CN101051223A - Air conditioner energy saving controller based on omnibearing computer vision - Google Patents

Abstract

An energy-saving control device of air-conditioning based on vision of omnibearing computer is prepared for utilizing an omnibearing vision transducer to obtain overall view video image of indoor, identifying out number of person in room by microprocessor based on identification of indoor omnibearing video image and carrying out duty ration control on outdoor unit of air-conditioning according number of person in room for realizing to supply air according to requirement.

Description

Air conditioner energy saving controller based on omnidirectional computer vision

(1) technical field

The invention belongs to omnidirectional computer vision technology, image recognition technology, Computer Control Technology, the application of air conditioner energy saving technology in the air-conditioning economize on electricity, especially a kind of air conditioner energy saving controller based on omnidirectional computer vision.

(2) background technology

China's intelligent building is considerably less at present, and nearly building more than 90% is non-intelligent building.In non intelligent building, what use in many large-area architecture indoor environment is common temperature controlled large power air-conditioned, and power is generally between 6900W to 12500W.Data shows that the energy of large-size air conditioning more than 70% is to consume from air-conditioner outdoor unit, and present air-conditioning control present situation realizes by setting indoor temperature.The contradiction of electricity shortage when just aggravating peak of power consumption along with the increasing air-conditioning use of growth in the living standard.Because the seasonality of air conditioning electricity, period and explosive, some electric power expert is referred to as " the electrical network killer " who influences safe power supply with it.

Design of air conditioning in the buildings is to consider full load situation, promptly considers the least favorable applying working condition, the comprehensive maximal value that various refrigeration dutys or thermal load mutual superposition form.And in the air-conditioning actual motion, have only working time of 1% in design conditions, 95% above time then was in part load condition, thereby had great energy-saving potential.

Flame Image Process 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 pre-service, the bottom, mid-level features known and by the explanation of image to senior sight.In general, computer vision comprises principal character, Flame Image Process and image understanding.Application in modern architecture is a new content, and people such as So.A.T.P. have delivered three pieces of papers altogether.But used a plurality of camera heads to be installed in the corner at indoor top respectively from the paper content, so that detect the space of whole air-conditioned room.

Come into operation based on the counting machine of the personnel amount of a series of images is commercial abroad, the market share is bigger two systems, ALTAIS and Sentec, the former is the program of a tracking individuals motion and flow of personnel, video camera is vertically mounted on the detection scene of continuous recording flow of personnel, this video camera is connected to the unit of analysis video data, and per hour system construction one width of cloth has the image of the flow of personnel of average density and speed; The latter is personnel's number system, and system adopts the closed-circuit television of standard, and video camera calculates different local pedestrians' quantity.But all there is common shortcoming in these two systems, make mistakes easily in crowded place, reason is to exist the overlapping situation of human body, the situation that will detect simultaneously than interior in a big way personnel needs a plurality of video cameras to work simultaneously, therefore exist the fusion problem of the video data of each video camera, realize very difficulty of real-time operation.

The omnibearing vision sensor ODVS that developed recently gets up (Omni-Directional 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 quantity 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 testing environment; Algorithm is simpler during moving object in the detection and tracking sensing 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 symposial (IEEE workshop on Omni-directional vision) of annual omni-directional visual since 2000.

Chinese invention patent 200610051632.6 discloses a kind of central air-conditioning energy control device based on omnidirectional computer vision, by realizing that central air conditioner system can detect the mobility status of indoor occupant exactly and hold indoor number, realize air feed as required truly, raising is carried out the ability of the speed of response according to load condition, reduces the consumption of additional energy (unmanned, when personnel are rare).

China family air-conditioning had number above 1.2 hundred million in 2006, though having number, China enterprises and institutions air-conditioning do not have correct data, estimate also can to have number, and data shows in the office building and has surpassed the electric energy that family's air-conditioning is consumed with regard to this electric energy that is consumed of air-conditioning according to statistics near family's air-conditioning.By this development trend, add the seasonality, period and explosive of air conditioning electricity, only depend on and build the power house and increase generating capacity and can't solve this contradiction, must solve by policy and technological means.

At present air-conditioning generally all is to adopt the thermostatic control mode, and this temperature control mode is the problem that exists two power consumption aspects at least: 1) no matter what of people no one, number whether indoor have, always air-conditioning moves in range of set temperature; 2) seasonality of air conditioning electricity, periodly and explosive make that the service time of air-conditioning is more concentrated, cause the pressure of electrical network excessively, these phenomenons are particularly outstanding in areas such as city office buildings.So, need a kind of control technology of new air-conditioning can be energy-conservation, peak of power consumption gently again guarantees the safety of electrical network.

(3) summary of the invention

For overcome existing air conditioner energy saving controller rest on a kind of simple temperature controlled water flat on, from to the control of air-conditioning not directly, rapid, uncomfortable, not energy-conservation deficiency, the invention provides and a kind ofly can detect the mobility status of indoor occupant exactly and hold indoor number, can realize air feed as required truly, the ability of the speed of response is carried out in raising according to load condition, reduce the consumption of additional energy (unmanned, when personnel are rare), the air conditioner energy saving controller based on omnidirectional computer vision of good energy-conserving effect.

The present invention for the technical scheme that solves its technical matters employing is:

A kind of air conditioner energy saving controller based on omnidirectional computer vision, comprise the air-conditioning temperature controller, microprocessor and be installed on the vision sensor that indoor center upper portion is used for perception indoor occupant quantity, described air-conditioning temperature controller is provided with first relay, described first relay connects air-conditioner outdoor unit, described vision sensor is connected with microprocessor, described energy-saving controller of air-conditioner also comprises the occupancy controller in order to the control air-conditioner outdoor unit power on/off cycle, described occupancy controller connects second relay, described second relay is connected with first relay, and described second relay is connected with power supply; Described vision sensor is an omnibearing vision sensor, described omnibearing vision sensor comprises in order to the evagination catadioptric minute surface of object in the reflection monitoring field, dark circles cone, transparent cylinder, the camera in order to prevent that anaclasis and light are saturated, described evagination catadioptric minute surface is positioned at the top of transparent cylinder, evagination catadioptric minute surface down, the dark circles cone is fixed on the center of catadioptric minute surface male part, camera faces toward the evagination mirror surface up, and described camera is positioned at the virtual focus position of evagination mirror surface;

Described microprocessor comprises:

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

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

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

The image stretching processing module, the circular video image that is used for gathering expands into the panorama histogram;

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;

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 the motion object;

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 stationary objects;

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

Indoor occupant is counted estimation module, is used to ask the width w of each connected region _iWith height h _i, use formula (33) zoning area attribute ε then _Area ⁱ, S wherein _iArea for certain connected region:

${\mathrm{\ϵ}}_{\mathrm{area}}^i=\frac{S_i}{w_i*h_i}---\left(33\right)$

Then carry out shape attribute ε with formula (34) _Rate ⁱCalculate, i.e. the width w of rectangle _iWith height h _iThe calculating of ratio.

${\mathrm{\ϵ}}_{\mathrm{rate}}^i=\frac{w_i}{h_i}---\left(34\right)$

Use formula (35) to carry out the comprehensive judgement of area and shape attribute, setting regions area effect factor F _sWith shape attribute factor of influence F _Sh:

$\stackrel{\→}{\mathrm{Rec}}=F_s\×({\mathrm{\ϵ}}_{\mathrm{area}}^i-{\mathrm{\ϵ}}_{\mathrm{area}\_s\tan \mathrm{dard}}^i)\stackrel{\→}{i}+F_{\mathrm{sh}}\×({\mathrm{\ϵ}}_{\mathrm{rate}}^i-{\mathrm{\ϵ}}_{\mathrm{rate}\_s\tan \mathrm{dard}}^i)\stackrel{\→}{j}---\left(35\right)$

As Value judges that less than preset threshold this connected region is a human body, and the total number of persons in the Data Analyzing Room;

Required dutycycle ratio setting module, be used to set up the corresponding sequence of personnel amount in architectural environment, room-size, the room and air-conditioning dutycycle, indoor occupant sum according to statistics obtains the air-conditioning dutycycle, and this duty cycle signals is sent to occupancy controller;

Further, the coordinate of undeformed horizontal coordinate that requires the scene object point and corresponding picture point is linear on the described catadioptric minute surface horizontal direction;

d(ρ)＝αρ (1)

ρ is and the distance of the face shape central point of catoptron in the formula (1), and α is the magnification of imaging system,

If the normal that catoptron is ordered at M and the angle of Z axle are γ, the angle of incident ray and Z axle is Φ, and the angle of reflection ray and Z axle is θ, then

$\mathrm{tg}\left(x\right)=\frac{d\left(x\right)-x}{z\left(x\right)-h}---\left(2\right)$

$\mathrm{tg\γ}=\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}---\left(3\right)$

$\mathrm{tg}\left(2\mathrm{\γ}\right)=\frac{2\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}}{1-\frac{d^{2}z\left(x\right)}{{\mathrm{dx}}^2}}---\left(4\right)$

By reflection law

2γ＝φ-θ

∴ $\mathrm{tg}\left(2\mathrm{\γ}\right)=\mathrm{tg}(\mathrm{\φ}-\mathrm{\θ})=\frac{\mathrm{tg\φ}-\mathrm{tg\θ}}{1+\mathrm{tg\φtg\θ}}---\left(6\right)$

Obtain the differential equation (7) by formula (2), (4), (5) and (6)

$\frac{d^{2}z\left(x\right)}{{\mathrm{<figure-callout\; id="2"\; label="dx"\; filenames="A20071006838300351.png,A20071006838300362.png"\; state="\{\{state\}\}">dx</figure-callout>}}^2}+2k\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}-1=0---\left(7\right)$

Formula $k=\frac{z\left(x\right)[z\left(x\right)-h]+x[d\left(x\right)-x]}{z\left(x\right)[d\left(x\right)-x]+x[z\left(x\right)-h]}$ In; (8)

Obtain the differential equation (9) by formula (7)

$\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}+k-\sqrt{{\mathrm{<figure-callout\; id="2"\; label="k"\; filenames="A20071006838300351.png,A20071006838300362.png"\; state="\{\{state\}\}">k</figure-callout>}}^2+1}=0---\left(9\right)$

Obtain formula (10) by formula (1), (5)

$d\left(x\right)=\frac{\mathrm{afx}}{z\left(x\right)}---\left(10\right)$

By formula (8), (9), (10) and starting condition, separate the digital solution that the differential equation can obtain reflecting mirror surface shape.Select suitable camera according to application requirements during the refractive and reflective panorama system design, calibrate Rmin, the focal distance f of lens is determined the distance H o of catoptron from camera, calculates aperture of a mirror Do by (1) formula,

Determining of systematic parameter:

Determine systematic parameter af according to the visual field of using desired short transverse, obtain formula (11), done some simplification here, z (x) ≈ z by formula (1), (2) and (5) ₀, main consideration is smaller with respect to the change in location of minute surface and camera for the height change of minute surface;

$\mathrm{tg\&phi;}=\frac{(\mathrm{af}-z_0)\frac{\mathrm{\&rho;}}{f}}{z_0-h}$

With the inconocenter point largest circumference place in the center of circle as the plane $\mathrm{\&rho;}=R\min \&RightArrow;{\mathrm{\&omega;}}_{\max }=\frac{R_{\min }}{f}$

Corresponding visual field is ф max.Then can obtain formula (12);

$\frac{\mathrm{\&rho;}}{f}=\frac{(z_0-h)\mathrm{tg}{\mathrm{\&phi;}}_{\max }}{{\mathrm{\&omega;}}_{\max }}+z_0---\left(12\right).$

Further again, described image stretching 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 (21):

P ^**(x ^**，y ^**)← M× P ^*(x ^*，y ^*) (21)

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.

Further, 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 (25):

${\stackrel{\&OverBar;}{Y}}_b=\frac{\underset{x=0}{\overset{W-1}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{H-1}{\mathrm{\&Sigma;}}}{Y}_n(x,y)(1-M_n(x,y))}{\underset{x=0}{\overset{W-1}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{H-1}{\mathrm{\&Sigma;}}}(1-M_n(x,y))}---\left(25\right)$

In the formula (25), 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 (27):

Yb0 is the background luminance of former frame when being judged to be the motion object, and Yb1 is when being judged to be the motion object

The background luminance of first frame, being changed to of two frame mean flow rates:

ΔY＝Yb1-Yb0 (26)

If Δ Y, then thinks the incident of turning on light that taken place greater than higher limit; 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 (22) when light changes naturally:

X _mix，bn+1(i)＝(1-λ)X _mix，bn(i)+λX _mix，cn(i) (22)

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 (23):

X _mix，bn+1(i)＝X _min，cn(i) (23)。

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 (16):

h[i，j]＝(1/M)∑f[k，1] (32)

In the following formula (32), M is the pixel sum in the neighborhood.

In the connected region computing module, utilize connected region to calculate its area and center of gravity, the center of gravity of described subject object can obtain by the X of aforementioned calculation resulting connected region area Si and this connected region, the accumulation calculated for pixel values of Y direction, and computing formula is calculated by formula (37):

$X_{\mathrm{cg}\left(i\right)}=\frac{\underset{x,y\&Element;S_i}{\mathrm{\&Sigma;}}x}{S_i};$ $Y_{\mathrm{cg}\left(i\right)}=\frac{\underset{x,y\&Element;S_i}{\mathrm{\&Sigma;}}y}{S_i}---37.$

Described microprocessor also comprises the color space conversion module, is used for the conversion of RGB color space to the YCrCb color space, and its formula (28) provides,

Y＝0.29990*R+0.5870*G+0.1140*B

Cr＝0.5000*R-0.4187*G-0.0813*B+128 (28)。

Cb＝-0.1787*R-0.3313*G+0.5000*B+128

In described required dutycycle ratio setting module, with effective strength and maximum galleryful recently represent indoor thermal load rate of change, convert thereof into nondimensional relative number ratio, as formula (36) expression,

Represent control strategy with formula (37):

PeopleRatio(％)＝sum/Max*100 (37)。

In the formula (36), sum is the number of indoor reality, and Max is maximum open ended occupancy, and Max is according to concrete building environment for use, air-conditioning power and the decision of room number matching relationship, and f (PeopleRatio) is a funtcional relationship.

Described microprocessor also comprises cycle zero-time setting module, is used for setting module and sets supply stop circle and cycle zero-time, carries out supply stop circle control, and the supply stop circle action start time is adopted the random fashion decision.

Principle of work of the present invention is: 1) the employing omnibearing vision sensor obtains the panorama realtime graphic in the air conditioning chamber; 2) adopt means to processing, identification and the understanding of dynamic image to obtain personnel amount and azimuth information in the air conditioning chamber; 3) according to the variation of indoor occupant quantity as input parameter, dynamically update the compressor operating time that off-premises station dutycycle (PWM) ratio is controlled the off-premises station of air-conditioning, thereby realize the purpose of air conditioner energy saving; 4) pass through the zero-time of the dutycycle control of the off-premises station of generation at random, realize staggering peak clipping, alleviate the pressure of electrical network.

Mainly be to have adopted computing machine omnibearing vision sensor (ODVS) to making a video recording in the air conditioning chamber, from captured image, identify the indoor occupant situation then, go directly to control the power on/off of the off-premises station of air-conditioning then according to the result who is identified, make that indoor personnel are more comfortable, air-conditioning system is more energy-conservation.Above-mentioned captured image 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, omnibearing vision sensor is installed in the situation of the central top of the interior space with regard to all sites in the energy sensing chamber, and there is not a dead angle, simultaneously point on the interior space becomes mapping relations with point in the picture frame, can calculate the indoor nobody of having by this mapping relations, how many people are arranged, and these people's position somewhere.

The application is on original air-conditioning and connect the air-conditioning occupancy controller, and the temperature controller of this controller in original air-conditioning participates in the control of air-conditioning.Say that in some sense the thermostatic control of air-conditioning part still plays temperature controlled effect, just the air-conditioning occupancy controller for the empty time period in the off-premises station of air-conditioning be in off working state.Form a kind of functions control relation between the dutycycle of among the application what and air-conditioning occupancy controller of indoor occupant being exported (ratio of off-premises station power on/off), conduction time was long when the people was many, when otherwise the people is few the time of energising short, in the time of nobody even can cut off the power supply of off-premises station fully.

Power on/off control action in the air-conditioning occupancy controller is realized by the Rx1 relay, what control module adopted is embedded system, in embedded system, to finish the detection of video image, embedded system is understood according to detected video image and is obtained indoor personnel's number, determine the output of air-conditioning occupancy controller then according to personnel's number, the power output of embedded system directly drives the control that the Rx1 relay is realized dutycycle.Therefore this patent key issue that will solve in embedded system is: 1) how to obtain indoor on a large scale video information and be processed into indoor personnel's number; 2) how to adopt which kind of control strategy to realize the power on/off of Rx1 relay is controlled by personnel's number; 3) how whole electrical network is separated operating air-conditioning power consumption time ratio on the electrical network more uniformly.Accompanying drawing 5 is on original air-conditioning and the system's control chart after having connect the air-conditioning occupancy controller.

Realize air-conditioning Energy Saving Control is as required needed a unified basis of calculation in order to adapt to different architectural environment.Can obtain personnel's number that indoor maximum holds from table 1 is to use power to become a kind of funtcional relationship with air-conditioning.The control strategy of the air feed as required that for this reason proposes among the present invention does not lose generality, at first with effective strength and maximum galleryful recently represent indoor thermal load rate of change, convert thereof into nondimensional relative number ratio, as formula (36) expression,

Sum is the number of indoor reality in the formula (36), and Max is maximum open ended occupancy, and Max is according to concrete building environment for use, and promptly air-conditioning power in the table 1 and room number matching relationship are set.

Beneficial effect of the present invention mainly shows: 1, detect the mobility status of indoor occupant exactly and hold indoor number, can realize air feed as required truly, raising is carried out the ability of the speed of response according to load condition, reduces the consumption of additional energy (unmanned, when personnel are rare); 2, good energy-conserving effect.

(4) description of drawings

Fig. 1 is the omni-directional visual optical schematic diagram;

Fig. 2 is a kind of hardware configuration schematic diagram of the energy-saving controller of air-conditioner based on omnidirectional computer vision;

Fig. 3 is the perspective projection imaging model synoptic diagram of omnibearing vision device and general perspective imaging model equivalence;

Fig. 4 is the omnibearing vision device undeformed simulation synoptic diagram of epigraph in the horizontal direction;

Fig. 5 is the schematic diagram based on the energy-saving controller of air-conditioner of omnidirectional computer vision;

Fig. 6 is the circuit diagram that the energy-saving controller of air-conditioner based on omnidirectional computer vision is connected with existing air-conditioner controller;

Fig. 7 interrupts the graph of a relation of dutycycle with off-premises station for indoor occupant compares;

Fig. 8 is with the supply stop circle start time mild electrical network peak of power consumption synoptic diagram that on average staggers.

(5) embodiment

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

In conjunction with Fig. 1 and with reference to Fig. 2, the image unit 5 of omnibearing vision sensor is connected in the microprocessor 6 of energy-saving controller of air-conditioner during comprehensive shooting of the present invention by USB interface, described microprocessor 6 reads in module through view data and reads in view data, indoor environment image when initialization when obtaining nobody, need this image is deposited in the image data memory cell 8 so that the image recognition of back and processing, carrying out the identification of indoor occupant number in the described microprocessor 6 handles, determine the energising of air-conditioner outdoor unit then according to the personnel's number that is identified, power-off time, by the parallel delivery outlet gauge tap control circuit 10 of microprocessor 6, ON-OFF control circuit is used to control the first relay Ax1 and the second relay R x1; Realize the air feed as required of air-conditioning; Microprocessor 6 connects display 7 and storage unit 8.

Count critical component in the energy-saving controller of air-conditioner that the omnibearing vision sensor of information is based on omnidirectional computer vision as catching the air-conditioning indoor occupant, the manufacturing technology scheme of the opticator of described omnibearing vision sensor (ODVS), ODVS camera head are mainly constituted by vertically downward catadioptric mirror 1 with towards last camera.It is concrete that to constitute be to be fixed on bottom by cylinder 3 bodies of transparent resin or glass by the image unit 5 that collector lens 4 and CCD (CMOS) constitute, the top of cylinder 3 is fixed with the catadioptric mirror 1 of a downward deep camber, the dark circles cone 2 that between catadioptric mirror and collector lens, has a diameter to diminish gradually, this coniform body 2 is fixed on the middle part of catadioptric mirror 1, the purpose of dark circles cone 2 is to cause light in cylinder inside light reflex saturated and that produce by the cylinder body wall in order to prevent superfluous light from injecting, and cylinder 3 is installed on the support 9.Fig. 1 is the schematic diagram of the optical system of expression omnibearing imaging device of the present invention.

Catadioptric omnidirectional imaging system can be carried out imaging analysis with the pin-hole imaging model, must be but will obtain the perspective panorama picture to the contrary projection of the real scene image of gathering, thereby calculated amount is big, particularly is used in the monitoring multiple goal, must satisfy the requirement of real-time.

Coordinate in order to ensure the horizontal coordinate of object point in the scene that is detected and corresponding picture point is linear promptly undistorted in horizontal scene, omnibearing vision device as personnel's measuring ability is installed in 3 meters left and right sides parts of middle overhead height in the air conditioning chamber, therefore detect personnel's situation in the horizontal direction, when the catadioptric minute surface of design omnibearing vision device, will guarantee in the horizontal direction indeformable.

At first select for use CCD (CMOS) device and imaging len to constitute camera in the design, preresearch estimates system physical dimension on the basis that the camera inner parameter is demarcated is determined the mirror surface shape parameter according to the visual field of short transverse then.

As shown in Figure 1, the projection centre C of camera is the horizontal scene h of distance place above horizontal scene, and the summit of catoptron is above projection centre, apart from projection centre zo place.Be that true origin is set up coordinate system with the camera projection centre among the present invention, the face shape of catoptron is with z (X) function representation.The pixel q of distance images central point ρ has accepted from horizontal scene O point (apart from Z axle d), at the light of mirror M point reflection in as the plane.Horizontal scene is undistorted to require the coordinate of the horizontal coordinate of scene object point and corresponding picture point linear;

d(ρ)＝αρ (1)

ρ is and the distance of the face shape central point of catoptron in the formula (1), and α is the magnification of imaging system.

If the normal that catoptron is ordered at M and the angle of Z axle are γ, the angle of incident ray and Z axle is Φ, and the angle of reflection ray and Z axle is θ.Then

$\mathrm{tg}\left(x\right)=\frac{d\left(x\right)-x}{z\left(x\right)-h}---\left(2\right)$

$\mathrm{tg\&gamma;}=\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}---\left(3\right)$

$\mathrm{tg}\left(2\mathrm{\&gamma;}\right)=\frac{2\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}}{1-\frac{d^{2}z\left(x\right)}{{\mathrm{dx}}^2}}---\left(4\right)$

By reflection law

2γ＝φ-θ

∴ $\mathrm{tg}\left(2\mathrm{\&gamma;}\right)=\mathrm{tg}(\mathrm{\&phi;}-\mathrm{\&theta;})=\frac{\mathrm{tg\&phi;}-\mathrm{tg\&theta;}}{1+\mathrm{tg\&phi;tg\&theta;}}---\left(6\right)$

Obtain the differential equation (7) by formula (2), (4), (5) and (6)

$\frac{d^{2}z\left(x\right)}{{\mathrm{<figure-callout\; id="2"\; label="dx"\; filenames="A20071006838300351.png,A20071006838300362.png"\; state="\{\{state\}\}">dx</figure-callout>}}^2}+2k\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}-1=0---\left(7\right)$

In the formula; $k=\frac{z\left(x\right)[z\left(x\right)-h]+x[d\left(x\right)-x]}{z\left(x\right)[d\left(x\right)-x]+x[z\left(x\right)-h]}---\left(8\right)$

Obtain the differential equation (9) by formula (7)

$\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}+k-\sqrt{{\mathrm{<figure-callout\; id="2"\; label="k"\; filenames="A20071006838300351.png,A20071006838300362.png"\; state="\{\{state\}\}">k</figure-callout>}}^2+1}=0---\left(9\right)$

Obtain formula (10) by formula (1), (5)

$d\left(x\right)=\frac{\mathrm{afx}}{z\left(x\right)}---\left(10\right)$

By formula (8), (9), (10) and starting condition, separate the digital solution that the differential equation can obtain reflecting mirror surface shape.The main digital reflex mirror of system's physical dimension is from the distance H o and the aperture of a mirror D of camera.Select suitable camera according to application requirements during the refractive and reflective panorama system design, calibrate Rmin, the focal distance f of lens is determined the distance H o of catoptron from camera, calculates aperture of a mirror Do by (1) formula.

Determining of systematic parameter:

Determine systematic parameter af according to the visual field of using desired short transverse.Obtain formula (11) by formula (1), (2) and (5), done some simplification here, with z (x) ≈ z ₀, main consideration is smaller with respect to the change in location of minute surface and camera for the height change of minute surface;

$\mathrm{tg\&phi;}=\frac{(\mathrm{af}-z_0)\frac{\mathrm{\&rho;}}{f}}{z_0-h}---\left(11\right)$

With the inconocenter point largest circumference place in the center of circle as the plane $\mathrm{\&rho;}=R\min \&RightArrow;{\mathrm{\&omega;}}_{\max }=\frac{R_{\min }}{f}$ Corresponding visual field is ф max.Then can obtain formula (12);

$\frac{\mathrm{\&rho;}}{f}=\frac{(z_0-h)\mathrm{tg}{\mathrm{\&phi;}}_{\max }}{{\mathrm{\&omega;}}_{\max }}+z_0---\left(12\right)$

The imaging simulation adopts the direction opposite with actual light to carry out.If light source is in the camera projection centre, equally spaced selected pixels point in the picture plane by the light of these pixels, intersects with surface level after mirror reflects, if intersection point is equally spaced, illustrates that then catoptron has the distortionless character of horizontal scene.The imaging simulation can be estimated the imaging character of catoptron on the one hand, can calculate aperture of a mirror and thickness exactly on the other hand.

Further specify the present invention and in implementation process, relate to Several Key Problems such as demarcation and Target Recognition:

(1) how to demarcate the pixel distance in the imaging plane of omnibearing vision sensor and the corresponding relation of actual three dimensions distance, and on this basis, moving image is classified.Because omni-directional visual video camera imaging plane is two-dimentional, is measurement unit with the pixel, for the ease of personnel's tracking, the correct classification of moving target is necessary fully.

(2) how to carry out target following, tracking is equivalent in the corresponding matching problem of continuous images interframe establishment based on features relevant such as shape, colors, attribute information with personage in the activity among the present invention combines, and a kind of effective, robustness method for tracking target high, that real-time is good is provided.This tracking be actually based on model, based on active contour and based on color characteristic etc. tracking a kind of comprehensive.

The demarcation of omni-directional visual camera field of view distance relates to the theory of imaging geometry, and the three-dimensional scenic of objective world is projected the two-dimentional image plane of video camera, need set up the model of video camera and describe.These image transformations relate to the conversion between the different coordinates.In the imaging system of video camera, what relate to has following 4 coordinate systems; (1) real-world coordinates is XYZ; (2) with the video camera be the coordinate system x^y^z^ that formulate at the center; (3) photo coordinate system, formed photo coordinate system x in video camera ^*y ^*o ^*(4) computer picture coordinate system, the coordinate system MN that the computer-internal digital picture is used is a unit with the pixel.

According to the different transformational relation of above several coordinate systems, just can obtain needed omnidirectional vision camera imaging model, converse the corresponding relation of two dimensional image to three-dimensional scenic.The approximate perspective imaging analytical approach that adopts catadioptric omnibearing imaging system among the present invention is with the formed corresponding relation that is converted to three-dimensional scenic as the planimetric coordinates two dimensional image in the video camera, Fig. 3 is general perspective imaging model, d is people's height, ρ is the image height of human body, t is the distance of human body, and F is the image distance (equivalent focal length) of human body.Can obtain formula (13)

$d=\frac{t}{F}\mathrm{\&rho;}---\left(13\right)$

When the design of the catadioptric omnibearing imaging system that above-mentioned horizontal scene does not have, require the coordinate of the horizontal coordinate of scene object point and corresponding picture point linear, represent suc as formula (1); Comparison expression (13), (1), horizontal as can be seen scene does not have the be imaged as perspective imaging of the catadioptric omnibearing imaging system of distortion to horizontal scene.Therefore with regard to horizontal scene imaging, the catadioptric omnibearing imaging system that horizontal scene can not had distortion is considered as having an X-rayed camera, and α is the magnification of imaging system.If the projection centre of this virtual perspective camera is C point (seeing accompanying drawing 3), its equivalent focal length is F.Comparison expression (13), (1) formula can obtain formula (14);

$\mathrm{\&alpha;}=\frac{t}{F};t=h---\left(14\right)$

Obtain formula (15) by formula (12), (14)

$F=\frac{\mathrm{fh}{\mathrm{\&omega;}}_{\max }}{(z_0-h)\mathrm{tg}{\mathrm{\&phi;}}_{\max }+{\mathrm{<figure-callout\; id="0"\; label="z"\; filenames="A20071006838300361.png"\; state="\{\{state\}\}">z</figure-callout>}}_0{\mathrm{\&omega;}}_{\max 0}}---\left(15\right)$

Carry out the system imaging simulation according to above-mentioned omnidirectional vision camera imaging model, by the camera projection centre send through in the pixel planes equidistantly after the reflection of the light family of pixel, intersection point on the surface level of distance projection centre 3m is equally spaced basically, as shown in Figure 4.Therefore according in the above-mentioned design concept this patent relation between the coordinate of the coordinate of level ground and corresponding comprehensive picture point being reduced to linear relationship, that is to say that design by mirror surface be XYZ to the conversion of photo coordinate system with real-world coordinates can be the linear dependence of ratio with magnification α.Be conversion below from photo coordinate system to the used coordinate system of computer-internal digital picture, the image coordinate unit that uses in the computing machine is the number of discrete pixel in the storer, so also need round the imaging plane that conversion just can be mapped to computing machine to reality as the coordinate on plane, its conversion expression formula is for to be provided by formula (16);

$M=O_m-\frac{x^{*}}{S_x};N=O_n-\frac{y^{*}}{S_y};---\left(16\right)$

In the formula:: Om, On are respectively the line number and the columns at the some pixel place that the initial point of image plane shone upon on the computer picture plane; Sx, Sy are respectively scale factor in the x and y direction.Determining of Sx, Sy is by placing scaling board apart from the Z place between camera and mirror surface, video camera is demarcated the numerical value that obtains Sx, Sy, and unit is (pixel); Om, On.Determine it is that unit is (pixel) according to selected camera resolution pixel.

Further, 360 ° of comprehensive principles of making a video recording are described, a some A on the space (x1, y1, z1) through catadioptric 1 direct reflection to the lens 4 to a subpoint P1 (x should be arranged ^*1, y ^*1), the light of scioptics 4 becomes directional light and projects CCD image unit 5, and microprocessor 6 reads in this ring-type image by video interface, adopts software that this ring-type image is launched to obtain omnibearing image.

Further, on method of deploying, adopted a kind of algorithm of approximate expansion fast in this patent, can drop to minimum, kept Useful Information simultaneously as much as possible with time loss with to the requirement of various parameters.Launching rule has three,

(1) X ^*Axle is a reference position, launches by counterclockwise mode;

(2) X among the left figure ^*Axle and the intersection point O of internal diameter r correspond to the initial point O (0,0) in the lower left corner among the right figure;

(3) width of the right figure after the expansion equals the girth of the circle shown in the dotted line among the left figure.Wherein broken circle is the concentric circles of external diameter in the left figure, and its radius r 1=(r+R)/2.

If the center of circle O of circular diagram ^*Coordinate (x ^*0, y ^*0), the histogram lower left corner origin O of expansion ^*(0,0), any 1 P in the histogram ^*=(x ^*, y ^*) pairing coordinate in circular diagram is (x ^*, y ^*). it is following that we need ask is (x ^*, y ^*) and (x ^*, y ^*) corresponding relation.Can obtain following formula according to geometric relationship:

β＝tan ^-1(y ^*/x ^*) (17)

r1＝(r+R)/2 (18)

Make the radius r 1=(r+R)/2 of broken circle, purpose is in order to allow the figure after launching seem that deformation is even.

x ^*＝y ^*/(tan(2x ^**/(R+r))) (19)

y ^*＝(y ^**+r)cosβ (20)

Can obtain a point (x on the circular omnidirectional images from formula (19), (20) ^*, y ^*) and the rectangle panorama sketch on a point (x ^*, y ^*) corresponding relation.This method has come down to do the process of an image interpolation.After the expansion, the image of dotted line top is that horizontal compression is crossed, and the image of dotted line below is that cross directional stretch is crossed, dotted line originally on one's body point then remain unchanged.

The calculating needs equally can be according to a point (x on the circular omnidirectional images in real time in order to satisfy ^*, y ^*) and the rectangle panorama sketch on a point (x ^*, y ^*) corresponding relation, set up (x ^*, y ^*) and (x ^*, y ^*) mapping matrix.Because this one-to-one relationship can be being transformed into indeformable panoramic picture by the mapping matrix method.Can set up formula (21) relation by the M mapping matrix.

P ^**(x ^**，y ^**)← M× P ^*(x ^*，y ^*) (21)

According to formula (21), for each the pixel P on the imaging plane ^*(x ^*, y ^*) a some P arranged on omnidirectional images ^*(x ^*, y ^*) correspondence, set up the M mapping matrix after, the task that realtime graphic is handled can obtain simplifying.

As a kind of energy-saving controller of air-conditioner based on omnidirectional computer vision after obtaining comprehensive video information, next must carry out background elimination, target extraction, target following, etc. image debate to know and handle evaluation work, this evaluation work is debated to know in the processing module at image and is carried out.

It is the problem that brightness changes that described background is eliminated the problem that at first will solve, operate the sudden change of the intensity of illumination that is caused as the detection meeting of flowing for indoor occupant owing to turning on light, turning off the light, therefore the background model that adopts in background is eliminated will adapt to these above-mentioned variations.

For Video Detection, because the comprehensive scene visual field is bigger, human body shared ratio in entire image is less, so personage's motion can be regarded approximate rigid motion as; In addition, the scene of Video Detection is fixed, and can think to have the relatively background of fixed range, and the Fast Segmentation Algorithm that therefore can adopt background to cut algorithm is come motion personage or the object in the real-time detection and tracking Video Detection; Background is eliminated and to be based on background and to cut algorithm and detect the key of motion object, its directly influence detect integrality and accuracy of motion object.Adopted the background adaptive method among the present invention, its core concept is that each background pixel is used 1 group of vector; (Xmix bi) represents the permission value (i is a frame number) of legal background pixel, and adopts IIR filtering that it is carried out following renewal the current mixed number that RGB changes.

(1) change (not being that switch lamp causes) naturally when light, and no abnormal object is when existing, 1 group of vector (being respectively RGB) carries out adaptive learning:

X _mix，bn+1(i)＝(1-λ)X _mix，bn(i)+λX _mix，cn(i) (22)

In the formula: X _{Min, cn}(i) be present frame RGB vector, X _{Min, bn}(i) be present frame background RGB vector, X _{Min, bn+1}(i) be next frame background forecast RGB vector, λ is the speed of context update: λ=0, uses changeless background (initial background); 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 having sudden change, light (causes) that (2) 1 group of vector is pressed present frame and reset by switch lamp:

X _min，bn+1(i)＝X _mix，cn(i) (23)

(3) when object enters sensing range, background remains unchanged.For avoiding that the partial pixel study of motion object is background pixel, adopt:

X _min，bn+1(i)＝X _mix，bn(i) (24)

X in the following formula _{Mix, bn+1}(i) (i=1,2,3) represent R respectively, G, and B3 component, for simplicity, above-mentioned formula has omitted coordinate (x, y) part of each pixel.

Can be used to judge what whether detected motion object caused because of switch lamp for the variation of background luminance, the variation of these background luminances such as switch lamp incident should not make system be judged as a large amount of personnel to exist causedly, thereby carry out the false recognition rate that the background luminance analysis helps to reduce system.Background luminance uses average background brightness Yb to measure, and computing formula is provided by formula (25),

${\stackrel{\&OverBar;}{Y}}_b=\frac{\underset{x=0}{\overset{W-1}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{H-1}{\mathrm{\&Sigma;}}}{Y}_n(x,y)(1-M_n(x,y))}{\underset{x=0}{\overset{W-1}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{H-1}{\mathrm{\&Sigma;}}}(1-M_n(x,y))}---\left(25\right)$

In the formula (25), (x y) is the brightness of each pixel of present frame to Yn, and (x y) is the mask table of present frame to Mn.The background luminance of former frame when representing to find the motion object is arranged with Yb0, the background luminance of first frame when Yb1 represents to detect the motion object, being changed to of two frame mean flow rates:

ΔY＝Yb1-Yb0 (26)

If Δ Y is greater than certain value then think the incident of turning on light that taken place, if Δ Y is less than certain negative value then think the incident of turning off the light that taken place.Present frame is reset with formula (23) according to above-mentioned judged result.

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, and this array is called mask mapping table (Mask Map):

Array M is the bianry image of motion object, is partitioned into the motion object thereby not only can be used to the mask frame of video, also can be used for tracking, analysis and the classification of motion object.

Background luminance in the formula (25) is being converted to from the RGB color space to the YCrCb color space, and its formula (28) provides,

Y＝0.29990*R+0.5870*G+0.1140*B (28)

Cr＝0.5000*R-0.4187*G-0.0813*B+128

Cb＝-0.1787*R-0.3313*G+0.5000*B+128

Described target extraction cuts algorithm by background and obtains the foreground target object, and described background cuts algorithm and is also referred to as difference method, is a kind of image processing method that is usually used in detected image variation and moving object. detects those pixel portion that have light source point to exist according to the correspondence relation of three dimensions and image pixel; A more stable reference image at first will be arranged; And this reference image is stored in the memory of computer; And by above-mentioned Adaptive background subtraction method the reference image is dynamically updated; Carry out image subtraction by photographing in real time between image and this reference image; The regional luminance that the result who subtracts each other changes strengthens; The computing formula of image subtraction represents suc as formula (29)

f _d(X，t ₀，t _i)＝f(X，t _i)-f(X，t ₀) (29)

F in the formula _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, be equivalent to the X in the formula (22) _{Mix, cn}(i); F (X, t ₀) be the reference image, be equivalent to the X in the formula (22) _{Mix, bn}(i).

Because the omnibearing vision sensor in the Video Detection is all fixed, and the stationary objects in the background may be moved sometimes, cut algorithm based on background and to detect the resulting motion pixel of motion object and may comprise object and move the hole that stays.Because the hole can not moved in frame of video subsequently, therefore available adjacent K frame difference method is eliminated the hole, adopts adjacent K frame difference method to judge whether certain pixel is the hole that background object stays among the present invention.Need to carry out the calculating of formula (30) for this reason,

f _d(X，t _i-k，t _i)＝f(X，t _i)-f(X，t _i-k) (30)

Moving in the unit that generally can consider to divide in the time of stationary objects worked as f _d(X, t ₀, t _i) 〉=threshold value and f _d(X, t _I-k, t _iWhen) 〉=threshold value is all set up, be considered to the motion object; If f _d(X, t ₀, t _i) 〉=threshold value and f _d(X, t _I-k, t _i)＜threshold value thinks among the present invention that the stationary objects in the background is moved the hole that the back is produced, and upgrades replacement reference image in order to eliminate the hole with formula (31),

$f(X,t_0)\&DoubleLeftArrow;f(X,t_{i-k})---\left(31\right)$

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.

Described rejecting is by image border point that noise produced, use the method for neighbours territory traversal in the present invention, the value that the average gray value of the neighborhood interior pixel that it is determined with the filtering mask removes each pixel of alternate image, be of the average displacement of each pixel value with all values in its local neighborhood, shown in formula (32):

h[i，j]＝(1/M)∑f[k，1] (32)

In the formula, M is the pixel sum in the neighborhood, is taken as 4 among the present invention.

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- scale 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 goal 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 monitored object with pixel, if there is monitored object 1 this sub-district of expression.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.

Described target following needs the interframe to cut apart and determined property realizes, described interframe is cut apart major issue: (1) utilizes the segmentation result of previous frame to instruct cutting apart of present frame as far as possible, thereby raise the efficiency, (2) realize the corresponding relation of same moving object in different frame.Therefore, algorithm must safeguard that a storage system preserves the segmentation result of previous frame and the present parameters of target motion.

The foreground target object that splits can exist various interference or other objects except human body.In the present invention, adopt region area attribute and the comprehensive of shape attribute to judge whether foreground target is human body.

In order to improve processing capability in real time, manikin is simplified rectangular model, ask (length of horizontal direction) width w of each connected region _i(length of vertical direction) height h _i, use formula (33) zoning area attribute ε then _Area ⁱ, S wherein _iBe certain connected region number of pixels.

${\mathrm{\&epsiv;}}_{\mathrm{area}}^i=\frac{S_i}{w_i*h_i}---\left(33\right)$

Then carry out shape attribute ε with formula (34) _Rate ⁱCalculate, i.e. the width w of rectangle _iWith height h _iThe calculating of ratio.

${\mathrm{\&epsiv;}}_{\mathrm{rate}}^i=\frac{w_i}{h_i}---\left(34\right)$

At last, use formula (35) to carry out the comprehensive judgement of area and shape attribute.Region area factor of influence F _sBe set at 1, shape attribute factor of influence F _ShBe set at 1.Region area factor of influence and shape attribute factor of influence can increase the factor that plays deciding factor the weight of its judgement according to concrete environment set.

$\stackrel{\&RightArrow;}{\mathrm{Rec}}=F_s\&times;({\mathrm{\&epsiv;}}_{\mathrm{area}}^i-{\mathrm{\&epsiv;}}_{\mathrm{area}\_s\tan \mathrm{dard}}^i)\stackrel{\&RightArrow;}{i}+F_{\mathrm{sh}}\&times;({\mathrm{\&epsiv;}}_{\mathrm{rate}}^i-{\mathrm{\&epsiv;}}_{\mathrm{rate}\_s\tan \mathrm{dard}}^i)\stackrel{\&RightArrow;}{j}---\left(35\right)$

To calculate ε _Area ⁱAnd ε _Rate ⁱCarry out the two-dimensional coordinate projection, obtain vector $F_s\&times;{\mathrm{\&epsiv;}}_{\mathrm{area}}^i\stackrel{\&RightArrow;}{i}+F_{\mathrm{sh}}\&times;{\mathrm{\&epsiv;}}_{\mathrm{rate}}^i\stackrel{\&RightArrow;}{j},$ With itself and normal vector $F_s\&times;{\mathrm{\&epsiv;}}_{\mathrm{area}\_s\tan \mathrm{dard}}^i\stackrel{\&RightArrow;}{i}+F_{\mathrm{sh}}\&times;{\mathrm{\&epsiv;}}_{\mathrm{rate}\_s\tan \mathrm{dard}}^i\stackrel{\&RightArrow;}{j}$ Compare.Utilize formula (35) to calculate

Comprehensive estimate value, wherein ε ⁱ _{Area_stan dard}Be the area standard value of corresponding region radius, ε ⁱ _{Rate_stan dard}It is the shape attribute standard value of corresponding region radius.ε ⁱ _{Area_stan dard}And ε ⁱ _{Rate_stan dard}The setting of standard value is to set again according to concrete environment.And

Be worth more for a short time, then connected region is similar to human body more.

The implementation method of the controller of this patent is on original air-conditioning and has connect the air-conditioning occupancy controller that as shown in Figure 5, the temperature controller of this controller in original air-conditioning participates in the control of air-conditioning.Say that in some sense the thermostatic control of air-conditioning part still plays temperature controlled effect, just the air-conditioning occupancy controller for the empty time period in the off-premises station of air-conditioning be in off working state.Form a kind of functions control relation between the dutycycle of in this patent what and air-conditioning occupancy controller of indoor occupant being exported (ratio of off-premises station power on/off), conduction time was long when the people was many, when otherwise the people is few the time of energising short, in the time of nobody even can cut off the power supply of off-premises station fully.

Described functions control relation, as shown in Figure 7, input quantity is nondimensional relative number, output quantity is the ratio of dutycycle, horizontal ordinate is occupancy (%) people Ratio that compares among Fig. 7, and ordinate is dutycycle (%) PWM, wherein above dotted line be the maximum dutycycle of controlling, following dotted line is minimum control dutycycle, and the left and right sides is threshold value 1 and threshold value 2.

Power on/off control action in the air-conditioning occupancy controller is realized by the Rx1 relay, as shown in Figure 6, number detects and what adopt according to the dutycycle control module of personnel's number is embedded system, in embedded system, to finish the detection of video image, embedded system is understood according to detected video image and is obtained indoor personnel's number, determine the output of air-conditioning occupancy controller then according to personnel's number, the power output of embedded system directly drives the control that the Rx1 relay is realized dutycycle.Therefore this patent key issue that will solve in embedded system is: 1) how to obtain indoor on a large scale video information and be processed into indoor personnel's number; 2) how to adopt which kind of control strategy to realize the power on/off of Rx1 relay is controlled by personnel's number; 3) how whole electrical network is separated operating air-conditioning power consumption time ratio on the electrical network more uniformly.Accompanying drawing 6 is on original air-conditioning and the system's control chart after having connect the air-conditioning occupancy controller, from Fig. 6, number is detected and be connected in series with the Ax1 relay that the temperature controller in the former air-conditioning is controlled according to the Rx1 relay that the dutycycle control module of personnel's number is controlled, only under all closed state of Rx1 relay and Ax1 relay, power supply is just powered to air-conditioner outdoor unit; In other words, the Ax1 relay that Rx1 relay that number detects and controlled according to the dutycycle control module of personnel's number and the temperature controller in the former air-conditioning are controlled all participates in the control of air-conditioner outdoor unit, even the Ax1 that the temperature controller in the former air-conditioning is controlled is in closure state, whether air-conditioner outdoor unit switches on also depends on the Rx1 relay of being controlled according to the dutycycle control module of personnel's number.Therefore a control strategy problem is arranged.

Table 1 is the match map of air-conditioning power and room area and indoor occupant number.From table 1, can draw, the different architectural environments and the size in room, the pairing suitable number of air-conditioning power is inconsistent.The strategy of air feed is the number according to indoor detection as required, dynamically updates the control method of dutycycle ratio, and what promptly need with regard to what intelligent power saving control method of air feed.

An air-conditioning number ()	Air-conditioning power (W)	Office		The shop		The restaurant
								Area (m 2)	Maximum number (people)	Area (m 2)	Maximum number (people)	Area (m 2)	Maximum number (people)
		3	7500	40～60	13～20	32～45	16～23							25～35	14～23
5	12000							60～80	20～27	50～70	25～35	30～45	20～30
		10	25000	80～ 100	20～33	75～95	37～47							45～60	30～40

Table 1 air-conditioning power and room number match map

Realize air-conditioning Energy Saving Control is as required needed a unified basis of calculation in order to adapt to different architectural environment.Can obtain personnel's number that indoor maximum holds from table 1 is to use power to become a kind of funtcional relationship with air-conditioning.The control strategy of the air feed as required that for this reason proposes among the present invention does not lose generality, at first with effective strength and maximum galleryful recently represent indoor thermal load rate of change, convert thereof into nondimensional relative number ratio, as formula (36) expression,

Sum is the number of indoor reality in the formula (36), and Max is maximum open ended occupancy, and Max is according to concrete building environment for use, and promptly air-conditioning power in the table 1 and room number matching relationship are set.

In the dutycycle control strategy, foundation of the present invention is: 1) temporary off-premises station power failure can not exert an influence to people's hotness; 2) nondimensional relative number specific energy more objectively reflects the demand of air-conditioning air feed.The present invention proposes a kind of more typical dutycycle control curve map, as shown in Figure 4.Represent nondimensional relative number ratio with PeopleRatio herein, in accompanying drawing 4, when PeopleRatio＞95%, dutycycle is set to 80%, if it is 15 minutes that a dutycycle control cycle promptly is set, be 12 minutes the conduction time of off-premises station, and power-off time is 3 minutes; When 0＜PeopleRatio＜15%, be 3 minutes the conduction time of off-premises station, and power-off time is 12 minutes; When PeopleRatio=0, be 0 minute the conduction time of off-premises station, and power-off time is 15 minutes; When 15%≤PeopleRatio≤95%, the power on/off time of off-premises station is set by funtcional relationship.In the specific implementation process, data such as each threshold value of above-mentioned PeopleRatio and maximum and minimum control dutycycle are to leave in the storage unit of controller, user's settings of can making amendment as required, but stipulate to have certain scope.Use formula (37) expression control strategy herein.PeopleRatio(％)＝sum/Max*100 (37)

In the formula, f (PeopleRatio) can be the line style relation, also can be the high order curve relation.But must be after one-period has moved, to carry out when dynamically adjusting dutycycle PWM.

Such as meeting room at about 80 square metres of areas, adopt ODVS can capture all indoor video informations, the foreground object that obtains through Flame Image Process is the judgement by region area and shape attribute then, can be fast, Real time identification goes out the quantity of indoor occupant.What this meeting room used is the air-conditioning of 10 power, its maximum number is 33 people, the personnel's number that goes out by video identification is 10 people, therefore calculate PeopleRatio=10/33*100=33% by formula (37), the dutycycle PWM that utilizes formula (36) to calculate under 10 people's situation then is 50%, following control strategy is just made by system so, and the power on/off time of off-premises station equates in a dutycycle control cycle.

Described number detects and according to setting supply stop circle and cycle zero-time in supply stop circle in the dutycycle control module of personnel's number and the cycle zero-time setting module, carry out supply stop circle control, supply stop circle can be selected in 10 minutes to 20 minutes, having adopted 15 minutes in this patent is a supply stop circle, the supply stop circle action start time is adopted the random fashion decision, produces formula and is represented by formula (38);

Pstart＝INT(RANDC()*15) (38)

The number that is produced according to formula (38) is the random integers between 0 to 14, the probability that occurs any numerical value between 0 to 14 from the angle of probability all is identical, if 100,000 operation of air conditioner are arranged on certain electrical network, and all are under full load situation, to move; According to formula (38) supply stop circle of 100,000 air-conditioner outdoor units action start time is provided with, it is identical that the air-conditioning supply stop circle action start time about 6666 is so just arranged, that is to say in certain supply stop circle of 15 minutes, there is the air-conditioning about 6666 to enter supply stop circle at first, there is the air-conditioning about 6666 to enter supply stop circle after one minute again, ..., effect as shown in Figure 8, it is obvious especially when this effect is reflected in peak of power consumption, if to account for the load of whole electrical network be 40% to air conditioner load during peak of power consumption, the power failure dutycycle all is set to 15% words, as 15% of the mild peak of power consumption of this energy of air-conditioning, concerning whole electrical network, can play 6% of mild peak of power consumption value at least, be referred to as the peak clipping method that on average staggers in this patent.The peak clipping method that realizes on average staggering is relatively simple, when air-conditioning one energising, air-conditioner controller carries out the initialization supply stop circle and cycle zero-time setting module is realized above-mentioned functions, this function can not produce the influence of any thermal comfort aspect to the personal user, and be very favorable to whole power grid security, if estimate that present air-conditioning number is 100,000,000, adopt the newly-increased generated energy that just is equivalent to power house, newly-built Three Gorges after this technology.

The invention effect that the above embodiments produced is, can bring into play the energy-saving potential of air-conditioning system to a greater degree, the real heating according to need (cooling) of realizing, make the operation energy consumption minimum of air-conditioning system, simultaneously also can play the minimizing contamination, save kilowatt-hour, just be equivalent to save the water purification of 0.4 kilogram of standard coal equivalent and 4 liters, also can reduce the carbon dioxide of about 0.27 kilogram dust, 0.8-2.5 kilogram and 0.037 kilogram dischargings such as sulphuric dioxide.

The present invention provides a kind of brand-new solution for the new product development and the technological transformation of energy-saving controller of air-conditioner, particularly at present nearly 100,000,000 domestic air conditionings being undergone technological transformation, as long as draw single line during concrete enforcement, an ODVS is installed then and connects an energy-saving controller of air-conditioner and just just finished present operating air-conditioning technical retrofit work, implement very convenient.Utilize ODVS in addition and increase some other software in embedded system, such as the fire detection algorithm, invade detection algorithm, function such as just can realize preventing fires, antitheft.

Claims (9)

1, a kind of air conditioner energy saving controller based on omnidirectional computer vision, comprise the air-conditioning temperature controller, microprocessor and be installed on the vision sensor that indoor center upper portion is used for perception indoor occupant quantity, described air-conditioning temperature controller is provided with first relay, described first relay connects air-conditioner outdoor unit, described vision sensor is connected with microprocessor, it is characterized in that: described energy-saving controller of air-conditioner also comprises the occupancy controller in order to the control air-conditioner outdoor unit power on/off cycle, described occupancy controller connects second relay, described second relay is connected with first relay, and described second relay is connected with power supply;

Described vision sensor is an omnibearing vision sensor, described omnibearing vision sensor comprises in order to the evagination catadioptric minute surface of object in the reflection monitoring field, dark circles cone, transparent cylinder, the camera in order to prevent that anaclasis and light are saturated, described evagination catadioptric minute surface is positioned at the top of transparent cylinder, evagination catadioptric minute surface down, the dark circles cone is fixed on the center of catadioptric minute surface male part, camera faces toward the evagination mirror surface up, and described camera is positioned at the virtual focus position of evagination mirror surface;

Described microprocessor comprises:

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

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

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

The image stretching processing module, the circular video image that is used for gathering expands into the panorama histogram;

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;

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 image in real time and adjacent K two field picture is asked the result who carries out image subtraction; 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 the motion object;

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 stationary objects;

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

Indoor occupant is counted estimation module, is used to ask the width w of each connected region _iWith height h _i, use formula (33) zoning area attribute ε then _Area ⁱ, S wherein _iArea for certain connected region:

${\mathrm{\&epsiv;}}_{\mathrm{area}}^i=\frac{S_i}{w_i*h_i}---\left(33\right)$

Then carrying out shape attribute with formula (34) accounts for ε _Rate ⁱCalculate, i.e. the width w of rectangle _iWith height h _iThe calculating of ratio.

${\mathrm{\&epsiv;}}_{\mathrm{rate}}^i=\frac{w_i}{h_i}---\left(34\right)$

Use formula (35) to carry out the comprehensive judgement of area and shape attribute, setting regions area effect factor F _sWith shape attribute factor of influence F _Sh:

$R\stackrel{\&RightArrow;}{e}c=F_s\&times;({\mathrm{\&epsiv;}}_{\mathrm{area}}^i-{\mathrm{\&epsiv;}}_{\mathrm{area}\_s\tan \mathrm{dard}}^i)\stackrel{\&RightArrow;}{i}+F_{\mathrm{sh}}\&times;({\mathrm{\&epsiv;}}_{\mathrm{rate}}^i-{\mathrm{\&epsiv;}}_{\mathrm{rate}\_s\tan \mathrm{dard}}^i)\stackrel{\&RightArrow;}{j}---\left(35\right)$

As

Value judges that less than preset threshold this connected region is a human body, and the total number of persons in the Data Analyzing Room;

Required dutycycle ratio setting module, be used to set up the corresponding sequence of personnel amount in architectural environment, room-size, the room and air-conditioning dutycycle, indoor occupant sum according to statistics obtains the air-conditioning dutycycle, and this duty cycle signals is sent to occupancy controller.

2, the air conditioner energy saving controller based on omnidirectional computer vision as claimed in claim 1 is characterized in that: the coordinate of undeformed horizontal coordinate that requires the scene object point and corresponding picture point is linear on the described catadioptric minute surface horizontal direction;

d(ρ)＝αρ (1)

ρ is and the distance of the face shape central point of catoptron in the formula (1), and α is the magnification of imaging system;

If the normal that catoptron is ordered at M and the angle of Z axle are γ, the angle of incident ray and Z axle is Φ, and the angle of reflection ray and Z axle is θ, then

$\mathrm{tg}\left(x\right)=\frac{d\left(x\right)-x}{z\left(x\right)-h}---\left(2\right)$

$\mathrm{tg\&gamma;}=\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}---\left(3\right)$

$\mathrm{tg}\left(2\mathrm{\&gamma;}\right)=\frac{2\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}}{1-\frac{d^{2}z\left(x\right)}{d{x}^2}}---\left(4\right)$

By reflection law

2γ＝φ-θ (6)

∴ $\mathrm{tg}\left(2\mathrm{\&gamma;}\right)=\mathrm{tg}(\mathrm{\&phi;}-\mathrm{\&theta;})=\frac{\mathrm{tg\&phi;}-\mathrm{tg\&theta;}}{1+\mathrm{tg\&phi;tg\&theta;}}$

Obtain the differential equation (7) by formula (2), (4), (5) and (6)

$\frac{d^{2}z\left(x\right)}{d{x}^2}+2k\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}-1=0---\left(7\right)$

Formula $k=\frac{z\left(x\right)[z\left(x\right)-h]+x[d\left(x\right)-x]}{z\left(x\right)[d\left(x\right)-x]+x[z\left(x\right)-h]}$ In; (8)

Obtain the differential equation (9) by formula (7)

$\frac{\mathrm{dz}\left(x\right)}{\mathrm{dx}}+k-\sqrt{k^2+1}=0---\left(9\right)$

Obtain formula (10) by formula (1), (5)

$d\left(x\right)=\frac{\mathrm{afx}}{z\left(x\right)}---\left(10\right)$

By formula (8), (9), (10) and starting condition, separate the digital solution that the differential equation can obtain reflecting mirror surface shape; Select suitable camera according to application requirements during the refractive and reflective panorama system design, calibrate Rmin, the focal distance f of lens is determined the distance H o of catoptron from camera, calculates aperture of a mirror Do by (1) formula;

Determining of systematic parameter:

Determine systematic parameter af according to the visual field of using desired short transverse, obtain formula (11), done some simplification here, z (x) ≈ z by formula (1), (2) and (5) ₀, main consideration is smaller with respect to the change in location of minute surface and camera for the height change of minute surface;

$\mathrm{tg\&phi;}=\frac{(\mathrm{af}-z_0)\frac{\mathrm{\&rho;}}{f}}{z_0-h}---\left(11\right)$

With the inconocenter point largest circumference place in the center of circle as the plane $\mathrm{\&rho;}=R\min \&RightArrow;{\mathrm{\&omega;}}_{\max }=\frac{R_{\min }}{f}$

Corresponding visual field is φ max.Then can obtain formula (12);

$\frac{\mathrm{\&rho;}}{f}=\frac{(z_0-h)\mathrm{tg}{\mathrm{\&phi;}}_{\max }}{{\mathrm{\&omega;}}_{\max }}+z_0---\left(12\right).$

3, the air conditioner energy saving controller based on omnidirectional computer vision as claimed in claim 1 is characterized in that: described image stretching 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 (21):

P ^**(x ^**，y ^**)← M× P ^*(x ^*，y ^*) (21)

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.

4, as the described air conditioner energy saving controller based on omnidirectional computer vision of one of claim 1-3, it 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 (25):

${\stackrel{\&OverBar;}{Y}}_b=\frac{\underset{x=0}{\overset{W-1}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{H-1}{\mathrm{\&Sigma;}}}{Y}_n(x,y)(1-M_n(x,y))}{\underset{x=0}{\overset{W-1}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{H-1}{\mathrm{\&Sigma;}}}(1-M_n(x,y))}---\left(25\right)$

In the formula (25), 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 (27):

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 (26)

If Δ Y, then thinks the incident of turning on light that taken place greater than higher limit; 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 (22) when light changes naturally:

X _mix，bn+1(i)＝(1-λ)X _mix，bn(i)+λX _mix，cn(i) (22)

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 (23):

X _mix，bn+1(i)＝X _mix，cn(i) (23)。

5, the air conditioner energy saving controller based on omnidirectional computer vision as claimed in claim 4, 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 (16):

h[i，j]＝(1/M)∑f[k，1] (32)

In the following formula (32), M is the pixel sum in the neighborhood.

6, the air conditioner energy saving controller based on omnidirectional computer vision as claimed in claim 5, it is characterized in that: in the connected region computing module, utilize connected region to calculate its area and center of gravity, the center of gravity of described subject object can obtain by the X of aforementioned calculation resulting connected region area Si and this connected region, the accumulation calculated for pixel values of Y direction, and computing formula is calculated by formula (37):

$X_{\mathrm{cg}\left(i\right)}=\frac{\underset{x,y\&Element;S_i}{\mathrm{\&Sigma;}}x}{S_i};Y_{\mathrm{cg}\left(i\right)}=\frac{\underset{x,y\&Element;S_i}{\mathrm{\&Sigma;}}y}{S_i}---\left(37\right).$

7, the air conditioner energy saving controller based on omnidirectional computer vision as claimed in claim 6, it is characterized in that: described microprocessor also comprises the color space conversion module, be used for the conversion of RGB color space to the YCrCb color space, its formula (28) provides

Y＝0.29990*R+0.5870*G+0.1140*B

Cr＝0.5000*R-0.4187*G-0.0813*B+128 (28)。

Cb＝-0.1787*R-0.3313*G+0.5000*B+128

8, as the described air conditioner energy saving controller of one of claim 1-3 based on omnidirectional computer vision, it is characterized in that: in described required dutycycle ratio setting module, effective strength and maximum galleryful recently represented indoor thermal load rate of change, convert thereof into nondimensional relative number ratio, represent as formula (36)

Represent control strategy with formula (37):

PeopleRatio(％)＝sum/Max*100 (37)。

In the formula (36), sum is the number of indoor reality, and Max is maximum open ended occupancy, and Max is according to concrete building environment for use, air-conditioning power and the decision of room number matching relationship, and f (PeopleRatio) is a funtcional relationship.

9, as the described air conditioner energy saving controller of one of claim 1-3 based on omnidirectional computer vision, it is characterized in that: described microprocessor also comprises cycle zero-time setting module, be used for setting module and set supply stop circle and cycle zero-time, carry out supply stop circle control, the supply stop circle action start time is adopted the random fashion decision.

Images