CN107330386A - A kind of people flow rate statistical method and terminal device - Google Patents
A kind of people flow rate statistical method and terminal device Download PDFInfo
- Publication number
- CN107330386A CN107330386A CN201710474803.4A CN201710474803A CN107330386A CN 107330386 A CN107330386 A CN 107330386A CN 201710474803 A CN201710474803 A CN 201710474803A CN 107330386 A CN107330386 A CN 107330386A
- Authority
- CN
- China
- Prior art keywords
- detection
- target
- detection target
- displacement
- moving direction
- 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.)
- Pending
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/337—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The present invention is applied to field of image recognition there is provided a kind of people flow rate statistical method and terminal device, including：Detection zone is determined in the imaging picture of monitoring device；When detecting appearance detection target in the detection zone, the detection target is tracked, to obtain the moving direction and displacement of the detection target；When the moving direction and displacement of the detection target meet preparatory condition, statistical number of person plus one.In the present invention, by the way that detection range is limited in a lesser width region, the degree of accuracy of target detection is improved.By being tracked to detection target, obtain the corresponding moving direction of detection target and displacement, when moving direction and displacement meet preparatory condition, just determine that effective statistical number of person adds one, statistical regions scope is avoided to hover the interference of personnel, jamming target is discharged to the scope of demographics, the false detection rate of demographics is reduced.
Description
Technical field
The invention belongs to field of image recognition, more particularly to a kind of people flow rate statistical method and terminal device.
Background technology
All kinds of places such as market, shop, hospital, passenger station, are typically necessary and floating population number are counted.Real-time people
Flow information is for the level of rent in estimation market bunk, shop operation situation, the flow of the people of gold vacation, public services
Peak period flow of the people and shop addressing etc. all have very great meaning.Utilize the flow of the people data of statistics, administrative staff
People's flow control scheme can be determined with rational management human and material resources, reasonable disposition resource, so as to obtain optimal operational effect.
There is scholar to propose many methods for demographics at present, the number system such as based on infrared sensor
Meter, demographics based on number of people feature etc..But, these demographic methods are primarily directed to the people occurred under current scene
The quantity statistics method of member, is not the statistical method for flow of the people.And most demographic method has certain
A little shortcomings, such as, for the personnel for hovering or being still in outdoors induction region in demographics place, also tend to be included into
The category of demographics；Or, when many people simultaneously by induction region when, cause genius loci easily to be hidden because the stream of people is crowded
Gear, occurs in that the low phenomenon of stream of people's statistical accuracy.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of people flow rate statistical method and terminal device, it is intended to solve existing
Demographic method for hovered outdoors in place or static personnel also to include demographics scope, people's stream statistics accurate
The problem of property is low.
The first aspect of the embodiment of the present invention provides a kind of people flow rate statistical method, including：
Detection zone is determined in the imaging picture of monitoring device；
When detecting appearance detection target in the detection zone, the detection target is tracked, to obtain
State the moving direction and displacement of detection target；
When the moving direction and displacement of the detection target meet preparatory condition, statistical number of person plus one.
The second aspect of the embodiment of the present invention provides a kind of people flow rate statistical device, including：
Unit is chosen, detection zone is determined in the imaging picture of monitoring device；
Detection unit, for when detecting appearance detection target in the detection zone, being carried out to the detection target
Tracking, to obtain the moving direction and displacement of the detection target；
Statistic unit, for when the moving direction and displacement of the detection target meet preparatory condition, will count
Number adds one.
The third aspect of the embodiment of the present invention provides a kind of terminal device, including memory, processor and is stored in
In the memory and the computer program that can run on the processor, described in the computing device during computer program
Realize following steps：
Detection zone is determined in the imaging picture of monitoring device；
When detecting appearance detection target in the detection zone, the detection target is tracked, to obtain
State the moving direction and displacement of detection target；
When the moving direction and displacement of the detection target meet preparatory condition, statistical number of person plus one.
The fourth aspect of the embodiment of the present invention provides a kind of computer-readable recording medium, the computer-readable storage
Media storage has computer program, and the computer program realizes following steps when being executed by processor：
Detection zone is determined in the imaging picture of monitoring device；
When detecting appearance detection target in the detection zone, the detection target is tracked, to obtain
State the moving direction and displacement of detection target；
When the moving direction and displacement of the detection target meet preparatory condition, statistical number of person plus one.
In embodiments of the present invention, by determining detection zone in the imaging picture of monitoring device so that detection range
It is limited in a lesser width region, improves the degree of accuracy of detection target.By being tracked to detection target, obtain
The corresponding moving direction of target and displacement are detected, when moving direction and displacement meet preparatory condition, just determination has
Effect statistical number of person adds one, it is to avoid the interference for the personnel that hovered in detection zone, and jamming target is discharged to the scope of demographics, drop
The false detection rate of low floating population number statistics, improves the accuracy rate of statistical result.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
In required for the accompanying drawing that uses be briefly described, it should be apparent that, drawings in the following description are only some of the present invention
Embodiment, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these
Accompanying drawing obtains other accompanying drawings.
Fig. 1 is the implementation process figure of people flow rate statistical method provided in an embodiment of the present invention；
Fig. 2 is that people flow rate statistical method S102 provided in an embodiment of the present invention implements flow chart；
Fig. 3 is people flow rate statistical method S102 provided in an embodiment of the present invention specific effect displaying figure；
Fig. 4 is the partial process view for the people flow rate statistical method that another embodiment of the present invention is provided；
Fig. 5 is the structured flowchart of people flow rate statistical device provided in an embodiment of the present invention；
Fig. 6 is the structural representation of terminal device provided in an embodiment of the present invention.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
In embodiments of the present invention, the people flow rate statistical, refers to the statistics to floating population number, further, refers to lead to
Cross a certain space or the number Jing Guo some designated area.
Fig. 1 shows the implementation process of people flow rate statistical method provided in an embodiment of the present invention, and details are as follows：
In S101, detection zone is determined in the imaging picture of monitoring device.
In the present embodiment, one needs the scene of progress people flow rate statistical, can and outdoor field indoor for any one
Doorway, passageway or a certain designated area., it is necessary to first set up a monitoring device in the scene, such as camera makes
Setting height(from bottom) and angle residing for camera is obtained to can be adapted to monitor this selected band of position.
Under preferable case, the height that camera is installed clearly display target characteristics of image can be defined by being imaged picture, special
It is not human face five-sense-organ feature and human body feature.
In the imaging picture of camera, detection zone one smaller than imaging picture scope is determined.Being imaged picture is
The whole image picture for obtaining and being shown on display terminal can be shot by referring to camera.Selecting for detection zone, can be used
Present frame and reference background model in image sequence are dynamically determined come the mode compared or static state specify out detection target image
The region of feature definition highest, most pronounced effects.The detection zone has been generally configured with light intensity and has changed smaller, backcolor
The features such as maximum portrait number that is relatively stable and can accommodating is not more than ten people.
In S102, when detecting appearance detection target in the detection zone, the detection target is tracked,
To obtain the moving direction and displacement of the detection target.
The video streaming image that camera is got can be dumped in background process server or other image processing sections.
According to the difference of camera standard, the number of image frames of record per second is about 25 to 120 frames.Image processing section is according to receiving
Multiple real-time image sequences frames, can be in piece image using some conventional sensing algorithms or customized matching algorithm
The feature of people is judged whether in frame or a sequence image, to judge whether occur detection target in the detection zone.Institute
The position that face, hand, pin, eyes, nose etc. possess characteristics of human body can be included but is not limited to by stating detection target.If there is detection
Target, can return to the information such as the size for detecting target, the position being currently located in picture frame.
Obtained detection target is tracked by Moving Target Tracking Algorithm.Track algorithm, for example, can be to utilize
The Face datection result of previous image frame, the position range that prediction face may occur in next image frame, in the model of restriction
Enclose interior use face template matching process or other detection methods orient the face occurred in present frame, so as to realize whole people
Face tracks process.Because current Moving Target Tracking Algorithm real-time is stronger, it is adaptable to the sequence flow graph of the embodiment of the present invention
As in.
In the multiple images frame obtained after continuous pursuit movement target, contrast any two picture frame or any fixed
Two picture frames at frame number interval, can obtain it is described detection target obtain two picture frames time in moving direction and
Displacement, can convert and show as the moving direction on imaging picture and displacement or the movement in actual place
Direction and displacement.
For example, default fixed frame number is at intervals of 40 frames, if the target detected is eyes, the eyes are in the 1st frame figure
Position as in is high order end centre, and position in the 41st two field picture is above low order end, according to fixing between 40 frame numbers
Every the two picture frames, the moving direction that can draw detection target is the left side upper direction to the right from imaging picture, also may be used
It is from the left side to the right and the movement of the direction away from camera to be converted into moving direction of the detection target in actual place.
Displacement variable of the same position point of same detection target in imaging picture is displacement.Can be with image
On displacement calculate, also actual displacement size can be calculated according to the engineer's scale relation of imaging picture and actual scene.
In S103, when the moving direction and displacement of the detection target meet preparatory condition, by statistical number of person
Plus one.
In the regional extent of people flow rate statistical, it will usually preset a people and flow into outgoing direction, be readily appreciated by
In the case of, the personnel only passed through on the preset direction should just include Statistics category.
If detecting the moving direction of target not on preset direction or when displacement is unsatisfactory for preparatory condition, the place
People flow rate statistical value keeps constant.Preparatory condition can be pre-determined distance value, and according to actual conditions demand, the pre-determined distance value can
To increase or reduce, but the distance range of whole detection zone must not be exceeded.
In embodiments of the present invention, by determining detection zone in the imaging picture of monitoring device so that detection range
It is limited in a lesser width region, improves the degree of accuracy of detection target., can by being tracked to detection target
Each corresponding moving direction of detection target and displacement are obtained, the moving direction and displacement of the detection target are met
During preparatory condition, just determine that effective statistical number of person adds one, it is to avoid the personnel flowed in detection zone in other directions hesitate
Wander the interference of personnel, jamming target is discharged to the scope of demographics, the false detection rate of floating population number statistics is reduced, improves
The accuracy rate of statistical result.
As one embodiment of the present of invention, in S103, can be specially：When the detection target is on preset direction
Displacement be more than default distance value when, statistical number of person plus one.
For example, in two picture frames of selection, if detecting position of the left eye in the first picture frame and in the second figure
The position of picture frame is for same imaging picture, and moving direction is enters cashier from doorway, the movement on image
Distance is 5cm.And enter on doorway on the direction of cashier, pre-determined distance value is 4cm.Now it can determine whether, the left side detected
Displacement of the eye on preset direction is more than pre-determined distance value, thus statistical number of person adds one.If detecting left eye in the first figure
As the position in frame and in the position of the second picture frame for same imaging picture, moving direction is to enter from doorway
Cashier, the displacement on image is 3cm, then displacement of the left eye that can be detected on preset direction is less than
Pre-determined distance value, statistical number of person is not added with one, and system keeps original people flow rate statistical value.
The embodiment of the present invention has been used when detecting that displacement of the target on preset direction is more than default distance value,
The technical scheme for plus one by statistical number of person, efficiently solves the personnel for being strayed into detection range including asking for people's stream statistics sum
Topic, gives the error range of such one permission activity of personnel, improves stream of people's statistical accuracy.
As one embodiment of the present of invention, as shown in Fig. 2 S102 is preferably：
In S201, the target frame of the detection target is surrounded in generation, and makes the target frame and the detection target same
Step motion.
As shown in figure 3, in the present embodiment, specific detection target is chosen to be face, the detection target is surrounded in generation
Target frame, is expressed as the rectangular or square frame of an encirclement human face in the picture.With the motion of human body, face frame is held
Continuous track human faces motion, keeps real-time update effect.
In S202, the movement locus of the predeterminated position of the target frame is recorded.
The predeterminated position, is a constant specified point position of relative target frame.Such as pixel in the face frame upper left corner
The location of point.During target frame is moved, multiple successive image frames are obtained.In multiple successive image frames, with mesh
When marking frame for object of reference, predeterminated position keeps constant；During being entirely imaged picture as object of reference, because predeterminated position follows target
Frame is moved, and position also persistently changes.Indicated in imaging picture in the picture frame of each picture frame or arbitrary interval
The specified point of target frame, can obtain and record the movement locus of the predeterminated position of the target frame.
In S203, the moving direction and displacement of the detection target are obtained by the movement locus.
In step S202, the point of predeterminated position is indicated in imaging picture in picture frame, and selection is wherein separated by solid
Two picture frames of framing number, obtain two front and rear coordinate points of predeterminated position in picture frame.
In the present embodiment, for example, setting up coordinate system to be imaged first, picture upper left corner pixel as the origin of coordinates, institute
The coboundary for stating imaging picture is x-axis positive direction, and left margin is y-axis negative direction.Except the picture on origin, coboundary, left margin
Outside vegetarian refreshments, other pixels in imaging picture are respectively positioned on the fourth quadrant of coordinate system.Predeterminated position is chosen to be face frame upper left
The location of angle pixel.Assuming that in the first picture frame, the coordinate of the pixel is (20,33), is being separated by the of 40 frames
In two picture frames, the top left corner pixel point coordinates for tracing into the face frame of same face characteristic is (50,90).According to two pictures
The difference of vegetarian refreshments coordinate, can obtain it is described detection target x-axis direction displacement be 30, y-axis direction movement away from
From for 57.
When meeting preparatory condition according to the moving direction and displacement of the detection target, statistical number of person plus one.
Concrete example is in the present embodiment, when preparatory condition for displacement in x-axis direction be 20 or y-axis direction movement away from
From for 30 when, statistical number of person plus one.Then displacement of two pixels in x-axis direction is 30 in above-mentioned example, in y-axis side
To displacement be 57.Preparatory condition is met, statistical number of person adds one.
Preferably, when the displacement be on the occasion of and absolute value be more than preset reference value when, determine first direction increase
One effective statistical number of person；When the displacement is negative value and absolute value is less than preset reference value, determine that second direction increases
Plus an effective statistical number of person.
In the above example, it is assumed that y-axis negative direction, which is behaved, flows the direction of entrance, movement of two pixels in y-axis direction
Distance be on the occasion of 57, and the displacement absolute value be more than preset reference value, then can be defined as effectively counting people into direction
Number Jia one.Assuming that in the first picture frame, the coordinate of the pixel is (50,90), in the second picture frame, the seat of the pixel
It is designated as (20,33).According to the difference of two pixel point coordinates, displacement of the detection target in y-axis direction can be obtained
Absolute value for negative value -57, and the displacement is more than preset reference value, it may be determined that add for the effective statistical number of person of outgoing direction
One.
Because the target frame that detects can be single or multiple, each target frame to appearing in detection zone, respectively with
Whether each target frame of track, statistical number of person is judged according to coordinate difference of each predeterminated position in picture frame and preset reference value
Effectively, thus realize many people simultaneously by detection zone when demographics.The positive and negative of coordinate difference is judged simultaneously,
The direction of flow of personnel can be distinguished.
As an alternative embodiment of the invention, judge whether occur the process of the detection target in the detection zone
As shown in figure 4, specific as follows：
In S401, the characteristics of image of the detection target is obtained.
Characteristics of image refers to the unique feature of target to be detected, including the feature based on geometry and Knowledge based engineering spy
Levy.Feature based on geometry, the part such as can refer to eyes, nose, mouth, chin, to these parts and it
Between structural relation geometric description.Knowledge based engineering feature can be the shape description and each other of human face
Range performance, its characteristic component generally includes Euclidean distance, curvature and angle between characteristic point etc..
In facial image, characteristics of image includes various modes feature, includes histogram feature, color characteristic, mould
Plate features, architectural feature and Haar features etc..In the present embodiment, characteristics of image can also may be used by user with self-defining
Defined with the combination according to above-mentioned pattern feature and wherein several pattern features, useful feature information is selected to come simultaneously
Pre-set in system or database.
In S402, match if existing in the imaging picture of the monitoring device with the characteristics of image for detecting target
Image-region, then judge occur the detection target in the detection zone.
According to default characteristics of image, in the imaging picture of the monitoring device, the feature of present image area is extracted
Data, scan for matching with the characteristics of image template stored in system or database.When the characteristic for extracting image-region
When being matched completely with the characteristic template of storage, judge occur detection target in the detection zone.
Preferably, when the feature templates stored in system or database scan for matching, a threshold can be set
Value, when similarity exceedes this threshold value, then judges that the extraction characteristic of present image area is matched with feature templates, that is, is sentenced
Occur detection target in the fixed detection zone, and the target detected is exported by exhibition by target frame or other manifestation modes
Show.
As an alternative embodiment of the invention, on the basis of above-described embodiment is converted on an equal basis, in addition to：
In S401, periodically the detection zone is detected.
In the embodiment described above, when detecting appearance detection target in the detection zone, to the detection mesh
Mark is tracked, to obtain the moving direction and displacement of the detection target.The embodiment of the present invention is judging the detection
When whether occurring detection target in region, not moment holding detection state, is preferably that periodically the detection zone is entered
Row detection.Periodically, refer to that detection operation has certain circulation law, detection operation circulation constantly has one
The yardstick of time.The yardstick of the time can be defined with still image frame number, and the time for for example often getting 20 two field pictures determines
Justice is a time interval, when being separated by 20 two field picture, the action of perform detection target.
Because the number of image frames of transmission per second is general more than 24 frames, zone of action of the detection target in 1 second is substantially
It is still located in detection zone.Set the rational time cycle to detect target, will not generally occur shadow to testing result
Ring.In addition, by periodically being detected to the detection zone, reducing the number of times to region detection so that flow of the people
The operand for counting equipment is reduced, and the processing pressure of system is reduced, so as to improve the performance of system.When target passes through detection
Region, and during more than default distance value, Active duration of the detection target in whole detection zone can generally continue up to a hundred
Picture frame, and periodically detection zone is detected by way of with every 20 picture frames, the target is passing through detection
During the entire process of region, its characteristics of image can be detected more than twice at least, increase the accuracy rate of target detection.
In S402, when occurring identical detection target in multiple detection cycles, target is detected on the identical
Statistical number of person only add one.
When step S401 periodically carries out detection basis to the detection zone, a detection cycle can be produced.
On the basis of detection cycle, a number measurement period is pre-set, the demographics cycle is two or more detections
Cycle.
Under conditions of detection cycle is met, if detecting the mesh that there is matching characteristics of image in former and later two picture frames
Whether timestamp, judges whether the target is identical, i.e., be same moving object or position.When detecting target because of first time,
Utilize target acquistion or other tracking techniques, it is possible to achieve when target is moved in the range of camera shooting, automatically
It is tracked.When being detected as target again in picture frame of the target persistently traced into second of perform detection, then
It can determine whether to detect target with identical in the picture frame of first time perform detection；Otherwise it is different detection targets.
When detecting that target is identical, the number of detection cycles of the second picture frame and the first picture frame is obtained first.For example, first
Picture frame is the 120th frame in sequence of video images, and the second picture frame is the 180th frame, default inspection in sequence of video images
The survey cycle is 30 frames, then the second picture frame and the number of detection cycles of the first picture frame got should be 2 cycles.
When occurring identical detection target in multiple detection cycles, the statistical number of person of target is detected on the identical
Only plus one.If for example, the moving direction and displacement of above-mentioned detection target meet preparatory condition, and default demographics week
Phase is 4 detection cycles, because the detection target currently obtained is identical, apart from a upper demographics moment, has only pass by 2
Detection cycle, not yet reaches next number measurement period and thus detects the statistical number of person holding of target not on the identical
Become.
The moving direction and displacement of the detection target whether meet the decision method of preparatory condition with it is above-mentioned other
Embodiment is identical, no longer repeats one by one herein.
By setting the demographics cycle, when occurring identical detection target within the demographics cycle, on the phase
The statistical number of person of same detection target only adds one so that demographics are only in a cycle period internal trigger, i.e., continuous several
Only triggered once in individual detection cycle.Avoid statistical number of person to act frequently generation, it is therefore prevented that same detection target is repeatedly united
Meter, improves the degree of accuracy of demographics.
Fig. 5 shows the structured flowchart of people flow rate statistical device provided in an embodiment of the present invention, and the system can be by monitoring
Equipment is constituted or the processing terminal comprising camera device with background server, noted earlier each for running the present invention
The people flow rate statistical method of embodiment.For convenience of description, it illustrate only part related to the present embodiment.
Reference picture 5, the system includes：
Unit 51 is chosen, for determining detection zone in the imaging picture of monitoring device；
Detection unit 52, for when detecting appearance detection target in the detection zone, entering to the detection target
Line trace, to obtain the moving direction and displacement of the detection target；
Statistic unit 53, for when the moving direction and displacement of the detection target meet preparatory condition, will unite
Meter number adds one.
Alternatively, the statistic unit 53 includes：
Subelement is counted, is more than default distance value for the displacement when the detection target on preset direction
When, statistical number of person plus one.
Alternatively, the detection unit 52 also includes：
Subelement is tracked, the target frame of the detection target is surrounded for generating, and makes the target frame and the detection
Object synchronization is moved；
Record subelement, the movement locus of the predeterminated position for recording the target frame；
Subelement is obtained, moving direction and displacement for obtaining the detection target by the movement locus.
Alternatively, the system also includes：
Acquiring unit, the characteristics of image for obtaining the detection target；
Matching unit, if for there is the characteristics of image phase with the detection target in the imaging picture of the monitoring device
The image-region of matching, then judge occur the detection target in the detection zone.
Alternatively, the system also includes：
Cycle detection unit, for periodically being detected to the detection zone；
Judging unit, for when occurring identical detection target in multiple detection cycles, on identical detection
The statistical number of person of target only adds one.
Fig. 6 is the structural representation of terminal device provided in an embodiment of the present invention.As shown in fig. 6, the terminal of the embodiment
Equipment 6 includes：Processor 60, memory 61 and it is stored in the memory 61 and can be run on the processor 60
Computer program 62, such as people flow rate statistical program.The processor 60 is realized above-mentioned each when performing the computer program 62
Step in personal flow statistical method embodiment, such as step 101 shown in Fig. 1 to 103.Or, the processor 60 is held
The function of each unit in said apparatus embodiment, such as unit 51 to 53 shown in Fig. 5 are realized during the row computer program 62
Function.
Exemplary, the computer program 62 can be divided into one or more modules, one or more of
Module is stored in the memory 61, and is performed by the processor 60, to complete the present invention.One or more of moulds
Block can complete the series of computation machine programmed instruction section of specific function, and the instruction segment is used to describe the computer journey
Implementation procedure of the sequence 62 in terminal device 6.For example, the computer program 62 can be divided into selection module, detection mould
Block and statistical module, each module concrete function are as follows：
Choosing module is used to determine detection zone in the imaging picture of monitoring device.
Detection module be used for when detect in the detection zone occur detection target when, to it is described detection target carry out with
Track, to obtain the moving direction and displacement of the detection target.
Statistical module is used to that, when the moving direction and displacement of the detection target meet preparatory condition, people will to be counted
Number Jia one.
The terminal device 6 can be that the calculating such as desktop PC, notebook, palm PC and cloud server is set
It is standby.The terminal device may include, but be not limited only to, processor 60, memory 61.It will be understood by those skilled in the art that Fig. 6
Only the example of terminal device 6, does not constitute the restriction to terminal device 6, can include than illustrating more or less portions
Part, either combines some parts or different parts, such as described terminal device can also include input-output equipment, net
Network access device, bus etc..
Alleged processor 60 can be CPU (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) or other PLDs, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
The memory 61 can be the internal storage unit of the terminal device 6, such as hard disk of terminal device 6 or interior
Deposit.The memory 61 can also be the External memory equipment of the terminal device 6, such as is equipped with described terminal device 6
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodges
Deposit card (Flash Card) etc..Further, the memory 61 can also both include the storage inside list of the terminal device 6
Member also includes External memory equipment.The memory 61 is used for needed for storing the computer program and the terminal device
Other programs and data.The memory 61 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that, for convenience of description and succinctly, only with above-mentioned each work(
Energy unit, the division progress of module are for example, in practical application, as needed can distribute above-mentioned functions by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completion
The all or part of function of description.Each functional unit, module in embodiment can be integrated in a processing unit, also may be used
To be that unit is individually physically present, can also two or more units it is integrated in a unit, it is above-mentioned integrated
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.In addition, each function list
Member, the specific name of module are also only to facilitate mutually differentiation, is not limited to the protection domain of the application.Said system
The specific work process of middle unit, module, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, without detailed description or note in some embodiment
The part of load, may refer to the associated description of other embodiments.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, depending on the application-specific and design constraint of technical scheme.Professional and technical personnel
Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed
The scope of the present invention.
, can be with embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method
Realize by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of division of logic function there can be other dividing mode, for example when actually realizing
Multiple units or component can combine or be desirably integrated into another system, or some features can be ignored, or not perform.Separately
A bit, shown or discussed coupling or direct-coupling or communication connection each other can be by some interfaces, device
Or INDIRECT COUPLING or the communication connection of unit, can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated module/unit realized using in the form of SFU software functional unit and as independent production marketing or
In use, can be stored in a computer read/write memory medium.Understood based on such, the present invention realizes above-mentioned implementation
All or part of flow in example method, can also instruct the hardware of correlation to complete, described meter by computer program
Calculation machine program can be stored in a computer-readable recording medium, and the computer program can be achieved when being executed by processor
The step of stating each embodiment of the method..Wherein, the computer program includes computer program code, the computer program
Code can be source code form, object identification code form, executable file or some intermediate forms etc..Computer-readable Jie
Matter can include：Can carry any entity or device of the computer program code, recording medium, USB flash disk, mobile hard disk,
Magnetic disc, CD, computer storage, read-only storage (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium is included can carry out appropriate increasing according to legislation in jurisdiction and the requirement of patent practice
Subtract, such as, in some jurisdictions, according to legislation and patent practice, computer-readable medium does not include electric carrier signal and electricity
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to foregoing reality
Example is applied the present invention is described in detail, it will be understood by those within the art that：It still can be to foregoing each
Technical scheme described in embodiment is modified, or carries out equivalent substitution to which part technical characteristic；And these are changed
Or replace, the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme, all should
Within protection scope of the present invention.
Claims (10)
1. a kind of people flow rate statistical method, it is characterised in that including：
Detection zone is determined in the imaging picture of monitoring device；
When detecting appearance detection target in the detection zone, the detection target is tracked, to obtain the inspection
Survey the moving direction and displacement of target；
When the moving direction and displacement of the detection target meet preparatory condition, statistical number of person plus one.
2. people flow rate statistical method as claimed in claim 1, it is characterised in that described when the moving direction of the detection target
When meeting preparatory condition with displacement, plus one by statistical number of person includes：
When displacement of the detection target on preset direction is more than default distance value, statistical number of person plus one.
3. people flow rate statistical method as claimed in claim 1, it is characterised in that described to be tracked to the detection target,
Included with the moving direction and displacement that obtain the detection target：
The target frame of the detection target is surrounded in generation, and makes the target frame and the detection object synchronization move；
Record the movement locus of the predeterminated position of the target frame；
The moving direction and displacement of the detection target are obtained by the movement locus.
4. people flow rate statistical method as claimed in claim 1, it is characterised in that methods described also includes：
Obtain the characteristics of image of the detection target；
If there is the image-region matched with the characteristics of image of the detection target in the imaging picture of the monitoring device,
Judge occur the detection target in the detection zone.
5. people flow rate statistical method as claimed in claim 1, it is characterised in that methods described also includes：
Periodically the detection zone is detected；
When occurring identical detection target in multiple detection cycles, the statistical number of person for detecting target on the identical only adds
One.
6. a kind of people flow rate statistical device, it is characterised in that including：
Unit is chosen, for determining detection zone in the imaging picture of monitoring device；
Detection unit, for when detecting appearance detection target in the detection zone, being tracked to the detection target,
To obtain the moving direction and displacement of the detection target；
Statistic unit, for when the moving direction and displacement of the detection target meet preparatory condition, by statistical number of person
Plus one.
7. people flow rate statistical device as claimed in claim 6, it is characterised in that the detection unit includes：
Subelement is tracked, the target frame of the detection target is surrounded for generating, and makes the target frame and the detection target
It is synchronized with the movement；
Record subelement, the movement locus of the predeterminated position for recording the target frame；
Subelement is obtained, moving direction and displacement for obtaining the detection target by the movement locus.
8. people flow rate statistical device as claimed in claim 6, it is characterised in that also include：
Cycle detection unit, for periodically being detected to the detection zone；
Judging unit, for when occurring identical detection target in multiple detection cycles, target to be detected on the identical
Statistical number of person only add one.
9. a kind of terminal device, including memory, processor and it is stored in the memory and can be on the processor
The computer program of operation, it is characterised in that realize such as claim 1 to 5 described in the computing device during computer program
The step of any one people flow rate statistical method.
10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, its feature exists
In the step of realization people flow rate statistical method as described in any one of claim 1 to 5 when the computer program is executed by processor
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710474803.4A CN107330386A (en) | 2017-06-21 | 2017-06-21 | A kind of people flow rate statistical method and terminal device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710474803.4A CN107330386A (en) | 2017-06-21 | 2017-06-21 | A kind of people flow rate statistical method and terminal device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107330386A true CN107330386A (en) | 2017-11-07 |
Family
ID=60193965
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710474803.4A Pending CN107330386A (en) | 2017-06-21 | 2017-06-21 | A kind of people flow rate statistical method and terminal device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107330386A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108334829A (en) * | 2018-01-23 | 2018-07-27 | 浙江大仓信息科技股份有限公司 | A kind of mobilism car passenger number statistical system |
| CN108875562A (en) * | 2018-04-28 | 2018-11-23 | 华南师范大学 | A kind of public transport people flow rate statistical method and system |
| CN108921983A (en) * | 2018-05-22 | 2018-11-30 | 浙江大学山东工业技术研究院 | Complex equipment colliery system waiting room people flow rate statistical method |
| CN109711369A (en) * | 2018-12-29 | 2019-05-03 | 深圳英飞拓智能技术有限公司 | Pedestrian count method, apparatus, system, computer equipment and storage medium |
| CN109871772A (en) * | 2019-01-21 | 2019-06-11 | 上海数迹智能科技有限公司 | A kind of statistical method of number, device, storage medium and equipment |
| CN110245611A (en) * | 2019-06-14 | 2019-09-17 | 腾讯科技（深圳）有限公司 | Image-recognizing method, device, computer equipment and storage medium |
| CN110245556A (en) * | 2019-05-06 | 2019-09-17 | 深圳耄耋看护科技有限公司 | A kind of detection method, device, system and the storage medium of the state of leaving home of being in |
| CN110276435A (en) * | 2019-05-27 | 2019-09-24 | 深圳市赛格车圣科技有限公司 | Population flow detection device and Pedestrian flow detection method based on millimetre-wave radar |
| CN111078751A (en) * | 2019-12-13 | 2020-04-28 | 万翼科技有限公司 | Method and system for carrying out target statistics based on UNREAL4 |
| CN112070555A (en) * | 2020-09-16 | 2020-12-11 | 青岛维感科技有限公司 | Passenger flow monitoring method, device, system, channel and storage medium |
| CN112116650A (en) * | 2020-09-29 | 2020-12-22 | 联想(北京)有限公司 | Datum line adjusting method and device |
| CN112149621A (en) * | 2020-10-15 | 2020-12-29 | 珠海格力智能装备有限公司 | Detection method, device, equipment and system for egg roll yield and readable storage medium |
| CN113536932A (en) * | 2021-06-16 | 2021-10-22 | 中科曙光国际信息产业有限公司 | Crowd gathering prediction method and device, computer equipment and storage medium |
| CN113988111A (en) * | 2021-12-03 | 2022-01-28 | 深圳佑驾创新科技有限公司 | Statistical method for pedestrian flow of public place and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008048979A2 (en) * | 2006-10-16 | 2008-04-24 | Viaspace Security, Inc. | Threat detection based on infra-red radiation contrast |
| CN102982598A (en) * | 2012-11-14 | 2013-03-20 | 三峡大学 | Video people counting method and system based on single camera scene configuration |
| CN105139425A (en) * | 2015-08-28 | 2015-12-09 | 浙江宇视科技有限公司 | People counting method and device |
| CN105631418A (en) * | 2015-12-24 | 2016-06-01 | 浙江宇视科技有限公司 | People counting method and device |
| CN106339690A (en) * | 2016-08-30 | 2017-01-18 | 上海交通大学 | Video object flow detecting method and system based on noise elimination and auxiliary determination line |
| CN106600643A (en) * | 2016-10-25 | 2017-04-26 | 长安大学 | People counting method based on trajectory analysis |
-
2017
- 2017-06-21 CN CN201710474803.4A patent/CN107330386A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008048979A2 (en) * | 2006-10-16 | 2008-04-24 | Viaspace Security, Inc. | Threat detection based on infra-red radiation contrast |
| CN102982598A (en) * | 2012-11-14 | 2013-03-20 | 三峡大学 | Video people counting method and system based on single camera scene configuration |
| CN105139425A (en) * | 2015-08-28 | 2015-12-09 | 浙江宇视科技有限公司 | People counting method and device |
| CN105631418A (en) * | 2015-12-24 | 2016-06-01 | 浙江宇视科技有限公司 | People counting method and device |
| CN106339690A (en) * | 2016-08-30 | 2017-01-18 | 上海交通大学 | Video object flow detecting method and system based on noise elimination and auxiliary determination line |
| CN106600643A (en) * | 2016-10-25 | 2017-04-26 | 长安大学 | People counting method based on trajectory analysis |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108334829B (en) * | 2018-01-23 | 2021-08-06 | 浙江大仓信息科技股份有限公司 | Dynamic passenger car number counting system |
| CN108334829A (en) * | 2018-01-23 | 2018-07-27 | 浙江大仓信息科技股份有限公司 | A kind of mobilism car passenger number statistical system |
| CN108875562B (en) * | 2018-04-28 | 2019-10-11 | 华南师范大学 | A kind of public transport people flow rate statistical method and system |
| CN108875562A (en) * | 2018-04-28 | 2018-11-23 | 华南师范大学 | A kind of public transport people flow rate statistical method and system |
| CN108921983B (en) * | 2018-05-22 | 2020-11-03 | 浙江大学山东工业技术研究院 | People flow statistical method for waiting room of complex equipment coal mine system |
| CN108921983A (en) * | 2018-05-22 | 2018-11-30 | 浙江大学山东工业技术研究院 | Complex equipment colliery system waiting room people flow rate statistical method |
| CN109711369A (en) * | 2018-12-29 | 2019-05-03 | 深圳英飞拓智能技术有限公司 | Pedestrian count method, apparatus, system, computer equipment and storage medium |
| CN109871772A (en) * | 2019-01-21 | 2019-06-11 | 上海数迹智能科技有限公司 | A kind of statistical method of number, device, storage medium and equipment |
| CN109871772B (en) * | 2019-01-21 | 2023-09-29 | 上海数迹智能科技有限公司 | Statistical method, device, storage medium and equipment for number of people |
| CN110245556A (en) * | 2019-05-06 | 2019-09-17 | 深圳耄耋看护科技有限公司 | A kind of detection method, device, system and the storage medium of the state of leaving home of being in |
| CN110276435A (en) * | 2019-05-27 | 2019-09-24 | 深圳市赛格车圣科技有限公司 | Population flow detection device and Pedestrian flow detection method based on millimetre-wave radar |
| CN110245611A (en) * | 2019-06-14 | 2019-09-17 | 腾讯科技（深圳）有限公司 | Image-recognizing method, device, computer equipment and storage medium |
| CN110245611B (en) * | 2019-06-14 | 2021-06-15 | 腾讯科技（深圳）有限公司 | Image recognition method and device, computer equipment and storage medium |
| CN111078751A (en) * | 2019-12-13 | 2020-04-28 | 万翼科技有限公司 | Method and system for carrying out target statistics based on UNREAL4 |
| WO2022057808A1 (en) * | 2020-09-16 | 2022-03-24 | 青岛维感科技有限公司 | Passenger flow monitoring method, apparatus and system, channel, and storage medium |
| CN112070555A (en) * | 2020-09-16 | 2020-12-11 | 青岛维感科技有限公司 | Passenger flow monitoring method, device, system, channel and storage medium |
| CN112116650A (en) * | 2020-09-29 | 2020-12-22 | 联想(北京)有限公司 | Datum line adjusting method and device |
| CN112149621A (en) * | 2020-10-15 | 2020-12-29 | 珠海格力智能装备有限公司 | Detection method, device, equipment and system for egg roll yield and readable storage medium |
| CN112149621B (en) * | 2020-10-15 | 2024-04-05 | 珠海格力智能装备有限公司 | Egg roll yield detection method, device, equipment, system and readable storage medium |
| CN113536932A (en) * | 2021-06-16 | 2021-10-22 | 中科曙光国际信息产业有限公司 | Crowd gathering prediction method and device, computer equipment and storage medium |
| CN113988111A (en) * | 2021-12-03 | 2022-01-28 | 深圳佑驾创新科技有限公司 | Statistical method for pedestrian flow of public place and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107330386A (en) | A kind of people flow rate statistical method and terminal device | |
| CN108509896B (en) | Trajectory tracking method and device and storage medium | |
| Zou et al. | Occupancy detection in the office by analyzing surveillance videos and its application to building energy conservation | |
| US10417503B2 (en) | Image processing apparatus and image processing method | |
| CN101231755B (en) | Moving target tracking and quantity statistics method | |
| Benezeth et al. | Abnormal events detection based on spatio-temporal co-occurences | |
| Hampapur et al. | Smart video surveillance: exploring the concept of multiscale spatiotemporal tracking | |
| US9443144B2 (en) | Methods and systems for measuring group behavior | |
| Patruno et al. | People re-identification using skeleton standard posture and color descriptors from RGB-D data | |
| US10157327B2 (en) | Image processing device, image processing method, and program | |
| Lin et al. | Visual-attention-based background modeling for detecting infrequently moving objects | |
| CN109325456A (en) | Target identification method, device, target identification equipment and storage medium | |
| Poonsri et al. | Fall detection using Gaussian mixture model and principle component analysis | |
| CN106778637B (en) | Statistical method for man and woman passenger flow | |
| Cheong et al. | A novel face detection algorithm using thermal imaging | |
| US9361705B2 (en) | Methods and systems for measuring group behavior | |
| CN109697385A (en) | A kind of method for tracking target and device | |
| CN115273208A (en) | Track generation method, system and device and electronic equipment | |
| CN102867214B (en) | Counting management method for people within area range | |
| CN113034544A (en) | People flow analysis method and device based on depth camera | |
| US20210312170A1 (en) | Person detection and identification using overhead depth images | |
| CN111178113B (en) | Information processing method, device and storage medium | |
| WO2012153868A1 (en) | Information processing device, information processing method and information processing program | |
| CN109241942A (en) | Image processing method, device, face recognition device and storage medium | |
| CN106503697A (en) | Target identification method and device, face identification method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171107 |
|
| RJ01 | Rejection of invention patent application after publication |