CN112446742A - Passenger flow statistical system - Google Patents

Passenger flow statistical system Download PDF

Info

Publication number
CN112446742A
CN112446742A CN202011469613.1A CN202011469613A CN112446742A CN 112446742 A CN112446742 A CN 112446742A CN 202011469613 A CN202011469613 A CN 202011469613A CN 112446742 A CN112446742 A CN 112446742A
Authority
CN
China
Prior art keywords
store
area
face
customer
coordinate
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
Application number
CN202011469613.1A
Other languages
Chinese (zh)
Inventor
姚国良
林喆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Sunmi Technology Group Co Ltd
Shanghai Sunmi Technology Co Ltd
Shenzhen Michelangelo Technology Co Ltd
Original Assignee
Shanghai Sunmi Technology Group Co Ltd
Shenzhen Michelangelo Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Sunmi Technology Group Co Ltd, Shenzhen Michelangelo Technology Co Ltd filed Critical Shanghai Sunmi Technology Group Co Ltd
Priority to CN202011469613.1A priority Critical patent/CN112446742A/en
Publication of CN112446742A publication Critical patent/CN112446742A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201Market modelling; Market analysis; Collecting market data
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0207Discounts or incentives, e.g. coupons or rebates
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/12Hotels or restaurants
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161Detection; Localisation; Normalisation

Abstract

The invention provides a passenger flow statistical system, which comprises a camera shooting unit, a judging unit, a database and a central control unit, wherein the camera shooting unit is used for shooting a passenger flow; the camera shooting unit, the judging unit and the database are in signal connection with the central control unit; the camera shooting unit is used for shooting a customer travelling path and face data; the judging unit comprises a face coordinate judging unit, a face area judging unit and a face ID judging unit; the database is used for storing customer information so as to provide a passenger flow statistical system for comprehensively recording the traveling and information of customers.

Description

Passenger flow statistical system
Technical Field
The invention relates to the technical field of passenger flow statistics, in particular to a passenger flow statistics system.
Background
Today, no matter what industry, data is the basis for analyzing industry patterns, mining industry depth, and searching new industry state of the industry. In the retail industry, the customer group data is more important, the flow rule can be analyzed by the customer group data, the operation states of supermarkets, markets, shopping centers and shops can be obtained, the sales potential can be mined to a greater extent, and the sales opportunities of retail stores are increased. The crowd data is derived from the traffic statistics. At present, the mainstream passenger flow statistical methods mainly comprise manual statistics, infrared statistics, induction device statistics, video statistics, gate machine statistics and the like, most of the methods can only obtain the number of the passenger flows entering and leaving a store, and no way is available for refining the passenger group attributes, so that a data basis cannot be provided for further passenger group analysis.
At present, the mainstream passenger flow statistical methods mainly comprise manual statistics, infrared statistics, induction device statistics, video statistics, gate machine statistics and the like, most of the methods can only roughly obtain the number of the passenger flows entering and leaving a store, and no way is available for refining the passenger group attributes, so that a data basis cannot be provided for further passenger group analysis. The method records the age, the sex and the time of each customer entering the store, and simultaneously counts the data of all the customers leaving the store and passing the store as far as possible, thereby providing data support for the analysis of the customer group.
Disclosure of Invention
The invention aims to provide a passenger flow statistical system for comprehensively recording the traveling and information of customers.
In order to achieve the above object, the present invention provides a passenger flow statistics system, which comprises a camera unit, a judgment unit, a database and a central control unit; the camera shooting unit, the judging unit and the database are in signal connection with the central control unit;
the camera shooting unit is used for shooting a customer travelling path and face data;
the judging unit comprises a face coordinate judging unit, a face area judging unit and a face ID judging unit;
the database is used for storing customer information.
Further, the determination unit includes a straight travel store determination, a left turn store determination, a right turn store determination, a line-in store determination, a straight travel store determination, a turn exit store determination, and a store-passing determination.
Further, the camera unit is a camera preset in the store or outside the store, the camera is arranged to photograph a fixed designated area, and when the customer enters the designated area, the judging unit judges the customer travel.
Further, the judging unit judges whether the customer enters the store, passes the store or leaves the store by the photographed image, and the database records the customer information according to three categories of entering the store, passing the store and leaving the store.
Further, the store-entering judgment method of the judgment unit includes:
the direct store entry determination step:
sa1, the face area judgment unit obtains that the initial area of the face/head of the customer entering the camera shooting area is smaller than an initial threshold value;
sa2, the face area judgment unit obtains that the initial threshold value of the maximum area of the face/head of the customer entering the camera shooting area is larger than the final threshold value;
sa3, the face area judgment unit judges that the area change value of the face/head of the customer in the camera shooting area is larger than a threshold value;
the left-turn shop judgment step:
sb1, the face area judging unit obtains that the initial area of the face/head of the customer entering the camera shooting area is smaller than an initial threshold value;
sb 2: the face coordinate judging unit divides coordinates in the shooting area, judges the coordinate position of the person entering the store, compares the coordinate position with the initial coordinate of the person entering the shooting area, and judges that the store entering coordinate is positioned in front of the original coordinate and is a left-turning store;
the right branch store judgment step:
the face area judgment unit acquires that the initial area of the face/head of the customer entering the camera shooting area is smaller than an initial threshold value;
sc 2: the face coordinate judging unit divides coordinates in the shooting area, judges the coordinate position of a person entering a store, compares the coordinate position with the initial coordinate of the person entering the shooting area, and judges that the store entering coordinate is positioned in the front right of the original coordinate to be transferred to the store right;
the step of judging the incoming of the incoming line:
sd1, a person is positioned at the edge of a picture of a shooting area, and the face area judgment unit acquires that the initial area of the face/head of a customer entering the shooting area is smaller than an initial threshold value;
and Sd2, the face coordinate determination unit divides two determination touch lines in the image pickup area, takes the chin of the person as a coordinate point, and determines that the touch line enters the store when the coordinate is shifted from the first determination touch line to the second determination touch line.
Further, the method for judging the exit of the store by the judging unit includes:
the straight-out-of-store determination step:
se1, the face area judgment unit obtains the initial area of the head of the customer entering the camera shooting area and the initial threshold value;
se2, the face area judgment unit obtains that the final area of the head of the customer leaving the camera shooting area is smaller than the final threshold value, the size of the head changes from large to small, and the customer is judged to go out of the store directly.
The turning store-out judging step:
sf1, judging that the customer is out of store by using the steps Se1 and Se 2;
sf2, the face coordinate judging unit divides the coordinates in the image pick-up area, judges the coordinate position of the person after the shop exit, compares the coordinate position with the left position before the person exits the shop, and confirms that the customer is the turning exit.
Further, the store-passing judgment method of the judgment unit includes the steps of:
sg1, dividing a door line in a shooting area by the face coordinate judging unit, wherein the customer does not cross the door line coordinate;
sg2, the face area judgment unit obtains that the initial area of the face/head of the customer entering the camera shooting area is smaller than a preset threshold value.
Compared with the prior art, the invention has the advantages that:
(1) the invention effectively analyzes the attributes of all the customers entering the store and provides data support for the analysis of the customer group of the store.
(2) The invention can count the store-entering and store-passing passenger flow data of the store as much as possible, and can effectively analyze the time period of the store which is most suitable for popularizing and promoting activities.
(3) Although the AI chip needs to be installed locally, the method effectively shares the work of the cloud, and avoids the phenomenon that all equipment cannot be used normally after the cloud goes wrong.
Drawings
FIG. 1 is a flow chart of the operation of a passenger flow statistics system in an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a straight-traveling store determination in an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a left-hand branch store determination in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a right turn store decision in an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating an exemplary approach to store determination in accordance with an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating a straight-out determination in an embodiment of the present invention;
FIG. 7 is a schematic view illustrating a turn-out determination in an embodiment of the present invention;
fig. 8 is a schematic diagram illustrating a store-passing determination in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be further described below.
The invention provides a passenger flow statistical system, which comprises a camera shooting unit, a judging unit, a database and a central control unit, wherein the camera shooting unit is used for shooting a passenger flow; the camera shooting unit, the judging unit and the database are in signal connection with the central control unit;
the camera shooting unit is used for shooting a customer travelling path and face data;
the judging unit comprises a face coordinate judging unit, a face area judging unit and a face ID judging unit;
the database is used for storing customer information.
In this embodiment, the imaging unit is a camera preset in the store or outside the store, the camera is arranged to photograph a fixed designated area, and the determining unit determines the route of the customer when the customer enters the designated area.
In the present embodiment, the determination unit determines whether the customer is entering, passing, or leaving the store by using the photographed image, and the database records the customer information in accordance with three categories, i.e., entering, passing, and leaving the store.
In this embodiment, the working flow of the system is as shown in fig. 1, the image pickup unit collects customer information, the determination unit determines whether a human face and a human head exist, if so, determines whether the customer meets the store-entering logic, and if so, records the age and gender information of the customer in a store-entering class of the database; if not, judging whether the customer accords with the store-passing logic, and if so, recording the age and gender information of the customer in a store-passing class of the database; if not, judging whether the customer accords with the store-out logic, if so, recording the age and gender information of the customer in a store-out class of the database, and if not, ignoring.
In the present embodiment, as shown in fig. 2, the straight travel determination:
the change of the human head face pixels is used for judging, when a customer enters the door from the outside, the human head face pixels can be increased, the customer can be judged to enter the store when the human head face pixels are larger than a certain value, the initial size of the human head face is limited, and the situation that the customer in the store moves wrongly is judged to enter the store is prevented. The travel-straight store can be judged only by meeting all the following conditions:
area _0< init _ max (initially acquired head area <16000 or face area < 9000).
area _2> enter _ min (maximum head/face area of customer is greater than specified value throughout store-in process, wherein maximum head area >22000 or maximum face area > 13000).
area _2-area _0 ≧ DIFF (customer head/face area needs to be satisfied with enough change in the store-entering process, where the change in head area ≧ 4000 or face area ≧ 3000).
In the present embodiment, as shown in fig. 3, the left-hand branch-in determination:
the human head face pixels and the coordinate tracks are used for judging, when a person enters the door from the outside, the human head face pixels can be increased, and the X coordinates and the Y coordinates can have certain offset. Where the current x1 coordinate is less than the left _ x coordinate on the left side of the door for a left turn, the difference between the y1 coordinate and the y0 coordinate is greater by a threshold. The left-hand trip to the store can be determined if all of the following conditions are satisfied:
area _0< init _ max (initially acquired head area <16000 or face area < 9000).
Left _ x-x 1> LR _ DISTANCE (the customer has to traverse some DISTANCE to the Left, which is 300).
y1-y0> TB _ DISTANCE (the customer needs to move a certain DISTANCE longitudinally during the store-entering process, TB _ DISTANCE is 200).
In the present embodiment, as shown in fig. 4, the right-turn shop determination:
the human head face pixels and the coordinate tracks are used for judging, when a person enters the door from the outside, the human head face pixels can be increased, and the X coordinates and the Y coordinates can have certain offset. In the case of a right turn, the current x1 coordinate is greater than the right _ x coordinate on the right side of the door by a threshold value greater than the difference between the y1 and y0 coordinates. The right-hand-turn can be determined only if all the following conditions are satisfied:
area _0< init _ max (initially acquired head area <16000 or face area < 9000);
x1-Right _ x > LR _ DISTANCE (the customer has to traverse a certain DISTANCE to the Right, LR _ DISTANCE is 300).
y1-y0> TB _ DISTANCE (the customer needs to move a certain DISTANCE longitudinally during the store-entering process, TB _ DISTANCE is 200).
In the present embodiment, as shown in fig. 5, the incoming line determination:
the coordinate track of the human head and the human face is used for judging, and the coordinates of the two lines need to be adjusted when the magnification of the lens is adjusted. The larger the camera magnification, the higher the position of the person in the picture. It should be noted that only a part of the human head face can be seen at the edge of the picture, so that the X and Y coordinates (the center position of the human head face) cannot be recognized by the AI chip, and the current strategy is to judge the X and Y coordinates of the chin, so that whether the human head face is shifted to the second line can be judged more accurately. The system can be judged to enter the store by touching the line when all the following conditions are met:
area _0< init _ max (initially acquired head area <16000 or face area < 9000);
y0 (head margin/chin) line1_ Y, the initial moment is outside the first line (magnification factor of-100 x according to the Y-axis coordinate of the gate line drawn in step 1).
Y1 (top of head/top of face) > line2_ Y, the current time being inside the second line (according to the Y-axis coordinate +100 magnification factor of the gate line drawn in step 1).
In the present embodiment, as shown in fig. 6, straight-out determination:
the judgment is carried out through the head pixels and the coordinate tracks, because the human face faces away from the camera when the person goes out of the store, the camera can only capture the head information. The following conditions are satisfied to be judged to go out of the store directly:
head _ y0-head _ y1> ly (the customer needs to move a certain distance outward, the ly being the head height of the customer).
head _1< head _0 (the customer's travel track meets the change from big to small).
(Head _1< Head _ out _ min (15000)) & (Head _0> Head _ init _ max (22000)) (customer initial Head area >22000 and the customer's Head area <15000 at the current time).
In the present embodiment, as shown in fig. 7, the turning exit determination:
the turning store-out is a supplement of a straight store-out, if a customer in the store-out directly turns right or left from a door to the store-out, the requirement of the head and the longitudinal distance determined by the store-out can not be met, the customer can transversely and longitudinally move when turning the store-out, and the size of the head is larger than that of a person outside the store. The driver can be judged to turn out of the store only by meeting all the following conditions:
head _ y0-head _ y1>0.5 by ly (the customer needs to move a certain distance outward, the ly being the head height of the customer).
(Head _ x1-Left _ x) <0.8 door width | (Right _ x-Head _ x1) <0.8 door width (customer needs to traverse a distance but cannot exceed the door width (i.e. the door set in step 1), excluding cross store interference and intra-store interference from Left to Right).
Head _0> Head _ entry _ min (15000) (customer Head area meets requirements, Head interference outside the store is excluded).
In the present embodiment, as shown in fig. 8, the store-passing determination:
the store-by decision is used to count the population that passes through the store doorway and does not enter the store. The store can be judged to be passed by meeting all the following conditions:
and after the customer disappears on the picture, judging whether the customer belongs to the store-passing customer flow.
After determining that the customer does not belong to the store-entering passenger flow or the store-exiting passenger flow, the customer is judged to be over-store.
Head _ x1-Head _ x0>0.5 door line width (the customer needs to traverse a distance, the door line width is the door line set in step 1).
To filter the flow of passengers traveling inside the store and traveling far outside the store, a limit (30-110) is set on the threshold for the size of the head.
The above description is only a preferred embodiment of the present invention, and does not limit the present invention in any way. It will be understood by those skilled in the art that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (9)

1. A passenger flow statistical system is characterized by comprising a camera shooting unit, a judging unit, a database and a central control unit; the camera shooting unit, the judging unit and the database are in signal connection with the central control unit;
the camera shooting unit is used for shooting a customer travelling path and face data;
the judging unit comprises a face coordinate judging unit, a face area judging unit and a face ID judging unit;
the database is used for storing customer information.
2. The passenger flow statistic system according to claim 1, wherein said determination unit includes a straight-traveling store determination, a left-hand-in store determination, a right-hand-in store determination, an approach-line store determination, a straight-traveling store determination, a turn-out store determination, and a store-passing determination.
3. The passenger flow statistic system according to claim 2, wherein said imaging means is a camera preset in a store or outside the store in advance, and said camera is provided to photograph a fixed specified area, and when a customer enters said specified area, said judging means judges a customer's travel.
4. The system according to claim 3, wherein the judging unit judges whether the customer is entering, passing, or leaving the store by taking a picture, and the database records the customer information in accordance with three categories, i.e., entering, passing, and leaving.
5. The passenger flow statistic system according to claim 4, wherein the store-entering judging method of the judging unit includes:
the direct store entry determination step:
sa1, the face area judgment unit obtains that the initial area of the face/head of the customer entering the camera shooting area is smaller than an initial threshold value;
sa2, the face area judgment unit obtains that the initial threshold value of the maximum area of the face/head of the customer entering the camera shooting area is larger than the final threshold value;
sa3, the face area judgment unit judges that the area change value of the face/head of the customer in the camera shooting area is larger than a threshold value;
the left-turn shop judgment step:
sb1, the face area judging unit obtains that the initial area of the face/head of the customer entering the camera shooting area is smaller than an initial threshold value;
sb 2: the face coordinate judging unit divides coordinates in the shooting area, judges the coordinate position of the person entering the store, compares the coordinate position with the initial coordinate of the person entering the shooting area, and judges that the store entering coordinate is positioned in front of the original coordinate and is a left-turning store;
the right branch store judgment step:
the face area judgment unit acquires that the initial area of the face/head of the customer entering the camera shooting area is smaller than an initial threshold value;
sc 2: the face coordinate judging unit divides coordinates in the shooting area, judges the coordinate position of a person entering a store, compares the coordinate position with the initial coordinate of the person entering the shooting area, and judges that the store entering coordinate is positioned in the front right of the original coordinate to be transferred to the store right;
the step of judging the incoming of the incoming line:
sd1, a person is positioned at the edge of a picture of a shooting area, and the face area judgment unit acquires that the initial area of the face/head of a customer entering the shooting area is smaller than an initial threshold value;
and Sd2, the face coordinate determination unit divides two determination touch lines in the image pickup area, takes the chin of the person as a coordinate point, and determines that the touch line enters the store when the coordinate is shifted from the first determination touch line to the second determination touch line.
6. The passenger flow statistic system according to claim 4, wherein the out-of-store judgment method of said judgment unit includes:
the straight-out-of-store determination step:
se1, the face area judgment unit obtains the initial area of the head of the customer entering the camera shooting area and the initial threshold value;
se2, the face area judgment unit obtains that the final area of the head of the customer leaving the camera shooting area is smaller than the final threshold value, the size of the head changes from large to small, and the customer is judged to go out of the store directly.
The turning store-out judging step:
sf1, judging that the customer is out of store by using the steps Se1 and Se 2;
sf2, the face coordinate judging unit divides the coordinates in the image pick-up area, judges the coordinate position of the person after the shop exit, compares the coordinate position with the left position before the person exits the shop, and confirms that the customer is the turning exit.
7. The passenger flow statistic system according to claim 4, wherein the store-passing judgment method of said judgment unit comprises the steps of:
sg1, dividing a door line in a shooting area by the face coordinate judging unit, wherein the customer does not cross the door line coordinate;
sg2, the face area judgment unit obtains that the initial area of the face/head of the customer entering the camera shooting area is smaller than a preset threshold value.
8. The passenger flow statistics system of claim 1, wherein the central control unit is an AI chip.
9. The system of claim 1, wherein the face ID determination unit is connected to a cloud public security database to obtain customer ID information.
CN202011469613.1A 2020-12-14 2020-12-14 Passenger flow statistical system Pending CN112446742A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011469613.1A CN112446742A (en) 2020-12-14 2020-12-14 Passenger flow statistical system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011469613.1A CN112446742A (en) 2020-12-14 2020-12-14 Passenger flow statistical system

Publications (1)

Publication Number Publication Date
CN112446742A true CN112446742A (en) 2021-03-05

Family

ID=74739655

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011469613.1A Pending CN112446742A (en) 2020-12-14 2020-12-14 Passenger flow statistical system

Country Status (1)

Country Link
CN (1) CN112446742A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100046836A1 (en) * 2008-08-25 2010-02-25 Chunghwa Picture Tubes, Ltd. Device of gathering statistics of gray distribution of image and method thereof
CN106372570A (en) * 2016-08-19 2017-02-01 云赛智联股份有限公司 Visitor flowrate statistic method
CN108985218A (en) * 2018-07-10 2018-12-11 上海小蚁科技有限公司 People flow rate statistical method and device, calculates equipment at storage medium
CN110135279A (en) * 2019-04-23 2019-08-16 深圳神目信息技术有限公司 A kind of method for early warning based on recognition of face, device, equipment and computer-readable medium
CN110766454A (en) * 2019-10-12 2020-02-07 广州臻一计算机系统有限公司 Method for collecting customer visit information of store and store subsystem architecture
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

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100046836A1 (en) * 2008-08-25 2010-02-25 Chunghwa Picture Tubes, Ltd. Device of gathering statistics of gray distribution of image and method thereof
CN106372570A (en) * 2016-08-19 2017-02-01 云赛智联股份有限公司 Visitor flowrate statistic method
CN108985218A (en) * 2018-07-10 2018-12-11 上海小蚁科技有限公司 People flow rate statistical method and device, calculates equipment at storage medium
CN110135279A (en) * 2019-04-23 2019-08-16 深圳神目信息技术有限公司 A kind of method for early warning based on recognition of face, device, equipment and computer-readable medium
CN110766454A (en) * 2019-10-12 2020-02-07 广州臻一计算机系统有限公司 Method for collecting customer visit information of store and store subsystem architecture
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

Similar Documents

Publication Publication Date Title
CN109784162B (en) Pedestrian behavior recognition and trajectory tracking method
EP3410415B1 (en) Image processing device, imaging device, moving body device control system and image processing program
CN105844234B (en) Method and equipment for counting people based on head and shoulder detection
JP3288474B2 (en) Image processing device
US8942913B2 (en) System and method for on-road traffic density analytics using video stream mining and statistical techniques
US9477892B2 (en) Efficient method of offline training a special-type parked vehicle detector for video-based on-street parking occupancy detection systems
CN105539293B (en) Lane departure warning method and device and car steering accessory system
KR101692628B1 (en) Method for detecting right lane area and left lane area of rear of vehicle using region of interest and image monitoring system for vehicle using the same
CN103366154B (en) Reconfigurable clear path detection system
US20190180111A1 (en) Image summarization system and method
CN107719361A (en) Automatic parking householder method and system based on image vision
KR101665961B1 (en) Apparatus for providing image of vehicle and method thereof
CN106412508A (en) Intelligent monitoring method and system of illegal line press of vehicles
CN102254428A (en) Traffic jam detection method based on video processing
KR101939350B1 (en) Method and apparatus for detecting free riding
KR20210122181A (en) Apparatus and method for controlling traffic signal based on reinforcement learning
CN109643488A (en) Traffic abnormal incident detection device and method
JP2020013206A (en) Device for detecting two-wheeled vehicle from moving image/camera, program, and system
US11727580B2 (en) Method and system for gathering information of an object moving in an area of interest
US20120189161A1 (en) Visual attention apparatus and control method based on mind awareness and display apparatus using the visual attention apparatus
KR20210004271A (en) Method and system for recognizing situation based on event tagging
CN112446742A (en) Passenger flow statistical system
Oh et al. Development of an automatic traffic conflict detection system based on image tracking technology
Suzuki et al. Pedestrian near-miss analysis on vehicle-mounted driving recorders
CN103606280B (en) A kind of information identifying method, device and system

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210305