CN100420304C - Vehicle antitheft device based on omnibearing computer vision - Google Patents

Abstract

The present invention relates to a vehicle burglarproof device based on the omnibearing computer vision, which comprises a microprocessor, an omnibearing visual transducer for monitoring the vehicle internal and external environment, a hanger installed in a vehicle, and a communication module for communicating the outside. The burglarproof judging method is mainly make use of the principle that if the external force acts on the vehicle, the hanger in the vehicle can do motion, and moreover, the factors which can be caused by other reasons and can bring the influence to the correct judgment are removed according to the (Cr and Cb) spatial color characteristic without relating to the brightness and the time-space continuous characteristic in the process of the vehicle intrusion. A user observes the swinging conditions of the swing sustaining time, the swing range and the swing range varying speed of the hanger in the vehicle to judge. Thus, if the swing sustaining time is the longer, the swing range is the larger, and the swing range varying speed is the irregular, the possibility of the vehicle intrusion is the higher. Furthermore, the comprehensive judgment is made according to the appearing conditions of the intrusion objects in the vehicle, etc. The present invention has the advantages of low wrong judgment rate, low using cost, low environmental dependence and high safety.

Description

Anti-theft device for vehicle based on omnidirectional computer vision

(1) technical field

The present invention relates to the application aspect vehicle anti-theft of omnidirectional computer vision sensor technology, image recognition technology, Computer Control Technology and the communication technology, especially a kind of anti-theft device for vehicle based on omnidirectional computer vision.

(2) background technology

Vehicle is a modern transportation instrument conveniently, and along with the raising day by day of the domestic present level of consumption, the vehicle number that has oneself grows proportionately, and particularly some middle-and-high-ranking vehicles are subjected to the conscientious care of car owner, inevitably also can the stolen car thieves pay close attention to.Because vehicle is mobile big, be impossible always and everywhere under car owner (or public security related personnel's) monitoring, widely popular acceptance of method of therefore adopting technological prevention also played tangible effect.But the vehicle anti-theft equipment of China is because technical merit is relatively backward at present, cartheft is found target accurately and is thought car steathily after knowing alarm wood property energy, from destroying anti-theft device to unblanking, and even the automobile that drives away after starting, the at most only time of two or three minutes ...

The definition of " anti-theft alarm system for vehicles " of international standard IEC839-10-1 definition is, and " predetermined being installed on the vehicle will attempt under the state of alert to invade or a kind of system that the behavior of invasion vehicle shows being provided with." its English name (Vehicle security alarm systems) is abbreviated as VSAS.The major function of VSAS can reduce: warning/releasing warning is set; Stop; Survey; Report to the police; Five major functions such as demonstration.Generally, 1. warning/releasing warning promptly is set--with Password Operations and control; 2. stop--prevent to use without approval vehicle motor moving vehicle (at least two kinds independently method for locking); 3. survey--basic is to detect vehicle-surroundings (car door, car bonnet) to be opened, selectable, additional detection is to detect other of vehicle invaded and harassed (using without approval as surveying the object of invading and moving in car, surveying that engine, vehicle window are broken, external force is raised or reduce behaviors such as vehicle, external force moving vehicle) to realize three-dimensional protection, space protection; 4. just realize to survey and report to the police (audible sound, visible light and wireless signal), but can not false alarm, can select emergent alarm as the calling for help means in addition; 5. show--adopt visible the demonstration usually, indicate the information (can utilize car light to show) that different operating state and state change, but show and answer binding hours, and can not have any demonstration to remove the visible indication of password, do not allow to send the sound (disturbing residents) of non-warning to prevent throat sound.

Proposing " software locks stop " (software lock immobilization) about stop Britain insurance standard, is a kind of method for locking of significant under the situation that vehicle mounting microprocessor and computer are popularized day by day.

Vehicle anti-theft at present can be divided into these two kinds of anti-thefts device for vehicle of mechanical safety device and electronics (electromechanics) anti-theft device haply, also has vehicle theft and robbery prevention warning (location, tracking) system of the networking that grows up recent years in addition; Modal as mechanical safety device is that the original-pack lockset of vehicle is (as car door lock, car bonnet lock, firing switch lock) and car owner's various anti-theft locks that can add later on (as pinning the lock of control members such as steering wheel, gear shift lever, pedal), the strick precaution emphasis of these anti-theft locks is to prevent to use engine.Standard GB 15740-1995 of China " alarms and security systems for automobiles performance requirement " and industry standards of public safety GA/T73-1994 " mechanical anti-theft lock " have made basic demand to mechanical safety device.From using, commercially available mechanical anti-theft lock mostly is simple, inexpensive device at present, almost everybody can adorn, everybody uses, to the performance of vehicle itself almost without any influence, but they only can pin the part of vehicle, and because the position obviously and can not report to the police, theftproof performance depends on self intensity and the intensity of the vehicle part that is lockable basically, make that (it is ruthless that the robber sets about to the increase of crime chance, you lock steering wheel, he is out of shape the steering wheel sled with crowbar, even just can take off anti-theft lock with the sawed-off steering wheel of instrument; You lock gear shift lever, and he exerts oneself to break off with the fingers and thumb, do not stint to damage and also want engage a gear to drive); Modal as electronics (electromechanics) anti-theft device is various electronic anti-theft alarms.Present electronic anti-theft alarm is existing simple, have again complicated, based on commercially available multiple car alarm.China is in order to integrate with world level, adopting by equivalent the IEC 839-10-1 of International Electrotechnical Commission standard formulation GA2-1999 " anti-theft alarm system for vehicles minibus " standard, replaced former GA/T2-1991 " car alarm general technical specifications " standard, came into effect in 2000, " anti-theft alarm system for vehicles " progressively replacing " car alarm " at present; Vehicle theft and robbery prevention warning (location, tracking) system as networking, though networked system is also not long in China's developing history, diversified system has also appearred, what have utilizes radio paging system, what have utilizes public wired and wireless communication system, the special radio transmission of the foundation that has is accepted system, and what have utilizes stellar-based global-positioning system (GPS), or the like.No matter but system how, it all must possess network center, car-mounted device two large divisions at least.Network center is each vehicle in the monitoring networking and manages whole network, car-mounted device serve as vehicle strick precaution and and network center keep in touch that (it should be basic identical with the function of above-mentioned anti-theft alarm system for vehicles on take precautions against requiring, and because the needs of networking, it must also have information transmit-receive and Presentation Function).Self-evident, the advantage of network-type system is that " technical precaution " adds " people's air defense ", that is to say, the vehicle in the detection can be whenever and wherever possible by " concern ".In the network area, keeping getting in touch between the vehicle of networking and the network center, vehicle just can access field rescue if alert takes place, and not only rescue mission is timely when having location, following function, can also implement to chase after stifled exactly to vehicle.

Image processing and computer vision are constantly new technologies of development, adopt computer vision to observe four purposes in principle, i.e. the debating of the feature extraction of preliminary treatment, the bottom, mid-level features known and by the explanation of image to senior sight.In general, computer vision comprises principal character, image processing and image understanding.

Image is the extension of human vision.By machine vision, can find the difficult generation of vehicle robber immediately exactly, this is a undisputable fact.The basis of image monitoring rapidity is that the information that vision is accepted is communication media with light; And image information is abundant and directly perceived, is that other various monitoring technology all can not provide so abundant and information intuitively at present.

(3) summary of the invention

In order to overcome existing anti-theft device for vehicle False Rate height, use cost height,, deficiency that fail safe low strong, the invention provides that a kind of False Rate is low, use cost is low, to low, the safe anti-theft device for vehicle of environmental factor dependence based on omnidirectional computer vision to environmental factor dependence.

The technical solution adopted for the present invention to solve the technical problems is:

A kind of anti-theft device for vehicle based on omnidirectional computer vision, this anti-theft device for vehicle comprise microprocessor, are used for the omnibearing vision sensor of monitoring vehicle internal and external environment, are installed on the hanger in the car, are used for and extraneous communication module of communicating by letter;

Described omnibearing vision sensor comprises evagination mirror surface, transparent cylinder, the camera that is used for reflecting monitoring field object, described evagination mirror surface down, described transparent cylinder supports the evagination mirror surface, the dark circles cone is fixed on the center of evagination mirror surface male part, the camera that is used to take imaging body on the evagination mirror surface is positioned at the inside of transparent cylinder, and camera is positioned on the virtual focus of evagination mirror surface;

Described microprocessor comprises:

The view data read module is used to read the video image information of coming from the vision sensor biography;

The image data file memory module, the video image information that is used for reading into is kept at memory cell by file mode;

The transducer calibration module is used for the parameter of omnibearing vision sensor is demarcated, and sets up the linear corresponding relation of material picture with the video image that is obtained in space;

Image launches processing module, and the circular video image that is used for gathering expands into the panorama block diagram;

The motion obj ect detection module, present frame live video image and a relatively stable reference image of being used for being obtained carry out the difference computing, and the computing formula of image subtraction is represented suc as formula (1):

f _d(X，t ₀，t _i)＝f(X，t _i)-f(X，t ₀)(1)

In the following formula, f _d(X, t ₀, t _i) be to photograph the result who carries out image subtraction between image and reference image in real time; F (X, t _i) be to photograph image in real time; F (X, t ₀) be the reference image;

With the image subtraction computing formula of present image and adjacent K frame shown in (2):

f _d(X，t _i-k，t _i)＝f(X，t _i)-f(X，t _i-k)(2)

In the following formula, f _d(X, t _I-k, t _i) be to photograph the result who carries out image subtraction between image and adjacent K two field picture in real time; F (X, t _I-k) image when being adjacent K frame;

As f _d(X, t ₀, t _i) 〉=threshold value, f _d(X, t _I-k, t _iWhen) 〉=threshold value is set up, be judged to be near vehicular events;

As f _d(X, t ₀, t _i) 〉=threshold value, f _d(X, t _I-k, t _i)＜threshold value is judged stationary objects, and upgrades replacement reference image with formula (3):

$f(X,t_0)\⇐f(X,t_{i-k})---\left(3\right)$

As f _d(X, t ₀, t _i)＜threshold value is judged to be nothing near vehicular events;

The color space conversion module is used for the image rgb color space is transformed into yuv space;

The connected region computing module, be used for after judgement has near vehicular events, present image is carried out mark, pixel grey scale is that 0 sub-district represents that this sub-district do not have suspicious intrusion, pixel grey scale is that 1 this sub-district of expression has suspicious intrusion, whether the pixel of calculating in the present image equate with the pixel of some points adjacent around the current pixel, equates to be judged as gray scale to have connectedness, and all are had the pixel of connectedness as a connected region;

People's face color judge module, the human face region of discrepancy place that is used to pick up the car calculate (Cri, value Cbi), and carry out the comparison of color difference components vector with formula (4):

${\mathrm{\ϵ}}_{\mathrm{color}}=\sqrt{{({\mathrm{Cr}}_i-150)}^2-{({\mathrm{Cb}}_i-120)}^2}---\left(4\right)$

If threshold value 1＜ε _Color＜threshold value 2 judges that this region of variation confirms as the someone and invade in the car, otherwise unmanned the intrusion in the car; Definition F _ColorBehaviour face color factor of influence is with threshold value 1＜ε _Color＜threshold value 2 is as the decision condition of this factor;

Hanger is swung the duration judge module, is used to monitor the swing duration of the hanger in the car, definition F _{Pendulum time}Be the duration factor of influence of swing, computing formula is provided by formula (5);

F _{pendulum?time}＝K _time*time

(5)

In the formula (5), K _TimeBe the time scale coefficient, time is the duration of the hanger swing in the car;

Hanger swinging strength judge module is used to monitor the amplitude of fluctuation of the hanger in the car, definition F _{Pendulum Range}Be the amplitude factor of influence of swing, computing formula is provided by formula (6);

F _{pendulum?range}＝K _range*range (6)

In the formula (6), K _RangeBe the amplitude proportional coefficient, range is the amplitude peak value of the hanger swing in the car;

Hanger judge module hunting period is used to monitor the hunting period of the hanger in the car, definition F _{Pendulum Period}Be the cycle factor of influence of swing, computing formula is provided by formula (7);

F _{pendulum?Period}＝K _period (7)

In the formula (7), K _PeriodIt is the cycle of swing and the direction of swing set point when changing;

Invade the object judge module, be used for judging near the vehicular events generation definition F according to motion detection block _InbreakFor invading the object influences factor, its computing formula is provided by formula (8),

F _inbreak＝1+K _inbreak*(times-1)(8)

In the formula (8), K _InbreakBe incident proportionality coefficient in the invasion car, times is the number of times of detected intrusion incident;

The weighted comprehensive judge module is used for according to above five kinds of factors of influence, and comprehensive judgment formula is provided by formula (9), has adopted weighting scheme in the comprehensive judgement:

$W_{\mathrm{guardalann}}=K_{\mathrm{pt}}\×F_{\mathrm{pendulumtime}}+K_{\mathrm{pr}}\×F_{{\mathrm{pendulumrange}}_s}+---\left(9\right)$

$K_{\mathrm{pp}}\×F_{\mathrm{pendulumPeriod}}+K_{\mathrm{co}}\×F_{\mathrm{color}}+K_{\mathrm{ib}}\×F_{\mathrm{inbreak}}$

In the formula:

K _PtWeight coefficient for the duration factor of influence of malaria swing in the car;

K _PrWeight coefficient for the intensity effect factor of malaria swing in the car;

K _PpWeight coefficient for the cycle factor of influence of malaria swing in the car;

K _CoFor invading the weight coefficient of object person face color factor of influence in the car;

K _IbFor being the weight coefficient of invading the object influences factor in the car;

And with unusual quantized value W _{Guard alarm}With preset alarm value K _AlarmRelatively, if W _{Guard alarm}〉=K _Alarm, be judged as suspicious intrusion, send a warning message to the car owner by communication module; Otherwise, be judged as normal.

Further, described warning value K _AlarmComprise suspicious intrusion warning value Kattention, steal difficult early stage warning value Kalarm1, confirm to steal difficult warning value Kalarm2,

If Kattention≤W _{Guard alarm}≤ Kalarm1 has been judged as suspicious intrusion, notifies the car owner to pass through the network validation image by the telex network module, starts image data file memory module record live video data;

If Kalarm1＜W _{Guard alarm}≤ Kalarm2 judges and steals difficult early warning, notifies the car owner to pass through the network validation image by the telex network module, starts image data file memory module record live video data;

If Kalarm2＜W _{Guard alarm}, be judged as and confirm to steal difficult the generation, notify the car owner to pass through the network validation image by the telex network module, and require the scene to confirm, start image data file memory module record live video data; Circular public security organ 110.

Further again, described microprocessor also comprises the background maintenance module, and described background maintenance module comprises:

The background luminance computing unit is used to calculate average background brightness Yb computing formula as the formula (10):

${\stackrel{\‾}{Y}}_b=\frac{\underset{x=0}{\overset{W-1}{\mathrm{\Σ}}}\underset{y=0}{\overset{H-1}{\mathrm{\Σ}}}{Y}_n(x,y)(1-M_n(x,y))}{\underset{x=0}{\overset{W-1}{\mathrm{\Σ}}}\underset{y=0}{\overset{H-1}{\mathrm{\Σ}}}(1-M_n(x,y))}---\left(10\right)$

In the formula (11), Y n (x y) is the brightness of each pixel of present frame, Mn (x y) is the mask table of present frame, and described mask table is to write down each pixel with one with the measure-alike array M of frame of video whether motion change is arranged, referring to formula (11):

Yb0 is the background luminance of former frame when being judged to be the motion object, and Yb1 is the background luminance of first frame when being judged to be the motion object, being changed to of two frame mean flow rates:

ΔY＝Yb1-Yb0(12)

If greater than higher limit, then thinking, Δ Y taken place to turn on light and the irradiation incident; If Δ Y, then thinks the incident of turning off the light that taken place less than certain lower limit; Between higher limit and lower limit, think then that light changes naturally as Δ Y;

The background adaptive unit is used for carrying out adaptive learning according to following formula (13) when light changes naturally:

X _mix，bn+1(i)＝(1-λ)X _mix，bn(i)+λX _mix，cn(i)(13)

In the formula: X _{Mix, cn}(i) be present frame RGB vector, X _{Mix, bn}(i) be present frame background RGB vector, X _{Mix, bn+1}(i) be next frame background forecast RGB vector, λ is the speed of context update; Changeless background (initial background) is used in λ=0; Present frame is used as a setting in λ=1; 0＜λ＜1, background is mixed by the background and the present frame of previous moment;

When light is caused that by switch lamp background pixel is reset according to present frame, referring to formula (14):

X _mix，bn+1(i)＝X _mix，cn(i)(14)。

Further again, described microprocessor also comprises:

Noise is rejected module, is used for the average displacement of each pixel value with all values in its local neighborhood, as shown in Equation (15):

h[i，j]＝(1/M)∑f[k，1](15)

In the following formula (15), M is the pixel sum in the neighborhood.

Further, described image launches processing module, is used for according to a point (x on the circular omnidirectional images ^*, y ^*) and rectangle column panorama sketch on a point (x ^*, y ^*) corresponding relation, set up (x ^*, y ^*) and (x ^*, y ^*) mapping matrix, shown in the formula (16):

P ^**(x ^**，y ^**)←M×P ^*(x ^*，y ^*)(16)

In the following formula, M is a mapping matrix, P ^*(x ^*, y ^*) be the picture element matrix on the circular omnidirectional images, P ^*(x ^*, y ^*) be the picture element matrix on the rectangle column panorama sketch.

Described color space conversion module, the relational expression that is transformed into yuv space from rgb color space is formula (17):

Y＝0.301*R+0.586*G+0.113*B

U＝-0.301*R-0.586*G+0.887*B (17)

V＝0.699*R-0.586*G-0.113*B

In the following formula, Y represents the brightness of YUV color model, and U, V are two chrominance components of YUV color model, the expression aberration; R represents the redness of rgb color space; G represents the green of rgb color space; B represents the blueness of rgb color space.

Described anti-theft device for vehicle also comprises software locks stop controller, be used for producing automatically identification code, and after identification code is confirmed, start or the releasing omnibearing vision sensor, described software locks stop controller is connected with the startup module radio communication of omnibearing vision sensor.

Operation principle of the present invention is: designed anti-theft alarm system for vehicles is after being provided with the function of setting up defences, adopt the computer omnibearing vision sensor to realize comprehensive realtime graphic anti-thefting monitoring to outside in the monitoring vehicle, from captured image, identify human body image, calculate and indicate intrusion or interfere the behavior of vehicle, and can prevent to use without approval vehicle.The captured monitoring image of omnibearing vision sensor is the 3-D view of a solid, before image recognition, at first to carry out the demarcation of image, the definite point that described demarcation will be implemented in the picture frame exactly is mapped to the accurate conversion with any point in big or small space according to coordinate system, Fig. 1 has represented the some mapping relations in certain position, space and picture frame in the computer omnibearing vision sensor, all to demarcate 9 parameters of omnibearing vision sensor according to coordinate system, these parameters have comprised the geographical position, direction, Focus length, non-linear distortion and lens aberration, the central top that omnibearing vision sensor is installed in monitored space just can monitor the situation of all sites in the field of monitoring, and there is not a dead angle, simultaneously point on institute's monitored space becomes mapping relations with point in the picture frame, can calculate the locus, behavior place that vehicle takes place to invade or interfere by this mapping relations, to realize that process monitoring is carried out in the behavior of this intrusion or interference vehicle improves the accuracy rate that vehicle anti-theft is reported to the police.

Omnidirectional computer vision sensing system shown in Figure 1 enters the light at the center of hyperbolic mirror, according to bi-curved minute surface characteristic towards its virtual focus refraction.Material picture reflexes to imaging in the collector lens through hyperbolic mirror, a some P1 (x on this imaging plane ^*1, y ^*1) corresponding the coordinate A of a point spatially in kind (x1, y1, z1).

1-hyperbola face mirror among Fig. 1,2-incident ray, the focus Om (0 of 3-hyperbolic mirror, 0, c), the virtual focus of 4-hyperbolic mirror is camera center O c (0,0 ,-c), the 5-reflection ray, the 6-imaging plane, the space coordinates A of 7-material picture (x1, y1, z1), 8-incides the space coordinates of the image on the hyperboloid minute surface, and 9-is reflected in the some P1 (x on the imaging plane ^*1, y ^*1).

The optical system that hyperbolic mirror shown in Fig. 1 constitutes can be represented by following 5 equatioies;

((X ²+Y ²)/a ²)-(Z ²/b ²)＝-1(Z＞0) (18)

$c=\sqrt{a^2+b^2}---\left(19\right)$

β＝tan ^-1(Y/X) (20)

α＝tan ^-1[(b ²+c ²)sinγ-2bc]/(b ²+c ²)cosγ?(21)

$\mathrm{\&gamma;}={\tan }^{-1}[f/\sqrt{({\mathrm{<figure-callout\; id="2"\; label="X"\; filenames="C20051006238900301.png,C20051006238900311.png"\; state="\{\{state\}\}">X</figure-callout>}}^2+Y^2)}]---\left(22\right)$

X in the formula, Y, Z representation space coordinate, c represents the focus of hyperbolic mirror, and 2c represents two distances between the focus, a, b is respectively the real axis of hyperbolic mirror and the length of the imaginary axis, β represents the angle-azimuth of incident ray on the XY plane, and α represents the angle-angle of depression of incident ray on the XZ plane, and f represents the distance of imaging plane to the virtual focus of hyperbolic mirror.

Correspondence relation according to Three-dimensional monitor space and image pixel detects vicissitudinous those pixel portion, at first will be in the memory of computer reference pictures store, carry out image subtraction between image and reference picture by photographing in real time, the regional luminance that the result who subtracts each other changes strengthens, the brightness that is to say those block of pixels that luminous point exists strengthens, and just can calculate according to the correspondence of the pixel in above-mentioned space geometry relational expression space.

Because omnibearing vision sensor is the middle and upper part of relative fixed in vehicle in the vehicular theft-prevention monitoring, by the intrusion incident of omnibearing vision sensor in can monitoring vehicle, the intrusion incident that while also can may take place by the vehicle monitoring of the glass all around periphery periphery of vehicle is for adopting different processing methods among these two kinds of different incident the present invention; The difficulty that takes place vehicle to steal all can experience and may the intrusion incident arrive the such process of intrusion incident, all has continuity on time and space, steals difficult accuracy by on time and the space judgement of invading incident being helped to improve the judgement vehicle;

The static vehicle of parking after the warning is set to be subjected to external force and to do the time spent and (comprise that vehicle window is broken, external force is raised or reduce behaviors such as vehicle, external force moving vehicle, comprised that also tool using opens car door, car bonnet) all can cause the object that is suspended in the vehicle to produce swing, whether the size of amplitude of fluctuation is relevant with the external force that is subjected to, swing by omnibearing vision sensor observation hanger also to can be used as the difficult foundation that takes place of a kind of judgement vehicle robber.

The design of the swing part of described hanger must be compared sensitivity, when on any direction of car body, being subjected to the external force about 1kg, the swing part of hanger will produce corresponding swing, the color of the swing part of hanger also must be at (Cr simultaneously, Cb) apparent in view feature is arranged on the spatial color, it produces the size and the speed of swing and amplitude of fluctuation so that machine vision can be easy to identification.Hanger and omnibearing vision sensor preferably can be designed to integrated, so just can realize producing in batches.

The static vehicle of parking after the warning is set, in a single day omnibearing vision sensor finds to have the zone of motion change except luminance index at color space in the monitor portion below the vehicle window, while is according to the monitor thread of the monitoring unit branch startup of vehicle window scope, the intrusion incident that just can be judged to be immediately in the vehicle takes place, determination methods mainly is to utilize (Cr, Cb) spatial color is characteristic and the robber difficult continuity characteristic that occurs in space-time on irrelevant with brightness, the irradiation influence of other light can be got rid of; Monitor portion for the vehicle window scope, situation outside the car is with regard to more complicated, may have passing through of pedestrian, also may have passing through of other vehicles, to observe the hanger in the car whether swing is arranged in this case simultaneously, the duration of swing and the size and the amplitude of fluctuation rate of change of amplitude of fluctuation, the duration of swing is long more, amplitude of fluctuation is big more, the amplitude of fluctuation variation is random shows that the possibility that vehicle robber difficulty takes place is high more, in case the monitor portion of vehicle window scope finds that moving target observes the interior hanger of car simultaneously the monitor thread of swing with regard to startup arranged.

Omnibearing vision sensor ODVS (OmniDirectional Vision Sensors) provide a kind of new solution for the panoramic picture that obtains scene in real time.The characteristics of ODVS are looking away (360 degree), can become piece image to the Information Compression in the hemisphere visual field, and the amount of information of piece image is bigger; When obtaining a scene image, the riding position of ODVS in scene is free more; ODVS is without run-home during monitoring environment; Algorithm is simpler during moving object in the detection and tracking monitoring range; Can obtain the realtime graphic of scene.Therefore the fully-directional visual system based on ODVS developed rapidly in recent years, just becoming the key areas in the computer vision research, IEEE held the special seminar (IEEE workshop on Omni-directional vision) of annual omni-directional visual since 2000.Also do not retrieve at present paper and the patent that omnibearing vision sensor is applied to vehicle anti-theft alarm technique field.

Therefore, adopt omnibearing vision sensor ODVS and utilize digital image processing techniques, find rational characteristic criterion, steal difficult some features that take place in conjunction with vehicle, particularly can further improve the vehicle anti-theft fail safe from space and time continuous protection solid, comprehensive and software locks stop equal angles.Solve in the present various anti-theft device for vehicle owing to using multiple sensors, and have obvious social and economic benefit along with all-environment variation causes False Rate height, use cost height, strong, the professional cartheft of environmental factor dependence such as is separated brokenly easily at outstanding shortcoming just becomes the primary study content of vehicle anti-theft technical field.

Beneficial effect of the present invention mainly shows: 1, False Rate is low; 2, use cost is low; 3, low to environmental factor dependence; 4, safe.

(4) description of drawings

Fig. 1 is that three-dimensional space reflexes to omni-directional visual planar imaging schematic diagram;

Fig. 2 is omni-directional visual optical accessories and camera and the schematic diagram that is used;

Fig. 3 is a kind of schematic diagram of the anti-theft alarm system for vehicles based on the omnidirectional computer vision transducer;

Fig. 4 is a kind of module frame chart of the anti-theft alarm system for vehicles based on the omnidirectional computer vision transducer;

Fig. 5 is a connected graph mark schematic diagram;

Fig. 6 is the anti-theft device for vehicle schematic diagram that the omnidirectional computer vision transducer is installed in the car;

Fig. 7 is the hanger schematic diagram that is suspended in the vehicle.

(5) embodiment

Below in conjunction with accompanying drawing the present invention is further described.

With reference to Fig. 1, Fig. 2, Fig. 3, Fig. 4, Fig. 5, Fig. 6, Fig. 7, a kind of anti-theft device for vehicle based on omnidirectional computer vision, this anti-theft device for vehicle comprises microprocessor 15, is used for the omnibearing vision sensor 13 of monitoring vehicle internal and external environment, is installed on the hanger in the car, is used for and extraneous communication module 26 of communicating by letter;

Described omnibearing vision sensor 13 comprises 11 of the evagination mirror surfaces 1 that are used for reflecting monitoring field object, transparent cylinder 10, shooting, described evagination mirror surface 1 down, described transparent cylinder supports the evagination mirror surface, the dark circles cone is fixed on the center of evagination mirror surface male part, the camera that is used to take imaging body on the evagination mirror surface is positioned at the inside of transparent cylinder, and camera is positioned on the virtual focus of evagination mirror surface;

Described microprocessor comprises:

View data read module 16 is used to read the video image information of coming from the video sensor biography;

Image data file memory module 18, the video image information that is used for reading into is kept at memory cell by file mode;

Transducer calibration module 17 is used for the parameter of omnibearing vision sensor is demarcated, and sets up the linear corresponding relation of material picture with the video image that is obtained in space;

Image launches processing module, and the circular video image that is used for gathering expands into the panorama block diagram, is used for according to a point (x on the circular omnidirectional images ^*, y ^*) and rectangle column panorama sketch on a point (x ^*, y ^*) corresponding relation, set up (x ^*, y ^*) and (x ^*, y ^*) mapping matrix, shown in the formula (16):

P ^**(x ^**，y ^**)←M×P ^*(x ^*，y ^*)(16)

In the following formula, M is a mapping matrix, P ^*(x ^*, y ^*) be the picture element matrix on the circular omnidirectional images, P ^*(x ^*, y ^*) be the picture element matrix on the rectangle column panorama sketch;

Motion obj ect detection module 20, present frame live video image and a relatively stable reference image of being used for being obtained carry out the difference computing, and the computing formula of image subtraction is represented suc as formula (1):

f _d(X，t ₀，t _i)＝f(X，t _i)-f(X，t ₀)(1)

In the following formula, f _d(X, t ₀, t _i) be to photograph the result who carries out image subtraction between image and reference image in real time; F (X, t _i) be to photograph image in real time; F (X, t ₀) be the reference image;

And with in the present image with the image subtraction computing formula of adjacent K frame shown in (2):

f _d(X，t _i-k，t _i)＝f(X，t _i)-f(X，t _i-k)(2)

In the following formula, f _d(X, t _I-k, t _i) be to photograph the result who carries out image subtraction between image and adjacent K two field picture in real time; F (X, t _I-k) image when being adjacent K frame;

As f _d(X, t ₀, t _i) 〉=threshold value, f _d(X, t _I-k, t _iWhen) 〉=threshold value is set up, be judged to be near vehicular events;

As f _d(X, t ₀, t _i) 〉=threshold value, f _d(X, t _I-k, t _i)＜threshold value is judged stationary objects, and upgrades replacement reference image with formula (3):

$f(X,t_0)\&DoubleLeftArrow;f(X,t_{i-k})---\left(3\right)$

As f _d(X, t ₀, t _i)＜threshold value is judged to be nothing near vehicular events;

Background maintenance module 19, described background maintenance module comprises:

The background luminance computing unit is used to calculate average background brightness Yb computing formula as the formula (10):

${\stackrel{\&OverBar;}{Y}}_b=\frac{\underset{x=0}{\overset{W-1}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{H-1}{\mathrm{\&Sigma;}}}{Y}_n(x,y)(1-M_n(x,y))}{\underset{x=0}{\overset{W-1}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{H-1}{\mathrm{\&Sigma;}}}(1-M_n(x,y))}---\left(10\right)$

In the formula (11), Yn (x y) is the brightness of each pixel of present frame, Mn (x y) is the mask table of present frame, and described mask table is to write down each pixel with one with the measure-alike array M of frame of video whether motion change is arranged, referring to formula (11):

Yb0 is the background luminance of former frame when being judged to be the motion object, and Yb1 is the background luminance of first frame when being judged to be the motion object, being changed to of two frame mean flow rates:

ΔY＝Yb1-Yb0(12)

If greater than higher limit, then thinking, Δ Y taken place to turn on light and the irradiation incident; If Δ Y, then thinks the incident of turning off the light that taken place less than certain lower limit; Between higher limit and lower limit, think then that light changes naturally as Δ Y;

The background adaptive unit is used for carrying out adaptive learning according to following formula (13) when light changes naturally:

X _mix，bn+1(i)＝(1-λ)X _mix，bn(i)+λX _mix，cn(i)(13)

In the formula: X _{Mix, cn}(i) be present frame RGB vector, X _{Mix, bn}(i) be present frame background RGB vector, X _{Mix, bn+1}(i) be next frame background forecast RGB vector, λ is the speed of context update; Changeless background (initial background) is used in λ=0; Present frame is used as a setting in λ=1; 0＜λ＜1, background is mixed by the background and the present frame of previous moment;

When light is caused that by switch lamp background pixel is reset according to present frame, referring to formula (14):

X _mix，bn+1(i)＝X _mix，cn(i)(14)。

Image pretreatment module 21 comprises noise rejecting module, is used for the average displacement of each pixel value with all values in its local neighborhood, as shown in Equation (15):

h[i，j]＝(1/M)∑f[k，1](15)

In the following formula (15), M is the pixel sum in the neighborhood.

Color space conversion module 22 is used for the image rgb color space is transformed into yuv space, and the relational expression that is transformed into yuv space from rgb color space is formula (17):

Y＝0.301*R+0.586*G+0.113*B

U＝-0.301*R-0.586*G+0.887*B (17)

V＝0.699*R-0.586*G-0.113*B

In the following formula, Y represents the brightness of YUV color model, and U, V are two chrominance components of YUV color model, the expression aberration; R represents the redness of rgb color space; G represents the green of rgb color space; B represents the blueness of rgb color space;

The connected region computing module, be used for after judgement has near vehicular events, present image is carried out mark, pixel grey scale is that 0 sub-district represents that this sub-district do not have suspicious intrusion, pixel grey scale is that 1 this sub-district of expression has suspicious intrusion, whether the pixel of calculating in the present image equate with the pixel of some points adjacent around the current pixel, equates to be judged as gray scale to have connectedness, and all are had the pixel of connectedness as a connected region;

People's face color judge module, the human face region of discrepancy place that is used to pick up the car calculate (Cri, value Cbi), and carry out the comparison of color difference components vector with formula (4):

${\mathrm{\&epsiv;}}_{\mathrm{color}}=\sqrt{{({\mathrm{Cr}}_i-150)}^2-{({\mathrm{Cb}}_i-120)}^2}---\left(4\right)$

If threshold value 1＜ε _Color＜threshold value 2 judges that this region of variation confirms as the someone and invade in the car, otherwise unmanned the intrusion in the car, with F _ColorSet and be people's face color factor of influence;

Hanger is swung the duration judge module, is used to monitor the swing duration of the hanger in the car, definition F _{Pendulum time}Be the duration factor of influence of swing, computing formula is provided by formula (5);

F _{pendulum?time}＝K _time*time

(5)

In the formula (5), K _TimeBe the time scale coefficient, time is the duration of the hanger swing in the car;

Hanger swinging strength judge module is used to monitor the amplitude of fluctuation of the hanger in the car, definition F _{Pendulum Range}Be the amplitude factor of influence of swing, computing formula is provided by formula (6);

F _{pendulum?range}＝K _range*range (6)

In the formula (6), K _RangeBe the amplitude proportional coefficient, range is the amplitude peak value of the hanger swing in the car;

Value;

Hanger judge module hunting period is used to monitor the hunting period of the hanger in the car, definition F _{Pendulum Period}Be the cycle factor of influence of swing, computing formula is provided by formula (7);

F _{pendulum?Period}＝K _period (7)

In the formula (7), K _PeriodIt is the cycle of swing and the direction of swing set point when changing;

Invade the object judge module, be used for judging near the vehicular events generation definition F according to motion detection block _InbreakFor invading the object influences factor, its computing formula is provided by formula (8),

F _inbreak＝1+K _inbreak*(times-1)(8)

In the formula (8), K _InbreakBe incident proportionality coefficient in the invasion car, times is the number of times of detected intrusion incident;

Weighted comprehensive judge module 24 is used for according to above five kinds of factors of influence, and comprehensive judgment formula is provided by formula (9), has adopted weighting scheme in the comprehensive judgement:

$W_{\mathrm{guardalarm}}=K_{\mathrm{pt}}\&times;F_{\mathrm{pendulumtime}}+K_{\mathrm{pr}}\&times;F_{{\mathrm{pendulumrange}}_s}+---\left(9\right)$

$K_{\mathrm{pp}}\&times;F_{\mathrm{pendulumPeriod}}+K_{\mathrm{co}}\&times;F_{\mathrm{color}}+K_{\mathrm{ib}}\&times;F_{\mathrm{inbreak}}$

In the formula:

K _PtWeight coefficient for the duration factor of influence of malaria swing in the car;

K _PrWeight coefficient for the intensity effect factor of malaria swing in the car;

K _PpWeight coefficient for the cycle factor of influence of malaria swing in the car;

K _CoFor invading the weight coefficient of object person face color factor of influence in the car;

K _IbFor being the weight coefficient of invading the object influences factor in the car;

And with unusual quantized value W _{Guard alrm}With preset alarm value K _AlarmRelatively, if W _{Guard alarm}〉=K _Alarm, be judged as suspicious intrusion, send a warning message to the car owner by communication module; Otherwise, be judged as normal.

Described warning value K _AlarmComprise suspicious intrusion warning value Kattention, steal difficult early stage warning value Kalarm1, confirm to steal difficult warning value Kalarm2,

If Kattention≤W _{Guard alarm}≤ Kalarm1 has been judged as suspicious intrusion, notifies the car owner to pass through the network validation image by the telex network module, starts image data file memory module record live video data;

If Kalarm1＜W _{Guard alarm}≤ Kalarm2 judges and steals difficult early warning, notifies the car owner to pass through the network validation image by the telex network module, starts image data file memory module record live video data;

If Kalarm2＜W _{Guard alarm}, be judged as and confirm to steal difficult the generation, notify the car owner to pass through the network validation image by the telex network module, and require the scene to confirm, start image data file memory module record live video data; Circular public security organ 110.

In conjunction with Fig. 1 and with reference to Fig. 2, the structure of the accessory of omni-directional visual function of the present invention by: hyperbola face mirroring parts 1, transparent housing cylinder 10, base 12 are formed, described hyperbola face mirror 1 is positioned at the upper end of cylinder 10, and the convex surface of mirror surface stretches in the cylinder downward; The rotating shaft of described hyperbola face mirror 1, cylinder 10, base 12 is on same central axis; Described digital camera head 11 is positioned at the below of cylinder 10; Have the circular groove identical on the described base 12 with the wall thickness of described cylinder 10; Described base 12 is provided with a hole of a size of the camera lens with digital camera 11, and the bottom of described base 12 disposes embedded hardware and software systems 15.

In conjunction with Fig. 1 and with reference to Fig. 4, digital camera 13 is connected in the microprocessor 15 of anti-theft alarm system for vehicles during comprehensive shooting of the present invention by usb 14, described microprocessor 15 reads in module 16 through view data and reads in view data after pressing the key interval certain hour of setting up defences, in order to obtain the ambient image inside and outside the car, need this image is deposited in the image data storage module 18 so that the image recognition of back and processing, simultaneously in order to discern object in motion and the modified-image, need demarcate 9 basic parameters that obtain the omnidirectional images system to space coordinates and carry out image recognition and processing, handle hereto in the transducer calibration module 17 in the present invention and carry out.

The image recognition of described monitored object and processing, at first to concern according to the correspondence of Three-dimensional monitor space and image pixel there being those pixel portion of existence to detect, therefore will be in the memory of computer reference pictures store, carry out image subtraction between image and reference picture by photographing in real time, the regional luminance that the result who subtracts each other changes strengthens, the brightness that is to say those block of pixels that luminous point exists strengthens, and just can calculate according to the correspondence of the pixel in above-mentioned space geometry relational expression space.Described monitored object comprises the of vehicle own and the environment that vehicle is inside and outside, as shown in Figure 6 by the omnidirectional computer vision transducer being installed in the middle and upper part in the monitoring vehicle, intrusion incident in can monitoring vehicle, the intrusion incident that also can may take place simultaneously by the vehicle monitoring of the glass all around periphery periphery of vehicle;

Background safeguards that be based on background cuts algorithm and detect the key of intrusion incident, its directly influence detect integrality and accuracy of intrusion incident.Adopted the background adaptive method in the background maintenance module 19, its core concept is the current mixed number (X that uses 1 group of vector: RGB to change to each background pixel _{Mix, bi}) represent the permission value (i is a frame number) of legal background pixel, and adopt IIR filtering that it is upgraded.

If as omnibearing vision sensor a weakness being arranged is exactly when a light direct irradiation is arranged under the environment of dark at the emission minute surface, entire emission imaging video image will be subjected to very big interference, may lose the video monitoring effect, therefore in the present invention in order to overcome this weakness, when certain regional luminance is much larger than average background brightness in detecting monitoring camera-shooting, and continued a stipulated time when above, system turns on the illuminating lamp above the omnibearing vision sensor automatically, use formula (14) that the present frame background is reset simultaneously, above-mentioned function is also finished in background maintenance module 19.

Above-mentionedly need to handle several times after to the monitoring picture collection through following modules through omnibearing vision sensor, according to handling process at first is to ask poor shadow figure processing module 20, mainly is to extract for the pixel portion with motion change asking poor shadow figure processing module 20; Image pretreatment module 21 is mainly finished the detection at edge and is asked processing such as connected region in image pretreatment module 21; Color space conversion processing module 22, in color space conversion processing module 22, mainly finish the conversion of in above-mentioned connected region of trying to achieve, carrying out from the RGB color space to the YCrCb color space, so that can judge whether it is that whether hanger has swing in people's face and the car, get ready for invading to detect according to some color characteristics; Invade and detect processing module 23, whether main detection has the generation of intrusion incident in invading detection processing module 23; Vehicle is stolen the difficult comprehensive judge module 24 that takes place, steal the difficult data that every detection index that comprehensive judge module 24 mainly calculated according to above-mentioned module 23 takes place at vehicle and be weighted calculating then, obtain that vehicle is stolen difficult omen, stolen in difficult the generation, the car stealer into the car, the car stealer manages judged results such as moving vehicle.

Carried out in the described image pretreatment module 21 rejecting and calculated this two parts work by image border point and connected region that noise produced; Include noise in the actual image signal, and generally all show as high-frequency signal, therefore in identifying, will reject the image border point that produces by noise.

Connectedness between pixel is to determine a key concept in zone.In two dimensional image, the individual adjacent pixels of m (m＜=8) is arranged around the hypothetical target pixel, if this pixel grey scale equate with the gray scale of some some A in this m pixel, claim this pixel so and put A to have connectedness.Connectedness commonly used has 4 connected sums 8 to be communicated with.4 are communicated with four points in upper and lower, left and right of generally choosing object pixel.8 are communicated with and then choose object pixel all neighbor in two-dimensional space.All are had connective pixel then constituted a connected region as a zone.

Described connected region is calculated and is mainly solved in image processing process, a width of cloth bianry image, and its background and target have gray value 0 and 1 respectively.To such bianry image, carry out mark to target, calculate each clarification of objective to discern, in the design of multiple target real-time tracking system, need a kind of connected component labeling algorithm of saving internal memory fast.We are that 0 sub-district represents that this sub-district do not have suspicious invasion with pixel for the vehicular window notch portion, if there is suspicious invasion 1 this sub-district of expression, what in general vehicle was stolen difficulty is from the suspicious such process of invasion that intrudes into, and can find from the suspicious such process of invasion that intrudes into by video dividing technique.So can adopt connection composition scale notation to carry out the merging of defect area.The connection labeling algorithm can find all the connection compositions in the image, and the institute in the same connection composition is distributed same mark a little.Fig. 5 is for being communicated with the mark schematic diagram.Be the connected region algorithm below,

1) from left to right, scan image from top to bottom;

2) if pixel is 1, then:

If upper point and left side point have a mark, then duplicate this mark.

If have identical mark, duplicate this mark at 2.

If 2 have different marks, then duplicate a little mark and with in two marks input table of equal value as mark of equal value.

Otherwise give the new mark of this picture element distribution and this mark is imported table of equal value.

3) go on foot if need to consider more point then get back to the 2nd.

4) find minimum mark each of equal value concentrating of equivalence table.

5) scan image replaces each mark with the minimum mark in the table of equal value.

The basic processing unit that the connected component labeling algorithm adopts straightway to detect as connected component, at first former bianry image is lined by line scan, whenever scan the straight line section (forming) of current line, then carry out connected component and detect with oneself detected straightway of lastrow by the continuous picture element that is labeled as I.Algorithm utilizes a linear analysis table to write down the connected relation of label, adopts the transitive relation from big to small of label to represent the attaching relation of connected component, and realizes the merger of label with the method for function recurrence simply.

Define orderly label sequence a: L={l ₁, l ₂, l ₃..., l _n, satisfy: l ₁=0 and l _i＜1 and l _i＜l _I+1, i belongs to 1 to n natural number.At first, all elements among the L is changed to 0, then from top to bottom, progressive scanning picture.Exist if detected line segment, then detect the situation of the straightway of lastrow at current line.If lastrow is not attached thereto the straightway that connects, distribute a new label just for the current straightway that scans; If there are 5 to be attached thereto the straightway that connects, then use the label S of straightway with minimum label _MinCome the current straightway of mark, write down the connectedness of this S label simultaneously, be about to this S label and be communicated with mark with minimum label respectively:

Connect(S _i，S _min)

Wherein, i is from 1 to S, and Connect is for being communicated with labeling function, and it is achieved as follows (23):

$\mathrm{Connect}(a,b):\left\{\begin{array}{c}{l}_a=b,\mathrm{if}(l_a=a)\\ \mathrm{Connect}(l_a,b),\mathrm{if}(l_a>b)\\ \mathrm{Connect}(l_a,b),\mathrm{if}(l_a<b)\end{array}\right.---\left(23\right)$

From left to right line by line scan,, finish all line segment marks up to finishing entire image.At last, the whole label series of merger:

l _i＝Merge(i)

Wherein, i is from the 1 label sum n to entire image, and Merge is merger function (24):

$\mathrm{Merge}\left(i\right)=\left\{\begin{array}{c}i,\mathrm{if}(l_i=i)\\ \mathrm{Merge}\left(l_i\right),\mathrm{otherwise}\end{array}\right.$ (24)

At last, marking image is carried out whole scan, by the label after merger marking image again:

pixel(i，j)＝l _pixe(i，j)

In the formula, (i j) is the index value of (i.j) position in the marking image to pixel.

Algorithm to the mark situation of image with reference to Fig. 5.

In color space conversion module 22, only above-mentioned module 21 is calculated resulting connection composition it is carried out the color space conversion processing, can reduce system operation time like this.

Invading to detect whether the main vehicle-surroundings (car door, car bonnet) that detects is opened in the processing module 23, surveying other invades and harasses (as survey the object of invading and moving in car, survey and to use without approval that engine, vehicle window are broken, external force is raised or reduce behaviors such as vehicle, external force moving vehicle), the means that detect mainly are made of 5 indexs, promptly; Invade in object person face color, the car in the cycle of malaria swing, the car in the intensity of malaria swing, the car in the duration of malaria swing, the car in the car and invade object, considered that in addition vehicle difficulty takes place to steal all can experience and may the intrusion incident arrive the such process of intrusion incident, on time and space, all had continuity;

Because omnibearing vision sensor is the middle and upper part of relative fixed in vehicle in the vehicular theft-prevention monitoring, by the intrusion incident of omnibearing vision sensor in can monitoring vehicle, the intrusion incident that while also can may take place by the vehicle monitoring of the glass all around periphery periphery of vehicle is for adopting different processing methods among these two kinds of different incident the present invention; The difficulty that takes place vehicle to steal all can experience and may the intrusion incident arrive the such process of intrusion incident, all has continuity on time and space, steals difficult accuracy by on time and the space judgement of invading incident being helped to improve the judgement vehicle;

The static vehicle of parking after the warning is set to be subjected to external force and to do the time spent and (comprise that vehicle window is broken, external force is raised or reduce behaviors such as vehicle, external force moving vehicle, comprised that also tool using opens car door, car bonnet) all can cause the object that is suspended in the vehicle to produce swing, whether the size of amplitude of fluctuation is relevant with the external force that is subjected to, swing by omnibearing vision sensor observation hanger also to can be used as the difficult foundation that takes place of a kind of judgement vehicle robber.

The design of the swing part of described hanger must be compared sensitivity, as shown in Figure 7, when the external force that is subjected on any direction of car body about 1kg, the swing part of hanger will produce corresponding swing, the color of the swing part of hanger also must be at (Cr simultaneously, Cb) apparent in view feature is arranged on the spatial color, it produces the size and the speed of swing and amplitude of fluctuation so that machine vision can be easy to identification.Hanger and omnibearing vision sensor preferably can be designed to integrated, so just can realize producing in batches.

The static vehicle of parking after the warning is set, in a single day omnibearing vision sensor finds to have the zone of motion change except luminance index at color space in the monitor portion below the vehicle window, while is according to the monitor thread of the monitoring unit branch startup of vehicle window scope, the intrusion incident that just can be judged to be immediately in the vehicle takes place, determination methods mainly is to utilize (Cr, Cb) spatial color is characteristic and the robber difficult continuity characteristic that occurs in space-time on irrelevant with brightness, can get rid of the mistake identification that is produced by the irradiation of other light; Monitor portion for the vehicle window scope, situation outside the car is with regard to more complicated, may have passing through of pedestrian, also may have passing through of other vehicles, to observe the hanger in the car whether swing is arranged in this case simultaneously, the duration of swing and the size and the amplitude of fluctuation rate of change of amplitude of fluctuation, the duration of swing is long more, amplitude of fluctuation is big more, the amplitude of fluctuation variation is random shows that the possibility that vehicle robber difficulty takes place is high more, in case the monitor portion of vehicle window scope finds that moving target observes the interior hanger of car simultaneously the monitor thread of swing with regard to startup arranged.

In order to improve the vehicle anti-theft level, be provided with software locks stop processing module 25 and wireless telecommunications processing module 26 in the present invention;

Described software locks stop is to produce an identification code when initially using the anti-theft alarm system for vehicles of omnidirectional computer vision automatically, this identification code is stored in the memory cell of anti-theft alarm system for vehicles of omnidirectional computer vision, simultaneously this identification code is sent to the controller of anti-theft alarm system for vehicles, automatically it is kept in the memory cell of controller when the controller of anti-theft alarm system for vehicles receives this identification code, the controller of anti-theft alarm system for vehicles and the anti-theft alarm system for vehicles of omnidirectional computer vision adopt communication, can guard against the warning/releasing that is provided with of anti-theft alarm system for vehicles by controller, need verify identification code when removing warning, have only both the consistent engine work that could remove warning and open the feasible permission of software locks vehicle simultaneously of identification code, by controller being provided with of anti-theft alarm system for vehicles guarded against the back on the other hand and do not allow engine work with software locks stop;

Described communication is to realize by the wireless remote control module that adopts 315MHz.The signal of wireless remote control module reads the decoded data of PT2272 by CPU after PT2272 decoding, realize control to vehicle according to different codings then, and described wireless remote control function is realized by following button;

1. " setting " button: sound antitheft setting.Two spring lamps dodge once, and loudspeaker are short to be rung two, points out the efficient in operation of setting up defences, and does not allow engine work with software locks stop.

2. " releasing " button: after the checking identification code is correct, removes acousto-optic and seek car; Remove lamp flicker and antitheft simultaneously.Loudspeaker are short to be rung one, and prompting operation is effective.

3. the button of " seeking car ": acousto-optic is sought car.Loudspeaker pipe, two spring lamp flickers.

4. " startup " button: squelch anti-stealing.Two spring lamps dodge once, and prompting operation is effective.

5. secondary is set up defences: warning system is at the state of setting up defences, and when pressing the removing function key, if the behavior of not getting on the bus within 20 seconds (as opening car door or using the car key ignition operation), system can get back to the state of setting up defences once more.After 20 seconds, automobile enters the state of setting up defences again, and the spring lamp dodges once.

6. flashing light opens the door: when removing anti-theft state, behind the car door opening, stop behind glittering 5 times of the automobile double spring lamp, prompting back vehicle is noted.Automobile double spring lamp dodges 5 times.

7. igniting is reported to the police: under the state of setting up defences, with former car key igniting, can trigger warning, because the software locks stopping function has guaranteed not allow engine work.Loudspeaker pipe, two spring lamp flickers.

8. the driving central controlled lock automatically locks: after car door shuts, step on service brake after the driving, central controlled lock automatically locks.The middle indicator light of locking of controlling is lighted.

Adopt wireless telecommunication system with the communication of car owner's mobile phone, communication modes with low cost at present, dependable performance adopts the GPRS module.GPRS allows the car owner to transmit and receive data under end (anti-theft alarm system for vehicles of omnidirectional computer vision) packet transfer mode at end (mobile phone), and does not need to utilize the Internet resources of circuit switched mode.Thereby provide a kind of efficiently, wireless packet data service cheaply.That be specially adapted to be interrupted, paroxysmal and frequent, a spot of transfer of data also are applicable to big data quantity transmission once in a while.Use the GPRS technology to realize that packet sends and receives, the car owner is always online and charge by flow, and greatly reduces the use cost of anti-theft alarm system for vehicles.

System realizes the transmission of long distance wireless data by this module and car owner's mobile phone.Car owner's mobile phone mainly is to obtain vehicle state information, realizes the long-range theftproof monitoring to vehicle, the W that calculates according to formula (9) _{Guard alarm}The result, can demonstrate the corresponding judgment result on car owner's the mobile phone so that the car owner can in time take measures, the property that protects oneself is avoided loss.

Described microprocessor 15 is embedded systems, and the implementation algorithm among the present invention is realized by Java language.

Whether the invention effect that present embodiment produced is to detect in the vehicle suspended swinging object simultaneously again by the vision-based detection around the outside vehicle to swing, so possesses antitheft effect during the parts of car stealer outside the theft car body (as tire etc.) too.

Present embodiment is by omnibearing computer vision transducer, the network communications technology, image processing techniques and detect in the vehicle means such as suspended swinging object provides anti-theft alarm system for vehicles a kind of reliable and economic quick and precisely, that technical precaution and people's air defense are combined closely.

Claims (7)

1. anti-theft device for vehicle based on omnidirectional computer vision, it is characterized in that: this anti-theft device for vehicle comprises microprocessor, is used for the omnibearing vision sensor of monitoring vehicle internal and external environment, is installed on the hanger in the car, is used for and extraneous communication module of communicating by letter;

Described omnibearing vision sensor comprises evagination mirror surface, transparent cylinder, the camera that is used for reflecting monitoring field object, described evagination mirror surface down, described transparent cylinder supports the evagination mirror surface, the dark circles cone is fixed on the center of evagination mirror surface male part, the camera that is used to take imaging body on the evagination mirror surface is positioned at the inside of transparent cylinder, and camera is positioned on the virtual focus of evagination mirror surface;

Described microprocessor comprises:

The view data read module is used to read the video image information of coming from the vision sensor biography;

The image data file memory module, the video image information that is used for reading into is kept at memory cell by file mode;

The transducer calibration module is used for the parameter of omnibearing vision sensor is demarcated, and sets up the linear corresponding relation of material picture with the video image that is obtained in space;

Image launches processing module, and the circular video image that is used for gathering expands into the panorama block diagram;

The motion obj ect detection module, present frame live video image and a relatively stable reference image of being used for being obtained carry out the difference computing, and the computing formula of image subtraction is represented suc as formula (1):

f _d(X，t ₀，t _i)＝f(X，t _i)-f(X，t ₀)(1)

In the following formula, f _d(X, t ₀, t _i) be to photograph the result who carries out image subtraction between image and reference image in real time; F (X, t _i) be to photograph image in real time; F (X, t ₀) be the reference image;

The image subtraction computing formula of present image and adjacent K frame is shown in (2):

f _d(X，t _i-k，t _i)＝f(X，t _i)-f(X，t _i-k)(2)

In the following formula, f _d(X, t _I-k, t _i) be to photograph the result who carries out image subtraction between image and adjacent K two field picture in real time; F (X, t _I-k) image when being adjacent K frame;

As f _d(X, t ₀, t _i) 〉=threshold value, f _d(X, t _I-k, t _iWhen) 〉=threshold value is set up, be judged to be near vehicular events;

As f _d(X, t ₀, t _i) 〉=threshold value, f _d(X, t _I-k, t _i)＜threshold value is judged stationary objects, and upgrades replacement reference image with formula (3):

$f(X,t_0)\&DoubleLeftArrow;f(X,t_{i-k})---\left(3\right)$

As f _d(X, t ₀, t _i)＜threshold value is judged to be nothing near vehicular events;

The color space conversion module is used for the image rgb color space is transformed into yuv space;

The connected region computing module, be used for after judgement has near vehicular events, present image is carried out mark, pixel grey scale is that 0 sub-district represents that this sub-district do not have suspicious intrusion, pixel grey scale is that 1 this sub-district of expression has suspicious intrusion, whether the pixel of calculating in the present image equate with the pixel of some points adjacent around the current pixel, equates to be judged as gray scale to have connectedness, and all are had the pixel of connectedness as a connected region;

People's face color judge module, the human face region of discrepancy place that is used to pick up the car calculate (Cri, value Cbi), and carry out the comparison of color difference components vector with formula (4):

${\mathrm{\&epsiv;}}_{\mathrm{color}}=\sqrt{{({\mathrm{Cr}}_i-150)}^2-{({\mathrm{Cb}}_i-120)}^2}---\left(4\right)$

If threshold value 1＜ε _Color＜threshold value 2 judges that this region of variation confirms as the someone and invade in the car, otherwise unmanned the intrusion in the car, with F _ColorSet and be people's face color factor of influence;

Hanger is swung the duration judge module, is used to monitor the swing duration of the hanger in the car, definition F _{Pendulum time}Be the duration factor of influence of swing, computing formula is provided by formula (5);

F _{pendulum?time}＝K _time*time (5)

In the formula (5), K _TimeBe the time scale coefficient, time is the duration of the hanger swing in the car;

Hanger swinging strength judge module is used to monitor the amplitude of fluctuation of the hanger in the car, definition F _{Pendulum Range}Be the amplitude factor of influence of swing, computing formula is provided by formula (6);

F _{pendulum?range}＝K _range*range (6)

In the formula (6), K _RangeBe the amplitude proportional coefficient, range is the amplitude peak value of the hanger swing in the car;

Hanger judge module hunting period is used to monitor the hunting period of the hanger in the car, definition F _{Pendulum Period}Be the cycle factor of influence of swing, computing formula is provided by formula (7);

F _{pendulum?Period}＝K _period (7)

In the formula (7), K _PeriodIt is the cycle of swing and the direction of swing set point when changing;

Invade the object judge module, be used for judging near the vehicular events generation definition F according to motion detection block _InbreakFor invading the object influences factor, its computing formula is provided by formula (8),

F _inbreak＝1+K _inbreak*(times-1)(8)

In the formula (8), K _InbreakBe incident proportionality coefficient in the invasion car, times is the number of times of detected intrusion incident;

The weighted comprehensive judge module is used for according to above five kinds of factors of influence, and comprehensive judgment formula is provided by formula (9), has adopted weighting scheme in the comprehensive judgement:

$W_{\mathrm{guard\; alarm}}=K_{\mathrm{pt}}\&times;F_{\mathrm{pendulum\; time}}+K_{\mathrm{pr}}\&times;F_{\mathrm{pendulum}{\mathrm{range}}_s}+---\left(9\right)$

$K_{\mathrm{pp}}\&times;F_{\mathrm{pendulumPeriod}}+K_{\mathrm{co}}\&times;F_{\mathrm{color}}+K_{\mathrm{ib}}\&times;F_{\mathrm{inbreak}}$

In the formula:

K _PtWeight coefficient for the duration factor of influence of malaria swing in the car;

K _PrWeight coefficient for the intensity effect factor of malaria swing in the car;

K _PpWeight coefficient for the cycle factor of influence of malaria swing in the car;

K _CoFor invading the weight coefficient of object person face color factor of influence in the car;

K _IbFor being the weight coefficient of invading the object influences factor in the car;

And with unusual quantized value W _{Guard alarm}With preset alarm value K _AlarmRelatively, if W _{Guard alarm}〉=K _Alarm, be judged as suspicious intrusion, send a warning message to the car owner by communication module; Otherwise, be judged as normal.

2. the anti-theft device for vehicle based on omnidirectional computer vision as claimed in claim 1 is characterized in that: described warning value K _AlarmComprise suspicious intrusion warning value Kattention, steal difficult early stage warning value Kalarm1, confirm to steal difficult warning value Kalarm2,

If Kattention≤W _{Guard alarm}≤ Kalarm1 has been judged as suspicious intrusion, notifies the car owner to pass through the network validation image by the telex network module, starts image data file memory module record live video data;

If Kalarm1＜W _{Guard alarm}≤ Kalarm2 judges and steals difficult early warning, notifies the car owner to pass through the network validation image by the telex network module, starts image data file memory module record live video data;

If Kalarm2＜W _{Guard alarm}, be judged as and confirm to steal difficult the generation, notify the car owner to pass through the network validation image by the telex network module, and require the scene to confirm, start image data file memory module record live video data; Circular public security organ 110.

3. the anti-theft device for vehicle based on omnidirectional computer vision as claimed in claim 1 is characterized in that: described microprocessor also comprises the background maintenance module, and described background maintenance module comprises:

The background luminance computing unit is used to calculate average background brightness Yb computing formula as the formula (10):

${\stackrel{\&OverBar;}{Y}}_b=\frac{\underset{x=0}{\overset{W-1}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{H-1}{\mathrm{\&Sigma;}}}{Y}_n(x,y)(1-M_n(x,y))}{\underset{x=0}{\overset{W-1}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{H-1}{\mathrm{\&Sigma;}}}(1-M_n(x,y))}---\left(10\right)$

In the formula (11), Yn (x y) is the brightness of each pixel of present frame, Mn (x y) is the mask table of present frame, and described mask table is to write down each pixel with one with the measure-alike array M of frame of video whether motion change is arranged, referring to formula (11):

Yb0 is the background luminance of former frame when being judged to be the motion object, and Yb1 is the background luminance of first frame when being judged to be the motion object, being changed to of two frame mean flow rates:

ΔY＝Yb1-Yb0(12)

If greater than higher limit, then thinking, Δ Y taken place to turn on light and the irradiation incident; If Δ Y, then thinks the incident of turning off the light that taken place less than certain lower limit; Between higher limit and lower limit, think then that light changes naturally as Δ Y;

The background adaptive unit is used for carrying out adaptive learning according to following formula (13) when light changes naturally:

X _mix，bn+1(i)＝(1-λ)X _mix，bn(i)+λX _mix，cn(i) (13)

In the formula: X _{Mix, cn}(i) be present frame RGB vector, X _{Mix, bn}(i) be present frame background RGB vector, X _{Mix, bn+1}(i) be next frame background forecast RGB vector, λ is the speed of context update; Changeless background is used, i.e. initial background in λ=0; Present frame is used as a setting in λ=1; 0＜λ＜1, background is mixed by the background and the present frame of previous moment;

When light is caused that by switch lamp background pixel is reset according to present frame, referring to formula (14):

X _mix，bn+1(i)＝X _mix，cn(i) (14)。

4. as the described anti-theft device for vehicle based on omnidirectional computer vision of one of claim 1-3, it is characterized in that: described microprocessor also comprises:

Noise is rejected module, is used for the average displacement of each pixel value with all values in its local neighborhood, as shown in Equation (15):

h[i，j]＝(1/M)∑f[k，1] (15)

In the following formula (15), M is the pixel sum in the neighborhood.

5. the anti-theft device for vehicle based on omnidirectional computer vision as claimed in claim 4 is characterized in that: described image launches processing module, is used for according to a point (x on the circular omnidirectional images ^*, y ^*) and rectangle column panorama sketch on a point (x ^*, y ^*) corresponding relation, set up (x ^*, y ^*) and (x ^*, y ^*) mapping matrix, shown in the formula (16):

P ^**(x ^**，y ^**)←M×P ^*(x ^*，y ^*) (16)

In the following formula, M is a mapping matrix, P ^*(x ^*, y ^*) be the picture element matrix on the circular omnidirectional images, P ^*(x ^*, y ^*) be the picture element matrix on the rectangle column panorama sketch.

6. the anti-theft device for vehicle based on omnidirectional computer vision as claimed in claim 4 is characterized in that: described color space conversion module, and the relational expression that is transformed into yuv space from rgb color space is formula (17):

Y＝0.301*R+0.586*G+0.113*B

U＝-0.301*R-0.586*G+0.887*B (17)

V＝0.699*R-0.586*G-0.113*B

In the following formula, Y represents the brightness of YUV color model, and U, V are two chrominance components of YUV color model, the expression aberration; R represents the redness of rgb color space; G represents the green of rgb color space; B represents the blueness of rgb color space.

7. the anti-theft device for vehicle based on omnidirectional computer vision as claimed in claim 4, it is characterized in that: described anti-theft device for vehicle also comprises software locks stop controller, be used for producing automatically identification code, and after identification code is confirmed, start or the releasing omnibearing vision sensor, described software locks stop controller is connected with the startup module radio communication of omnibearing vision sensor.

Images