CN106845344B - Demographics' method and device - Google Patents
Demographics' method and device Download PDFInfo
- Publication number
- CN106845344B CN106845344B CN201611163976.6A CN201611163976A CN106845344B CN 106845344 B CN106845344 B CN 106845344B CN 201611163976 A CN201611163976 A CN 201611163976A CN 106845344 B CN106845344 B CN 106845344B
- Authority
- CN
- China
- Prior art keywords
- information
- crowd
- demographics
- image
- video image
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
Abstract
The present invention provides a kind of Demographics' method and devices, belong to monitoring system technical field.Wherein, Demographics' method includes: to obtain in preset time, the occupied area ratio of crowd's image in every frame video image;By in preset time, all occupied area ratio is averaged, to obtain the crowd density information in preset time;Crowd density information and default crowd density information are compared, when crowd density information is greater than default crowd density information, generation alarm command.Therefore, the video image of acquisition can not only play the role of monitoring, and by the processing of the video image to acquisition, to the actual crowd density in preset time that can obtain of monitoring, and then greatly improve the convenience and applicability of monitoring system.
Description
Technical field
The present invention relates to monitoring system technical fields, in particular to a kind of Demographics' method and device.
Background technique
With the development of society, and microelectric technique, Video compression technology, network technology rapid development, prison
Control system cost increasingly reduces, therefore monitoring system is socially widely used.
Current monitoring system can be typically mounted at the public place discrepancy of Automatic Teller Machine, residential property, station, commercial circle
Mouthful or the opening hall of commercial circle in, and discrepancy to a large amount of crowds or stay realization monitoring.It is produced well by monitoring system
Economic benefit and social benefit.But in current existing monitoring technology, the function of monitoring system is more single, is merely able to realize
Video acquisition, and the function that the video of acquisition is played out or played back.Therefore, the monitoring system of traditional public area, often
It is to watch display screen in monitoring room found the abnormal situation by monitoring personnel.The mode of such direct surveillance is difficult to being monitored
The depth information of crowd is further obtained.To which single function has not only gradually been unable to satisfy monitoring system in each neck
The depth application in domain, and also seriously affected the convenience and applicability of monitoring system.
Therefore, how effectively to improve the convenience of monitoring system and applicability is current industry a great problem.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of crowd's quantity statistics method and device, it can be effective
Improve the convenience and applicability of monitoring system.
The embodiment of the present invention is achieved in that
In a first aspect, being applied to monitoring system, crowd's system the embodiment of the invention provides a kind of Demographics' method
Meter method includes: to obtain in preset time, the occupied area ratio of crowd's image in every frame video image.By preset time
Interior, all occupied area ratios are averaged, to obtain the crowd density information in preset time.The crowd is close
Degree information and default crowd density information be compared, when the crowd density information be greater than the default crowd density information,
Generate alarm command.
Further, it obtains in preset time, the occupied area ratio of crowd's image in video image described in every frame
Step, comprising: the video image described in every frame carries out edge detection, is obtained with filtering out the background in every frame video image
Crowd's image in video image described in every frame.The sum of all pixels for obtaining crowd's image described in every frame, according to crowd described in every frame
The ratio of the pixel summation of the sum of all pixels of image and the video image and obtain the occupied area ratio.
Further, Demographics' method further include: preset areas will be entered by the first preset boundary in video image
Each portrait in domain is marked, and obtains the coordinate of each labeled portrait.Tracking is each labeled described
The variation in the predeterminable area of the coordinate of portrait, when the coordinate is moved to positioned at the second pre- of the predeterminable area
It is accumulative once to pass through data if boundary.What is added up in the corresponding video image of acquisition preset time passes through data.
Further, it will be marked in video image by each portrait that the first preset boundary enters predeterminable area,
And before obtaining the coordinate step of each labeled portrait, further includes: obtain in video image by the first preset boundary
Into the trunk characteristic information and infrared thermal imaging information of each object of predeterminable area.It will be described in each object
Trunk characteristic information and default trunk characteristic information match and obtain the first similar value.By the described infrared of each object
Thermal imaging information and default subrange temperature information match and obtain the second similar value.When first similar value is greater than first
Preset threshold, second similar value determine that the trunk characteristic information of the object is also greater than the second preset threshold
Portrait.
Further, the default subrange temperature information is multiple, each default subrange temperature information
It is respectively positioned on one position of trunk, by the infrared thermal imaging information of each object and default subrange temperature information
The step of matching and obtaining the second similar value, comprising: by the infrared thermal imaging information of each object according to trunk
Position is divided into multiple local infrared thermal imaging information, and it is right to obtain the institute of the local infrared thermal imaging information in each object
The local average temperatures information answered.By in each object the local average temperatures information and trunk position it is identical
The default subrange temperature information is compared, if the local average temperatures information is located at the default local temperature model
Within the scope of enclosing information, then success is compared.The successfully local average temperature is compared according to all in each object
Degree information and all local average temperatures information compare and obtain second similar value of the object.
Second aspect, the embodiment of the invention provides a kind of Demographics' devices, are applied to monitoring system, crowd's system
Counter device includes: image processing module, for obtaining in preset time, the occupied area of crowd's image in every frame video image
Ratio.Data computation module is used in preset time, and all occupied area ratio is averaged, default to obtain
Crowd density information in time.Information comparison module, for by the crowd density information and default crowd density information into
Row compares, when the crowd density information is greater than the default crowd density information, generation alarm command.
Further, described image processing module includes: image extraction unit, is carried out for the video image described in every frame
Edge detection, crowd's image in video image described in the every frame obtained with filtering out the background in every frame video image.It is special
Comparing unit is levied, for obtaining the sum of all pixels of crowd's image described in every frame, according to the sum of all pixels of crowd's image described in every frame
The occupied area ratio is obtained with the ratio of the pixel summation of the video image.
Further, Demographics' device further include: mark module, for by video image by the first default side
Each portrait that boundary enters predeterminable area is marked, and obtains the coordinate of each labeled portrait.Tracking module,
For tracking the variation in the predeterminable area of the coordinate of each labeled portrait, when the coordinate is moved to
It is accumulative once to pass through data positioned at the second preset boundary of the predeterminable area.Computing module, it is corresponding for obtaining preset time
Video image in add up pass through data.
Further, Demographics' device further include: infrared module is preset for obtaining in video image by first
Boundary enters the trunk characteristic information and infrared thermal imaging information of each object of predeterminable area.First comparison module, is used for
The trunk characteristic information of each object and the matching of default trunk characteristic information are obtained into the first similar value.Second
Comparison module, for by the infrared thermal imaging information of each object and default subrange temperature information matching and
Obtain the second similar value.Processing module, for being greater than the first preset threshold, second similar value when first similar value
Greater than the second preset threshold, determine that the trunk characteristic information of the object is portrait.
Further, second comparison module includes: extraction unit, for by the described infrared of each object
Thermal imaging information is divided into multiple local infrared thermal imaging information according to trunk position, and obtains the part in each object
Local average temperatures information corresponding to infrared thermal imaging information presses the infrared thermal imaging information of each object
It is divided into multiple local infrared thermal imaging information according to trunk position, and obtains the letter of the local infrared thermal imaging in each object
The corresponding local average temperatures information of breath.Comparing unit, for by the local average temperatures in each object
Information and the identical default subrange temperature information of trunk position are compared, if the local average temperatures information bit
Within the scope of the default local temperature range information, then success is compared.Computing unit, for according to each target
All successfully the local average temperatures information and all local average temperatures information of comparing compare and obtain institute in object
State second similar value of object.
The beneficial effect of the embodiment of the present invention is:
Video image in preset time can successively be arranged and be formed by multi-frame video image sequentially in time.From
And Demographics' device, after getting the video image in preset time in preset time, Demographics' device can be by the view
Frequency image is split as the individual video image of multiframe.Demographics' device will include the image section of crowd in every frame video image
It extracts, to obtain crowd's image in every frame video image.Demographics' device calculates the shared of every frame crowd image
Area, just can be by comparing the occupied area of every frame crowd image with the occupied area of the frame video image, and then can
Obtain the ratio of the occupied area of every frame crowd image and the occupied area of the frame video image.
Furthermore Demographics' device calculates the occupied area and frame view of crowd's image of all frame numbers in preset time
After the ratio of the occupied area of frequency image, all occupied area ratio can be carried out the meter of average value by Demographics' device
It calculates.By the calculating of average value, Demographics' device just can obtain the average value of the occupied area ratio in preset time, into
And the average value is also the crowd density information of preset time video image.
The crowd density information and itself default crowd density information that Demographics' device will acquire are compared.Work as crowd
When density information comparison is compared greater than itself default crowd density information, crowd density is excessively high at this time, is prone to accidents.
Therefore, Demographics' device can generate alarm command to prompt.
Therefore, the video image of acquisition can not only play the role of monitoring, and pass through the place of the video image to acquisition
Reason, can obtain actual crowd density in preset time to monitoring, and then greatly improve the convenience of monitoring system
And applicability.
Other features and advantages of the present invention will be illustrated in subsequent specification, also, partly be become from specification
It is clear that being understood by implementing the embodiment of the present invention.The objectives and other advantages of the invention can be by written
Specifically noted structure is achieved and obtained in specification, claims and attached drawing.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.By the way that shown in attached drawing, above and other purpose of the invention, feature and advantage will be more clear.In whole
Identical appended drawing reference indicates identical part in attached drawing.Attached drawing, emphasis deliberately are not drawn by actual size equal proportion scaling
It is to show the gist of the present invention.
Fig. 1 shows a kind of structural block diagram of monitoring system provided in an embodiment of the present invention;
Fig. 2 shows the method streams of crowd density statistics in a kind of crowd's quantity statistics method provided in an embodiment of the present invention
Cheng Tu;
Fig. 3 shows the method flow of step S110 in a kind of crowd's quantity statistics method provided in an embodiment of the present invention
Figure;
Fig. 4 shows the method stream of crowd's quantity statistics in a kind of crowd's quantity statistics method provided in an embodiment of the present invention
Cheng Tu;
Fig. 5 shows the method flow of step S230 in a kind of crowd's quantity statistics method provided in an embodiment of the present invention
Figure;
Fig. 6 shows a kind of a kind of structural block diagram of Demographics' device provided in an embodiment of the present invention;
Fig. 7 shows the structural block diagram of image processing module in a kind of Demographics' device provided in an embodiment of the present invention;
Fig. 8 shows a kind of another structural block diagram of Demographics' device provided in an embodiment of the present invention;
Fig. 9 shows the structural block diagram of the second comparison module in a kind of Demographics' device provided in an embodiment of the present invention.
Icon: 100- monitoring system;200- Demographics' device;101- memory;102- storage control;103- processing
Device;104- Peripheral Interface;105- input-output unit;106- audio unit;107- display unit;210- image processing module;
211- image extraction unit;212- feature comparing unit;220- data computation module;230- information comparison module;310- is infrared
Module;The first comparison module of 320-;The second comparison module of 330-;331- extraction unit;332- comparing unit;333- calculates single
Member;340- processing module;350- mark module;360- tracking module;370- computing module.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Term " first ", " the
Two " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
As shown in Figure 1, being the structural block diagram of the monitoring system 100.The monitoring system 100 includes: Demographics' dress
Set 200, memory 101, storage control 102, processor 103, Peripheral Interface 104, input-output unit 105, audio unit
106, display unit 107.
The memory 101, storage control 102, processor 103, Peripheral Interface 104, input-output unit 105, sound
Frequency unit 106, each element of display unit 107 are directly or indirectly electrically connected between each other, to realize the transmission or friendship of data
Mutually.It is electrically connected for example, these elements can be realized between each other by one or more communication bus or signal wire.The crowd
Statistic device 200 include at least one can be stored in the form of software or firmware (firmware) in the memory 101 or
The software function module being solidificated in the operating system (operating system, OS) of Demographics' device 200.It is described
Processor 103 for executing the executable module stored in memory 101, such as Demographics' device 200 include it is soft
Part functional module or computer program.
Wherein, memory 101 may be, but not limited to, random access memory 101 (Random Access Memory,
RAM), read-only memory 101 (Read Only Memory, ROM), 101 (Programmable of programmable read only memory
Read-Only Memory, PROM), (the Erasable Programmable Read-Only of erasable read-only memory 101
Memory, EPROM), (the Electric Erasable Programmable Read-Only of electricallyerasable ROM (EEROM) 101
Memory, EEPROM) etc..Wherein, memory 101 is for storing program, the processor 103 after receiving and executing instruction,
Described program is executed, method performed by the server that the stream process that aforementioned any embodiment of the embodiment of the present invention discloses defines can
To be applied in processor 103, or realized by processor 103.
Processor 103 may be a kind of IC chip, the processing capacity with signal.Above-mentioned processor 103 can
To be general processor 103, including central processing unit 103 (Central Processing Unit, abbreviation CPU), network processes
Device 103 (Network Processor, abbreviation NP) etc.;It can also be digital signal processor 103 (DSP), specific integrated circuit
(ASIC), ready-made programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.It is general
Processor 103 can be microprocessor 103 or the processor 103 is also possible to any conventional processor 103 etc..
Various input/output devices are couple processor 103 and memory 101 by the Peripheral Interface 104.Some
In embodiment, Peripheral Interface 104, processor 103 and storage control 102 can be realized in one single chip.Other one
In a little examples, they can be realized by independent chip respectively.
Input-output unit 105 realizes user and the server (or local terminal) for being supplied to user input data
Interaction.The input-output unit 105 may be, but not limited to, mouse and keyboard etc..
Audio unit 106 provides a user audio interface, may include one or more microphones, one or more raises
Sound device and voicefrequency circuit.
Display unit 107 provides an interactive interface (such as user's operation circle between the monitoring system 100 and user
Face) or for display image data give user reference.In the present embodiment, the display unit 107 can be liquid crystal display
Or touch control display.It can be the capacitance type touch control screen or resistance of support single-point and multi-point touch operation if touch control display
Formula touch screen etc..Single-point and multi-point touch operation is supported to refer to that touch control display can sense on the touch control display one
Or at multiple positions simultaneously generate touch control operation, and the touch control operation that this is sensed transfer to processor 103 carry out calculate and
Processing.
Various input/output devices are couple processor 103 and memory 101 by the Peripheral Interface 104.Some
In embodiment, Peripheral Interface 104, processor 103 and storage control can be realized in one single chip.In some other reality
In example, they can be realized by independent chip respectively.
Input-output unit 105 is used to be supplied to the interaction that user input data realizes user and processing terminal.It is described defeated
Entering output unit 105 may be, but not limited to, mouse and keyboard etc..
Referring to Fig. 2, being the Demographics side applied to monitoring system shown in FIG. 1 that present pre-ferred embodiments provide
The method flow diagram of method.In the present embodiment, Demographics' device can obtain video figure by the video image that processing obtains
The area ratio shared by crowd's image as in, and reminded according to the size of shared area ratio.
Specifically, the process for obtaining area ratio shared by crowd's image in video image includes: step S110, step
S120 and step S130.
Step S110: it obtains in preset time, the occupied area ratio of crowd's image in video image described in every frame.
Demographics' device can get the collected video image of video capture device.In the present embodiment, crowd
Statistic device is to be segmented to obtain the collected video image of video capture device according to preset time.As a kind of mode, preset
Time can be certain period of time, such as: 30 seconds, one minute, two minutes etc..For the update iteration convenient for crowd density,
Preset time can be 30 seconds, but be not limited to 30 seconds.That is Demographics' device every 30 seconds acquisition primary video images, and
The video image obtained every time when it is 30 seconds a length of.Due to the characteristic of video image, every section of video image is by multi-frame video
Image forms the video image that can be played sequentially in time.To which Demographics' device gets one section of video image
Afterwards, Demographics' device can intercept video image simultaneously by video image according to the time interval between every two field pictures
It is split as multi-frame video image.Then, Demographics' device can in every frame video image include crowd image section into
Row extracts, and gets individual crowd's image in every frame video image.Demographics' device will acquire every frame video image
In crowd's image carry out the calculating of area, obtain the occupied area of every frame crowd image.Demographics' device passes through will be every
The occupied area of frame crowd's image is compared with the occupied area of the frame video image, just can be crossed and be obtained every frame crowd image in the frame
The ratio of occupied area in video image, and then the crowd that the ratio of the occupied area also represents in the frame video image is close
Degree.
Step S120: by preset time, all occupied area ratio is averaged, to obtain in preset time
Crowd density information.
Demographics' device calculates in preset time, the occupied area of crowd's image of all frame numbers and the frame video figure
After the ratio of the occupied area of picture.The ratio of all occupied areas can be carried out the calculating of average value by Demographics' device,
The ratio of occupied area that will be all is added, then divided by the frame number in the preset time.Pass through the calculating of average value, Ren Quntong
Counter device just can obtain the average value of the occupied area ratio in preset time, and then the average value is also preset time video
The crowd density information of image.Since every section of preset time is 30 seconds, thus when Demographics' device persistently obtains video image
When, if actual flow of the people changes, can also be changed with 30 seconds for the crowd density information of period, and then Demographics' device energy
Dynamic change crowd density information is exported, enough to reflect actual flow of the people variation.
Step S130: the crowd density information and default crowd density information are compared, when the crowd density
Information is greater than the default crowd density information, generates alarm command.
After Demographics' device gets the crowd density information in preset time, Demographics' device can also be will acquire
Crowd density information and itself default crowd density information be compared.As a kind of mode, presetting crowd density information can
Think 90%.When crowd density information comparison, which is greater than itself default crowd density information, to be compared, crowd density information is high
In 90%.Crowd density is excessively high at this time, is easy to happen and the safety accidents such as tramples.Therefore, Demographics' device can generate alarm
It instructs to external alert device and plays out, to prompt staff or user to pay attention to the life safety of itself.Due to video
Image is constantly updated, and carries out warning reminding so as to change according to actual flow of the people, to reach real-time accurate effect.
Referring to Fig. 3, Fig. 3 shows the method stream for obtaining the step S110 of occupied area ratio of every frame crowd image
Journey.Demographics' device first extracts every frame video image, then calculates the area of the crowd's image extracted.
Specifically, the sub-process for obtaining the occupied area ratio of every frame crowd image includes: step S111 and step S112.
Step S111: the video image described in every frame carries out edge detection, to filter out the background in every frame video image
And crowd's image in video image described in the every frame obtained.
In the present embodiment, carrying out edge detection to every frame video image can be used mixed Gauss model.Pass through detection
Each pixel in every frame video image, and judging the pixel is to belong to background image to still fall within crowd's image.
Specifically, being made of in every frame video image multiple pixels.Due to each pixel itself rgb value not
Together, so that multiple pixels can constitute the various scenery in image.Furthermore each picture can be calculated by mixed Gauss model
Gaussian component corresponding to the rgb value of vegetarian refreshments itself.Therefore, different, the corresponding Gaussian component of the rgb value of each pixel
It is different.As a kind of mode, preset background is trained by mixed Gauss model first, to obtain each pixel
Gaussian component, and by the default crowd Gauss of the default background Gaussian component of default background pixel point and default crowd's pixel
Component carries out classification storage.When practical application, by the pixel in every frame video image in a certain order by mixed
It closes Gauss model and calculates Gaussian component.It wherein, in a certain order can be with are as follows: from top to bottom, then from left to right, but simultaneously
It does not limit.By be compared with preset Gaussian component the Gaussian component of each pixel calculated, can receive
The pixel is to belong to background to still fall within crowd.After calculating Gaussian component, also need to carry out the edge of crowd's image
It is accurate to determine.Alternatively, the color of image of identical scenery is regarded as gradual change, and different scene images are then
It is regarded as mutation.Demographics' device obtains side corresponding to the rgb value of each pixel by boundary capacity calculation
Boundary's energy.When the boundary energy value of calculated two pixels is close or identical, then it is assumed that two pixels belong to same scenery
In, and the boundary energy of two pixels differs greatly, then two pixels are belonging respectively to different scenery.Pass through the meter of boundary energy
It calculates, just can accurately determine the boundary of crowd's image and background image.To just be extracted to crowd's image.
Step S112: obtaining the sum of all pixels of crowd's image described in every frame, total according to the pixel of crowd's image described in every frame
The ratio of several and the video image pixel summation and obtain the occupied area ratio.
The image of every frame can be made of multiple pixels, and the size of the image as captured by video capture equipment is solid
Fixed, so that the pixel value for each frame video image that Demographics' device obtains is fixed.Demographics' device will extract
Crowd's image carry out pixel calculating constitute the institute of crowd's image to get the summation of pixel in crowd's image
There is the summation of pixel.Demographics' device is total by pixel fixed in the sum of all pixels and video image in every frame crowd image
Number is compared to obtain a ratio result.Since each pixel all has certain area, the ratio result is also
Occupied area ratio of crowd's image in video image can be corresponded to, and then the occupied area ratio is also every frame video image
In crowd density value.
Referring to Fig. 4, Fig. 4 shows the method flow of crowd's quantity statistics.In the present embodiment, Demographics' device is not
It is counted into crowd density, Demographics' device is also to crowd's quantity in video image into statistics.Demographics' device
Each of video image is identified and is marked, by calculating everyone labeled coordinate situation of movement, thus
Everyone whether be displaced according to preset position got.If so, being counted, and then obtain in video image
Crowd's quantity.
Specifically, the method flow for obtaining crowd's quantity in video image includes: step S210, step S220, step
S230, step S240, step S250, step S260 and step S270.
Step S210: it is special to obtain the trunk that each object of predeterminable area is entered by the first preset boundary in video image
Reference breath and infrared thermal imaging information.
In video image, a region in image is set as the first preset boundary.Wherein, the first preset boundary can be with
It is multiple.By the way that the first preset boundary is arranged, then after the movement of object enters video image by the first preset boundary, just can
It is identified by Demographics' device.Trunk characteristic information is stored in Demographics' device, wherein trunk characteristic information
It can be with are as follows: the characteristic information for connecting the characteristic point of human body, i.e., by the connection of head and trunk and trunk and arm
Connection.After each object enters image by the first preset boundary, Demographics' device according to default characteristic point so as to
Obtain the trunk characteristic information of each object.
Furthermore since each object all has certain temperature, so that each object can give off infrared light.
For camera when obtaining into video image, can also receive each object can give off infrared light, and by its
Form infrared thermal imaging information.Demographics' device obtain video image in just can comprising each object it is infrared heat at
As information.
Step S220: the trunk characteristic information of each object and default trunk characteristic information are matched and obtained
Take the first similar value.
After Demographics' device gets the trunk characteristic information of each object, Demographics' device is by each object
Trunk characteristic information and default trunk characteristic information be compared.Default trunk characteristic information is Demographics' device memory
The trunk characteristic information of storage.Since object can be with are as follows: human body, vehicle or building etc..Therefore, Demographics' device is pressed
Trunk characteristic information according to each object of feature point extraction is different.Demographics' device is by the body of each object
When dry characteristic information and default trunk characteristic information compare and obtain the first similar value, according to head and trunk connection and
The connection of trunk and arm is compared.If two connection features compare matching, the first similar value is 100%;If only
There is one of aspect ratio to correct, then the first similar value is 50%;If two connection features mismatch, first is similar
Value is 0%.
Step S230: by the infrared thermal imaging information of each object and default subrange temperature information
Match and obtains the second similar value.
Due to the difference of temperature, the wavelength of infrared light is also different.Demographics' device gets the infrared of each object
After thermal imaging information, Demographics' device according to infrared thermal imaging medium wave long message, will acquire the infrared heat of each object at
As information corresponding conversion is temperature information.In the present embodiment, the position of object is different, and corresponding temperature is also different.For just
In being compared, all temperature informations of each object are averaged by Demographics' device, to obtain each object
Mean temperature information.As a kind of mode, Demographics' device is stored with default subrange temperature information.Default part model
Enclose the range that temperature information is a temperature.Demographics' device is by the infrared thermal imaging information of each object and presets part
Range temperature information matches and when the second similar value obtained, if the temperature information of object is in default subrange temperature information
Within, then the second similar value be 100%, if the temperature information of object other than default subrange temperature information, second
Similar value is 0%.
Step S240: when first similar value is greater than the first preset threshold, second similar value is pre- also greater than second
If threshold value, determine that the trunk characteristic information of the object is portrait.
The first preset threshold and the second preset threshold are also preset in Demographics' device, it is pre- as a kind of mode, first
If threshold value can be 40%, and the second preset threshold is also 40%.The first similar value after comparison is greater than the first preset threshold,
And compare after the second similar value also greater than the second preset threshold when, Demographics' device determines that the feature of the object meets people
Body characteristics, so that the object is determined as portrait.
Step S250: will be marked in video image by each portrait that the first preset boundary enters predeterminable area,
And obtain the coordinate of each labeled portrait.
After object enters video image by the first preset boundary, and Demographics' device determines target for portrait, people
The portrait is marked in group's statistic device, wherein mark point is the central point of the portrait.Since Demographics' device can will regard
Frequency image analysis is a two-dimensional coordinate system, so that the portrait after entering video image by the first preset boundary, can be located at
A certain position in video image.Demographics' device just can obtain the coordinate of the portrait mark point.
Step S260: the variation in the predeterminable area of the coordinate for the portrait that tracking is each labeled, when
The coordinate is moved to the second preset boundary positioned at the predeterminable area, accumulative once to pass through data.
After the coordinate of Demographics' device portrait mark point, if portrait moves in video image, correspondingly, the people
Also corresponding variation, Demographics' device can track the variation of the coordinate of each portrait to the coordinate of picture.
As a kind of mode, another or multiple regions of video image are set as the second preset boundary, it is corresponding, second
Preset boundary also has coordinate in video image.When the coordinate of changes in coordinates to the second preset boundary of tracked portrait is identical
When, portrait is also moved to the second preset boundary accordingly.At this point, Demographics' device determines that the portrait passes through video image,
And accumulative primary counting.It is appreciated that movement side just can be set by the first preset boundary of setting and the second preset boundary
To, and the portrait of the direction is determined and counted.
Step S270: what is added up in the corresponding video image of acquisition preset time passes through data.
In the present embodiment, the preset time of corresponding crowd's quantity can be longer, can be with are as follows: 1 hour, 2 hours or 3 are small
When etc., it is not limited here.Demographics' device can be counted in preset time by the portrait of the second preset boundary,
Pass through total quantity to just obtain preset time crowd.Due to being set by the first preset boundary and the second preset boundary
Moving direction is determined, Demographics' device just can obtain in preset time, pass through total quantity according to the crowd of preset direction.
Referring to Fig. 5, Fig. 5 shows the method for obtaining the step S230 of the second similar value by infrared thermal imaging information
Process.In the present embodiment, Demographics' device is by setting regional area to object, and believes respectively each local temperature
Breath is matched and obtains the second similar value.
Specifically, the method flow for obtaining the second similar value includes: step S231, step S232 and step S233.
Step S231: the infrared thermal imaging information of each object is divided into multiple parts according to trunk position
Infrared thermal imaging information, and obtain local average temperatures corresponding to the local infrared thermal imaging information in each object
Information.
After Demographics' device obtains the infrared thermal imaging information of each object, Demographics' device is according to preset spy
The infrared thermal imaging information of each object is divided into multiple local infrared thermal imaging information, i.e. Demographics' device by sign region
What is obtained is thermodynamic chart corresponding to the local infrared thermal imaging information of each characteristic area.As a kind of mode, characteristic area
It can be with are as follows: head zone, torso area and arm regions.Each characteristic area all has certain area, thus in each spy
There is also difference for local infrared thermal imaging information in sign region, it can be understood as, the thermodynamic chart in each characteristic area is simultaneously
It is not only a kind of color, but various temperature corresponding to multiple color.For convenient for subsequent matching, Demographics' device is first
The area ratio of area corresponding to each color and characteristic area in each thermodynamic chart will be calculated, then each color institute is right
The temperature answered multiplied by the color area ratio, and by after each product addition divided by the number of colors in characteristic area, thus
Demographics' device just obtains the local average temperatures information in each characteristic area.
Step S232: by each object the local average temperatures information and trunk position it is identical described
Default subrange temperature information is compared, if the local average temperatures information is located at the default local temperature range letter
Within the scope of breath, then success is compared.
The default subrange temperature letter of each characteristic area is stored in Demographics' device according further to characteristic area
Breath.As a kind of mode, presetting subrange temperature information is also a temperature range.Demographics' device is by each characteristic area
Local average temperatures information and default subrange temperature information in domain are compared.Alternatively, comparison can be with
It is characterized the corresponding of region to compare, i.e. the default local average temperatures of the local average temperatures information of head zone and head zone
Information comparison, the local average temperatures information of torso area and the default local average temperatures information comparison of torso area, arm
The local average temperatures information in region and the default local average temperatures information comparison of arm regions.When the part in characteristic area
Mean temperature information is fallen within the scope of default subrange temperature information, then compares success, conversely, then comparing failure.
Step S233: it compares the successful local average temperatures information according to all in each object and owns
The local average temperatures information compares and obtains second similar value of the object.
In the present embodiment, the characteristic area of each object be three, be respectively as follows: head zone, torso area and
Arm regions, corresponding local average temperatures information are also three.When three regions compare success, three are compared successfully
The ratio of local average temperatures information and all local average temperatures information is 100%, so that Demographics' device can be sentenced
Fixed second similar value is 100%.When two regions compare success, two compare successful local average temperatures information and own
Local average temperatures information ratio be 67%, thus Demographics' device can determine the second similar value be 67%.When only
There is a region to compare success, one compares successful local average temperatures information and all local average temperatures information
Ratio is 33%, so that Demographics' device can determine that the second similar value is 33%.And when three regions compare it is unsuccessful,
The ratio for comparing successful local average temperatures information and all local average temperatures information is 0%, so that Demographics fill
It sets and can determine that the second similar value is 0%.Therefore, Demographics' device compares the ratio of successfully region and overall area by obtaining
Just the second similar value can be got.
Referring to Fig. 6, Fig. 6 is the Demographics provided in an embodiment of the present invention applied to monitoring system 100 shown in FIG. 1
A kind of structural block diagram of device 200.The device includes: image processing module 210, data computation module 220, information comparison
Module 230.
Image processing module 210, for obtaining in preset time, crowd's image in video image described in every frame it is shared
Area ratio.
Data computation module 220, for by preset time, all occupied area ratio to be averaged, to obtain
Take the crowd density information in preset time.
Information comparison module 230 works as institute for the crowd density information and default crowd density information to be compared
Crowd density information is stated greater than the default crowd density information, generates alarm command.
Referring to Fig. 7, Fig. 7 is the knot of image processing module 210 in Demographics' device 200 provided in an embodiment of the present invention
Structure block diagram.The image processing module 210 includes: image extraction unit 211 and feature comparing unit 212.
Image extraction unit 211 carries out edge detection for the video image described in every frame, to filter out every frame video figure
Crowd's image in video image described in background as in and every frame for obtaining;
Feature comparing unit 212 is schemed for obtaining the sum of all pixels of crowd's image described in every frame according to crowd described in every frame
The ratio of the pixel summation of the sum of all pixels of picture and the video image and obtain the occupied area ratio.
Referring to Fig. 8, Fig. 8 shows another structural block diagram of Demographics' device 200 provided in an embodiment of the present invention.It should
Crowd's statistic device 200: infrared module 310, the first comparison module 320, the second comparison module 330, processing module 340, mark
Remember module 350, tracking module 360, computing module 370.
Infrared module 310, for obtaining each object for entering predeterminable area in video image by the first preset boundary
Trunk characteristic information and infrared thermal imaging information;
First comparison module 320, for by the trunk characteristic information of each object and default trunk feature
Information matches and obtain the first similar value;
Second comparison module 330, for by the infrared thermal imaging information of each object and default local model
It encloses temperature information matching and obtains the second similar value;
Processing module 340, for when first similar value be greater than the first preset threshold, second similar value also greater than
Second preset threshold determines that the trunk characteristic information of the object is portrait.
Mark module 350, for by video image by the first preset boundary enter each portrait of predeterminable area into
Line flag, and obtain the coordinate of each labeled portrait;
Tracking module 360, for track each labeled portrait the coordinate in the predeterminable area
Variation, it is accumulative once to pass through data when the coordinate is moved to the second preset boundary positioned at the predeterminable area;
Computing module 370, for obtain in the corresponding video image of preset time add up pass through data.
Referring to Fig. 9, Fig. 9 is the knot of the second comparison module 330 in Demographics' device 200 provided in an embodiment of the present invention
Structure block diagram, second comparison module 330 include: extraction unit 331, comparing unit 332 and computing unit 333.
Extraction unit 331, for the infrared thermal imaging information of each object to be divided into according to trunk position
Multiple part infrared thermal imaging information, and obtain part corresponding to the local infrared thermal imaging information in each object
It is infrared that the infrared thermal imaging information of each object is divided into multiple parts according to trunk position by mean temperature information
Thermal imaging information, and obtain the letter of local average temperatures corresponding to the local infrared thermal imaging information in each object
Breath;
Comparing unit 332, for by the local average temperatures information and trunk position phase in each object
The same default subrange temperature information is compared, if the local average temperatures information is located at the default part temperature
It spends within the scope of range information, then compares success;
Computing unit 333, for being believed according to the successfully local average temperatures that compare all in each object
Breath and all local average temperatures information compare and obtain second similar value of the object.
It should be noted that due to it is apparent to those skilled in the art that, for the convenience and letter of description
Clean, system, the specific work process of device and unit of foregoing description can be with reference to corresponding in preceding method embodiment
Journey, details are not described herein.
In conclusion the embodiment of the invention provides a kind of Demographics' method and devices, in crowd's statistical method
In, it can successively arrange and form by multi-frame video image sequentially in time by the video image in preset time.To
For Demographics' device after getting the video image in preset time in preset time, Demographics' device can be by the video
Image is split as the individual video image of multiframe.Demographics' device by every frame video image include crowd image section into
Row extracts, to obtain crowd's image in every frame video image.Demographics' device calculates the shared face of every frame crowd image
Product, just can be by comparing the occupied area of every frame crowd image with the occupied area of the frame video image, and then can obtain
Obtain the ratio of the occupied area of every frame crowd image and the occupied area of the frame video image.
Furthermore Demographics' device calculates the occupied area and frame view of crowd's image of all frame numbers in preset time
After the ratio of the occupied area of frequency image, all occupied area ratio can be carried out the meter of average value by Demographics' device
It calculates.By the calculating of average value, Demographics' device just can obtain the average value of the occupied area ratio in preset time, into
And the average value is also the crowd density information of preset time video image.
The crowd density information and itself default crowd density information that Demographics' device will acquire are compared.Work as crowd
When density information comparison is compared greater than itself default crowd density information, crowd density is excessively high at this time, is prone to accidents.
Therefore, Demographics' device can generate alarm command to prompt.
Therefore, the video image of acquisition can not only play the role of monitoring, and pass through the place of the video image to acquisition
Reason, can obtain actual crowd density in preset time to monitoring, and then greatly improve the convenience of monitoring system
And applicability.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (8)
1. a kind of Demographics' method, which is characterized in that be applied to monitoring system, Demographics' method includes:
It obtains in preset time, the occupied area ratio of crowd's image in every frame video image;
By in preset time, all occupied area ratio is averaged, to obtain the letter of the crowd density in preset time
Breath;
The crowd density information and default crowd density information are compared, when the crowd density information is greater than described pre-
If crowd density information, alarm command is generated;
Wherein, the method also includes:
It obtains in video image and the trunk characteristic information of each object of predeterminable area and infrared is entered by the first preset boundary
Thermal imaging information;
The trunk characteristic information of each object and the matching of default trunk characteristic information are obtained into the first similar value;
The infrared thermal imaging information of each object and the matching of default subrange temperature information are obtained second
Similar value;
When first similar value is greater than the first preset threshold, second similar value determines institute also greater than the second preset threshold
The trunk characteristic information for stating object is portrait.
2. Demographics' method according to claim 1, which is characterized in that obtain in preset time, video described in every frame
The step of occupied area ratio of crowd's image in image, comprising:
The video image described in every frame carries out edge detection, the every frame institute obtained to filter out the background in every frame video image
State crowd's image in video image;
The sum of all pixels for obtaining crowd's image described in every frame, according to the sum of all pixels of crowd's image described in every frame and the video figure
The ratio of the pixel summation of picture and obtain the occupied area ratio.
3. Demographics' method according to claim 1, which is characterized in that Demographics' method further include:
It is marked each of predeterminable area portrait is entered by first preset boundary in the video image, and
Obtain the coordinate of each labeled portrait;
The variation in the predeterminable area of the coordinate for the portrait that tracking is each labeled, when the coordinate is moved to
It is accumulative once to pass through data positioned at the second preset boundary of the predeterminable area;
What is added up in the corresponding video image of acquisition preset time passes through data.
4. Demographics' method according to claim 3, which is characterized in that the default subrange temperature information is more
A, each default subrange temperature information is respectively positioned on one position of trunk, by the described infrared of each object
The step of thermal imaging information and default subrange temperature information match and obtain the second similar value, comprising:
The infrared thermal imaging information of each object is divided into multiple local infrared thermal imaging letters according to trunk position
Breath, and obtain local average temperatures information corresponding to the local infrared thermal imaging information in each object;
By the local average temperatures information and the identical default subrange of trunk position in each object
Temperature information is compared, if the local average temperatures information be located at the range of the default local temperature range information with
It is interior, then compare success;
Successfully the local average temperatures information and all local averages are compared according to all in each object
Temperature information compares and obtains second similar value of the object.
5. a kind of Demographics' device, which is characterized in that be applied to monitoring system, Demographics' device includes:
Image processing module, for obtaining in preset time, the occupied area ratio of crowd's image in every frame video image;
Data computation module, for by preset time, all occupied area ratio to be averaged, when obtaining default
Interior crowd density information;
Information comparison module, for the crowd density information and default crowd density information to be compared, as the crowd
Density information is greater than the default crowd density information, generates alarm command;
Wherein, Demographics' device further include:
Infrared module, it is special for obtaining the trunk for entering each object of predeterminable area by the first preset boundary in video image
Reference breath and infrared thermal imaging information;
First comparison module, for matching the trunk characteristic information of each object and default trunk characteristic information
And obtain the first similar value;
Second comparison module, for believing the infrared thermal imaging information of each object and default subrange temperature
Breath matches and obtains the second similar value;
Processing module, for being greater than the first preset threshold when first similar value, second similar value is pre- also greater than second
If threshold value, determine that the trunk characteristic information of the object is portrait.
6. Demographics' device according to claim 5, which is characterized in that described image processing module includes:
Image extraction unit carries out edge detection for the video image described in every frame, to filter out in every frame video image
Crowd's image in video image described in background and every frame for obtaining;
Feature comparing unit, for obtaining the sum of all pixels of crowd's image described in every frame, according to the picture of crowd's image described in every frame
The ratio of the pixel summation of plain sum and the video image and obtain the occupied area ratio.
7. Demographics' device according to claim 5, which is characterized in that Demographics' device further include:
Mark module, for each of predeterminable area portrait will to be entered by first preset boundary in the video image
It is marked, and obtains the coordinate of each labeled portrait;
Tracking module, the variation in the predeterminable area of the coordinate for tracking each labeled portrait, when
The coordinate is moved to the second preset boundary positioned at the predeterminable area, accumulative once to pass through data;
Computing module, for obtain in the corresponding video image of preset time add up pass through data.
8. Demographics' device according to claim 7, which is characterized in that second comparison module includes:
Extraction unit, for the infrared thermal imaging information of each object to be divided into multiple parts according to trunk position
Infrared thermal imaging information, and obtain local average temperatures corresponding to the local infrared thermal imaging information in each object
The infrared thermal imaging information of each object is divided into multiple local infrared thermal imaging letters according to trunk position by information
Breath, and obtain local average temperatures information corresponding to the local infrared thermal imaging information in each object;
Comparing unit, for by each object the local average temperatures information and trunk position it is identical described
Default subrange temperature information is compared, if the local average temperatures information is located at the default local temperature range letter
Within the scope of breath, then success is compared;
Computing unit, for comparing the successful local average temperatures information according to all in each object and owning
The local average temperatures information compares and obtains second similar value of the object.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611163976.6A CN106845344B (en) | 2016-12-15 | 2016-12-15 | Demographics' method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611163976.6A CN106845344B (en) | 2016-12-15 | 2016-12-15 | Demographics' method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106845344A CN106845344A (en) | 2017-06-13 |
CN106845344B true CN106845344B (en) | 2019-10-25 |
Family
ID=59140018
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611163976.6A Active CN106845344B (en) | 2016-12-15 | 2016-12-15 | Demographics' method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106845344B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107180542A (en) * | 2017-07-14 | 2017-09-19 | 安徽智星交通科技股份有限公司 | Traffic control method, apparatus and system |
CN108289206B (en) * | 2018-02-13 | 2021-02-26 | 山东顺国电子科技有限公司 | Civil air defense visualization method, device and system |
CN109101888B (en) * | 2018-07-11 | 2022-06-14 | 南京农业大学 | Visitor flow monitoring and early warning method |
CN108921137A (en) * | 2018-08-01 | 2018-11-30 | 深圳市旭发智能科技有限公司 | A kind of unmanned plane and storage medium |
CN110008834B (en) * | 2019-02-28 | 2021-04-06 | 中电海康集团有限公司 | Steering wheel intervention detection and statistics method based on vision |
CN110263619A (en) * | 2019-04-30 | 2019-09-20 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and computer storage medium |
CN110472599B (en) * | 2019-08-20 | 2021-09-03 | 北京海益同展信息科技有限公司 | Object quantity determination method and device, storage medium and electronic equipment |
CN110852208B (en) * | 2019-10-29 | 2023-06-02 | 贵州民族大学 | Crowd density estimation method and readable storage medium |
CN111405239B (en) * | 2020-02-17 | 2021-08-31 | 浙江大华技术股份有限公司 | Monitoring method, server, monitoring system, and computer-readable storage medium |
CN113537172B (en) * | 2021-09-16 | 2021-12-10 | 长沙海信智能系统研究院有限公司 | Crowd density determination method, device, equipment and storage medium |
CN115083112B (en) * | 2022-08-22 | 2022-11-22 | 枫树谷(成都)科技有限责任公司 | Intelligent early warning emergency management system and deployment method thereof |
CN116129361B (en) * | 2023-03-24 | 2023-08-08 | 武汉中科通达高新技术股份有限公司 | Crowd gathering identification method and device based on distance measurement |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101587537A (en) * | 2008-05-21 | 2009-11-25 | 上海新联纬讯科技发展有限公司 | Method and system of crowd density statistics based on intelligent video identification technology |
CN102750539A (en) * | 2012-06-06 | 2012-10-24 | 深圳市海亿达能源科技股份有限公司 | Device and method for counting regional space population |
CN104061662A (en) * | 2014-07-17 | 2014-09-24 | 珠海格力电器股份有限公司 | Human body detecting method, device and air conditioner |
CN104463121A (en) * | 2014-12-08 | 2015-03-25 | 北京市新技术应用研究所 | Crowd density information obtaining method |
CN104820995A (en) * | 2015-04-21 | 2015-08-05 | 重庆大学 | Large public place-oriented people stream density monitoring and early warning method |
CN105243418A (en) * | 2015-11-18 | 2016-01-13 | 桂林电子科技大学 | Pedestrian flow counting method and device based on infrared temperature measurement sensor |
CN105303159A (en) * | 2015-09-17 | 2016-02-03 | 中国科学院合肥物质科学研究院 | Far-infrared pedestrian detection method based on distinctive features |
WO2016174659A1 (en) * | 2015-04-27 | 2016-11-03 | Snapaid Ltd. | Estimating and using relative head pose and camera field-of-view |
CN106096561A (en) * | 2016-06-16 | 2016-11-09 | 重庆邮电大学 | Infrared pedestrian detection method based on image block degree of depth learning characteristic |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011067790A2 (en) * | 2009-12-02 | 2011-06-09 | Tata Consultancy Services Limited | Cost-effective system and method for detecting, classifying and tracking the pedestrian using near infrared camera |
-
2016
- 2016-12-15 CN CN201611163976.6A patent/CN106845344B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101587537A (en) * | 2008-05-21 | 2009-11-25 | 上海新联纬讯科技发展有限公司 | Method and system of crowd density statistics based on intelligent video identification technology |
CN102750539A (en) * | 2012-06-06 | 2012-10-24 | 深圳市海亿达能源科技股份有限公司 | Device and method for counting regional space population |
CN104061662A (en) * | 2014-07-17 | 2014-09-24 | 珠海格力电器股份有限公司 | Human body detecting method, device and air conditioner |
CN104463121A (en) * | 2014-12-08 | 2015-03-25 | 北京市新技术应用研究所 | Crowd density information obtaining method |
CN104820995A (en) * | 2015-04-21 | 2015-08-05 | 重庆大学 | Large public place-oriented people stream density monitoring and early warning method |
WO2016174659A1 (en) * | 2015-04-27 | 2016-11-03 | Snapaid Ltd. | Estimating and using relative head pose and camera field-of-view |
CN105303159A (en) * | 2015-09-17 | 2016-02-03 | 中国科学院合肥物质科学研究院 | Far-infrared pedestrian detection method based on distinctive features |
CN105243418A (en) * | 2015-11-18 | 2016-01-13 | 桂林电子科技大学 | Pedestrian flow counting method and device based on infrared temperature measurement sensor |
CN106096561A (en) * | 2016-06-16 | 2016-11-09 | 重庆邮电大学 | Infrared pedestrian detection method based on image block degree of depth learning characteristic |
Non-Patent Citations (2)
Title |
---|
《Pedestrian detection by means of far-infrared stereo vision》;Dip.Ing.Informazione et al;;《Computer Vision and Image Understanding》;20071231;第194–204页; * |
《基于图像局部区域梯度特征描述的红外人体识别算法》;云廷进;《光学技术》;20050531;第34卷(第3期);第441-448页; * |
Also Published As
Publication number | Publication date |
---|---|
CN106845344A (en) | 2017-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106845344B (en) | Demographics' method and device | |
Hsieh et al. | A real time hand gesture recognition system using motion history image | |
Foggia et al. | Real-time fire detection for video-surveillance applications using a combination of experts based on color, shape, and motion | |
TW201911130A (en) | Method and device for remake image recognition | |
CN105913037A (en) | Face identification and radio frequency identification based monitoring and tracking system | |
US20170039455A1 (en) | Computer-vision based security system using a depth camera | |
WO2019194091A1 (en) | Intrusion detection system and intrusion detection method | |
CN105187786A (en) | Voice prompting method of intelligent cat eye, and intelligent cat eye | |
US20180025233A1 (en) | Image-capturing device, recording device, and video output control device | |
CN101609660A (en) | Digital frame, the information processing system control method of unifying | |
CN106534789A (en) | Integrated intelligent security and protection video monitoring system | |
CN108616718B (en) | Monitoring display method, device and system | |
US11659144B1 (en) | Security video data processing systems and methods | |
JP2011227654A (en) | Collation device | |
JP6157165B2 (en) | Gaze detection device and imaging device | |
CN114885119A (en) | Intelligent monitoring alarm system and method based on computer vision | |
CN108230607B (en) | Image fire detection method based on regional characteristic analysis | |
CN108289191B (en) | Image recognition method and device | |
CN110505438B (en) | Queuing data acquisition method and camera | |
Pandya et al. | Smart home anti-theft system: a novel approach for near real-time monitoring, smart home security and large video data handling for wellness protocol | |
CN112580522A (en) | Method, device and equipment for detecting sleeper and storage medium | |
CN112689120A (en) | Monitoring method and device | |
CN114550079A (en) | Image processing method, device, equipment and storage medium | |
Zou et al. | A low-power VGA vision sensor with embedded event detection for outdoor edge applications | |
Cokbas et al. | Spatio-visual fusion-based person re-identification for overhead fisheye images |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210806 Address after: 400000 No. 27-3, Fengsheng Road, Jiulongpo District, Chongqing Patentee after: Yijing Huitong Intelligent Technology (Chongqing) Co.,Ltd. Address before: 400,000 Fengsheng Road, Jiulongpo District, Chongqing Patentee before: CHONGQING KAIZE TECHNOLOGY Co.,Ltd. |
|
TR01 | Transfer of patent right |