CN102479416A - Method, system and device for eliminating false alarm in monitoring system - Google Patents
Method, system and device for eliminating false alarm in monitoring system Download PDFInfo
- Publication number
- CN102479416A CN102479416A CN2010105658989A CN201010565898A CN102479416A CN 102479416 A CN102479416 A CN 102479416A CN 2010105658989 A CN2010105658989 A CN 2010105658989A CN 201010565898 A CN201010565898 A CN 201010565898A CN 102479416 A CN102479416 A CN 102479416A
- Authority
- CN
- China
- Prior art keywords
- alarm
- vector
- state description
- template
- false alarm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses a method for eliminating a false alarm in a monitoring system. The method comprises the following steps: carrying out color space conversion on image data of an alarm zone, thus reducing the color dimensionality; generating state description vector of the image data, wherein the state description vector is utilized as an quantitative index for describing image characteristics; and calculating the distance between the state description vector and a template vector, wherein the template vector is the state description vector of the image data of the alarm zone under a non-alarm state. The invention also discloses a device for eliminating a false alarm in a monitoring system, and the device comprises a color space conversion unit, a state description vector generation unit coupled with the color space conversion unit and an alarm judgment unit coupled with the state description vector generation unit. The invention further discloses a system for eliminating a false alarm in a monitoring system. By utilizing the method for eliminating the false alarm, the false alarm caused by light reflection on a side panel due to flickering of a faucet indicating lamp in an existing monitoring system can be eliminated and the alarm accuracy rate is improved.
Description
Technical field
The present invention relates to the ATM field of intelligent monitoring, relate in particular to a kind of method, system and device of eliminating false alarm in the supervisory system.
Background technology
The safety problem of ATM perplexs banking industry and ATM manufacturer always, in order to Strengthen Safety Management, generally adopts the method for camera head monitor, and one, two or more cameras, monitoring user operation process are installed between ATM is withdrawn the money.Camera between ATM is withdrawn the money had both comprised monitoring, identification user's camera, also comprised the camera of monitoring ATM itself and user's operating process.
Artificial monitoring needs the manpower and financial resources of labor, nor can guarantee monitoring effect.The importance of ATM intelligent monitor system in social safety is remarkable day by day.Intelligent monitor system generally is that the variation according to prospect, background two two field pictures determines whether and reporting to the police.For example, application number is that 201010109588.6 Chinese invention patent application discloses monitor processing method and system in a kind of monitoring, when human body does not appear in the monitored body region, obtains monitored body original image and monitored body detecting image; When judging that said monitored body original image and said monitored body detecting image there are differences, send the detecting alarm signal.I.e. variation through movement images determines whether and reporting to the police.
When reality was carried out intelligent monitoring to ATM, card inserting mouth pilot lamp zone had been set to the shadow zone, not in image scope relatively; But,, thereby brought false alarm because the reflective image change of prospect, background relevant position that also can cause that the flicker of card inserting mouth pilot lamp causes is bigger on side panel.
Iff is not reported to the police and then can be brought the risk of failing to report through the shadow zone simply is set, and this situation has directly influenced the reliability of intelligent monitor system.
Summary of the invention
The problem that the present invention solves provides a kind of reflective method that causes false alarm in the intelligent monitor system of eliminating; When eliminating because of the reflective false alarm that causes; Avoid only through the risk of not reporting to the police and bring in the shadow zone of failing to report simply being set, the availability of raising intelligent monitor system.
For addressing the above problem, the present invention provides a kind of method of eliminating false alarm in the supervisory system, comprising: the view data to alarm region is carried out color space transformation, reduces the color dimension of said view data; View data computing mode to reducing the color dimension is described vectorial V
a, as the quantizating index of describing characteristics of image; Calculate said state description vector V
aAnd the distance between the template vector, said template vector is the state description vector of the view data of alarm region under the non-alarm condition; If it is the corresponding non-alarm condition of said template vector that said distance, is confirmed current state less than preset threshold value, this time reporting to the police is false alarm.
Optional, the view data of alarm region is carried out color space transformation comprises: by following conversion regime with the view data of alarm region from (R, G, B) color space transformation to (r, g, b) color space,
r＝R/(R+G+B)
g＝G/(R+G+B)
b＝B/(R+G+B)。
Optional, the view data computing mode that reduces the color dimension is described vectorial V
aComprise: select (r, g) or (g, b) or (b, r) color space respectively carries out statistics with histogram to the view data of said alarm region at two components of selected normalization color space as the normalization color space; Said histogrammic horizontal ordinate is the intensity quantized level, and ordinate is the frequency that pixel occurs in this intensity; Generate the joint histogram of selected normalization color space; Generate the state description vector of above-mentioned joint histogram; The content of said state description vector is the class frequency value according to the ordering of intensity quantized level.
Optional, said template vector comprises the bright template vector V of lamp
OnWith the lamp template vector V that goes out
OffDistance between the template vector that the said state description vector sum of said calculating is preserved comprises: calculate said state description vector V by following conversion regime
aWith the bright template vector V of said lamp
OnBetween distance B 1 and said state description vector V
aWith the said lamp template vector V that goes out
OffBetween distance B 2:
D1＝Va·Von/(|Va|×|Von|)
D2＝Va·Voff/(|Va|×|Voff|)。
Optional, if said distance comprises less than preset threshold value: if having one among D1 and the D2 less than the alarm threshold value of setting.
Optional, the method for upgrading said template vector comprises: input modeling image; The modeling image is carried out color space transformation; Generate the state description vector of alarm region; According to template number, the classification preservation state is described vector; Continue statistics if desired, time-delay a period of time, import the modeling image once more; If need not continue statistics, the state description vector based on classification is preserved calculates average template vector.
Optional, said template vector comprises bright state description template vector of lamp and the lamp state description template vector that goes out; The method of calculating average template vector is for carry out statistics with histogram to the state description vector of preserving in batches.
Optional, the method for false alarm also comprises in the described elimination supervisory system: the standard deviation of calculating average template vector; The corresponding lamp of the average template vector that standard deviation the is big state description template vector that goes out, the bright state description template vector of the corresponding lamp of average template vector that standard deviation is little.
Further; The present invention also provides a kind of device of eliminating false alarm in the supervisory system; Comprise: color space transformation unit, the state description that couples with color space transformation unit vector generation unit, the alarm decision unit that couples with state description vector generation unit; Said color space transformation unit is suitable for receiving the view data of alarm region, and the view data of alarm region is carried out color space transformation, reduces the color dimension of said view data; Said state description vector generation unit is suitable for generating the state description vector of said view data, as the quantizating index of describing characteristics of image; Said alarm decision unit is suitable for calculating the distance between the said state description vector sum template vector and judges according to the relation between said distance and the preset threshold value whether this time report to the police is false alarm; Said template vector is the state description vector of the view data of alarm region under the non-alarm condition.
Optional, the device of false alarm also comprises template storage unit in the said elimination supervisory system, couples with said alarm decision unit, is suitable for preserving said template vector.
Optional; The device of false alarm also comprises the template vector updating block in the said elimination supervisory system; Couple with said state description vector generation unit and template storage unit respectively; The state description vector that is suitable for receiving and classifies and preserve the modeling image calculates average template vector and upgrades the template vector that said template storage unit is preserved; The function selecting unit couples with state description vector generation unit, is suitable for being provided with the state flag bit of said device; Said state description vector generation unit is suitable for obtaining this state flag bit, and according to this state flag bit, the state description vector is sent to template vector updating block or the alarm decision unit that couples with it.
Further, the present invention also provides a kind of system of eliminating false alarm in the supervisory system, comprising: the device of false alarm in the above-mentioned elimination supervisory system, image acquisition units, pre-alarm unit and alarm unit; Said image acquisition units is suitable for gathering at set intervals the view data of the monitored object of a frame, and sends to the pre-alarm unit; Said pre-alarm unit is suitable for calculating the variable quantity of front and back two frame image datas and judges whether to surpass threshold value; Said false alarm cancellation element is suitable for receiving pre-alarm signal and the alarm region view data from the pre-alarm unit, and judges whether this pre-alarm signal is false alarm; Said alarm unit is suitable for receiving from the alerting signal of false alarm cancellation element and to the monitor staff reports to the police.
Optional, the variable quantity of calculating front and back two frame image datas also judges whether to comprise above threshold value: said front and back two frame image datas are carried out gray processing respectively handle; Obtain the difference value of said front and back two frame image datas; Whether poor score value surpasses preset threshold value.
Compared with prior art, the present invention has the following advantages: has eliminated in the existing supervisory system because the reflective false alarm that causes that the flicker of card inserting mouth pilot lamp causes on side panel has improved the warning accuracy rate through adopting above-mentioned false alarm removing method (1); (2) through upgrading template vector; Eliminated because the influence that exterior light is brought according to conditional variation; Further improve warning accuracy rate (3) through utilizing the normalization color space, compressed the redundant information of view data, not only can be to normal alarm generation influence; Can reduce the wrong report that illumination variation causes on the contrary, further improve the warning accuracy rate.
Description of drawings
Fig. 1, the 2nd, in the prior art, the synoptic diagram of the image that camera obtains in the ATM intelligent monitor system;
Fig. 3 is the reflective method flow diagram that causes false alarm in the elimination intelligent monitor system that provides in the one embodiment of the invention;
Fig. 4 provides template vector update method process flow diagram in the one embodiment of the invention;
Fig. 5 provides a kind of automatic classification to preserve the method flow diagram of template vector in one embodiment of the present of invention;
Fig. 6, the 7th, the joint histogram that lamp goes out in the one embodiment of the invention, the bright template vector of lamp is corresponding;
Fig. 8 is the false alarm method for removing of the renewable template vector that provides in the one embodiment of the invention;
Fig. 9,10,11 is in the different embodiments of the invention, eliminates the structural representation of the device of false alarm in the supervisory system;
Figure 12 is the structural representation of the system of false alarm in the elimination supervisory system that provides in the one embodiment of the invention.
Embodiment
For make above-mentioned purpose of the present invention, feature and advantage can be more obviously understandable, does detailed explanation below in conjunction with the accompanying drawing specific embodiments of the invention.
Among the present invention, image is transformed into the normalization color space from rgb color space refers to:
(1) by following conversion regime with the view data of alarm region from (R, G, B) color space transformation to (r, g, b) color space:
r＝R/(R+G+B)
g＝G/(R+G+B)
b＝B/(R+G+B)。
Wherein, utilize any two normalization components, can generate the 3rd component, for example:
b＝1-r-g
(2) r, and two components formations of g normalization color space (r, g).
Can select any two components in the rgb color space to carry out above-mentioned normalization calculating, can realize reducing the color dimension, reduce the purpose of redundant information through normalization.
Among the present invention, " intensity quantized level " is used to describe the component of normalization color space.For example, the span of r and g evenly is divided into 256 quantized levels, obtains (r0-r255), (g0-g255), each quantized level corresponds to an intensity quantized level.
Among the present invention, " statistics with histogram " is to the component of the normalization color space of image.Histogrammic horizontal ordinate is the intensity quantized level, and ordinate is the frequency that pixel occurs in this intensity.
Among the present invention, " joint histogram " is to the normalization color space of image.For example, the normalization color space (r, g) in, the histogram of r component and the histogrammic horizontal ordinate of g component are together in series, obtain r, the joint histogram of g component.That is: 256 intensity quantized levels of the corresponding r of horizontal ordinate 0-255,256 intensity quantized levels of the corresponding g of horizontal ordinate 256-511, ordinate are the frequency that pixel occurs at the corresponding strength quantized level.R, the g component combination has characterized the color statistical information of image together jointly.
Among the present invention, " state description vector " is a vector that draws according to joint histogram to the normalization color space of image.Its content is the class frequency value according to the ordering of intensity quantized level.State description vector (a0, a1, a2 ..., a511), have 512 elements, preceding 256 elements and be 1, back 256 elements and be 1, that is:
For example, piece image comprises 1000 pixel datas, has 10 pixels to occur in r 0 intensity, and 20 pixels occur in r 1 intensity; ..., 15 pixels occur in r 255 intensity, and then state description vector r component is (0.01,0.02; ..., 0.015) and be 1; Have 30 pixels to occur in g 0 intensity, 5 pixels occur in g1 intensity ..., 50 pixels occur in g 255 intensity, then state description vector g component be (0.03,0.005 ..., 0.05) and be 1; The state description vector of this width of cloth image be (0.01,0.02 ..., 0.015,0.03,0.005 ..., 0.05).The state description vector is the quantizating index that is used to describe characteristics of image.
Among the present invention, " the bright state description template vector of lamp " and " lamp go out state description template vector " is illustrated under the card inserting mouth pilot lamp " lamp is bright " and " lamp goes out " two states on the ATM, the state description vector that the image of alarm region is corresponding respectively.They are " reference vector "." template vector " is the abbreviation of " state description template vector ".
In order to eliminate the reflective false alarm that causes in the intelligent monitor system; The present invention proposes a kind of solution based on the color joint histogram: at first to image being carried out color space transformation to reduce illumination effect; Obtain the state description template vector through calculating the color joint histogram then, and on the basis of bulk statistics, use the joint histogram standard deviation to confirm template vector and the corresponding relation that lamp is bright, lamp goes out this two states; When practical application, the on-the-spot test picture is calculated color joint histogram vector too, and carry out distance relatively finally to judge whether and report to the police with corresponding state description template vector.
Set forth detail in the following description so that make much of the present invention.But the present invention can be different from alternate manner described here and implements with multiple, and those skilled in the art can do similar popularization under the situation of intension of the present invention.Therefore the present invention does not receive the restriction of following disclosed embodiment.
Be depicted as image 101 that camera obtains in the ATM intelligent monitor system like Fig. 1,2.Image 101 content displayed comprise ATM and wall on every side thereof.ATM comprises display screen 102, plug-in card district 104, card inserting mouth pilot lamp 103, and user input area.The card inserting mouth pilot lamp 103 that Fig. 1 shows is for extinguishing state, and the card inserting mouth pilot lamp that shows among Fig. 2 is a blink states.Retroreflective regions 105 when also having shown 103 flickers of card inserting mouth pilot lamp among Fig. 2 on the ATM side panel, problem to be solved by this invention is retroreflective regions 105 caused false alarms just, and retroreflective regions 105 is above-mentioned alarm region.
In the process of ATM intelligent monitor system work, judge whether to report to the police through the variation of comparing front and back two two field pictures.Supervisory system generally at first obtains colored monitoring image, colored monitoring image is carried out gray processing handle, and uses various gray processing formula to carry out; Then two two field pictures are carried out grey scale difference and handle, produced enough variations, report to the police thereby cause if the absolute value of difference was just thought when surpassing threshold value, and transmitting, monitoring image and identify the alarm region in the monitoring image.Described threshold value is an empirical value.
For fear of false alarm, among the present invention, the image of alarm region is done further analysis.
As shown in Figure 3, the reflective method of false alarm that causes comprises the steps: in the elimination intelligent monitor system that provides in the one embodiment of the invention
S101 carries out color space transformation to alarm region;
S102, the state description that generates alarm region is vectorial;
S103, computing mode is described the distance between the vector sum template vector;
S104, if distance less than threshold value, current state is the corresponding state of reference vector, is false alarm;
S105, if distance is not less than threshold value, the corresponding state of the non-reference vector of current state is true warning.
In step S101, in order to reduce illumination effect, by following conversion regime, with the image of alarm region from (R, G, B) color space transformation to (r, g, b) color space:
r＝R/(R+G+B)
g＝G/(R+G+B)
b＝B/(R+G+B)
(r, g, b) three components in the color space and be 1, it is redundant component that one-component is promptly wherein arranged.In the present embodiment, (r, g) color space has reduced the illumination redundant information as the normalization color space in selection.In other embodiments, also can select (g, b) or (b is r) as the normalization color space.
For monitoring image, (B) color space has comprised a large amount of illumination redundant informations for R, G, has then compressed this part redundant information after the normalization, and the own chromatic characteristic of concentrating more of reflection is favourable to follow-up further processing.Not only can not reduce the wrong report that illumination variation causes on the contrary to normal alarm generation influence.
The color space transformation mode has multiple; In other embodiments of the invention, can also be with the image of alarm region from (R, G; B) color space transformation is to color spaces such as YUV, HSV, LAB, CMYK; Reach the purpose of brightness, chrominance separation, but the arbitrary component in conversion back can not be by other 2 component derivation, their dimensionality reduction is realized through abandoning luminance component.In the foregoing description, select with the image of alarm region from (R, G, B) color space transformation to (r, g, b) color space, mainly be considered that its conversion is simple, dimensionality reduction advantage easily.
In step S102, the process that generates the state description vector of alarm region is:
S201, to the alarm region image (r, g) r of color space, g component carry out statistics with histogram respectively;
S202, the joint histogram of generation r, g component;
S203 generates the state description vector V of above-mentioned joint histogram
a
In step S103, the distance that computing mode is described between the vector sum template vector comprises:
Calculate said state description vector V
aWith the bright template vector V of said lamp
OnBetween distance B 1;
Calculate said state description vector V
aWith the said lamp template vector V that goes out
OffBetween distance B 2.
The bright template vector V of described lamp
OnWith the lamp template vector V that goes out
OffImplication be: under the state that goes out with the card inserting mouth pilot lamp under the bright state of card inserting mouth pilot lamp, calculate the state description vector of alarm region view data respectively; Its computing method also are to utilize the step among S201～S203 to accomplish, and are saved as reference vector and be used for comparison.
The method of calculating the distance between two state description vectors is:
D1＝Va·Von/(|Va|×|Von|)
D2＝Va·Voff/(|Va|×|Voff|)
Promptly utilize the included angle cosine distance between vector, judge the similarity distance between two vectors.
If have one among D1 and the D2 less than the alarm threshold value T0 (empirical value) that sets; The present state of card inserting mouth pilot lamp or for the bright state of lamp or be the lamp state that goes out then; The state of corresponding alarm region or for the bright state of lamp or be the lamp state that goes out, this is reported to the police and is false alarm, can get rid of.
If D1 and D2, represent the state of present alarm region greater than alarm threshold value T0 neither the bright state of lamp, the state that neither lamp goes out, this is reported to the police and reports to the police for true.
Through above-mentioned method, got rid of the false alarm that retroreflective regions causes, improved the warning accuracy of intelligent monitor system, saved time and relevant resource.
Further, because outside illumination condition may change,, just need renewal at set intervals, better to avoid the appearance of false alarm so the state description template vector of setting up comprises the bright template vector of lamp and the lamp template vector that goes out.
As shown in Figure 4, a kind of template renewal method is provided in one embodiment of the present of invention, comprising:
S300 is provided with zone of alarm;
S301, input modeling image (setting up the template vector image) is the view data of zone of alarm;
S302 carries out color space transformation to alarm region;
S303, the state description that generates alarm region is vectorial;
S304, the classification preservation state is described vector;
S305 continues statistics if desired, time-delay a period of time, gathers and import the modeling image once more;
S306 if need not continue statistics, calculates average template vector.
In step S300; The purpose that zone of alarm is set is to indicate the scope that possibly produce false alarm; Promptly in this scope, normal state is a kind of incessantly, and the method for two two field picture grey scale differences or the alarming result that other comparative approach obtain might belong to false alarm before and after supervisory system adopted.In the present embodiment, alarm region is above-mentioned retroreflective regions.
The modeling image is the image of alarm region among the step S301.In other embodiments of the invention, if adopt whole monitoring image, step S300 can cancel, and in step S301, increases an operation steps of choosing alarm region.
Step S302, S303 distinguish corresponding with above-mentioned step S101, S102.
Among the step S304, the state description vector classification that obtains is kept in the template storage unit.In the present embodiment, template vector has two types, and one type is the bright template of lamp, and another kind of is the lamp template of going out.Classification thresholds T1 is used to judge that newly-generated state description vector belongs to the template vector of which kind of type.In the present embodiment, a kind of method of template type of automatic judgement state description vector is provided,, comprises with reference to figure 5:
S401 is if the state description that generates for the first time vector saves as type I;
S402, if not, input vector and type I template vector distance calculated;
S403 is if distance saves as type I template vector sample less than classification thresholds T1;
S404 is if distance saves as Type II template vector sample greater than classification thresholds T1.
The method of the distance between the aforementioned calculation vector still adopts the included angle cosine range formula between vector:
D＝a·b/(|a|×|b|)
After obtaining some samples, in step S306, the sample of type I and Type II template vector is carried out statistics with histogram respectively in batches obtain type I and the average template vector of Type II.
Concrete, be located at certain time period to have obtained the picture of a collection of type I, these pictures amount to and include 10000 pixels, through statistics; Wherein have 100 pixels to occur in r 0 intensity, 200 pixels occur in r1 intensity ...; 150 pixels occur in r 255 intensity, and then average template vector r component is (0.01,0.02; ..., 0.015) and be 1; Have 300 pixels to occur in g 0 intensity, 50 pixels occur in g1 intensity ..., 500 pixels occur in g 255 intensity, then average template vector g component be (0.03,0.005 ..., 0.05) and be 1; The average template vector of the picture of whole type I be (0.01,0.02 ..., 0.015,0.03,0.005 ..., 0.05).
Two types the average template vector that said method obtains will be as two types of template vectors, compare with the state description vector of image to be detected.
In the present embodiment, for the go out corresponding relation of template of clear and definite these two types of template vectors and the bright template of lamp, lamp, can be by operating personnel's manual configuration.
Further, in the one embodiment of the invention, through the standard deviation of compute type I and Type II template vector, the bright template of automatic corresponding lamp, the lamp template of going out.Its principle is: when lamp went out, color background was often more single, and lamp bright after; Both had powerful connections in the zone, light was also arranged, so distribution of color can be broad relatively; The basis of calculation is poor respectively to the template of type I and Type II, the corresponding lamp that standard deviation the is big state that goes out, the bright state of corresponding lamp that standard deviation is little.Like Fig. 6, shown in Figure 7, the standard deviation of (r-g) joint histogram is 0.0194 among Fig. 6, the indication lamp template of going out; The standard deviation of (r-g) joint histogram is 0.0077 among Fig. 7, the bright template of indication lamp.
Further, above-mentioned false alarm method for removing and template vector update method can combine, and become the false alarm method for removing that upgrades template vector.As shown in Figure 8, a kind of false alarm method for removing is provided in one embodiment of the present of invention, comprising:
S501, input modeling image; Perhaps S502, the input test image;
S503 carries out color space transformation to alarm region;
S504, the state description that generates alarm region is vectorial;
S505, if not test pattern, the classification preservation state is described vector;
S506 if be test pattern at present, no longer need continue to gather statistical sample, calculates average template vector;
S507, the average template vector that obtains with S506 substitutes the template vector of preserving;
S508, if test pattern calls the template vector of preservation, the distance of calculation template vector sum state description vector also judges that whether it is less than alarm threshold value;
S509 according to the comparative result of S508, judges whether to report to the police; If distance is less than threshold value, current state is the corresponding state of reference vector, is false alarm.
Further, though the method that the above embodiments are described is directed against the alarm region that has two kinds of normal conditions, method provided by the invention also can be used for monitored object has multiple normal condition, and whether need further to analyze alarm region be in the system of true warning.During application; Only need various normal conditions all be set up corresponding template vector respectively; After obtaining alarm region, calculate respectively and judge whether the state description vector of alarm region can be summed up as template vector (as utilizing included angle cosine formula between vector), if can be summed up as template vector; Then this is reported to the police to false alarm, can get rid of.
Further, the present invention also provides a kind of device of eliminating false alarm in the supervisory system.As shown in Figure 9, in one embodiment of the invention, eliminate the structural representation of the device of false alarm in the supervisory system.Comprising color space transformation unit 901, the state description vector generation unit 902 that couples with color space transformation unit 901, the alarm decision unit 903 that couples with state description vector generation unit 902.Image with the alarm region that receives is responsible for from (B) color space transformation is to (r, g, b) color space for R, G in color space transformation unit 901.Described in conversion formula such as the step S101; State description vector generation unit 902 is responsible for generating the state description vector of alarm region, and the method such as the step S102 that generate the state description vector are said; The relation that computing modes are described the distance between the vector sum template vector and judged this distance and preset threshold is responsible in alarm decision unit 903, and is of step S103, S104 and S105.
Of the present invention another executed in the example, and be shown in figure 10, and the device of eliminating false alarm in the supervisory system also comprises template storage unit 904, couples with alarm decision unit 903, is responsible for preserving template vector.The function of in other embodiments, preserving template vector also can be accomplished by alarm decision unit 903.
Further, for new template more, the another kind of device of eliminating false alarm in the supervisory system is provided in the one embodiment of the invention.Shown in figure 11, this device comprises: image input block 1001 is used to receive modeling image or test pattern; Color space transformation unit 1002; State description vector generation unit 1003; Template vector updating block 1004, the preservation state that is suitable for classifying is described vector, calculates average template vector at last and upgrades the template vector in the template storage unit 1005; The function selecting unit 1007 and alarm decision unit 1006 that couple with state description vector generation unit 1003.
In the present embodiment, the data flow of eliminating the device of false alarm in the supervisory system depends on the setting of function selecting unit 1007.Function selecting unit 1007 receives user's selection, and state flag bit Flag is set; State flag bit Flag can be set to 0 or 1, respectively corresponding templates update functions and false alarm recognition function.
When the template renewal function was chosen, device received data stream 1011 and is the modeling image, and state description vector generation unit 1003 obtains the state flag bit Flag in the function selecting unit 1007, and value is 0.State description vector generation unit 1003 sends to the state description vector template vector updating block 1004 that couples with it.Accomplish the template renewal operation by template vector updating block 1004, content of operation such as step S304, S305 and S306 are said.
When the false alarm recognition function was chosen, device received data stream 1012 and is test pattern, i.e. alarm region image, and state description vector generation unit 1003 obtains the state flag bit Flag in the function selecting unit 1007, and value is 1.State description vector generation unit 1003 sends to the state description vector alarm decision unit 1006 that couples with it.Alarm decision unit 1006 obtains the bright template of lamp and the lamp template of going out from template storage unit 1005, and computing mode is described the distance between vector and two templates, judges whether to be false alarm.
In other embodiments of the invention, the also state flag bit of setting device otherwise, or switch through other the function of mode finishing device.For example, the image input block receives user's function selecting, and increases state flag bit for all view data, and the state flag bit that view data is entrained is depended in the function switching.
Further, shown in figure 12, a kind of system of eliminating false alarm in the supervisory system also is provided in the one embodiment of the invention.This system comprises: image acquisition units 1101, pre-alarm unit 1102, false alarm cancellation element 1103 and alarm unit 1104.
Gray(i，j)＝0.299*R(i，j)+0.587*G(i，j)+0.114*B(i，j)
I wherein, j is a horizontal coordinate, and RGB is a color component, and Gray is a gray-scale value.
Whether the difference of two each gray values of pixel points of frame surpasses first predetermined value relatively.If the pixel quantity that surpasses reaches second predetermined value, generate the pre-alarm signal.Simultaneously, alarm region (comprising the pixel that gray-value variation surpasses first predetermined value) is extracted.Wherein, first predetermined value and second predetermined value all are empirical values.
In other embodiments of the invention, also can carry out difference to front and back two frame image datas, will obtain difference value and preset threshold value compares, judge whether to generate the pre-alarm signal then through other mode.
Pre-alarm signal and alarm region view data that false alarm cancellation element 1103 receives from pre-alarm unit 1102.Adopt the method for above-mentioned elimination false alarm, get rid of false alarm wherein, and real pre-alarm signal is sent to alarm unit 1104.
Through adopting above-mentioned false alarm removing method, Apparatus and system, eliminated in the existing supervisory system because the reflective false alarm that causes that the flicker of card inserting mouth pilot lamp causes on side panel has improved the warning accuracy rate.
Though the present invention with specific embodiment openly as above; But it is not to be used for limiting the present invention; Any those skilled in the art are not breaking away from the spirit and scope of the present invention; Can utilize the method and the technology contents of above-mentioned announcement that technical scheme of the present invention is made possible change and modification, therefore, every content that does not break away from technical scheme of the present invention; To any simple modification, equivalent variations and modification that above embodiment did, all belong to the protection domain of technical scheme of the present invention according to technical spirit of the present invention.
Claims (13)
1. a method of eliminating false alarm in the supervisory system is characterized in that, comprising:
View data to alarm region is carried out color space transformation, reduces the color dimension of said view data;
View data computing mode to reducing the color dimension is described vectorial V
a, as the quantizating index of describing characteristics of image;
Calculate said state description vector V
aAnd the distance between the template vector, said template vector is the state description vector of the view data of alarm region under the non-alarm condition;
If it is the corresponding non-alarm condition of said template vector that said distance, is confirmed current state less than preset threshold value, this time reporting to the police is false alarm.
2. the method for false alarm is characterized in that in the elimination supervisory system as claimed in claim 1, the view data of alarm region is carried out color space transformation comprise:
By following conversion regime with the view data of alarm region from (R, G, B) color space transformation to (r, g, b) color space,
r＝R/(R+G+B)
g＝G/(R+G+B)
b＝B/(R+G+B)。
3. the method for false alarm is characterized in that in the elimination supervisory system as claimed in claim 2, and the view data computing mode that reduces the color dimension is described vectorial V
aComprise:
Select (r, g) or (g, b) or (b, r) color space respectively carries out statistics with histogram to the view data of said alarm region at two components of selected normalization color space as the normalization color space; Said histogrammic horizontal ordinate is the intensity quantized level, and ordinate is the frequency that pixel occurs in this intensity;
Generate the joint histogram of selected normalization color space;
Generate the state description vector of above-mentioned joint histogram; The content of said state description vector is the class frequency value according to the ordering of intensity quantized level.
4. the method for false alarm in the elimination supervisory system as claimed in claim 1 is characterized in that:
Said template vector comprises the bright template vector V of lamp
OnWith the lamp template vector V that goes out
Off
Distance between the template vector that the said state description vector sum of said calculating is preserved comprises:
Calculate said state description vector V by following conversion regime
aWith the bright template vector V of said lamp
OnBetween distance B 1 and said state description vector V
aWith the said lamp template vector V that goes out
OffBetween distance B 2:
D1＝Va·Von/(|Va|×|Von|)
D2＝Va·Voff/(|Va|×|Voff|)
5. the method for false alarm is characterized in that in the elimination supervisory system as claimed in claim 4, if said distance comprises less than preset threshold value:
If have one among D1 and the D2 less than the alarm threshold value of setting.
6. the method for false alarm is characterized in that in the elimination supervisory system as claimed in claim 1, and the method for upgrading said template vector comprises:
Input modeling image;
The modeling image is carried out color space transformation;
Generate the state description vector of alarm region;
According to template number, the classification preservation state is described vector;
Continue statistics if desired, time-delay a period of time, import the modeling image once more;
If need not continue statistics, the state description vector based on classification is preserved calculates average template vector.
7. the method for false alarm in the elimination supervisory system as claimed in claim 6 is characterized in that:
Said template vector comprises bright state description template vector of lamp and the lamp state description template vector that goes out;
The method of calculating average template vector is for carry out statistics with histogram to the state description vector of preserving in batches.
8. the method for false alarm is characterized in that in the elimination supervisory system as claimed in claim 7, also comprises:
Calculate the standard deviation of average template vector; The corresponding lamp of the average template vector that standard deviation the is big state description template vector that goes out, the bright state description template vector of the corresponding lamp of average template vector that standard deviation is little.
9. a device of eliminating false alarm in the supervisory system is characterized in that, comprising: color space transformation unit, the state description that couples with color space transformation unit vector generation unit, the alarm decision unit that couples with state description vector generation unit;
Said color space transformation unit is suitable for receiving the view data of alarm region, and the view data of alarm region is carried out color space transformation, reduces the color dimension of said view data;
Said state description vector generation unit is suitable for generating the state description vector of said view data, as the quantizating index of describing characteristics of image;
Said alarm decision unit is suitable for calculating the distance between the said state description vector sum template vector and judges according to the relation between said distance and the preset threshold value whether this time report to the police is false alarm; Said template vector is the state description vector of the view data of alarm region under the non-alarm condition.
10. the device of false alarm in the elimination supervisory system as claimed in claim 9 is characterized in that: also comprise template storage unit, couple with said alarm decision unit, be suitable for preserving said template vector.
11. the device of false alarm is characterized in that in the elimination supervisory system as claimed in claim 10, also comprises:
The template vector updating block; Couple with said state description vector generation unit and template storage unit respectively; The state description vector that is suitable for receiving and classifies and preserve the modeling image calculates average template vector and upgrades the template vector that said template storage unit is preserved;
The function selecting unit couples with state description vector generation unit, is suitable for being provided with the state flag bit of said device; Said state description vector generation unit is suitable for obtaining this state flag bit, and according to this state flag bit, the state description vector is sent to template vector updating block or the alarm decision unit that couples with it.
12. a system of eliminating false alarm in the supervisory system is characterized in that, comprising: like the device of false alarm in any described elimination supervisory system in the claim 9 to 11, image acquisition units, pre-alarm unit and alarm unit;
Said image acquisition units is suitable for gathering at set intervals the view data of the monitored object of a frame, and sends to the pre-alarm unit;
Said pre-alarm unit is suitable for calculating the variable quantity of front and back two frame image datas and judges whether to surpass threshold value;
Said false alarm cancellation element is suitable for receiving pre-alarm signal and the alarm region view data from the pre-alarm unit, and judges whether this pre-alarm signal is false alarm;
Said alarm unit is suitable for receiving from the alerting signal of false alarm cancellation element and to the monitor staff reports to the police.
13. the system of false alarm is characterized in that in the elimination supervisory system described in claim 12, calculates the variable quantity of front and back two frame image datas and judge whether to surpass threshold value to comprise:
Said front and back two frame image datas are carried out gray processing respectively to be handled;
Obtain the difference value of said front and back two frame image datas;
Whether poor score value surpasses preset threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010565898.9A CN102479416B (en) | 2010-11-29 | 2010-11-29 | Method and device for eliminating false alarm in monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010565898.9A CN102479416B (en) | 2010-11-29 | 2010-11-29 | Method and device for eliminating false alarm in monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102479416A true CN102479416A (en) | 2012-05-30 |
| CN102479416B CN102479416B (en) | 2014-08-13 |
Family
ID=46092042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010565898.9A Expired - Fee Related CN102479416B (en) | 2010-11-29 | 2010-11-29 | Method and device for eliminating false alarm in monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102479416B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104320388A (en) * | 2014-10-13 | 2015-01-28 | 杭州海兴电力科技股份有限公司 | S-FSK carrier based active alarming method |
| CN104700532A (en) * | 2013-12-11 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Video alarm method and video alarm device |
| CN104794827A (en) * | 2014-01-17 | 2015-07-22 | 温科尼克斯多夫国际有限公司 | Method and apparatus for prevention of false alarms in monitoring systems |
| WO2017071084A1 (en) * | 2015-10-28 | 2017-05-04 | 小米科技有限责任公司 | Alarm method and device |
| CN108447208A (en) * | 2018-05-17 | 2018-08-24 | 普联技术有限公司 | Light warning method, equipment, web camera and storage medium |
| WO2021223665A1 (en) * | 2020-05-08 | 2021-11-11 | 华为技术有限公司 | Method and device for reducing invalid warnings |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010176533A (en) * | 2009-01-30 | 2010-08-12 | Secom Co Ltd | Transaction monitoring device |
| CN101808234A (en) * | 2010-02-09 | 2010-08-18 | 成都市华为赛门铁克科技有限公司 | Monitor processing method and system |
-
2010
- 2010-11-29 CN CN201010565898.9A patent/CN102479416B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010176533A (en) * | 2009-01-30 | 2010-08-12 | Secom Co Ltd | Transaction monitoring device |
| CN101808234A (en) * | 2010-02-09 | 2010-08-18 | 成都市华为赛门铁克科技有限公司 | Monitor processing method and system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700532A (en) * | 2013-12-11 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Video alarm method and video alarm device |
| CN104700532B (en) * | 2013-12-11 | 2018-03-09 | 杭州海康威视数字技术股份有限公司 | A kind of video alarm method and apparatus |
| CN104794827A (en) * | 2014-01-17 | 2015-07-22 | 温科尼克斯多夫国际有限公司 | Method and apparatus for prevention of false alarms in monitoring systems |
| CN104794827B (en) * | 2014-01-17 | 2021-01-08 | 温科尼克斯多夫国际有限公司 | Method and apparatus for avoiding false alarms in a surveillance system |
| CN104320388A (en) * | 2014-10-13 | 2015-01-28 | 杭州海兴电力科技股份有限公司 | S-FSK carrier based active alarming method |
| WO2017071084A1 (en) * | 2015-10-28 | 2017-05-04 | 小米科技有限责任公司 | Alarm method and device |
| US10147288B2 (en) | 2015-10-28 | 2018-12-04 | Xiaomi Inc. | Alarm method and device |
| CN108447208A (en) * | 2018-05-17 | 2018-08-24 | 普联技术有限公司 | Light warning method, equipment, web camera and storage medium |
| CN108447208B (en) * | 2018-05-17 | 2019-10-29 | 普联技术有限公司 | Light warning method, equipment, web camera and storage medium |
| WO2021223665A1 (en) * | 2020-05-08 | 2021-11-11 | 华为技术有限公司 | Method and device for reducing invalid warnings |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102479416B (en) | 2014-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102479416B (en) | Method and device for eliminating false alarm in monitoring system | |
| CN106412501B (en) | A kind of the construction safety behavior intelligent monitor system and its monitoring method of video | |
| CN106845890B (en) | Storage monitoring method and device based on video monitoring | |
| CN101334924B (en) | Fire hazard probe system and its fire hazard detection method | |
| KR101846537B1 (en) | Monitoring system for automatically selecting cctv, monitoring managing server for automatically selecting cctv and managing method thereof | |
| CN106897720A (en) | A kind of firework detecting method and device based on video analysis | |
| WO2022011828A1 (en) | System and method for detecting object that gets in and out of elevator, object detection system, elevator light curtain, and elevator device | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| US20080136934A1 (en) | Flame Detecting Method And Device | |
| CN102348128A (en) | Surveillance camera system having camera malfunction detection function | |
| CN110021133B (en) | All-weather fire-fighting fire patrol early-warning monitoring system and fire image detection method | |
| KR102207393B1 (en) | Expressway traffic monitoring system of transport information center CCTV using artificial intelligence | |
| CN109741565B (en) | Coal mine fire disaster recognition system and method | |
| CN113706523B (en) | Belt deviation and abnormal operation state monitoring method based on artificial intelligence technology | |
| CN107437318A (en) | A kind of visible ray Intelligent Recognition algorithm | |
| CN110441320B (en) | Coal gangue detection method, device and system | |
| EP2000998B1 (en) | Flame detecting method and device | |
| CN116310943B (en) | Method for sensing safety condition of workers | |
| CN111460917B (en) | Airport abnormal behavior detection system and method based on multi-mode information fusion | |
| CN112560816A (en) | Equipment indicator lamp identification method and system based on YOLOv4 | |
| CN110636281A (en) | Real-time monitoring camera shielding detection method based on background model | |
| CN109460705A (en) | Oil pipeline monitoring method based on machine vision | |
| CN114917519B (en) | Building intelligent fire control system | |
| CN111123251B (en) | Target object detection method and device of radar | |
| CN110728212A (en) | Road well lid monitoring device and method based on computer vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140813 Termination date: 20191129 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |