CN110334569A - The volume of the flow of passengers passes in and out recognition methods, device, equipment and storage medium - Google Patents
The volume of the flow of passengers passes in and out recognition methods, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110334569A CN110334569A CN201910253943.8A CN201910253943A CN110334569A CN 110334569 A CN110334569 A CN 110334569A CN 201910253943 A CN201910253943 A CN 201910253943A CN 110334569 A CN110334569 A CN 110334569A
- Authority
- CN
- China
- Prior art keywords
- client
- image
- flow
- passengers
- volume
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to the technical fields of image recognition, and more particularly, to a kind of volume of the flow of passengers disengaging recognition methods, device, equipment and storage medium, it includes: S10 that the volume of the flow of passengers, which passes in and out recognition methods: obtaining identify video recording in shop in real time；S20: sub-frame processing is carried out to the identification video recording acquired, obtains framing image sequentially in time；S30: using number of people detection model in such a way that the framing image detection goes out number of people feature, head image is obtained；S40: according to the head image in the framing image of continuous several frames, client's motion profile is obtained；S50: client's motion profile is analyzed, if client's motion profile meets preset angular range, then obtain client's direction of motion of client's motion profile, and client is obtained according to client's direction of motion and passes in and out situation, and client disengaging situation is sent and is written in volume of the flow of passengers analytical database.The present invention has the effect of improving volume of the flow of passengers analysis accuracy rate.
Description
Technical field
The present invention relates to the technical fields of image recognition, more particularly, to a kind of volume of the flow of passengers disengaging recognition methods, device, set
Standby and storage medium.
Background technique
Currently, the volume of the flow of passengers is the data that the place such as supermarket, market is managed and decision is important.Wherein guest flow statistics
Mostly use be image recognition data statistical approach.In existing technology, by being provided with taking the photograph for volume of the flow of passengers analysis in the storefront
As head, the head zone of the guest of disengaging is identified and to the corresponding motion trail analysis of the head zone of guest, from
And the corresponding volume of the flow of passengers is obtained, but in the prior art, there can be the camera that the guest to hover in shop enters volume of the flow of passengers analysis
It is interior, the volume of the flow of passengers can be analyzed and be impacted.
Summary of the invention
The object of the present invention is to provide it is a kind of raising the volume of the flow of passengers analysis accuracy rate the volume of the flow of passengers disengaging recognition methods, device,
Equipment and storage medium.
Foregoing invention purpose one of the invention has the technical scheme that
A kind of volume of the flow of passengers disengaging recognition methods, the volume of the flow of passengers disengaging recognition methods include:
S10: it obtains identify video recording in shop in real time；
S20: sub-frame processing is carried out to the identification video recording acquired, obtains framing image sequentially in time；
S30: using number of people detection model in such a way that the framing image detection goes out number of people feature, head image is obtained；
S40: according to the head image in the framing image of continuous several frames, client's motion profile is obtained；
S50: analyzing client's motion profile, if client's motion profile meets preset angular range, obtains
Client's direction of motion of client's motion profile is taken, and client is obtained according to client's direction of motion and passes in and out situation, and will
The client passes in and out situation and sends and be written in volume of the flow of passengers analytical database.
By using above-mentioned technical proposal, when analyzing the volume of the flow of passengers, by being provided with camera shooting above shop door mouth
Device, and the guest into shop is shot using photographic device, to count the volume of the flow of passengers；When counting the volume of the flow of passengers, from identification
Head image starts out, and the guest can be judged by recording client's motion profile if client's motion profile meets certain angle
It is to have been come into shop from doorway, rather than hover near doorway, in this way, can will not be into shop or out point, and
It is that the customer to hover in shop door mouth excludes outside the volume of the flow of passengers, to improve the really degree of volume of the flow of passengers analysis, and then improves
The accuracy of volume of the flow of passengers analysis.
The present invention is further arranged to: before the step S30, the volume of the flow of passengers passes in and out recognition methods further include:
S301: the background picture of identification video recording in the shop is obtained, and using the background picture as comparison picture；
S302: several human body head region pictures are obtained, and extract head region in the picture of the human body head region respectively
Characteristic value, construction feature vector；
S303: being trained the comparison picture and described eigenvector using deep learning, obtains the number of people detection mould
Type.
By using above-mentioned technical proposal, identified to the customer into shop, before obtaining the head image of client,
First by the way of deep learning, number of people detection model is trained, is identified convenient for server and counts the volume of the flow of passengers.
The present invention is further arranged to: stating step S30 includes:
S31: the framing image and the similarity compared between image are successively calculated sequentially in time, and is chosen similar
Degree is less than the framing image of preset threshold value, as identification image；
S32: the identification image is detected using the number of people detection model, if detecting institute in the identification image
Number of people feature is stated, then using the identification image as the head image.
By using above-mentioned technical proposal, when identifying head image, by calculating between adjacent two framing images
Similarity chooses similarity less than the framing image of preset threshold value and is used as identification image, can be by point of not motion change
Frame image is excluded, and can be reduced radix when server identification head image, be improved the efficiency of identification, while also reducing
The quantity for storing photo, alleviates the memory space of server.
The present invention is further arranged to: the step S40 includes:
S41: coordinate is divided according to pixel for the framing image, and obtains head image institute described in each frame framing image
Coordinate points；
S42: the distance between the coordinate points where head image described in adjacent two frame are judged, if between the coordinate points
Distance then determines that the head image of two adjacent two frames is the same person between 20-30 pixel；
S43: obtaining the head image that continuous several frames are determined as same people, and by head image pair described in several frames
The coordinate points answered are put into the coordinate, and are linked to be client's motion profile sequentially in time.
By using above-mentioned technical proposal, by that can judge two neighboring framing image to the distance between coordinate points
In head image whether be same customer, consequently facilitating obtain client's motion profile of the customer, convenient for being carried out to the volume of the flow of passengers
Statistics.
The present invention is further arranged to: the step S50 includes:
S51: center line is set in the coordinate；
S52: it if the beginning of client's motion profile and end are located at the center line both ends, obtain the client and moves rail
The angle of mark and the center line；
S53: corresponding with end acquisition according to client's motion profile beginning if the angle meets the angular range
Client's direction of motion.
By using above-mentioned technical proposal, by the setting of center line, and to the client's motion profile for crossing the center line
The angle of the angle between client's motion profile and center line is judged, so as to not count the customer to hover in shop door mouth
In the volume of the flow of passengers, to realize the accuracy for improving guest flow statistics.
Foregoing invention purpose two of the invention has the technical scheme that
A kind of volume of the flow of passengers disengaging identification device, the volume of the flow of passengers disengaging identification device include:
Video recording obtains module, and video recording is identified in shop for obtaining in real time；
Framing module obtains framing sequentially in time for carrying out sub-frame processing to the identification video recording acquired
Image；
Feature recognition module, in such a way that the framing image detection goes out number of people feature, being obtained using number of people detection model
Head image；
Track generation module obtains client's fortune for the head image in the framing image according to continuous several frames
Dynamic rail mark；
Analysis and memory module, for analyzing client's motion profile, if client's motion profile meet it is default
Angular range, then obtain client's direction of motion of client's motion profile, and visitor is obtained according to client's direction of motion
Family passes in and out situation, and client disengaging situation is sent and is written in volume of the flow of passengers analytical database.
By using above-mentioned technical proposal, when analyzing the volume of the flow of passengers, by being provided with camera shooting above shop door mouth
Device, and the guest into shop is shot using photographic device, to count the volume of the flow of passengers；When counting the volume of the flow of passengers, from identification
Head image starts out, and the guest can be judged by recording client's motion profile if client's motion profile meets certain angle
It is to have been come into shop from doorway, rather than hover near doorway, in this way, can will not be into shop or out point, and
It is that the customer to hover in shop door mouth excludes outside the volume of the flow of passengers, to improve the really degree of volume of the flow of passengers analysis, and then improves
The accuracy of volume of the flow of passengers analysis.
Foregoing invention purpose three of the invention has the technical scheme that
A kind of computer equipment, including memory, processor and storage are in the memory and can be on the processor
The computer program of operation, the processor realize the step of the above-mentioned volume of the flow of passengers disengaging recognition methods when executing the computer program
Suddenly.
Foregoing invention purpose four of the invention has the technical scheme that
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the computer
The step of above-mentioned volume of the flow of passengers disengaging recognition methods is realized when program is executed by processor.
In conclusion advantageous effects of the invention are as follows:
When analyzing the volume of the flow of passengers, by being provided with photographic device above shop door mouth, and using photographic device into shop
Guest shoot, to count the volume of the flow of passengers；When counting the volume of the flow of passengers, since identifying head image, record client's fortune
Dynamic rail mark, if client's motion profile meets certain angle, can judge the guest be come into shop from doorway, rather than
It hovers near doorway, in this way, can will not be into shop or out point, but the customer to hover in shop door mouth excludes to exist
Outside the volume of the flow of passengers, to improve the really degree of volume of the flow of passengers analysis, and then the accuracy of volume of the flow of passengers analysis is improved.
Detailed description of the invention
Fig. 1 is a flow chart of volume of the flow of passengers disengaging recognition methods in one embodiment of the invention；
Fig. 2 is another implementation flow chart of volume of the flow of passengers disengaging recognition methods in one embodiment of the invention；
Fig. 3 is the implementation flow chart of step S30 in volume of the flow of passengers disengaging recognition methods in one embodiment of the invention；
Fig. 4 is the implementation flow chart of step S40 in volume of the flow of passengers disengaging recognition methods in one embodiment of the invention；
Fig. 5 is the implementation flow chart of step S50 in volume of the flow of passengers disengaging recognition methods in one embodiment of the invention；
Fig. 6 is a functional block diagram of volume of the flow of passengers disengaging identification device in one embodiment of the invention；
Fig. 7 is a schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
Below in conjunction with attached drawing, invention is further described in detail.
Embodiment one:
In one embodiment, as shown in Figure 1, the invention discloses a kind of volumes of the flow of passengers to pass in and out recognition methods, following step is specifically included
It is rapid:
S10: it obtains identify video recording in shop in real time.
In the present embodiment, identification video recording refers to situation about taking inside the places such as shop or supermarket, and needs from this
The video recording of customer is identified in the case where inside.
Specifically, it is provided with recording apparatus, such as camera above the doorway in shop, to the Gu by the doorway in shop
Visitor records a video, to obtain identification video recording.
S20: sub-frame processing is carried out to the identification video recording acquired, obtains framing image sequentially in time.
In the present embodiment, framing image refers to each frame image in identification video recording.
Specifically, the time sequencing played according to identification video recording obtains identification video recording using existing sub-frame processing method
In each frame image, as framing image.
S30: using number of people detection model in such a way that framing image detection goes out number of people feature, head image is obtained.
In the present embodiment, number of people detection model refers to trains in advance, can be in the framing image in identification video recording
It identifies client's head zone, and then determines the model of customer's individual according to the head zone.
Specifically, number of people detection model is trained in advance, the identification of number of people feature is carried out in framing image, if in framing
Number of people feature is identified in image, using in the region for identifying number of people feature as the head image.
S40: according to the head image in the framing image of continuous several frames, client's motion profile is obtained.
In the present embodiment, client's motion profile refers to the track that customer moves in identification video recording.
Specifically, since the photographic device in shop is fixed, situation in the shop shot by photographic device
It is also fixed.Therefore each by several frames, such as the framing image of 50 frames using the background of situation in shop as base map
In the framing image of frame, after the head image of same customer is sequentially written in base map sequentially in time, by all head images
It is linked to be client's motion profile.
S50: analyzing client's motion profile, if client's motion profile meets preset angular range, obtains visitor
Client's direction of motion of family motion profile, and client is obtained according to client's direction of motion and passes in and out situation, and client is passed in and out into situation
It sends and is written in volume of the flow of passengers analytical database.
In the present embodiment, client's direction of motion refers to client in shop along the direction that client's motion profile moves.
Specifically, line of reference is first pre-set, and client's motion profile is compared with line of reference.If client transports
Angle is formed between dynamic rail mark and the line of reference, i.e. client's motion profile and line of reference has intersection point in identification video recording, then passes through
The angle of the angle is calculated, and the angle takes acute angle or right angle.If the angle is in 45 ° -90 °, obtains client and move rail
Client's direction of motion of mark, and client is obtained according to client's direction of motion and passes in and out situation, i.e., using doorway as object of reference, if the client
The direction of motion is gradually distance from the doorway, then determines that customer is into shop；If client's direction of motion is to move closer to the doorway
, then determine customer for departure.
Further, client's disengaging situation is sent and is written in volume of the flow of passengers analytical database.
In the present embodiment, when analyzing the volume of the flow of passengers, by being provided with photographic device above shop door mouth, and make
The guest into shop is shot with photographic device, to count the volume of the flow of passengers；When counting the volume of the flow of passengers, from identifying head image
Start, recording client's motion profile if client's motion profile meets certain angle can judge that the guest is walked from doorway
Into in shop, rather than hover near doorway, in this way, can will not be into shop or out point, but in shop door mouth
The customer to hover excludes outside the volume of the flow of passengers, to improve the really degree of volume of the flow of passengers analysis, and then improves volume of the flow of passengers analysis
Accuracy.
In one embodiment, as shown in Fig. 2, before step step S30, the volume of the flow of passengers passes in and out recognition methods further include:
S301: the background picture of identification video recording in shop is obtained, and using background picture as comparison picture.
Specifically, after the photographic device in shop installs, the back in the shop taken in the state of no one is obtained
Scape picture, using the background picture as comparison picture.
S302: obtaining several human body head region pictures, and extracts head region in the picture of human body head region respectively
Characteristic value, construction feature vector.
Specifically, the picture for having human body head zone can be obtained from different channels, and can pass through existing edge
Detection technique carries out identifying human body head region.Edge detecting technology is Digital Image Processing, pattern-recognition, computer view
One of important foundation of feel can satisfy the implementation of this embodiment.
Further, after going out the picture recognition in human body head region, existing convolutional neural networks can be passed through
(Convolutional Neural Networks, hereinafter referred to as CNN).Extract head region characteristic value, construction feature to
Amount.
S303: comparison picture and feature vector are trained using deep learning, obtain number of people detection model.
Specifically, the corresponding feature vector of all head regions got is put into and is compared in picture, and pass through CNN-
LSTM model carries out deep learning, obtains number of people detection model, and the number of people detection model is enable to identify in comparing picture
Head image.
In one embodiment, as shown in figure 3, in step s 30, i.e., being gone out using number of people detection model in framing image detection
The mode of number of people feature, obtains head image, specifically comprises the following steps:
S31: framing image is successively calculated sequentially in time and compares the similarity between image, and chooses similarity and is less than in advance
If threshold value framing image, as identification image.
Specifically, if there is no motion change between the framing image of two adjacent frames, illustrate do not have in the identification image
Have that customer passes through or customer is in stationary state.
Further, gray proces are carried out by the framing image to adjacent two frame, and is taken according to the result of gray proces
Difference value, and using the difference value as the similarity.If the similarity is less than preset threshold value, such as 0.05, then illustrate adjacent
Two frames framing image between there are motion changes, then using this two frame, there are the framing images of motion change as identification figure
Picture.
S32: detecting identification image using number of people detection model, if detecting number of people feature in identification image,
It will then identify image as head image.
Specifically, by way of step S30, identification image is detected using number of people detection model, if identifying
Number of people feature is detected in image, then image will be identified as head image.
In one embodiment, as shown in figure 4, in step s 40, i.e., according to the head in the framing image of continuous several frames
Image obtains client's motion profile, specifically comprises the following steps:
S41: coordinate is divided according to pixel for framing image, and obtains the coordinate in each frame framing image where head image
Point.
Specifically, coordinate system is established in each framing image, and using the framing image lower left corner as origin, i.e., entire framing
Image is in the first quartile in coordinate system.Further, as unit of every one 10 pixels, x-axis in the coordinate system
With coordinate is divided in y-axis.
Further, the coordinate points in each frame framing image where head image are obtained.
S42: the distance between the coordinate points where adjacent two frames head image are judged, if the distance between coordinate points exist
Between 20-30 pixel, then determine that the head image of two adjacent two frames is the same person.
Specifically, by judging the distance between the coordinate points where adjacent two frames head image, for example, for the i-th frame
Head image and the i-th+2 frame head image, head image A and head image B are existed simultaneously, if the head figure of the i-th frame
As the distance between head image A ' in A and i+1 frame is in 25 pixels, then this head image A and head image are determined
A ' is the same customer.
S43: obtaining the head image that continuous several frames are determined as same people, and by the corresponding coordinate of several frame head images
Point is put into coordinate, and is linked to be client's motion profile sequentially in time.
Specifically, in the framing image of continuous several frames, the head image of same people is obtained.When obtaining, in order to protect
Accuracy is demonstrate,proved, can be got always until disappearing from identification video recording since when the head image appears in identification video recording.
Further, the head image for being determined as same people is not write according in the successful time write-in coordinate of judgement
Enter once, and the last head image that the left side is written is linked to be elder generation, and then obtains client's motion profile.
In one embodiment, as shown in figure 5, i.e. client's motion profile is analyzed, if client's motion profile meet it is pre-
If angular range, then obtain client's direction of motion of client's motion profile, and client's disengaging is obtained according to client's direction of motion
Situation, and client's disengaging situation is sent and is written in volume of the flow of passengers analytical database, specifically comprise the following steps:
S51: center line is set in coordinate.
Specifically, in the position close to 10 pixels in doorway, the parallel line of reference in the doorway being set in shop, by the ginseng
According to line centered on line.
S52: if the beginning of client's motion profile and end are located at center line both ends, client's motion profile and center are obtained
The angle of line.
Specifically, in client's motion profile, the corresponding coordinate points of head image of coordinate are added as this using first
The corresponding coordinate points of head image of coordinate are added as client's motion profile in the last one by the beginning of client's motion profile
End.If client's motion profile is located at the both ends of center line, i.e., client's motion profile intersects with center line and forms folder
Angle.
Further, the angle of the angle and center line is obtained.
S53: if angle meets angular range, according to client's motion profile beginning, client corresponding with end acquisition is moved
Direction.
Specifically, if the angle is between 45 ° to 90 °, such as 87 °, then illustrate the client may be into shop either from
Shop.If the beginning of client's motion profile relative to end close to doorway, determine client's direction of motion be into shop, otherwise be
Departure.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Embodiment two:
In one embodiment, a kind of volume of the flow of passengers disengaging identification device is provided, which passes in and out identification device and above-described embodiment
Middle volume of the flow of passengers disengaging recognition methods corresponds.As shown in fig. 6, volume of the flow of passengers disengaging identification device includes that video recording obtains module
10, framing module 20, feature recognition module 30, track generation module 40 and analysis and memory module 50.Each functional module is detailed
It is described as follows:
Video recording obtains module 10, and video recording is identified in shop for obtaining in real time；
Framing module 20 obtains framing figure sequentially in time for carrying out sub-frame processing to the identification video recording acquired
Picture；
Feature recognition module 30, in such a way that framing image detection goes out number of people feature, being obtained to the end using number of people detection model
Portion's image；
Track generation module 40 obtains client's motion profile for the head image in the framing image according to continuous several frames；
Analysis and memory module 50, for analyzing client's motion profile, if client's motion profile meets preset angle
Range then obtains client's direction of motion of client's motion profile, and obtains client according to client's direction of motion and pass in and out situation, and will
Client passes in and out situation and sends and be written in volume of the flow of passengers analytical database.
Preferably, the volume of the flow of passengers passes in and out identification device further include:
It compares picture and obtains module 301, for obtaining the background picture for identifying video recording in shop, and using background picture as comparison chart
Piece；
Feature vector constructs module 302, for obtaining several human body head region pictures, and extracts human body head region respectively
The characteristic value of head region in picture, construction feature vector；
Deep learning module 303 obtains number of people detection for being trained using deep learning to comparison picture and feature vector
Model.
Preferably, feature recognition module 30 includes:
Similarity calculation submodule 31, for sequentially in time successively calculate framing image to compare it is similar between image
Degree, and the framing image that similarity is less than preset threshold value is chosen, as identification image；
Detection sub-module 32, for being detected using number of people detection model to identification image, if being detected in identification image
Number of people feature will then identify image as head image.
Preferably, track generation module 40 includes:
Coordinate setting up submodule 41 for dividing coordinate according to pixel for framing image, and obtains in each frame framing image
Coordinate points where head image；
Distance Judgment submodule 42, for judging the distance between the coordinate points where adjacent two frames head image, if coordinate points
The distance between 20-30 pixel, then determine two adjacent two frames head image be the same person；
Track generates submodule 43, the head image for being determined as same people for obtaining continuous several frames, and by several frame head portions
The corresponding coordinate points of image are put into coordinate, and are linked to be client's motion profile sequentially in time.
Preferably, it analyzes with memory module 50 and includes:
Submodule 51 is arranged in center line, for center line to be arranged in coordinate；
Angle acquisition submodule 52 obtains client if being located at center line both ends for the beginning of client's motion profile and end
The angle of motion profile and center line；
Direction of motion acquisition submodule 53, if meeting angular range for angle, according to client's motion profile beginning and end
Obtain corresponding client's direction of motion.
Specific restriction about volume of the flow of passengers disengaging identification device may refer to pass in and out recognition methods above for the volume of the flow of passengers
Restriction, details are not described herein.Modules in above-mentioned volume of the flow of passengers disengaging identification device can be fully or partially through software, hard
Part and combinations thereof is realized.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment,
It can also be stored in a software form in the memory in computer equipment, execute the above modules in order to which processor calls
Corresponding operation.
Embodiment three:
In one embodiment, a kind of computer equipment is provided, which can be server, internal structure chart
It can be as shown in Figure 7.The computer equipment includes processor, memory, network interface and the data connected by system bus
Library.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory of the computer equipment includes non-
Volatile storage medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and database.
The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The computer is set
Standby database passes in and out situation for storing client.The network interface of the computer equipment is used to pass through network with external terminal
Connection communication.To realize a kind of volume of the flow of passengers disengaging recognition methods when computer program is executed by processor.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor perform the steps of when executing computer program
S10: it obtains identify video recording in shop in real time；
S20: sub-frame processing is carried out to the identification video recording acquired, obtains framing image sequentially in time；
S30: using number of people detection model in such a way that framing image detection goes out number of people feature, head image is obtained；
S40: according to the head image in the framing image of continuous several frames, client's motion profile is obtained；
S50: analyzing client's motion profile, if client's motion profile meets preset angular range, obtains client's fortune
Client's direction of motion of dynamic rail mark, and client is obtained according to client's direction of motion and passes in and out situation, and client is passed in and out into situation and is sent
And it is written in volume of the flow of passengers analytical database.
Example IV:
In one embodiment, a kind of computer readable storage medium is provided, computer program, computer journey are stored thereon with
It is performed the steps of when sequence is executed by processor
S10: it obtains identify video recording in shop in real time；
S20: sub-frame processing is carried out to the identification video recording acquired, obtains framing image sequentially in time；
S30: using number of people detection model in such a way that framing image detection goes out number of people feature, head image is obtained；
S40: according to the head image in the framing image of continuous several frames, client's motion profile is obtained；
S50: analyzing client's motion profile, if client's motion profile meets preset angular range, obtains client's fortune
Client's direction of motion of dynamic rail mark, and client is obtained according to client's direction of motion and passes in and out situation, and client is passed in and out into situation and is sent
And it is written in volume of the flow of passengers analytical database.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM(EPROM), electrically erasable ROM(EEPROM) or flash memory.Volatile memory may include
Random-access memory (ram) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM(SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM(ESDRAM), synchronization link (Synchlink) DRAM(SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution 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 completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of volume of the flow of passengers passes in and out recognition methods, which is characterized in that the volume of the flow of passengers passes in and out recognition methods and includes:
S10: it obtains identify video recording in shop in real time；
S20: sub-frame processing is carried out to the identification video recording acquired, obtains framing image sequentially in time；
S30: using number of people detection model in such a way that the framing image detection goes out number of people feature, head image is obtained；
S40: according to the head image in the framing image of continuous several frames, client's motion profile is obtained；
S50: analyzing client's motion profile, if client's motion profile meets preset angular range, obtains
Client's direction of motion of client's motion profile is taken, and client is obtained according to client's direction of motion and passes in and out situation, and will
The client passes in and out situation and sends and be written in volume of the flow of passengers analytical database.
2. the volume of the flow of passengers as described in claim 1 passes in and out recognition methods, which is characterized in that before the step S30, the visitor
Flow passes in and out recognition methods further include:
S301: the background picture of identification video recording in the shop is obtained, and using the background picture as comparison picture；
S302: several human body head region pictures are obtained, and extract head region in the picture of the human body head region respectively
Characteristic value, construction feature vector；
S303: being trained the comparison picture and described eigenvector using deep learning, obtains the number of people detection mould
Type.
3. the volume of the flow of passengers as described in claim 1 passes in and out recognition methods, which is characterized in that the step S30 includes:
S31: the framing image and the similarity compared between image are successively calculated sequentially in time, and is chosen similar
Degree is less than the framing image of preset threshold value, as identification image；
S32: the identification image is detected using the number of people detection model, if detecting institute in the identification image
Number of people feature is stated, then using the identification image as the head image.
4. the volume of the flow of passengers as described in claim 1 passes in and out recognition methods, which is characterized in that the step S40 includes:
S41: coordinate is divided according to pixel for the framing image, and obtains head image institute described in each frame framing image
Coordinate points；
S42: the distance between the coordinate points where head image described in adjacent two frame are judged, if between the coordinate points
Distance then determines that the head image of two adjacent two frames is the same person between 20-30 pixel；
S43: obtaining the head image that continuous several frames are determined as same people, and by head image pair described in several frames
The coordinate points answered are put into the coordinate, and are linked to be client's motion profile sequentially in time.
5. the volume of the flow of passengers as described in claim 1 passes in and out recognition methods, which is characterized in that the step S50 includes:
S51: center line is set in the coordinate；
S52: it if the beginning of client's motion profile and end are located at the center line both ends, obtain the client and moves rail
The angle of mark and the center line；
S53: corresponding with end acquisition according to client's motion profile beginning if the angle meets the angular range
Client's direction of motion.
6. a kind of volume of the flow of passengers passes in and out identification device, which is characterized in that the volume of the flow of passengers passes in and out identification device and includes:
Video recording obtains module, and video recording is identified in shop for obtaining in real time；
Framing module obtains framing sequentially in time for carrying out sub-frame processing to the identification video recording acquired
Image；
Feature recognition module, in such a way that the framing image detection goes out number of people feature, being obtained using number of people detection model
Head image；
Track generation module obtains client's fortune for the head image in the framing image according to continuous several frames
Dynamic rail mark；
Analysis and memory module, for analyzing client's motion profile, if client's motion profile meet it is default
Angular range, then obtain client's direction of motion of client's motion profile, and visitor is obtained according to client's direction of motion
Family passes in and out situation, and client disengaging situation is sent and is written in volume of the flow of passengers analytical database.
7. the volume of the flow of passengers as claimed in claim 6 passes in and out identification device, which is characterized in that the volume of the flow of passengers disengaging identification device is also
Include:
Compare picture and obtain module, for obtaining the background picture for identifying video recording in the shop, and using the background picture as
Compare picture；
Feature vector constructs module, for obtaining several human body head region pictures, and extracts the human body head area respectively
The characteristic value of head region in the picture of domain, construction feature vector；
Deep learning module obtains institute for being trained using deep learning to the comparison picture and described eigenvector
State number of people detection model.
8. the volume of the flow of passengers as claimed in claim 6 passes in and out identification device, which is characterized in that the feature recognition module includes:
Similarity calculation submodule, for successively calculating the framing image sequentially in time and described comparing between image
Similarity, and the framing image that similarity is less than preset threshold value is chosen, as identification image；
Detection sub-module, for being detected using the number of people detection model to the identification image, if scheming in the identification
The number of people feature is detected as in, then using the identification image as the head image.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
The step of any one of 5 volume of the flow of passengers disengaging recognition methods.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realization volume of the flow of passengers as described in any one of claim 1 to 5 passes in and out recognition methods when the computer program is executed by processor
The step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910253943.8A CN110334569B (en) | 2019-03-30 | 2019-03-30 | Passenger flow volume in-out identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910253943.8A CN110334569B (en) | 2019-03-30 | 2019-03-30 | Passenger flow volume in-out identification method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110334569A true CN110334569A (en) | 2019-10-15 |
| CN110334569B CN110334569B (en) | 2022-09-16 |
Family
ID=68139237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910253943.8A Active CN110334569B (en) | 2019-03-30 | 2019-03-30 | Passenger flow volume in-out identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110334569B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110713082A (en) * | 2019-10-22 | 2020-01-21 | 日立楼宇技术（广州）有限公司 | Elevator control method, system, device and storage medium |
| CN111091057A (en) * | 2019-11-15 | 2020-05-01 | 腾讯科技（深圳）有限公司 | Information processing method and device and computer readable storage medium |
| CN111160243A (en) * | 2019-12-27 | 2020-05-15 | 深圳云天励飞技术有限公司 | Passenger flow volume statistical method and related product |
| CN111738134A (en) * | 2020-06-18 | 2020-10-02 | 北京市商汤科技开发有限公司 | Method, device, equipment and medium for acquiring passenger flow data |
| CN112232262A (en) * | 2020-10-27 | 2021-01-15 | 上海依图网络科技有限公司 | Passenger flow volume statistical method and device |
| CN112668525A (en) * | 2020-12-31 | 2021-04-16 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
| CN113095209A (en) * | 2021-04-07 | 2021-07-09 | 深圳海智创科技有限公司 | Crowd identification method and system for passenger flow and electronic equipment |
| CN113469075A (en) * | 2021-07-07 | 2021-10-01 | 上海商汤智能科技有限公司 | Method, device and equipment for determining traffic flow index and storage medium |
| CN114220141A (en) * | 2021-11-23 | 2022-03-22 | 慧之安信息技术股份有限公司 | Shop frequent visitor identification method based on face identification |
| 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 |
| CN114937241A (en) * | 2022-06-01 | 2022-08-23 | 北京凯利时科技有限公司 | Transition zone based passenger flow statistics method and system and computer program product |
| CN117690094A (en) * | 2024-02-01 | 2024-03-12 | 通用电梯股份有限公司 | Elevator passenger flow volume data statistics method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070122058A1 (en) * | 2005-11-28 | 2007-05-31 | Fujitsu Limited | Method and apparatus for analyzing image, and computer product |
| US20110142282A1 (en) * | 2009-12-14 | 2011-06-16 | Indian Institute Of Technology Bombay | Visual object tracking with scale and orientation adaptation |
| CN104637058A (en) * | 2015-02-06 | 2015-05-20 | 武汉科技大学 | Image information-based client flow volume identification statistic method |
| CN108932464A (en) * | 2017-06-09 | 2018-12-04 | 北京猎户星空科技有限公司 | Passenger flow volume statistical method and device |
| CN109272347A (en) * | 2018-08-16 | 2019-01-25 | 苏宁易购集团股份有限公司 | A kind of statistical analysis technique and system of shops's volume of the flow of passengers |
-
2019
- 2019-03-30 CN CN201910253943.8A patent/CN110334569B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070122058A1 (en) * | 2005-11-28 | 2007-05-31 | Fujitsu Limited | Method and apparatus for analyzing image, and computer product |
| US20110142282A1 (en) * | 2009-12-14 | 2011-06-16 | Indian Institute Of Technology Bombay | Visual object tracking with scale and orientation adaptation |
| CN104637058A (en) * | 2015-02-06 | 2015-05-20 | 武汉科技大学 | Image information-based client flow volume identification statistic method |
| CN108932464A (en) * | 2017-06-09 | 2018-12-04 | 北京猎户星空科技有限公司 | Passenger flow volume statistical method and device |
| CN109272347A (en) * | 2018-08-16 | 2019-01-25 | 苏宁易购集团股份有限公司 | A kind of statistical analysis technique and system of shops's volume of the flow of passengers |
Non-Patent Citations (1)
| Title |
|---|
| 宋晓冰: "基于轮廓线的三维人脸特征提取与识别", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110713082A (en) * | 2019-10-22 | 2020-01-21 | 日立楼宇技术（广州）有限公司 | Elevator control method, system, device and storage medium |
| CN111091057A (en) * | 2019-11-15 | 2020-05-01 | 腾讯科技（深圳）有限公司 | Information processing method and device and computer readable storage medium |
| CN111160243A (en) * | 2019-12-27 | 2020-05-15 | 深圳云天励飞技术有限公司 | Passenger flow volume statistical method and related product |
| CN111738134A (en) * | 2020-06-18 | 2020-10-02 | 北京市商汤科技开发有限公司 | Method, device, equipment and medium for acquiring passenger flow data |
| 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 |
| CN112232262A (en) * | 2020-10-27 | 2021-01-15 | 上海依图网络科技有限公司 | Passenger flow volume statistical method and device |
| CN112668525B (en) * | 2020-12-31 | 2024-05-07 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
| CN112668525A (en) * | 2020-12-31 | 2021-04-16 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
| CN113095209A (en) * | 2021-04-07 | 2021-07-09 | 深圳海智创科技有限公司 | Crowd identification method and system for passenger flow and electronic equipment |
| CN113095209B (en) * | 2021-04-07 | 2024-05-31 | 深圳海智创科技有限公司 | Crowd identification method and system for passenger flow and electronic equipment |
| CN113469075A (en) * | 2021-07-07 | 2021-10-01 | 上海商汤智能科技有限公司 | Method, device and equipment for determining traffic flow index and storage medium |
| CN114220141A (en) * | 2021-11-23 | 2022-03-22 | 慧之安信息技术股份有限公司 | Shop frequent visitor identification method based on face identification |
| CN114937241B (en) * | 2022-06-01 | 2024-03-26 | 北京凯利时科技有限公司 | Transition zone-based passenger flow statistics method and system and computer program product |
| CN114937241A (en) * | 2022-06-01 | 2022-08-23 | 北京凯利时科技有限公司 | Transition zone based passenger flow statistics method and system and computer program product |
| CN117690094B (en) * | 2024-02-01 | 2024-04-09 | 通用电梯股份有限公司 | Elevator passenger flow volume data statistics method and device, electronic equipment and storage medium |
| CN117690094A (en) * | 2024-02-01 | 2024-03-12 | 通用电梯股份有限公司 | Elevator passenger flow volume data statistics method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110334569B (en) | 2022-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110334569A (en) | The volume of the flow of passengers passes in and out recognition methods, device, equipment and storage medium | |
| JP6646124B2 (en) | Method for obtaining bounding box corresponding to an object on an image using CNN (Convolutional Neural Network) including tracking network and apparatus using the same | |
| CN110533925B (en) | Vehicle illegal video processing method and device, computer equipment and storage medium | |
| CN109190508B (en) | Multi-camera data fusion method based on space coordinate system | |
| US10140508B2 (en) | Method and apparatus for annotating a video stream comprising a sequence of frames | |
| CN109919977B (en) | Video motion person tracking and identity recognition method based on time characteristics | |
| CN110379050A (en) | A kind of gate control method, apparatus and system | |
| US20160321507A1 (en) | Person counting method and device for same | |
| US20120093362A1 (en) | Device and method for detecting specific object in sequence of images and video camera device | |
| CN105518744A (en) | Pedestrian re-identification method and equipment | |
| JP7246104B2 (en) | License plate identification method based on text line identification | |
| US20150302240A1 (en) | Method and device for locating feature points on human face and storage medium | |
| CN106169071A (en) | A kind of Work attendance method based on dynamic human face and chest card recognition and system | |
| CN107330371A (en) | Acquisition methods, device and the storage device of the countenance of 3D facial models | |
| CN104318263A (en) | Real-time high-precision people stream counting method | |
| CN111160172A (en) | Parking space detection method and device, computer equipment and storage medium | |
| CN103093212A (en) | Method and device for clipping facial images based on face detection and face tracking | |
| CN110298268A (en) | Method, apparatus, storage medium and the camera of the single-lens two-way passenger flow of identification | |
| CN112651291A (en) | Video-based posture estimation method, device, medium and electronic equipment | |
| CN110399835A (en) | A kind of analysis method of personnel's residence time, apparatus and system | |
| CN109297489A (en) | A kind of indoor navigation method based on user characteristics, electronic equipment and storage medium | |
| CN112017212B (en) | Training and tracking method and system of face key point tracking model | |
| CN110705366A (en) | Real-time human head detection method based on stair scene | |
| CN110334568B (en) | Track generation and monitoring method, device, equipment and storage medium | |
| CN116912880A (en) | Bird recognition quality assessment method and system based on bird key point detection |
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 |