveillance center and householder receive early warning or warning, can confirm by the warning message of sending back, and take counter-measure.

Experiment:

The installation of native system: inhale the top and install, guarantee that monitoring range can cover whole door region and zone, part passageway in front of the door, adjust shooting angle and guarantee to access in the monitoring visual field approximate positive portrait, lighting condition is good, can access facial image clearly, people's face elemental area is greater than the 80*80 pixel.

The present invention judges that two foundations that the behavior that enters takes place are:

(1) a suspect has appearred in guarded region: the mode that combines by multiple alarm sensor realizes a suspect's detection.

(2) a suspect's authentication failure: the householder can finish authentication by dual mode: video human face recognition method and WIFI communication.The video human face recognition method: the user enters and cooperates with video camera on one's own initiative behind the zone and finish recognition of face, by comparing with the face database of registration, finishes the checking of identity.The WIFI communication: video camera is communicated by letter by WIFI with user mobile phone and is finished authentication.

Therefore experiment is divided into two parts: the zone enters to be detected and authentication.

The zone enters test experience

The present invention at first passes through audio analysis, vibration detection, infrared detection is carried out preliminary examination to the behavior that enters the zone, and next the mode of checking by Video Motion Detection realizes that the zone enters detection, in order to verify the actual performance of product, 5 tests have been carried out, each test is 7*24 hour, and the performance of while and single-sensor compares, as long as triggered warning for single detection mode, think that then the zone has taken place enters behavior, test result is as follows:

No matter the effective combination that has proved multiple alarm sensor by experiment, still reduce wrong report aspect all improves a lot aspect the accuracy of detection than single alarm.

The authentication experiment

When detecting intrusion behavior, authentication is opened by system, and setting the checking time-out time is 10 seconds, if do not confirm user identity in 10 seconds, then thinks illegal invasion.Respectively recognition of face this two kinds of verification modes of communicating by letter with WIFI are tested, test result is as follows:

The identity validation mode	Experiment number	Number of success	The frequency of failure	Errors number
					WIFI communication	1000	991	9	0
Recognition of face	1000	947	53	17
					Both combine	1000	1000	2	0

In experiment, find, recognition of face is to human face posture, the requirement of photoenvironment is all than higher, if the environment sidelight is serious or personnel's attitude cooperates not tacit meeting to cause can't to identify or wrong identification, and need not user's cooperation by the mode of WIFI communication, but the interference that may be subjected to other WIFI equipment causes to connect and gets nowhere, explanation by experiment, adopt WIFI communication to carry out identity validation and be better than recognition of face realization identity validation, both combinations can further be improved the accuracy rate of identity validation.

Although invention has been described with reference to a plurality of explanatory embodiment of the present invention here, but, should be appreciated that those skilled in the art can design a lot of other modification and embodiments, these are revised and embodiment will drop within the disclosed principle scope and spirit of the application.More particularly, in the scope of, accompanying drawing open in the application and claim, can carry out multiple modification and improvement to building block and/or the layout of subject combination layout.Except modification that building block and/or layout are carried out with improving, to those skilled in the art, other purposes also will be tangible.

Claims (9)

1. an intelligent door and window anti-intrusion system is characterized in that: comprise

Video acquisition module adopts video sensor to gather video stream signal, finishes the digitizing of picture signal, and the pre-service of picture signal is met the digital video signal of signal processing module requirement and exports to signal processing module;

The audio collection module is finished the digital-to-analog conversion of voice signal, and the sample code of voice signal and filtering are handled, and is met the digital audio and video signals of signal processing module requirement and exports to signal processing module;

Heat discharges the infrared detection alarm module, the difference of the temperature of inducing moving objects and background object, and heat is released the infrared different information that can sense human body temperature and ambient temperature when human body moves, and converts the output of voltage signal backward signal processing module to;

The vibration detection module produces extraneous vibration deformation or is subjected to force information to change voltage signal into, exports to signal processing module;

The broken detection module of glass and door magnetic detection module are transformed into voltage signal by the wired or wireless communication mode with corresponding information and export to signal processing module;

Signal processing module, collect heat and discharge the signal that infrared detection alarm module, vibration detection module, video acquisition module and audio collection module transmit, carry out analysis-by-synthesis, differentiate intrusion behavior or guest visiting, send alerting signal or send visitor's photo to the owner that is in to the warning sending module respectively;

The warning sending module adopts the wired or wireless communication mode, is used for receiving alerting signal that signal processing module sends and to sending warning message to householder's mobile phone or cell management center;

Power management module connects external power supply and accumulator, when the external power supply normal power supply, entire product is used external power supply, when extraneous power cut-off, inner standby battery is enabled automatically, guarantees that above-mentioned each module continues operate as normal after external power interruption.

2. a kind of intelligent door and window anti-intrusion system according to claim 1, it is characterized in that: be arranged on the cartridge type light fixture, described heat discharges infrared detection alarm module, vibration detection module, video acquisition module, audio collection module and warning sending module and is integrated on the shell of cartridge type light fixture, and the switch lamp control module of described signal processing module, power management module and cartridge type light fixture itself is installed in the middle part of cartridge type light fixture.

3. a kind of intelligent door and window anti-intrusion system according to claim 1, it is characterized in that: described signal processing module, main process chip adopts main core processor and the double-core architecture mode of being combined from core processor, described main core processor is finished the collection of digital video signal and word sound signal, audio/video coding, collect the signal of heat release infrared detection alarm module output and the signal of vibration detection module output, receive the signal that the broken detection module of glass and door magnetic detection module send, the multi-source signal is sent to from core processor together with audio, video data; Described judgement and the householder's authentication of carrying out intrusion behavior from core processor, wherein invasion should be judgement and mainly comprises operation audio-video intelligent analysis algorithm, judge whether to exist intrusion behavior by video and sound, the signal of the signal of exporting in conjunction with heat release infrared detection alarm module, the signal of vibration detection module output, the broken detection module of glass and the transmission of door magnetic detection module forms final decision signal simultaneously.

4. a kind of intelligent door and window anti-intrusion system according to claim 3, it is characterized in that: described householder's identity judgement comprises recognition of face or at user mobile phone the WIFI communication software is installed, video acquisition module is communicated by letter by WIFI with user mobile phone and is carried out identity validation, and the method for wherein said recognition of face mainly comprises with the lower part:

The front face photo of same individual's different angles is gathered in the registration of people's face, finds the position of people's face in image by people's face location, and standardization people face size, people's face angle and illumination, the feature of extraction standardization facial image, typing registered user database;

Recognition of face, adopt the HAAR feature to realize that in conjunction with the adaboost algorithm people's face detects realization people face location, adopted two-layer human eye steady arm, all be to obtain the human eye location by the adaboost algorithm, utilize people's face positioning result by the image rotation eyes to be proofreaied and correct and be the standardization of level realization people face, carry out feature extraction by two-dimensional Gabor filter, utilize the covariance between vector to mate the tolerance mode apart from conduct, realize the facial image of inquiry and the coupling of database facial image by the arest neighbors classification.

5. a kind of intelligent door and window anti-intrusion system according to claim 1, it is characterized in that: described signal processing module is connected with memory module;

Be connected with external power supply and battery by power management module;

Be connected with the internal memory for the master cpu operation;

Be connected with the flash memory for storage system start-up routine, configuration parameter, log information;

Be connected with by external warning lamp, the warning signal interlocking equipment is realized local sound and light alarm, or controls the interlink warning module of other associate device.

6. a kind of intelligent door and window anti-intrusion system according to claim 1, it is characterized in that: the detection method of described video acquisition module mainly is divided into background modeling and motion detection, goal verification, target following and behavioural analysis four parts, wherein said background modeling and motion detection, be that the mode that has adopted multiple image to be averaging obtains background mean value, the variance of background is initialized as a constant, pass through formula

$f(x,y)=\left\{\begin{array}{cc}1& |f(x,y)-\mathrm{\&mu;}(x,y)|>N\&times;\mathrm{\&sigma;}(x,y)\\ 0& \mathrm{else}\end{array}\right.$

With foreground detection with background pixels and prospect pixel separation, 1 expression prospect pixel wherein, 0 expression background pixels, f (x, y) in the presentation video (x y) locates the gray-scale value of pixel, μ (x, y) the corresponding background mean value of expression, σ (x, the y) variance of the corresponding background of expression,

Described goal verification, by the foreground area of target size wave filter according to cun requirement of the discontented full size of the size filtering of setting, by the highlighted target filter foreground area highlighted according to the setting threshold filtering, foreground area is done gradient difference with corresponding background, by time domain filtering motion continuity, motion conspicuousness and area change continuity are carried out filtering respectively, the tracking of described target, according to present frame and before the location estimation target of target in the position of next frame, pass through formula $v_t^x=\frac{\underset{n=0}{\overset{N-2}{\mathrm{\&Sigma;}}}(x_{t-n}-x_{t-n-1})}{N-1}$ With $v_t^y=\frac{\underset{n=0}{\overset{N-2}{\mathrm{\&Sigma;}}}(y_{t-n}-y_{t-n-1})}{N-1}$ Estimating target speed is realized target prodiction, wherein With

Target is in the speed of x direction and y direction constantly to represent t respectively, and N is time window, x _T-nAnd y _T-nRepresent t-n horizontal ordinate and the ordinate at the extraneous rectangle frame of target center, in like manner x constantly respectively _T-n-1And y _T-n-1Represent t-n-1 horizontal ordinate and the ordinate at the extraneous rectangle frame of target center constantly respectively.

The judgement of alarm region and corresponding rule realization specific behavior is set in described behavioural analysis by the user.

7. a kind of intelligent door and window anti-intrusion system according to claim 1 is characterized in that: the detection method of described audio collection module,

Obtain the power spectrum density of sound signal, the sampling rate of establishing sound signal X (t) is f _s, X (t) is passed through pre-emphasis successively, divide frame and windowing process, before handling, signal at first removes average, adopt the period map method in the Classical Spectrum estimation, use Fast Fourier Transform (FFT) FFT to realize, finally obtain normalized power spectrum X ^(t)(f _n), n ∈ [1, N] wherein, N is sampling number, t represents sampling instant, adopts the sub belt energy ratio A _i ^(t)Describe power spectrum density, utilize formula

Calculate the sub belt energy ratio A _i ^(t)Be defined as the ratio of sub belt energy and gross energy, wherein coboundary and the lower boundary of U (i) and L (i) expression subband i are M subband according to logarithm with frequency band division here;

Based on mixed Gaussian background modeling and the sound detection of sub belt energy ratio, the probability distribution that mixed Gaussian background modeling hypothesis signal changes can be used K Gaussian distribution match, and the probability distribution of sound signal is expressed as

Each Gaussian distribution η in the model _i(x, μ _i, σ _i) all give a weights omega _i, μ wherein _iAnd σ _iAverage and the standard deviation of representing Gaussian distribution respectively, a plurality of Gaussian distribution obtain the probability distribution of signal by linear combination, and with preceding B Gaussian distribution model as a setting, remaining Gaussian distribution is as foreground model, wherein

Current demand signal amplitude and a preceding B Gaussian distribution are mated, and if wherein any one Gaussian distribution the match is successful then this signal is background, otherwise be foreground signal, utilization | I (x, t)-μ _i(x, t-1) |＜c * σ _i(x t-1) mates.

8. a kind of intelligent door and window anti-intrusion system according to claim 1 is characterized in that its anti-intrusion method is as follows:

The first step, collect digital video signal by video acquisition module, collect digital audio and video signals by the audio collection module, discharging the infrared detection alarm module by heat collects the external heat temperature information and changes voltage signal into, collect extraneous vibration by the vibration detection module and produce the information of deformation or stressed transformation and change voltage signal into, collect the broken and door magnetic variation information of glass by the broken detection module of glass and a door magnetic detection module and close and change voltage signal into;

Second step, signal processing module receives the voltage signal that heat discharges infrared detection alarm module, vibration detection module, the broken detection module of glass and door magnetic detection module, and in conjunction with audio-video intelligent analysis, mastership identification checking, the generation of synthetic determination intrusion behavior, when having intrusion behavior, send alerting signal;

In the 3rd step, the warning sending module is received alerting signal, and the receiver, video acquisition module is collected digital video signal and collected digital audio and video signals by the audio collection module simultaneously, and is transferred to external management terminal or handheld terminal by wired or wireless mode.

9. a kind of intelligent door and window anti-intrusion system according to claim 1 is further characterized in that its method that is used as visual entrance guard is as follows:

The first step, collect digital video signal by video acquisition module, collect digital audio and video signals by the audio collection module, discharging the infrared detection alarm module by heat collects the external heat temperature information and changes voltage signal into, collect extraneous vibration by the vibration detection module and produce the information of deformation or stressed transformation and change voltage signal into, collect the broken and door magnetic variation information of glass by the broken detection module of glass and a door magnetic detection module and close and change voltage signal into;

Second step, signal processing module receives the voltage signal that heat discharges infrared detection alarm module, vibration detection module, the broken detection module of glass and door magnetic detection module, and judge whether to be guest visiting in conjunction with audio-video intelligent analysis, if there is the visit generation of behavior of guest, then by wireless mode the visitor is sent to mobile or fixed terminals such as the indoor master cellular phone of being in automatically at outdoors video or photographic intelligence, and activated terminals provides ring, vibrations or voice suggestion.

Images