CN211699033U - Human body tracking system - Google Patents

Abstract

The invention provides a human body tracking system, which realizes the tracking and positioning of coordinates of target object users in different areas without dead angles in the whole shopping process of an unmanned supermarket; the human body tracking system comprises a human body marking tracking device I arranged at an entrance gate machine of an entrance guard system of an unmanned supermarket, a human body marking tracking device II arranged in the front area of a goods shelf, a human body marking tracking device III arranged on the roof of the closed space of the unmanned supermarket, and a human body marking tracking device IV arranged at an exit gate machine of the closed space. The coordinate tracking and positioning of the target object user in different regions without dead angles in the whole shopping process of the unmanned supermarket are realized, and the risk that the supermarket is lost due to the fact that goods are carried by the unmanned supermarket customer privately is greatly avoided.

Description

Human body tracking system

Technical Field

The utility model relates to a human tracking system who uses in supermarket retail particularly, relates to a human tracking system who uses in intelligent unmanned supermarket.

Background

Compared with the traditional supermarket with specific management staff, the unmanned supermarket has the advantages that the management staff can be used for managing the supermarket. In a traditional shopping mode of supermarket retail industry, each supermarket or convenience store needs special salesmen and cashiers, and labor cost is high. With the great development of the electronic payment technology, the identity recognition technology and the commodity recognition technology, the supermarket with specific management workers has great development space when the unmanned supermarket is used for replacing the traditional supermarket in the retail industry, and the supermarket has development feasibility under the existing technical conditions.

The self-service shopping and self-service settlement method is characterized in that the self-service shopping and self-service settlement can be carried out in the unmanned supermarket, namely the supermarket without salesmen. In the unmanned supermarket project, commodity selection and payment are completed by customers. In the preliminary attempt of the unmanned supermarket, due to the fact that supervision of workers is not available, meanwhile, accurate identity recognition, positioning and tracking devices are not available for customers entering the unmanned supermarket, and the customers carry commodities privately, and the commodities are taken out of the supermarket without settlement.

In order to solve the above problems, in the existing unmanned supermarket system technology, someone senses goods purchased by a user by using an RFID technology, and in this way, an RFID tag needs to be arranged on each goods, and an RFID reader is arranged at an entrance guard, so that the consumption content of the user can be recorded when the user walks out of the entrance guard. The scheme has the problems that firstly, due to the fact that the RFID tag needs to be arranged on each commodity, the hardware cost is high, the cost of the commodity is increased by adding the RFID tag on each commodity, the operation cost of the supermarket is increased, and the competitiveness of the supermarket is reduced; secondly, monitoring of the commodities is realized by adding RFID tags to the commodities, and if a user intentionally shields and removes the RFID tags or the RFID tags break down, the goods cannot be identified and settled, even the goods are taken away by a customer privately, and the system cannot sense the monitoring; third, if a user eats an edible item before leaving the store, the package is left in a supermarket, and the RFID reader cannot sense and determine the actual consumption amount of the user.

SUMMERY OF THE UTILITY MODEL

For effectively solving the problem that exists among the prior art, the utility model provides a human tracking system is applied to unmanned supermarket.

In order to achieve the purpose, the application provides a human body tracking system which can realize the tracking and positioning of coordinates of target object users in different areas without dead angles in the whole shopping process of an unmanned supermarket; the human body tracking system comprises a human body marking tracking device I arranged at an entrance gate machine of an entrance guard system of an unmanned supermarket, a human body marking tracking device II arranged in the front area of a goods shelf, a human body marking tracking device III arranged on the roof of the closed space of the unmanned supermarket, and a human body marking tracking device IV arranged at an exit gate machine of the closed space.

Further, the human body labeling and tracking devices I to IV adopt imaging devices for acquiring images in real time, wherein the acquired images at least comprise all or part of images of the target object; the multi-image device shares the spliced image at the same time, and the image conversion tracking mark of the target object user is not lost or mistakenly recognized.

Further, the human body tracking system establishes a plane coordinate system in the closed space through human body labeling and tracking devices I to IV arranged at an entrance, a region in front of the goods shelf, a roof of the closed space and an exit, demarcates the region of the electronic fence in the range of the coordinate system, demarcates the region of the entrance, the exit and the region of one square meter in front of each goods shelf, and acquires the coordinate system coordinate of the current target object in the closed region and the region number of the electronic fence through the image acquired in real time.

Further, the human body labeling and tracking devices I to IV finish image acquisition of a target object and then send the acquired image to the main processor, and the main processor finishes target object image receiving, target object image splicing and target object coordinate operation, so that tracking and calibration of the target object and the human body are realized.

Further, initially, when a user opens the two-dimensional code at the mobile end through the entrance of the closed space to scan the code by the scanning device of the gate, the human body labeling and tracking device collects at least one frame of image for tracking and calibrating the human body.

The beneficial technical effect of this application lies in: the application provides a human body tracking system, can use in intelligent unmanned supermarket control system, adopts this tracking system's supermarket to sell goods, does not need salesperson and managers in the supermarket, also need not set up RIFD label on commodity, greatly reduced operation cost. The method comprises the following steps that a user enters a supermarket entrance and passes through a gate, and real-time coordinate tracking and positioning of a target object user without dead angles in different areas in the whole shopping process of an unmanned supermarket are achieved through the human body tracking system; due to the fact that the human body tracking system accurately positions and tracks the customers entering the unmanned supermarket, the situations that the customers carry commodities privately and the commodities are taken out of the supermarket without settlement are greatly reduced, the commodity loss rate in the unmanned supermarket is effectively reduced, and the operation loss of merchants is reduced.

Drawings

Fig. 1 is a schematic structural diagram of an intelligent unmanned supermarket control system according to an embodiment of the present application;

FIG. 2 is a schematic view of an overall structure of a shelf in an unmanned supermarket according to an embodiment of the application;

fig. 3 is a schematic diagram illustrating a structure of shelf board slots of a shelf in an unmanned supermarket according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of an access control system according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a face recognition system according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a human body tracking system according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of a merchandise monitoring system according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a system for matching commodities for a shopping user according to an embodiment of the present application.

Detailed Description

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. In order to make the objects, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The preferred embodiments of the present application will be fully described below with reference to the accompanying drawings, so that the technical contents thereof will be more clearly understood. The present invention may be embodied in many different forms of embodiments and its scope is not limited to the embodiments described herein.

In the drawings, elements having the same structure are denoted by the same reference numerals, and elements having similar structure or function are denoted by the same reference numerals throughout. The directional terms used in the present invention, such as upper, lower, front, rear, left, right, inner, outer, side, top, bottom, end, etc., are only directions in the drawings, and are used only for explaining and explaining the present invention, but not for limiting the scope of the present invention.

When certain components are described as being "on" another component, the components can be directly on the other component; there may also be an intermediate member disposed on the intermediate member and the intermediate member disposed on the other member. When an element is referred to as being "mounted to" or "connected to" another element, they may be directly "mounted to" or "connected to" the other element or indirectly "mounted to" or "connected to" the other element through an intermediate element.

As a specific embodiment, the human body tracking system of the present application is applied to an unmanned supermarket, can be applied alone, and can also be applied to an unmanned supermarket as a part of the entire intelligent unmanned supermarket control system.

General structure of intelligent unmanned supermarket control system

As shown in fig. 1 to 3, the present embodiment provides an intelligent unmanned supermarket control system, which includes: an access control system 1; a face recognition system 2; a human body tracking system 3; the commodity monitoring control system comprises a commodity monitoring system 4 and a weight monitoring system 5; the shopping user matches the merchandise system 6; a shopping-related data recording system 7; a shopping settlement system 8;

the control system is arranged in a closed space of an unmanned supermarket; a plurality of groups of goods shelves are arranged in the closed space, each group of goods shelves is provided with a proper number of layers of shelf boards, each layer of shelf board is provided with a plurality of groups of goods grooves, and goods are placed in each goods groove. Preferably, only the same type of merchandise is placed on each shelf. The goods shelves are arranged in the goods shelf area in the defined closed space, 4-5 layers of shelf boards are arranged on each goods shelf, 3-5 goods grooves are arranged on each shelf board, and goods are arranged on each goods groove.

The intelligent unmanned supermarket control system comprises a commodity database, wherein the commodity database records and stores all basic data information of commodities in each goods shelf and each goods slot, including the serial numbers, the types, the names and the individual weight values of the commodities, and the goods shelf serial numbers and the goods slot serial numbers corresponding to the commodities.

And the unmanned supermarket control system further comprises a general processor, preferably, the general processor is a data processing device such as a computer or a server; the main processor is connected with other parts of the unmanned supermarket control system to realize control of the unmanned supermarket control system.

As further shown in fig. 4, the access control system 1 is disposed at an entrance and an exit of a closed area of an unmanned supermarket, and the access control system 1 includes a gate 11 and a code scanning device 12 disposed on the gate.

(II) the face recognition system 2:

as shown in fig. 5, the face recognition system 2 includes a first face collecting device 21 disposed at an entrance of the access control system 1, and a second face collecting device 22 disposed in a front area of the shelf; a third face acquisition device 23 arranged at the exit of the access control system;

further, a first face acquisition device 21 arranged at an entrance of the access control system is used for acquiring face images of the customers entering the entrance at the entrance of the closed space;

further, a first face recognition acquisition device 21 is arranged at the upper part of the entrance gate 11, a user scans the two-dimensional code through a code scanning device 12 to trigger the first face recognition acquisition device 21 to acquire at least one frame of image, the acquired image comprises a face image of a customer user, and a general processor connected with the first face recognition acquisition device 2 is used for carrying out face feature extraction modeling on the target object, namely the face image of the user;

further, a second face acquisition device 22 arranged in the shelf area is used for identifying face images of the customer users in the shelf area, and a general processor connected with the second face acquisition device 22 is used for identifying the faces of the customer users so as to correct coordinates of the customer users, namely the target objects;

and the third face acquisition device 23 at the outlet is used for identifying face images at the outlet, and the general processor connected with the third face acquisition device 23 is used for identifying the face of the customer user so as to verify the identity of the customer user, namely the target object, and determine the identity of the user.

(III) human body tracking system 3:

as shown in fig. 6, the human body tracking system 3 includes a first human body labeling and tracking device 31 disposed at the entrance gate 11, a second human body labeling and tracking device 32 disposed at the front area of the shelf, a third human body labeling and tracking device 33 disposed on the roof of the enclosed space, and a first human body labeling and tracking device 34 disposed at the exit gate 11.

The human body labeling and tracking devices I to IV 31, 32, 33 and 34 are realized by imaging devices and are used for acquiring images in real time, and the acquired images at least comprise all or part of images of the target object; the multi-image device shares the spliced image at the same time, and the image conversion tracking mark of the target object user is not lost or mistakenly recognized.

The human body tracking system 3 establishes a plane coordinate system in the closed area through human body labeling and tracking devices I to IV 31, 32, 33 and 34 arranged at the entrance, the area in front of the goods shelf, the roof of the closed space and the exit, demarcates the area of the electronic fence in the range of the coordinate system, demarcates the area of the entrance and the exit and the area of one square meter in front of each goods shelf, and acquires the coordinate of the current target object in the closed area and the area number of the electronic fence through the image acquired in real time.

The human body labeling and tracking devices I to IV 31, 32, 33 and 34 are used for completing the image acquisition of the target object and then sending the acquired image to the general processor, and the general processor completes the image receiving of the target object, the image splicing of the target object and the coordinate operation of the target object, so that the tracking and the calibration of the human body of the target object are realized.

Initially, when a user opens the two-dimensional code at the mobile end through the entrance of the closed space to scan the code by the scanning device 11 of the gate, the human body labeling and tracking device one 31 at least collects one frame of image for tracking and calibrating the human body.

The first to fourth human body labeling and tracking devices 31, 32, 33 and 34 arranged at the entrance, the area in front of the goods shelf, the roof of the closed space and the exit realize the coordinate tracking and positioning of the target object user in different areas without dead angles in the whole shopping process of the unmanned supermarket. By the tracking and positioning of the target object users in different areas, the risk that the supermarket is lost due to the fact that the unmanned supermarket customers carry commodities privately is greatly avoided.

(IV) commodity monitoring control system

And the commodity monitoring and controlling system is used for monitoring the change of the weight value of each goods groove in real time, so that the types and the quantity of the commodities which are taken away or put back are monitored and obtained in real time.

The commodity monitoring control system includes: a weight monitoring system 4 and a merchandise monitoring system 5.

The weight monitoring system 4 monitors the real-time weight value of the goods slot, and when goods in any goods slot are taken away or put back, the weight value of the taken away or put back goods is obtained in real time; and then, calculating a multiple relation according to the real-time weight value of the goods taken away from each goods slot and the weight value of the single goods corresponding to the goods slot stored in the goods database, thereby judging the number of the goods taken away.

Further, as the monitoring mode for realizing the real-time weight value of the cargo tank, preferably, the weight monitoring system 4 is configured to set a weight sensor at the bottom of the cargo tank of the shelf board of each shelf, so as to collect the weight value of each cargo tank in real time.

And the commodity monitoring system 5 is used for capturing the operation of the user before the goods shelf when the user purchases commodities in real time, carrying out dynamic commodity identification on the commodities in the hand of the user in the video image, and further confirming the types and the quantity of the commodities by combining the weight value change data of the goods slot provided by the weight monitoring system 4.

Specifically, as shown in fig. 7, the merchandise monitoring system 5 includes: arranging an imaging device in each shelf area, specifically, arranging a first imaging device 51 above the top of a shelf in the closed area, and adjusting a camera of the first imaging device 51 to be vertical to a horizontal plane; the second imaging device 52 is installed at the top corners of two sides of the shelf, and the camera of the second imaging device 52 is adjusted to form a forty-five degree angle with the horizontal plane; the first imaging device 51 and the second imaging device 52 are arranged, so that the imaging devices cover the front area of the shelf. And a third imaging device 53 is arranged at the center above each goods groove of each shelf, and a camera of the third imaging device 53 covers and monitors all goods placed in each goods groove.

Through the first to third image devices 51, 52 and 53 arranged at different positions, the operation of a user for purchasing commodities before the snapshot shelf is monitored in real time in different areas of a supermarket is realized, the monitoring fineness and accuracy are improved, the commodities in hands of the user in a video image are accurately and dynamically identified, and meanwhile, the type and the quantity of the commodities are further confirmed by combining with the weight value change data of the cargo tank provided in the weight monitoring system 4.

(V) shopping user matching commodity system

The shopping user matches the commodity system 6, when any commodity is taken away and put back, the user identity information and the real-time position of the user obtained by the human body identification, positioning and tracking system and the video image of the goods shelf area obtained by the commodity monitoring and controlling system are used for deducing the user identity information of the commodity taken away or put back and the commodity type and quantity in the hand of the user.

As shown in fig. 8, the shopping-user matching merchandise system 6 includes:

the commodity-related information storage unit 61 stores commodity information (including weight value information) of each slot of each shelf board in a corresponding database for operation and query of the weight monitoring system.

And the goods shelf and goods slot coordinate storage unit 62 establishes a coordinate system in the closed space, defines an electronic fence, defines the goods slot area of each goods shelf by using the electronic fence and stores goods shelf coordinates and goods slot coordinates.

The cargo tank and user matching judgment unit 63 is used for matching the cargo tank with a user when the coordinate set of the electronic fence of a certain cargo tank is intersected with the coordinate set of the hand of the user;

the matching determination unit 64 for matching a commodity with a user determines that the commodity matches with the user when the commodity is taken away from or placed on a certain slot and a user matches with the slot at the same time.

(VI) shopping related data information recording system

The shopping related data information recording system 7 generates a corresponding shopping database according to the identity information of each user, so as to record the quantity and the type of the commodities purchased by each user.

Specifically, the shopping-related data information recording system includes: generating a shopping cart database and updating the shopping cart database.

Generating a shopping cart database: when the identity of a user is recognized and enters the closed space, the shopping cart database of the user is generated according to the identity information of the user obtained by the human body recognition, positioning and tracking system.

Updating the shopping cart database: when the goods are taken away from the goods slot, the types and the quantity of the taken goods are put into a shopping cart database of the user who takes away the goods according to the result obtained by the goods monitoring and controlling system. When the goods are put back to the goods slot, the types and the quantity of the put-back goods are taken out from the shopping cart database of the goods user according to the result obtained by the goods monitoring and controlling system.

(seventh) shopping settlement system

And a shopping settlement system 8 for settling the amount of consumption according to the types and the amounts of all the commodities in the current shopping cart of each shopping user recorded in the shopping-related data information recording system 7.

The shopping settlement system comprises an amount calculation part and a payment part.

And a money calculating part for calculating the money to be paid according to the types and the quantities of all commodities purchased by the user and recorded in the shopping related data information recording system 7 when the user finishes shopping and enters the electronic fence area of the exit to leave the closed area.

And the payment part automatically deducts the amount of the current purchased commodities from the account of the user through the secret-free payment function signed by the mobile terminal, wherein the account of the user comprises but is not limited to a payment treasure, a WeChat change or a bound bank card and the like.

The beneficial technical effect of this application lies in: the application provides a human body identification positioning tracking system, uses in intelligent unmanned supermarket control system, adopts this control system's supermarket to sell goods, does not need salesperson and managers in the supermarket, also need not set up RIFD label on commodity, greatly reduced operation cost. The method comprises the steps that a user enters a supermarket entrance through a gate, real-time identity recognition and coordinate tracking and positioning of a target object user in different areas without dead angles in the whole shopping process of an unmanned supermarket are achieved through mutual matching of a face recognition system and a human body tracking system; the human body identification, positioning and tracking system is an accurate identification, positioning and tracking device for the customers entering the unmanned supermarket, so that the situations that the customers carry commodities privately and the commodities are taken out of the supermarket without settlement are greatly reduced, the commodity loss rate in the unmanned supermarket is effectively reduced, and the operation loss of merchants is reduced.

The description of the present invention has been presented for purposes of illustration and description, but is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will occur to those skilled in the art. Those skilled in the art will appreciate that the methods and apparatus of embodiments of the present invention may be implemented in software, hardware, firmware, or a combination thereof.

Therefore, the embodiments were chosen and described in order to best explain the principles of the invention, the practical application, and to enable others of ordinary skill in the art to understand the invention for all modifications and substitutions that may be made without departing from the spirit of the invention as defined by the appended claims.

Claims (2)

1. A human body tracking system is characterized in that,

the human body tracking system realizes the tracking and positioning of coordinates of target object users in different areas without dead angles in the whole shopping process of an unmanned supermarket;

the human body tracking system comprises a first human body marking tracking device arranged at an entrance of an entrance guard system gate of an unmanned supermarket, a second human body marking tracking device arranged in the front area of a goods shelf, a third human body marking tracking device arranged on the roof of the closed space and a fourth human body marking tracking device arranged at an exit of the closed space;

the human body labeling and tracking devices I to IV adopt imaging devices for acquiring images in real time, wherein the acquired images at least comprise all or part of images of a target object; the multiple image devices share the spliced image at the same time.

2. The body tracking system of claim 1, wherein:

and the human body labeling and tracking devices I to IV finish image acquisition of the target object and then send the image to the main processor.

Images