CN106600777A - Infrared array number-of-personnel sensor-based counting method and apparatus - Google Patents
Infrared array number-of-personnel sensor-based counting method and apparatus Download PDFInfo
- Publication number
- CN106600777A CN106600777A CN201611125413.8A CN201611125413A CN106600777A CN 106600777 A CN106600777 A CN 106600777A CN 201611125413 A CN201611125413 A CN 201611125413A CN 106600777 A CN106600777 A CN 106600777A
- Authority
- CN
- China
- Prior art keywords
- pixel
- personnel
- infrared
- sensor
- point
- 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
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Closed-Circuit Television Systems (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
An infrared array number-of-personnel sensor-based counting method and apparatus comprises the following steps: processing an output signal of an infrared array sensor arranged above a door, identifying the contour of human bodies, and tracking the movement direction of the contour; and judging personnel goes in or out according to the movement track of the contour to realize counting of personnel access to the door. A counting apparatus comprises a single-chip microcomputer system, and the infrared array sensor, a PIR sensor and a power supply circuit which are connected with the single-chip microcomputer system, and the single-chip microcomputer system acquires the infrared image of a detection area through the infrared array sensor, and detects whether personnel passes by the door or not through the PIR sensor. The counting method and the counting apparatus solve the problem of low detection precision of infrared emission and reception sensors in the process of multiple persons passing through the door, has the advantages of multi-target tracking, high identification precision and low power dissipation, is difficult to damage due to high installing position, has substantial advantages, and adapts to application promotion.
Description
Technical field
The present invention relates to a kind of personnel's method of counting and device, in particular, more particularly to it is a kind of based on infrared array
The method of counting and device of number sensor.
Background technology
Number sensor, also known as passenger flow counter, is a kind of a kind of sensor of statistician by quantity.Various
It is used widely in intelligence control system.Common number sensor main will have infrared emission and video identification two types.
Infrared two-way emission type number sensor includes transmitting terminal and receiving terminal, and they are separately mounted to the both sides at gate.Transmitting
End produces two infrared-rays, and receiving terminal is mainly forward-backward counter, two infrared-rays are blocked when being passed through by survey crew
The difference of priority, determines that personnel enter outgoing direction;By the counting to blocking pulse number, the number of turnover sensor personnel is calculated
Amount, both combine the purpose for reaching statistical number of person.This sensor construction is simple, easy for installation, low price.But number is counted
Precision is not high, and when especially many people pass through, personnel are interlaced, and sensor may count into an only people and pass through.It is only used for
The occasion not high to number error requirements.
Video identification number sensor adopts image processing techniquess, by the various shapes that personnel are entered with video sensing area
State is modeled, and based on motion target tracking and technology of identification, realization is entered outgoing direction to personnel and is identified, and respectively to turnover
Number realizes accurate count.This sensor counting precision is high, but price, needs good hardware and software to realize differentiating
Algorithm, while having high demands the ambient parameters such as search coverage illumination, is mainly used in counting number the high occasion of required precision.
Research and development are a kind of moderate, and the high number sensor of counting precision is an urgent demand of Based Intelligent Control.Take me as I am
Infrared array sensor number sensor.
The content of the invention
The present invention is in order to overcome the shortcoming of above-mentioned technical problem, there is provided a kind of meter based on infrared array number sensor
Counting method and device.
The method of counting based on infrared array number sensor of the present invention, it is characterised in that come real by the following method
It is existing:The output signal of the infrared sensor array to being arranged above doorway is processed, and identifies the profile produced by human body,
And the direction of motion to profile is tracked;Judge that by the movement locus of profile personnel enter or go out, to realize
Turnover personnel count.
The method of counting based on infrared array number sensor of the present invention, it is characterised in that set infrared sensor array
The top being arranged in door, the most lastrow pixel collection of its output image is near doorway region;Come especially by following steps
Realize:
A). personnel are determined whether through doorway, if no personnel pass through, execution step b);If personnel pass through, then hold
Row step c);B). ambient temperature value is calculated, the numerical value of infrared sensor array present frame is read, and by the original of all pixels point
Beginning data reduction is true temperature value;The N frame temperatures data that amount to by each pixel present frame and its before carry out meansigma methodss
Calculate, ambient temperature value of the meansigma methodss for obtaining as each pixel;Execution step a);C). the noise reduction process of background, reads
The initial data of all pixels point is scaled true temperature value by the numerical value of infrared sensor array present frame, and by present frame
Temperature value subtracting background temperature value, obtain the temperature approach of each pixel;If isolated picture of the temperature approach more than ± 0.5 DEG C
Vegetarian refreshments is present, then reset the temperature approach of respective pixel point;Then obtain the temperature approach of each pixel again by time filtering;
Execution step d);D). binary image is obtained, by the temperature approach of each pixel and threshold value VthIt is compared, if it exceeds
Threshold value VthThen pixel is set to 1, if being less than threshold value VthThen pixel is set to 0, to obtain the binary picture of present frame
Picture;Execution step e);E). profile is polymerized and characteristic point judges, by present frame binary image promising 1 pixel carry out
Spatial clustering, after to polymerization, the profile of pixel is analyzed, and identifies the profile that expression personnel are present;By the several of profile
The pixel for having maximum temperature difference value in what corresponding pixel in center or profile is labeled as characteristic point, and characteristic point is used as profile
The trace point of motion;Execution step f);F). the movement and generation of trace point, after a new two field picture occurs, sequentially pass through step d)
And same treatment e), in identifying a new two field picture, characteristic point is somebody's turn to do relative to the moving direction of characteristic point in previous frame image
Moving direction is the direction of motion of trace point, completes trace point movement or new trace point is produced;Execution step g);G). tracking
The judgement that point is removed, with the continuous output and the judgement of trace point kinestate of picture frame, for the trace point for having disappeared,
Record time and position that its last time occurs;If the time that trace point last time occurs, compared with current time, surpasses
Corresponding threshold T is crossedth, then show that the human body tracked by this characteristic point has moved out sensor lenses scope;Execution step
h);H). personnel's turnover judges and accumulates, if the direction of motion of a trace point is " by the corresponding most lastrow pixel in doorway
Point enter, and by remaining 3 direction outermost pixel disappear ", then be judged as personnel enter, plus 1 into number;If one
The direction of motion of individual trace point for " entered by the pixel of 3 direction outermosts of remaining in addition to doorway, it is and corresponding by doorway
Most lastrow pixel disappears ", then it is judged as that personnel go out, outgoing number adds 1.
The method of counting based on infrared array number sensor of the present invention, determines whether that personnel pass through door in step a)
Mouth is that the signal exported by pir sensor is judged, if the signal of pir sensor output exceedes the window door of setting
Limit, then it is assumed that have personnel to pass through, if be not above, then it is assumed that no personnel pass through.
Mean value calculation picture frame is participated in the method for counting based on infrared array number sensor of the present invention, step b)
Number is acquired image frame number in 5~20s, and the time filtering method described in step c) is:Ask for each picture in present frame
The arithmetic mean of instantaneous value of corresponding pixel points temperature value in vegetarian refreshments temperature value and former frame, the meansigma methodss of acquisition are used as in current frame image
The meansigma methodss of pixel;Threshold value V described in step d)thSize be inversely proportional to current outside temperature.
The method of counting based on infrared array number sensor of the present invention, the infrared sensor array are 8 pixel × 8
Pixel is exported, in step h), if trace point entered by 8 pixels in a line at gate, and from away from gate
Outermost 7 pixels of 8 pixels or both sides in a line disappear, then be judged as that personnel enter;If trace point by
Enter away from outermost 7 pixels of 8 pixels in a line at gate or both sides, and from a line at gate
8 pixels disappear, then be judged as that personnel go out.
The counting assembly based on infrared array number sensor of the present invention, it is characterised in that:Including Single Chip Microcomputer (SCM) system and
Coupled infrared sensor array, pir sensor and power circuit, the amplified filter circuit of pir sensor and monolithic
Machine system is connected, and power circuit provides stable voltage to the work of each circuit;Single Chip Microcomputer (SCM) system is sensed by infrared array
Device obtains the infrared image of detection zone, has detected whether personnel through doorway by pir sensor, and the Single Chip Microcomputer (SCM) system is also
It is connected with for exporting the communication interface circuit of people's numerical signal.
The counting assembly based on infrared array number sensor of the present invention, the Single Chip Microcomputer (SCM) system is by model
The chip composition of STM32F103, infrared sensor array pass through I2C buses are connected with Single Chip Microcomputer (SCM) system, communication interface circuit
Using RS485 communication interfaces.
The invention has the beneficial effects as follows:The method of counting based on infrared array number sensor and device of the present invention, leads to
The output signal for crossing the infrared sensor array to being arranged above doorway is processed, and identifies the profile produced by human body,
And the direction of motion to profile is tracked;Judge that by the movement locus of profile personnel enter or go out, to realize
Turnover personnel count.Solve the problems, such as that infrared two-way emission type sensor accuracy of detection when many people pass through is low, with multiple target with
High, the low in energy consumption advantage of track, accuracy of identification, as installation site is high, with non-damageable advantage, beneficial effect significantly, is fitted
In application.
The advantage of the method for counting based on infrared array number sensor and device of the present invention is embodied in:
1., number sensor is arranged on above gate, mutually will not be blocked when personnel pass through.Sensor can be tracked simultaneously simultaneously
Multiple targets so that the number counting precision of sensor, especially many people simultaneously by when counting precision compare infrared two-way emission type
Sensor has and increases substantially;
2., relative to video identification technology, low price many.There is no illumination requirement to erecting bed, evening is not any
As usual work in the case of illumination.Power consumption is also much lower than video identification;
3., easy for installation, without the need for needing respectively to install an equipment in gate both sides as infrared two-way emission type sensor, centre also needs to
Both are coupled together with cable.Array-type sensor only has an equipment, and easy for installation is more.
4., resistant to damage ability is strong, and sensor array installs 3 meters above gate of height, it is not easy to destroyed by personnel.Unlike
Infrared emission sensor, setting height(from bottom) only have 1 meter or so, are easy to suffer artificial damage.
Description of the drawings
Structural representations of the Fig. 1 for 8 × 8 thermopile array infrared sensors;
Imaging schematic diagrams of the Fig. 2 for infrared sensor array;
The circuit theory diagrams of the number sensor of Fig. 3 present invention;
Schematic diagrams of the Fig. 4 for current frame image;
Fig. 5 is ambient temperature value image;
Fig. 6 human motions and corresponding pixel shifting principle figure.
In figure:1 silicon substrate camera lens, 2 MEMS sensor chips, 3 digital ASIC chips;4 infrared sensor arrays, 5 PIR are passed
Sensor, 6 filtering and amplifying circuits, 7 Single Chip Microcomputer (SCM) system, 8 communication interface circuits, 9 power circuits.
Specific embodiment
The invention will be further described with embodiment below in conjunction with the accompanying drawings.
According to Seebeck effect, in the junction of two kinds of different materials, when their temperature is variant, can be at both
Electric current is produced in the closed loop circuit of material composition.This phenomenon is widely used in the temperature survey of thermocouple.
Thermoelectric pile or thermoelectric are made up of many thermocouple elements, and each thermocouple element is one different by two kinds
The filament of thermo-sensitive material composition.When difference occurs in the temperature at filament two ends, just voltage is generated at filament two ends.Thermal center point set
In in a very thin common uptake zone, i.e. measured zone.And cold node positioned at one be connected with surrounding enviroment it is high-quality
On amount fin.
As shown in figure 1, giving the structural representation of 8 × 8 thermopile array infrared sensors in the present invention, which is by silicon
Base camera lens 1, MEMS sensor chip 2 and digital ASIC chip 3 are constituted, and which is a 64 pixel infrared camera, using one
The compact SMD encapsulation changed, based on MEMS(MEMS Micro-Electro-Mechanical System)Technology.
Infrared sensor array can on the premise of testee is not contacted detecting object surface absolute temperature.With list
Point thermopile infrared sensor is compared with pyroelectric sensor, and it can not only detect mobile human body and object, additionally it is possible to visit
Appearance and position, the direction of motion and the accurate surface temperature of motionless human body and object are surveyed, temperature measurement range is -20 °
C~+100 °C.
As shown in Fig. 2 giving the imaging schematic diagram of infrared sensor array.Infrared sensor array is to detection zone
Realize that array relative temperature is detected, 2 dimensional region temperature detection is realized by 8 × 8 (64 pixels), support in short distance
The detection of absolute temperature, for heat source thermo(Particularly human body)Realize motion or the detection of resting state.Using I2C's
Numeral output, convenience and microprocessor communication.
Infrared array sensor possesses following characteristics:1., detect thermal source(Such as:Human body)Information:The quantity of people, the position of people
Put;2., detection temperature information:Environmental background temperature, heat source temperature;3. mode of operation, is can customize, optimal use effect is obtained
Really;4. parameter adjustment function is supported, the parameters such as sensitivity, context update speed can be set.
As shown in figure 3, give the circuit theory diagrams of the number sensor of invention, its by Single Chip Microcomputer (SCM) system 7 and with its phase
The infrared sensor array 4 of connection, pir sensor 5 and power circuit 9 are constituted, 5 amplified filter circuit 6 of pir sensor with it is single
Piece machine system 7 is connected, and power circuit 9 provides stable voltage to the work of each circuit.Single Chip Microcomputer (SCM) system have signals collecting,
The effect of data operation and controlled output.Single Chip Microcomputer (SCM) system 7 obtains the infrared figure of detection zone by infrared sensor array 4
Picture, has detected whether personnel through doorway by pir sensor 5, and Single Chip Microcomputer (SCM) system 7 is also associated with for exporting people's numerical signal
Communication interface circuit.Infrared sensor array 4 passes through I2C buses are connected with Single Chip Microcomputer (SCM) system 7.
Pir sensor 5 is an aiding sensors, mainly for detection of whether having personnel through sensor detection areas,
Blow the interference to infrared sensor array when opening wide at during avoiding switch gate or gate.The effect of filtering and amplifying circuit 6 be by
Faint pir sensor output signal be amplified to Single Chip Microcomputer (SCM) system correctly can process needed for level, while filter high frequency into
Point, prevent the generation of frequency alias phenomenon.
Single Chip Microcomputer (SCM) system completes whole number processing procedure, as the operand for needing is larger, have selected performance higher
STM32F103 is serial.Communication interface circuit employs RS-485 for people's numerical value of detection is transferred in various intelligence systems
Interface, host-host protocol employ Modbus-RTU.
The method of counting based on infrared array number sensor of the present invention, realizes especially by following steps:If red
Outer sensor array is arranged at the top in door, and the most lastrow pixel collection of its output image is near doorway region;
A). personnel are determined whether through doorway, if no personnel pass through, execution step b);If personnel pass through, then hold
Row step c);
If the infrared sensor array for adopting is 8 pixel × 8 pixel outputs, single-chip microcomputer is after analog port reads and amplifies
Pir sensor signal, by I2C buses are communicated with infrared sensor array, read the temperature initial data of 64 pixels
And it is scaled true temperature data.
In the step, determine whether that personnel are that the signal exported by pir sensor is judged through doorway, if
The signal of pir sensor output exceedes the window threshold of setting, then it is assumed that have personnel to pass through, if be not above, then it is assumed that do not have
There are personnel to pass through.For example, if the voltage range of the pir sensor output signal after amplifying is 0~5V, the signal of its output
Exceed(2.5±0.5)V, then it is assumed that have personnel to pass through;If voltage range is 0~3.3V, the signal for exporting exceedes(1.65
±0.5)V, then it is assumed that have personnel to pass through;Window threshold value Vth1, can also be set according to practical situation.
B). ambient temperature value is calculated, the numerical value of infrared sensor array present frame is read, and by the original of all pixels point
Data reduction is true temperature value;The N frame temperatures data that amount to by each pixel present frame and its before carry out meansigma methodss meter
Calculate, ambient temperature value of the meansigma methodss for obtaining as each pixel;Execution step a);
In search coverage, it is understood that there may be changeless other infrared heat sources, such as light fixture etc..Simultaneously infrared sensor array by
Difference when manufacture, there is also the inconsistent of each pixel background temperature value.Background value is exactly that these immobilize(Or
It is slowly varying with ambient temperature), data unrelated with number counting.
In the step, it is acquired image frame number in 5~20s to participate in mean value calculation number of image frames;If image
Frequency acquisition is 10 frames/s, then the number of image frames for participating in mean value calculation is 50~200 frames.
As shown in figure 4, the schematic diagram of current frame image is given, wherein different gray values represents different temperature,
After having carried out mean value calculation, acquired background image is as shown in Figure 5.
C). the noise reduction process of background, reads the numerical value of infrared sensor array present frame, by the original number of all pixels point
According to being scaled true temperature value, and by the temperature value subtracting background temperature value of present frame, obtain the temperature approach of each pixel;Such as
Isolated pixel point of the fruit with the presence of temperature approach more than ± 0.5 DEG C, then reset the temperature approach of respective pixel point;When then passing through again
Between filtering obtain each pixel temperature approach;Execution step d);
The data of infrared sensor array output in addition to the temperature data of normal detection, also with nominal ± 2 DEG C pink
Noise signal.Image just as shown in Fig. 4, this is that the number to us counts maximum interference, is that this must first carry out noise reduction
Computing.Conventional method is filtered using room and time, and using frame in, each pixel spot noise space filtering occurs
Randomness, general two neighbor pixels occur simultaneously noise probability it is extremely low the characteristics of, will appear from temperature difference data more than 0.5 DEG C
Isolated pixel point data directly reset.Time filtering is exactly to be filtered the same pixel point temperature difference data of each interframe, this
Sample just obtains the less or constant available signal that fluctuates.
Time filtering method can be adopted:Ask for each pixel temperature value and corresponding pixel points in former frame in present frame
The arithmetic mean of instantaneous value of temperature value, the meansigma methodss of the meansigma methodss of acquisition as pixel in current frame image.
D). binary image is obtained, by the temperature approach of each pixel and threshold value VthIt is compared, if it exceeds thresholding
Value VthThen pixel is set to 1, if being less than threshold value VthThen pixel is set to 0, to obtain the binary image of present frame;Hold
Row step e);
In the step, threshold value VthSize be inversely proportional to current outside temperature, due to extraneous temperature it is lower, human body and ring
The temperature difference in border is bigger, threshold value VthThat what is should chosen is larger;Extraneous temperature is higher, and human body is less with the temperature difference of environment, threshold value
VthThat what is should chosen is less.
E). profile is polymerized and characteristic point judges, by present frame binary image promising 1 pixel carry out space and gather
Close, the profile of pixel is analyzed after to polymerization, identify the profile that expression personnel are present;By the geometric center of profile
The pixel for having maximum temperature difference value in corresponding pixel or profile is labeled as characteristic point, and characteristic point is used as contour motion
Trace point;Execution step f);
F). the movement and generation of trace point, after a new two field picture occurs, step d) and same treatment e) are sequentially passed through, recognized
Go out moving direction of the characteristic point relative to characteristic point in previous frame image in a new two field picture, the moving direction is trace point
The direction of motion, completes trace point movement or new trace point is produced;Execution step g);
G). the judgement that trace point is removed, with the continuous output and the judgement of trace point kinestate of picture frame, for having disappeared
The trace point of mistake, records time and position that its last time occurs;If trace point last time occur time with it is current
Time is compared, and has exceeded corresponding threshold Tth, then show that the human body tracked by this characteristic point has moved out sensor lenses model
Enclose;Execution step h);
Threshold T in the stepthIt is the time value set by the speed for normally passing in and out doorway according to personnel.
H). personnel's turnover judges and accumulates, if the direction of motion of a trace point is " by the corresponding most lastrow in doorway
Pixel enter, and by remaining 3 direction outermost pixel disappear ", then be judged as personnel enter, plus 1 into number;Such as
Really the direction of motion of a trace point for " entered by the pixel of 3 direction outermosts of remaining in addition to doorway, and by doorway pair
The most lastrow pixel answered disappears ", then it is judged as that personnel go out, outgoing number adds 1.
If the infrared sensor array for adopting is 8 pixel × 8 pixel outputs, when trace point is beyond gate correspondence a line
8 pixels, are judged as personnel and go out;After trace point is entered from corresponding 8 pixels in gate, from other 3 directions
Outermost pixel(7 pixels of 8 pixels and both sides away from gate)Disappear, be then judged as that personnel enter
Enter.From gate, corresponding 8 pixels are entered, then outgoing from these pixels, then be judged as that personnel do not enter into;From except gate
Pixel for 3 direction outermosts is entered, then outgoing from these pixels, then be judged as that personnel do not go out.According to entrance
With the quantity of outgoing trace point, the quantity that personnel pass through just is obtained.
As shown in fig. 6, human motion and corresponding pixel shifting principle figure are given, if the installation side of situation 1
Formula, then personnel are entered by the side inside gate, opposite side is gone out, and personnel do not go out;If situation 2, illustrate personnel by
Enter outdoors greatly, disappear from opposite side, show there are personnel to enter.
Claims (7)
1. a kind of method of counting based on infrared array number sensor, it is characterised in that by the following method realizing:To setting
The output signal of the infrared sensor array being placed in above doorway is processed, and identifies the profile produced by human body, and to wheel
The wide direction of motion is tracked;Judge that by the movement locus of profile personnel enter or go out, to realize passing in and out people
Member counts.
2. the method for counting based on infrared array number sensor according to claim 1, it is characterised in that set infrared battle array
Sensor is arranged at the top in door, and the most lastrow pixel collection of its output image is near doorway region;Especially by with
Lower step is realizing:
A). personnel are determined whether through doorway, if no personnel pass through, execution step b);If personnel pass through, then hold
Row step c);
B). ambient temperature value is calculated, the numerical value of infrared sensor array present frame is read, and by the initial data of all pixels point
It is scaled true temperature value;The N frame temperatures data that amount to by each pixel present frame and its before carry out mean value calculation, obtain
Ambient temperature value of the meansigma methodss for arriving as each pixel;Execution step a);
C). the noise reduction process of background, reads the numerical value of infrared sensor array present frame, the initial data of all pixels point is changed
Calculate as true temperature value, and by the temperature value subtracting background temperature value of present frame, obtain the temperature approach of each pixel;If
Isolated pixel point of the temperature approach more than ± 0.5 DEG C is present, then reset the temperature approach of respective pixel point;Then filtered by the time again
Ripple obtains the temperature approach of each pixel;Execution step d);
D). binary image is obtained, by the temperature approach of each pixel and threshold value VthIt is compared, if it exceeds threshold value Vth
Then pixel is set to 1, if being less than threshold value VthThen pixel is set to 0, to obtain the binary image of present frame;Execution step
e);
E). profile is polymerized and characteristic point judges, by present frame binary image promising 1 pixel carry out spatial clustering,
After to polymerization, the profile of pixel is analyzed, and identifies the profile that expression personnel are present;By the geometric center pair of profile
There is in the pixel answered or profile the pixel of maximum temperature difference value to be labeled as characteristic point, characteristic point as contour motion with
Track point;Execution step f);
F). the movement and generation of trace point, after a new two field picture occurs, step d) and same treatment e) are sequentially passed through, recognized
Go out moving direction of the characteristic point relative to characteristic point in previous frame image in a new two field picture, the moving direction is trace point
The direction of motion, completes trace point movement or new trace point is produced;Execution step g);
G). the judgement that trace point is removed, with the continuous output and the judgement of trace point kinestate of picture frame, for having disappeared
The trace point of mistake, records time and position that its last time occurs;If trace point last time occur time with it is current
Time is compared, and has exceeded corresponding threshold Tth, then show that the human body tracked by this characteristic point has moved out sensor lenses model
Enclose;Execution step h);
H). personnel's turnover judges and accumulates, if the direction of motion of a trace point is " by the corresponding most lastrow pixel in doorway
Point enter, and by remaining 3 direction outermost pixel disappear ", then be judged as personnel enter, plus 1 into number;If one
The direction of motion of individual trace point for " entered by the pixel of 3 direction outermosts of remaining in addition to doorway, it is and corresponding by doorway
Most lastrow pixel disappears ", then it is judged as that personnel go out, outgoing number adds 1.
3. the method for counting based on infrared array number sensor according to claim 2, it is characterised in that:In step a)
Determine whether that personnel are that the signal exported by pir sensor is judged through doorway, if the letter of pir sensor output
Number exceed the window threshold of setting, then it is assumed that there are personnel to pass through, if be not above, then it is assumed that no personnel pass through.
4. the method for counting based on infrared array number sensor according to claim 2, it is characterised in that:In step b)
Mean value calculation number of image frames is participated in for acquired image frame number in 5~20s, the time filtering method described in step c)
For:The arithmetic mean of instantaneous value of each pixel temperature value and corresponding pixel points temperature value in former frame in present frame is asked for, acquisition
Meansigma methodss of the meansigma methodss as pixel in current frame image;Threshold value V described in step d)thSize and current outside temperature
It is inversely proportional to.
5. the method for counting based on infrared array number sensor according to claim 2, it is characterised in that:It is described infrared
Sensor array is 8 pixel × 8 pixel outputs, in step h), if trace point is by 8 pixels in a line at gate
Into, and outermost 7 pixels of 8 pixels or both sides from a line away from gate disappear, then judge for people
Member enters;If trace point by a line away from gate in outermost 7 pixels of 8 pixels or both sides enter,
And disappear from 8 pixels in a line at gate, then it is judged as that personnel go out.
6. a kind of counting assembly of the method for counting based on infrared array number sensor based on described in claim 1, which is special
Levy and be:Including Single Chip Microcomputer (SCM) system(7)And coupled infrared sensor array(4), pir sensor(5)With power supply electricity
Road(9), the amplified filter circuit of pir sensor(6)It is connected with Single Chip Microcomputer (SCM) system, power circuit is provided to the work of each circuit
Stable voltage;Single Chip Microcomputer (SCM) system obtains the infrared image of detection zone by infrared sensor array, is examined by pir sensor
Whether survey has personnel through doorway, and the Single Chip Microcomputer (SCM) system is also associated with for exporting the communication interface circuit of people's numerical signal
(8).
7. a kind of counting assembly of the method for counting based on infrared array number sensor according to claim 6, which is special
Levy and be:The Single Chip Microcomputer (SCM) system(7)It is made up of the chip of model STM32F103, infrared sensor array(4)By I2C
Bus is connected with Single Chip Microcomputer (SCM) system, communication interface circuit(8)Using RS485 communication interfaces.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611125413.8A CN106600777B (en) | 2016-12-09 | 2016-12-09 | Method of counting and device based on infrared array number sensor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611125413.8A CN106600777B (en) | 2016-12-09 | 2016-12-09 | Method of counting and device based on infrared array number sensor |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106600777A true CN106600777A (en) | 2017-04-26 |
CN106600777B CN106600777B (en) | 2019-02-22 |
Family
ID=58597939
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611125413.8A Active CN106600777B (en) | 2016-12-09 | 2016-12-09 | Method of counting and device based on infrared array number sensor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106600777B (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107358166A (en) * | 2017-06-16 | 2017-11-17 | 华南理工大学 | A kind of staircase mouth passenger flow congestion detection means and its passenger flow congestion level method of discrimination |
CN108152532A (en) * | 2017-12-29 | 2018-06-12 | 浙江摩根智能技术有限公司 | A kind of human body exists and mobile detection method |
CN108388178A (en) * | 2018-03-09 | 2018-08-10 | 昆山翰辉电子科技有限公司 | A kind of full angle infrared identification device |
CN108830311A (en) * | 2018-06-01 | 2018-11-16 | 南京邮电大学 | A kind of infrared image photovoltaic array recognition methods based on Adaboost |
CN108875701A (en) * | 2018-07-11 | 2018-11-23 | 温州亿通自动化设备有限公司 | A kind of inlet/outlet passenger number automatic statistics method |
CN109064619A (en) * | 2018-07-22 | 2018-12-21 | 薛永芳 | A kind of multiwindow queuing guide device |
CN109087434A (en) * | 2018-07-22 | 2018-12-25 | 薛永芳 | A kind of queuing guide device of limitation number |
CN110298433A (en) * | 2019-07-09 | 2019-10-01 | 杭州麦乐克科技股份有限公司 | A kind of indoor human body quantity survey (surveying) device |
WO2020051082A1 (en) * | 2018-09-06 | 2020-03-12 | Current Lighting Solutions, Llc | Sensor data array and method of counting occupants |
CN111158062A (en) * | 2020-01-06 | 2020-05-15 | 杭州涂鸦信息技术有限公司 | Human body existence detection method and system |
CN111768520A (en) * | 2020-06-04 | 2020-10-13 | 站坐(北京)科技有限公司 | Target detection device and method |
CN113298025A (en) * | 2021-06-11 | 2021-08-24 | 浙江华消科技有限公司 | Target object determination method and device, storage medium and electronic device |
CN113379772A (en) * | 2021-07-06 | 2021-09-10 | 新疆爱华盈通信息技术有限公司 | Mobile temperature measurement method based on background elimination and tracking algorithm in complex environment |
CN113611012A (en) * | 2021-06-16 | 2021-11-05 | 南京邮电大学 | Non-invasive people number detection method, device and system based on infrared array sensor |
CN113612939A (en) * | 2020-04-17 | 2021-11-05 | 上海邦定建筑科技有限公司 | Indoor personnel detection camera based on infrared sensing array |
EP3910531A1 (en) * | 2020-05-14 | 2021-11-17 | Kaba Gallenschütz GmbH | Method for detecting movements and passenger detection system |
CN114757907A (en) * | 2022-04-06 | 2022-07-15 | 上海擎测机电工程技术有限公司 | Data processing method of infrared sensor |
US20230003865A1 (en) * | 2019-11-04 | 2023-01-05 | Assa Abloy Ab | Detecting people using a people detector provided by a doorway |
US11928846B2 (en) | 2018-05-18 | 2024-03-12 | Essity Hygiene And Health Aktiebolag | Presence and absence detection |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07318661A (en) * | 1994-05-27 | 1995-12-08 | Matsushita Seiko Co Ltd | Human detection algorithm |
US6081619A (en) * | 1995-07-19 | 2000-06-27 | Matsushita Electric Industrial Co., Ltd. | Movement pattern recognizing apparatus for detecting movements of human bodies and number of passed persons |
CN102739919A (en) * | 2011-04-14 | 2012-10-17 | 江苏中微凌云科技股份有限公司 | Method and equipment for dynamic monitoring |
CN103279791A (en) * | 2013-05-30 | 2013-09-04 | 上海汇纳网络信息科技有限公司 | Pedestrian counting method based on multiple features |
CN103530874A (en) * | 2013-10-09 | 2014-01-22 | 上海大学 | People flow counting method on basis of Kinect |
CN103955980A (en) * | 2014-05-13 | 2014-07-30 | 温州亿通自动化设备有限公司 | Human body model feature based bus passenger flow statistic device and processing method |
CN104658088A (en) * | 2015-01-28 | 2015-05-27 | 四川君逸数码科技发展有限公司 | Novel human body infrared tracking and counting device and implementation method |
-
2016
- 2016-12-09 CN CN201611125413.8A patent/CN106600777B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07318661A (en) * | 1994-05-27 | 1995-12-08 | Matsushita Seiko Co Ltd | Human detection algorithm |
US6081619A (en) * | 1995-07-19 | 2000-06-27 | Matsushita Electric Industrial Co., Ltd. | Movement pattern recognizing apparatus for detecting movements of human bodies and number of passed persons |
CN102739919A (en) * | 2011-04-14 | 2012-10-17 | 江苏中微凌云科技股份有限公司 | Method and equipment for dynamic monitoring |
CN103279791A (en) * | 2013-05-30 | 2013-09-04 | 上海汇纳网络信息科技有限公司 | Pedestrian counting method based on multiple features |
CN103530874A (en) * | 2013-10-09 | 2014-01-22 | 上海大学 | People flow counting method on basis of Kinect |
CN103955980A (en) * | 2014-05-13 | 2014-07-30 | 温州亿通自动化设备有限公司 | Human body model feature based bus passenger flow statistic device and processing method |
CN104658088A (en) * | 2015-01-28 | 2015-05-27 | 四川君逸数码科技发展有限公司 | Novel human body infrared tracking and counting device and implementation method |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107358166A (en) * | 2017-06-16 | 2017-11-17 | 华南理工大学 | A kind of staircase mouth passenger flow congestion detection means and its passenger flow congestion level method of discrimination |
CN107358166B (en) * | 2017-06-16 | 2023-05-26 | 华南理工大学 | Escalator entrance passenger flow congestion detection device and passenger flow congestion degree judgment method thereof |
CN108152532A (en) * | 2017-12-29 | 2018-06-12 | 浙江摩根智能技术有限公司 | A kind of human body exists and mobile detection method |
CN108388178A (en) * | 2018-03-09 | 2018-08-10 | 昆山翰辉电子科技有限公司 | A kind of full angle infrared identification device |
US11928846B2 (en) | 2018-05-18 | 2024-03-12 | Essity Hygiene And Health Aktiebolag | Presence and absence detection |
CN108830311A (en) * | 2018-06-01 | 2018-11-16 | 南京邮电大学 | A kind of infrared image photovoltaic array recognition methods based on Adaboost |
CN108875701A (en) * | 2018-07-11 | 2018-11-23 | 温州亿通自动化设备有限公司 | A kind of inlet/outlet passenger number automatic statistics method |
CN109064619A (en) * | 2018-07-22 | 2018-12-21 | 薛永芳 | A kind of multiwindow queuing guide device |
CN109087434A (en) * | 2018-07-22 | 2018-12-25 | 薛永芳 | A kind of queuing guide device of limitation number |
US11107491B2 (en) | 2018-09-06 | 2021-08-31 | Current Lighting Solutions, Llc | Sensor data array and method of counting occupants |
WO2020051082A1 (en) * | 2018-09-06 | 2020-03-12 | Current Lighting Solutions, Llc | Sensor data array and method of counting occupants |
CN110298433A (en) * | 2019-07-09 | 2019-10-01 | 杭州麦乐克科技股份有限公司 | A kind of indoor human body quantity survey (surveying) device |
US20230003865A1 (en) * | 2019-11-04 | 2023-01-05 | Assa Abloy Ab | Detecting people using a people detector provided by a doorway |
CN111158062A (en) * | 2020-01-06 | 2020-05-15 | 杭州涂鸦信息技术有限公司 | Human body existence detection method and system |
CN113612939A (en) * | 2020-04-17 | 2021-11-05 | 上海邦定建筑科技有限公司 | Indoor personnel detection camera based on infrared sensing array |
EP3910531A1 (en) * | 2020-05-14 | 2021-11-17 | Kaba Gallenschütz GmbH | Method for detecting movements and passenger detection system |
CN111768520A (en) * | 2020-06-04 | 2020-10-13 | 站坐(北京)科技有限公司 | Target detection device and method |
CN111768520B (en) * | 2020-06-04 | 2023-01-24 | 站坐(北京)科技有限公司 | Target detection device and method |
CN113298025A (en) * | 2021-06-11 | 2021-08-24 | 浙江华消科技有限公司 | Target object determination method and device, storage medium and electronic device |
CN113611012A (en) * | 2021-06-16 | 2021-11-05 | 南京邮电大学 | Non-invasive people number detection method, device and system based on infrared array sensor |
CN113611012B (en) * | 2021-06-16 | 2023-02-14 | 南京邮电大学 | Non-invasive people number detection method, device and system based on infrared array sensor |
CN113379772B (en) * | 2021-07-06 | 2022-10-11 | 新疆爱华盈通信息技术有限公司 | Mobile temperature measurement method based on background elimination and tracking algorithm in complex environment |
CN113379772A (en) * | 2021-07-06 | 2021-09-10 | 新疆爱华盈通信息技术有限公司 | Mobile temperature measurement method based on background elimination and tracking algorithm in complex environment |
CN114757907A (en) * | 2022-04-06 | 2022-07-15 | 上海擎测机电工程技术有限公司 | Data processing method of infrared sensor |
Also Published As
Publication number | Publication date |
---|---|
CN106600777B (en) | 2019-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106600777A (en) | Infrared array number-of-personnel sensor-based counting method and apparatus | |
JP3233584B2 (en) | Passenger detection device | |
US11079482B2 (en) | Presence detection system | |
US11625828B2 (en) | Cost effective, mass producible system for rapid detection of fever conditions based on thermal imaging | |
Yang et al. | A novel low-cost and small-size human tracking system with pyroelectric infrared sensor mesh network | |
CN211717628U (en) | Intelligent through type lifting temperature measuring door | |
CN112084813B (en) | Abnormal target detection method, device and storage medium | |
CN107608002A (en) | Multi-sensor Fusion apparatus for detecting human body and detection method | |
TWI776798B (en) | Motion and presence detector | |
CN102256107B (en) | Automatic tracking system and method thereof for implementing automatic tracking | |
Luo et al. | Human tracking using ceiling pyroelectric infrared sensors | |
Hashimoto et al. | Development of people-counting system with human-information sensor using multi-element pyroelectric infrared array detector | |
JPH07159236A (en) | Heat source detector | |
US11195002B2 (en) | Method and system for image based occupancy detection | |
CN105890770A (en) | Human body state detection device based on pyroelectric technology | |
Altaf et al. | Usage of IR sensors in the HVAC systems, vehicle and manufacturing industries: A review | |
Faulkner et al. | Device-free localization using privacy-preserving infrared signatures acquired from thermopiles and machine learning | |
CN112771534A (en) | Electronic device and object counting method | |
WO2021165408A1 (en) | Systems and methods for infrared sensing | |
CN112347920A (en) | Intelligent people flow statistics and acquisition system based on neural network exhibition hall region | |
CN115778374B (en) | Fall detection method and system | |
JP2012103901A (en) | Intrusion object detection device | |
Wong et al. | Off-time swimming pool surveillance using thermal imaging system | |
CN207895648U (en) | Fire source probing apparatus and system | |
Chidurala et al. | IoT based Sensor System Design for Real-Time Non-Intrusive Occupancy Monitoring |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 250022 Second Floor 201-209, 24 Office Buildings, 24566 Jingshi Road, Huaiyin District, Jinan City, Shandong Province Applicant after: Jinan Sailingde Electronic Information Co., Ltd. Address before: Room 207 on the east side of the second floor of the office building of Jinan Foundry and Forging Research Institute, No. 646 Jingshi Road, Huaiyin District, Jinan City, Shandong Province Applicant before: Jinan Sine-lead Electronic Technology Co., Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |