CN111986383A - Commodity checking method and vending machine - Google Patents

Abstract

The application provides a commodity checking method and a vending machine, and relates to the technical field of self-service vending. According to the commodity checking method provided by the embodiment of the application, the first distance from the target commodity in the target commodity channel to the outlet of the target commodity channel can be obtained before the commodity in the target commodity channel is checked, and the commodity in the target commodity channel is driven to move the first distance to enable the target commodity to be located at the outlet of the target commodity channel, so that the distance between the target commodity and the camera is shortened, and the accuracy of identifying the commodity type through the image of the commodity channel is improved; in addition, before the goods are checked, the target goods are located at a determined position, so that the accuracy of measuring the total length of the goods in the goods channel through the distance measuring sensor is improved, and the automatic checking accuracy of the vending machine is improved. The self-service vending machine provided by the embodiment of the application is used for realizing the commodity checking method, and therefore the self-service vending machine also has the advantage of high automatic checking accuracy.

Description

Commodity checking method and vending machine

Technical Field

The application relates to the technical field of self-service selling, in particular to a commodity checking method and a vending machine.

Background

With the development of automatic vending technology, many current vending machines have an automatic checking function. The related art discloses an automatic vending machine with automatic check function, this automatic vending machine includes controlling means and the cabinet body, internal goods fill and a plurality of goods way of being provided with of cabinet, cabinet body surface is provided with gets the goods mouth, the goods way sets up to a plurality of commodities of arranging in proper order along goods way length direction, the goods way has the export, be provided with the push pedal that is used for promoting commodity to remove in the goods way, the goods fill sets up to can be relative with arbitrary goods way, receive the commodity of being sent out by the export of goods way and transport commodity to getting the goods mouth, be provided with camera and laser ranging sensor on the goods fill, the camera sets up to the image of shooting commodity in the goods way, controlling means passes through the type of this image recognition commodity, laser ranging sensor sets up to measure the total length of commodity in the goods way through measuring the distance of push pedal to laser ranging sensor, controlling means is according to the type of commodity in the goods way and the quantity of commodity of total length calculation goods in.

However, the inventors found that, with the related art vending machine, there is an inaccuracy in article recognition or an inaccuracy in the measured total length of the article, resulting in a low accuracy in article inventory.

Disclosure of Invention

An object of the present application includes providing an article counting method and a vending machine, which can improve the problem of low accuracy of article counting in the related art.

The embodiment of the application can be realized as follows:

in a first aspect, an embodiment of the present application provides a commodity checking method, which is applied to an automatic vending machine, where the automatic vending machine includes a cabinet, a plurality of commodity channels for storing commodities are provided in the cabinet, each commodity channel has an outlet for outputting commodities, each commodity channel is provided with a conveying mechanism, each conveying mechanism is configured to convey commodities in each commodity channel to the outlet of each commodity channel, and the commodity checking method includes:

acquiring a first distance from a target commodity in a target commodity channel to an outlet of the target commodity channel; the target commodity is a commodity which is closest to an outlet of the target commodity channel in the target commodity channel;

driving the goods in the target goods channel to move a first distance, so that the target goods are positioned at an outlet of the target goods channel;

and checking the commodities in the target goods channel.

In an optional embodiment, a camera is further arranged in a cabinet of the vending machine, and the camera is configured to acquire an image of the goods channel; the method comprises the following steps of obtaining a first distance from a target commodity in a target commodity channel to an outlet of the target commodity channel, wherein the first distance comprises the following steps:

controlling a camera to shoot an image of the goods channel;

and calculating a first distance from the target commodity in the target cargo channel to an outlet of the target cargo channel according to the image of the cargo channel.

In an alternative embodiment, the aisle includes a floor for supporting the commodity, and the step of calculating a first distance from a target commodity in the target aisle to an exit of the target aisle based on an image of the aisle includes:

determining a plurality of pixel points on an intersection line of a target commodity and a bottom plate of a target goods way according to the image of the goods way;

respectively calculating to obtain a second distance between a target commodity and an outlet of the target goods way according to each pixel point;

and taking the minimum value in the plurality of second distances corresponding to the plurality of pixel points as the first distance from the target commodity to the outlet of the target goods channel.

In an optional implementation manner, the step of calculating a second distance between one target commodity and an exit of the target goods way according to each pixel point includes:

determining the position of a pixel point in the image of the goods channel along the width direction of the goods channel;

determining a conversion polynomial of the pixel point according to the position of the pixel point in the image of the cargo channel along the width direction of the cargo channel and a pre-stored conversion comparison table; the conversion polynomial is used for calculating a second distance corresponding to the pixel point according to the position of the pixel point;

and calculating a second distance corresponding to the pixel point according to the position of the pixel point in the image of the cargo channel along the width direction of the cargo channel and the conversion polynomial corresponding to the pixel point.

In an alternative embodiment, the conversion look-up table is obtained in advance by:

the method comprises the steps that a camera is controlled to shoot an image of a preset goods channel, wherein a test mark is arranged in the preset goods channel and is located on a bottom plate of the preset goods channel, the test mark comprises M first dividing lines and N second dividing lines, the first dividing lines extend along the length direction of the preset goods channel, the second dividing lines extend along the width direction of the preset goods channel, and the M first dividing lines and the N second dividing lines divide the bottom plate of the preset goods channel into a plurality of areas;

for each first dividing line, selecting a plurality of intersections on the first dividing line, and obtaining a conversion polynomial of the first dividing line according to the position of each intersection in the image of the preset goods way and the actual position of the intersection; wherein, the intersection point refers to the point where the first dividing line and the second dividing line intersect;

and storing the corresponding relation of each first division line and the conversion polynomial thereof as a conversion comparison table.

In an optional implementation manner, the step of determining the conversion polynomial of the pixel point according to the position of the pixel point in the image of the cargo way along the cargo way width direction and a conversion comparison table stored in advance includes:

determining a first dividing line closest to the pixel point according to the position of the pixel point in the image of the cargo channel along the width direction of the cargo channel;

and determining a conversion polynomial corresponding to the latest first dividing line according to a pre-stored conversion comparison table, and taking the conversion polynomial corresponding to the latest first dividing line as the conversion polynomial of the pixel point.

In an optional implementation manner, the step of determining a plurality of pixel points on an intersection line of the target commodity and a bottom plate of the target commodity channel according to the image of the commodity channel includes:

analyzing and processing the image of the goods channel, and determining a detection area of a target goods channel in the image of the goods channel; the detection area of the target cargo way is an area defined by the edge of the bottom plate of the target cargo way;

and carrying out line-by-line detection on the pixel points of the detection area along the set direction, determining the mutation points in the detection area, and taking the mutation points in the detection area as the pixel points on the intersection line of the target commodity and the bottom plate of the target goods way.

In an optional embodiment, the analyzing and processing the image of the cargo way to determine the detection area of the target cargo way in the image of the cargo way includes:

acquiring the width of a target cargo channel;

determining a plurality of positioning points in the image of the goods way according to the width of the target goods way;

and determining a detection area of the target cargo channel in the image of the cargo channel according to the positioning points.

In an optional embodiment, the cargo way includes a bottom plate, a first partition plate and a second partition plate, the first partition plate and the second partition plate are oppositely disposed on the bottom plate along the width direction of the cargo way and are parallel to each other, an accommodating space of the cargo way is formed among the bottom plate, the first partition plate and the second partition plate, an image of the cargo way is analyzed, and a detection area of a target cargo way in the image of the cargo way is determined, including:

segmenting the image of the goods channel by adopting a deep learning algorithm through a pre-trained feature file, and extracting a partition plate area of a target goods channel in the image of the goods channel;

determining the front ends of a first partition plate and a second partition plate of a target cargo way from the partition plate area, calculating the rear end of each partition plate by taking an adjacent distance fit line corresponding to the front end of each partition plate as a reference line, and calculating according to the front end and the rear end of the first partition plate and the front end and the rear end of the second partition plate to obtain the detection area of the target cargo way.

In a second aspect, an embodiment of the present application provides an automatic vending machine, including controlling means and rack, be provided with a plurality of goods way that are used for saving commodity in the rack, the goods way has the export that is used for exporting commodity, and the goods way is provided with conveying mechanism, and conveying mechanism sets up to the export of goods way and carries the commodity in the goods way, and controlling means sets up to:

acquiring a first distance from a target commodity in a target commodity channel to an outlet of the target commodity channel; the target commodity is a commodity which is closest to an outlet of the target commodity channel in the target commodity channel;

driving the goods in the target goods channel to move a first distance, so that the target goods are positioned at an outlet of the target goods channel;

and checking the commodities in the target goods channel.

The beneficial effects of the embodiment of the application include, for example:

according to the commodity checking method provided by the embodiment of the application, the first distance from the target commodity in the target commodity channel to the outlet of the target commodity channel can be obtained before the commodity in the target commodity channel is checked, and the commodity in the target commodity channel is driven to move the first distance to enable the target commodity to be located at the outlet of the target commodity channel, so that the distance between the target commodity and the camera is shortened, and the accuracy of identifying the commodity type through the image of the commodity channel is improved; in addition, before the goods are checked, the target goods are located at a determined position, so that the accuracy of measuring the total length of the goods in the goods channel through the distance measuring sensor is improved, and the automatic checking accuracy of the vending machine is improved. The self-service vending machine provided by the embodiment of the application is used for realizing the commodity checking method, and therefore the self-service vending machine also has the advantage of high automatic checking accuracy.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

FIG. 1 is a schematic view of a vending machine according to one embodiment of the present application;

FIG. 2 is a schematic internal view of a vending machine according to an embodiment of the present application;

FIG. 3 is a block diagram of the components of a vending machine according to one embodiment of the present application;

FIG. 4 is a schematic illustration of a lane according to an embodiment of the present application;

FIG. 5 is a schematic view of a bucket according to an embodiment of the present disclosure;

FIG. 6 is a schematic view of a bucket engaged with a lane according to an embodiment of the present disclosure;

FIG. 7 is an enlarged view of section VII of FIG. 6;

FIG. 8 is a flow chart of a method for inventory of items according to an embodiment of the present application;

FIG. 9 is a schematic illustration of an image of a target lane in one embodiment of the present application;

FIG. 10 is a schematic view of the distribution of test marks in a predetermined lane according to an embodiment of the present application;

FIG. 11 is a schematic diagram of an image of a cargo way taken by a camera in one embodiment of the present application.

Icon: 010-vending machines; 100-a cabinet; 110-a cabinet body; 120-a cabinet door; 121-a human-computer interaction device; 122-a pick-up port; 200-cargo channel; 210-a backplane; 211-a first separator; 212-a second separator; 220-push plate; 221-a detection section; 222-a drive gear; 223-a pulley; 224-a conveyor belt; 230-a first dividing line; 240-second dividing line; 300-a goods taking device; 310-a cargo bucket; 311-cargo inlet; 312-a shipment port; 313-a drive gear; 314-a drive motor; 315-a loading roller; 320-a drive mechanism; 400-a camera; 500-a ranging sensor; 600-control means.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

In the description of the present application, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. are used for indicating the orientation or positional relationship based on the orientation or positional relationship shown in the drawings or the orientation or positional relationship which the present invention product is usually put into use, it is only for convenience of describing the present application and simplifying the description, but it is not intended to indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and be operated, and thus, should not be construed as limiting the present application.

Furthermore, the appearances of the terms "first," "second," and the like, if any, are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.

It should be noted that the features of the embodiments of the present application may be combined with each other without conflict.

Related art's automatic vending machine, when the staff mended a goods to certain goods way, often be used to put the commodity that will mend in proper order from inside to outside in the goods way, the staff often can appear after the goods mended the condition that the commodity of mended can not occupy whole goods way, under this condition, the commodity of foremost will have a certain distance apart from the export of goods way in the goods way. When the vending machine is used for checking the commodities in the commodity channel, the distance between the commodity at the forefront end in the commodity channel (namely, the commodity closest to the outlet of the commodity channel) and the camera is too large, so that the condition of missing identification or error identification occurs when the type of the commodity is identified through the image shot by the camera, or the condition that the total length of the measured commodity is inaccurate when the total length of the commodity is measured by measuring the distance from the push plate to the laser ranging sensor through the laser ranging sensor occurs, and the accuracy of commodity checking is affected.

Therefore, the embodiment of the application provides a commodity checking method and a vending machine, before commodity checking is performed on a target commodity channel, commodities in the target commodity channel are moved to a commodity channel outlet, so that the commodities at the forefront end are located at the outlet of the target commodity channel, and then checking is performed. Through the mode, when the commodities on the target goods channel are checked, the commodities can be closer to the camera, the distance measuring sensor and the like, so that the accuracy of image recognition and the accuracy of distance measurement are improved, and the checking accuracy is improved. To facilitate understanding of the method for checking the merchandise provided by the present application, a description will be first given below of a vending machine provided in an embodiment of the present application.

FIG. 1 is a schematic view of a vending machine 010 according to an embodiment of the subject application; FIG. 2 is a schematic view of the interior of the vending machine 010 of one embodiment of the subject application; fig. 3 is a block diagram of the vending machine 010 according to an embodiment of the present application. Referring to fig. 1 to fig. 3, the vending machine 010 of the present embodiment includes a cabinet 100, a cargo channel 200 disposed in the cabinet 100, a pickup device 300, a camera 400, a distance measuring sensor 500, and a control device 600. The goods channel 200 is used for storing goods and can realize that the goods are sent out from the goods channel 200; the goods taking device 300 is used for delivering goods sent out from the goods channel 200 to a user; the camera 400 is used for acquiring images in the cabinet 100, including images of the cargo way 200 and images of goods in the cargo way 200; the distance measuring sensor 500 is used for detecting the length of the goods arranged in the goods passage 200 to calculate the number of the goods in the goods passage 200. The cargo channel 200, the cargo taking device 300, the camera 400 and the distance measuring sensor 500 are all electrically connected with the control device 600. The control apparatus 600 may control each apparatus to execute a corresponding job.

In this embodiment, the cabinet 100 includes a cabinet body 110 and a cabinet door 120, the cabinet body 110 has a horizontal front opening, and the cabinet door 120 is rotatably connected to the cabinet body 110 for opening or closing the opening of the cabinet body 110. The cabinet door 120 is provided with a goods access opening 122, and the goods access opening 122 communicates with the inside and the outside of the cabinet 100, so that a user can access goods on the goods access device 300 in the cabinet 100 through the goods access opening 122. Optionally, the goods taking opening 122 may be further provided with a goods taking door to open or close the goods taking opening 122, so that when the vending machine 010 is idle, the goods taking opening 122 may be kept closed to prevent animals such as snakeworms, rats and ants, or other foreign matters from entering the cabinet 100 of the vending machine 010. Optionally, a human-computer interaction device 121 is further disposed on the cabinet door 120, the human-computer interaction device 121 is configured to receive an instruction (e.g., a purchase instruction, an inquiry instruction, a parameter configuration instruction, and the like) input by a user and send information (e.g., information about a product being sold, advertisement information, a prompt message, and the like) to the user, and the human-computer interaction device 121 is electrically connected to the control device 600. In this embodiment, the human-computer interaction device 121 includes a touch screen, which can simultaneously satisfy the input and output of information. In alternative embodiments, the human-computer interaction device 121 may also include a keyboard, a mouse, a speaker, etc.

In the present embodiment, the vending machine 010 includes a plurality of lanes 200, the plurality of lanes 200 are disposed in the cabinet 110 in a distribution of rows and columns, and each of the lanes 200 extends in a front-rear direction (i.e., a direction indicated by an arrow ef in the drawing) of the vending machine 010. The end of the cargo channel 200 near the door 120 has an outlet, and the goods can be sent out of the cargo channel 200 from the outlet of the cargo channel 200 to the goods taking device 300. A certain space is reserved between the outlet of the cargo channel 200 and the cabinet door 120, and the cargo taking device 300 is disposed in the space. In the present embodiment, one lane 200 is used to store the same kind of goods, and the goods in the lane 200 are arranged along the length direction of the lane 200.

Fig. 4 is a schematic view of the cargo way 200 according to an embodiment of the present invention, and as shown in fig. 4, each cargo way 200 includes a bottom plate 210, a first partition 211, and a second partition 212. The bottom plate 210 is used for supporting goods, the first partition 211 and the second partition 212 are oppositely arranged on the bottom plate 210 along the width direction of the cargo channel 200 (i.e. the direction indicated by the arrow ab in the figure) and are parallel to each other, and a receiving space of the cargo channel 200 is formed among the bottom plate 210, the first partition 211 and the second partition 212. It should be understood that multiple lanes 200 in the same row (floor) may share a floor 210; the receiving spaces of two adjacent lanes 200 may be separated by the same partition between two lanes 200, and thus, the first partition 211 of one lane 200 may simultaneously serve as the second partition 212 of another adjacent lane 200. In the present embodiment, the partition on the left side of a cargo way 200 is defined as a first partition 211 of the cargo way 200, and the partition on the right side is defined as a second partition 212 of the cargo way 200.

With continued reference to fig. 4, in the present embodiment, each of the lanes 200 is provided with a conveying mechanism, and the conveying mechanism is used for sending out the goods in the lanes 200 from the outlet of the lane 200. In this embodiment, the conveying mechanism includes a transmission component and a push plate 220 disposed in the cargo channel 200, the transmission component is configured to drive the push plate 220 to move in the cargo channel 200, and when the push plate 220 moves, the push plate 220 pushes the goods in the cargo channel 200 to move along the length direction of the cargo channel 200. It should be understood that in the present embodiment, the position of the push plate 220 in the cargo way 200 is behind the last product, so that all the products in the cargo way 200 can be pushed to move together toward the outlet of the cargo way 200, and the product at the front end (i.e., the product closest to the outlet of the cargo way 200) first reaches the outlet of the cargo way 200 and is sent out of the cargo way 200.

In the present embodiment, the transmission assembly includes a transmission gear 222, a pulley 223, a transmission belt 224, and a driven pulley (not shown in the figure). The transmission gear 222 is coaxially and fixedly connected with the belt wheel 223, the belt wheel 223 and the driven wheel are arranged at intervals in the length direction of the cargo passage 200, the transmission belt 224 is sleeved between the belt wheel 223 and the driven wheel, and the transmission belt 224 is connected with the push plate 220. It can be understood that when the transmission gear 222 rotates, the pulley 223 rotates with the transmission gear 222 at the same angular speed, so as to drive the transmission belt 224 to move, and the transmission belt 224 further drives the push plate 220 to move along the length direction of the cargo way 200 in the cargo way 200, so as to push the goods to move towards the outlet of the cargo way 200. In this embodiment, the transmission assembly is disposed on the first partition 211 of the corresponding cargo way 200, and most of the transmission belt 224 and the driven wheel are embedded inside the first partition 211, so that the structure is compact and the occupied space is reduced.

In this embodiment, the push plate 220 is provided with a detection portion 221. The detection unit 221 serves as a detection target of the distance measuring sensor 500, and the distance measuring sensor 500 may detect the total length of the commodity in the cargo way 200 by measuring the distance between the detection unit 221 and the distance measuring sensor 500. In the present embodiment, the detecting portion 221 is located above the first partition 211 of the corresponding cargo way 200.

FIG. 5 is a schematic view of bucket 310 in one embodiment of the present disclosure; FIG. 6 is a schematic view of the engagement of a bucket 310 with a lane 200 according to one embodiment of the present disclosure; fig. 7 is an enlarged view of a portion VII in fig. 6. Referring to fig. 5 to 7, in the present embodiment, the pickup device 300 is disposed in a space between the exit of the cargo passage 200 and the cabinet door 120, and the pickup device 300 includes a bucket 310 and a driving mechanism 320 for driving the bucket 310 to move between the pickup opening 122 and the exit of any one of the cargo passages 200. The driving mechanism 320 can drive the bucket 310 to the outlet of any one of the lanes 200 to receive the goods sent out by the lane 200 and convey the goods to the position corresponding to the goods-taking opening 122 for the user to take. Alternatively, the drive mechanism 320 may include a horizontal drive mechanism and a vertical drive mechanism to effect movement of the bucket 310 to the exit of any one of the aisles 200. For example, the horizontal driving mechanism is used to drive the vertical driving mechanism and the bucket 310 to move in the horizontal direction together, and the vertical driving mechanism is used to drive the bucket 310 to move in the vertical direction.

In the present embodiment, the loading bucket 310 has a loading opening 311 and a discharging opening 312, wherein the loading opening 311 is opposite to the outlet of the loading channel 200, and the discharging opening 312 is opposite to the cabinet door 120. The goods sent out from the cargo channel 200 enter the cargo container 310 from the inlet 311 of the cargo container 310, and when the cargo container 310 moves to the position of the access opening 122, the user can take out the goods in the cargo container 310 through the access opening 122 and the outlet 312. In order to enable the goods sent out from the cargo channel 200 to smoothly enter the cargo bed 310, a loading roller 315 is disposed at the loading port 311 of the cargo bed 310, and the loading roller 315 may be driven by a motor (not shown) disposed on the cargo bed 310, so as to transport the goods at the loading port 311 into the cargo bed 310.

In this embodiment, a driving gear 313 and a driving motor 314 for driving the driving gear 313 to rotate are further disposed on a side of the bucket 310 facing the cargo way 200. When the bucket 310 moves to the outlet of one of the channels 200, the driving gear 313 on the bucket 310 can mesh with the transmission gear 222 of the transmission assembly of the channel 200, so that the driving motor 314 can finally drive the push plate 220 of the channel 200 to move through the driving gear 313, the transmission gear 222 and the transmission belt 224, thereby realizing the delivery of the goods from the outlet of the channel 200. The goods delivered from the outlet of the cargo passage 200 can be dropped into the bucket 310. The push plates 220 in the cargo channel 200 are driven in such a way that all the push plates 220 of the cargo channel 200 are driven by the same driving motor 314 and the driving gear 313, so that the cost and the occupied space in the cabinet 100 are reduced by reducing the use of the driving motor 314. Of course, in alternative embodiments, a drive motor 314 may be disposed within each lane 200 to drive the push plate 220.

In order to enable the camera 400 to better acquire the image of the goods in the cargo channel 200 to determine the type of the goods, in the embodiment of the present application, the camera 400 is disposed on the cargo bucket 310. Similarly, the distance measuring sensor 500 is also disposed on the bucket 310 and is located on a side of the bucket 310 facing the cargo way 200. By arranging the camera 400 and the distance measuring sensor 500 on the bucket 310, when the bucket 310 moves to the exit position of the target channel 200, the camera 400 can obtain the image of the target channel 200 in a targeted manner, and the distance measuring sensor 500 can be opposite to the detection part 221 on the push plate 220 of the target channel 200, so as to obtain the distance between the push plate 220 of the target channel 200 and the distance measuring sensor 500. The distance measuring sensor 500 may be a laser sensor that detects a position between the detecting part 221 and the distance measuring sensor 500 by emitting laser light and receiving the laser light reflected by the detecting part 221. It can be understood that when the bucket 310 moves to the exit of the target cargo way 200, the image collected by the camera 400 should include the image of the target cargo way 200, and may also include the image of the area around the target cargo way 200; when the bucket 310 moves to the exit of the target lane 200, the ranging sensor 500 should be opposite to the detection part 221 of the push plate 220 of the target lane 200 in the length direction of the target lane 200. It should be understood that in other alternative embodiments of the present application, the distance measuring sensors 500 may also be fixedly disposed at the outlets of the cargo ways 200, and one distance measuring sensor 500 is disposed in each cargo way 200; the camera 400 may also be disposed at the exit of the cargo way 200, even inside the cabinet door 120.

In the embodiment of the present application, the control device 600 is configured to:

acquiring a first distance from a target commodity in the target commodity channel 200 to an outlet of the target commodity channel 200; wherein, the target commodity is a commodity which is closest to the outlet of the target commodity channel 200 in the target commodity channel 200; driving the goods in the target goods way 200 to move a first distance, so that the target goods are positioned at the outlet of the target goods way 200; the items in the target lane 200 are inventoried.

Specifically, the control device 600 controls the bucket 310 to move to the exit of the target cargo way 200, and controls the camera 400 to acquire an image of the target cargo way 200, where the image should include an image of the target commodity. The control device 600 analyzes and processes the image of the target cargo way 200 acquired by the camera 400, and then calculates a first distance between the outlet of the target cargo way 200 (i.e., the front end of the bottom plate 210) and the target commodity. The first distance may be considered a distance where no merchandise is displayed within the target lane 200. In the related art, since the target goods is far from the camera 400 in the case where the goods in the target goods passage 200 cannot occupy the entire goods passage 200, it is difficult to accurately recognize the types of the goods in the goods passage 200 by the camera 400; furthermore, since the total length of the commodity in the target lane 200 is obtained by subtracting the distance between the distance measuring sensor 500 and the target commodity from the distance between the distance measuring sensor 500 and the pushing plate 220, in the case that the commodity in the target lane 200 cannot occupy the entire lane 200, the position of the target commodity is uncertain, and further the distance between the distance measuring sensor 500 and the target commodity is uncertain, which may cause difficulty in accurately detecting the total length of the commodity in the target lane 200. However, in the present application, after the first distance is obtained, the push plate 220 is controlled to move the first distance, so that the goods in the target cargo way 200 move the first distance, and the target goods are located at the exit of the target cargo way 200. The distance between the target commodity and the camera 400 is shortened, so that the camera 400 can shoot the image of the commodity with higher definition, and further the control device 600 can more accurately obtain the characteristic information of the commodity through the image shot by the camera 400, so as to accurately determine the type of the commodity, meanwhile, when the target commodity is positioned at the outlet of the target commodity channel 200, because the target commodity is positioned at a determined position, the total length of the commodity in the target commodity channel 200 can be accurately calculated according to the measurement result of the distance measuring sensor 500, and the length is equal to the distance between the distance measuring sensor 500 and the detection part 221 minus the fixed distance from the distance measuring sensor 500 to the outlet of the target commodity channel 200, so that the commodity in the target commodity channel 200 can be accurately checked.

It should be understood that the image of each type of article and the length of the single article may be stored in the memory of the vending machine 010 in advance, so that the type of the article and thus the length of the single article corresponding to the article can be obtained through the captured article image. The distance measuring sensor 500 can detect the distance between the distance measuring sensor 500 and the detecting portion 221 of the push plate 220, and since the push plate 220 abuts against the rear end of the last product in the lane 200, the distance between the distance measuring sensor 500 and the detecting portion 221 can be regarded as the distance between the last product in the lane 200 and the distance measuring sensor 500. Since the distance between the distance measuring sensor 500 and the outlet of the cargo channel 200 in the longitudinal direction of the cargo channel 200 is a fixed value, the distance between the outlet of the target cargo channel 200 and the push plate 220 can be calculated by subtracting the fixed value from the measured value of the distance measuring sensor 500. Since the target commodity has been moved to the exit of the target cargo way 200 before the distance between the push plate 220 and the exit of the target cargo way 200 is calculated, the distance between the exit of the target cargo way 200 and the push plate 220 can be regarded as the total length of the commodity in the target cargo way 200. Then, the total length of the goods in the target goods way 200 is divided by the length of the single goods, so as to obtain the number of the goods in the target goods way 200.

The distance measuring sensor 500 used in this embodiment is a laser distance measuring sensor, and a push plate 220 having a detecting portion 221 is provided in the conveying mechanism, and the total length of the commodity in the cargo way 200 is calculated by measuring the distance between the distance measuring sensor 500 and the push plate 220. It should be understood that the use of such a distance measuring sensor and the arrangement of the push plate 220 with the detecting portion 221, and the corresponding detecting and calculating methods, are an alternative embodiment of the present application, and in other embodiments of the present application, the type of the distance measuring sensor 500, the arrangement of the conveying mechanism, and the method for detecting and calculating the total length of the commodity may be replaced, such as the following embodiments: the distance measuring sensor 500 is an image sensor, a scale is arranged on the cargo channel 200, an image of the rearmost commodity in the cargo channel and the scale at the position of the rearmost commodity is acquired through the image sensor, and the position of the commodity in the target cargo channel 200 is determined through image analysis. Since the position of the target product at the forefront is already determined (located at the exit of the target lane 200), the total length of the product in the target lane 200, and thus the number of the product in the lane, can also be accurately calculated from the position of the product at the rearmost.

Fig. 8 is a flowchart illustrating a method for checking an item according to an embodiment of the present application. Referring to fig. 8 in combination with fig. 1 to 7, an embodiment of the present application provides a method for checking a commodity, which can be applied to the vending machine 010 provided in the embodiment of the present application. The commodity checking method comprises the following steps:

s100, acquiring a first distance from a target commodity in a target commodity channel to an outlet of the target commodity channel; the target commodity is a commodity which is closest to an outlet of the target commodity channel in the target commodity channel.

Taking the vending machine 010 provided in the embodiment of the present application as an example, in this embodiment, acquiring the first distance from the target product in the target channel 200 to the exit of the target channel 200 may include: controlling the camera 400 to shoot the image of the cargo channel 200; a first distance from a target commodity in the target lane 200 to an exit of the target lane 200 is calculated from the image of the lane 200. Specifically, the control device 600 controls the driving mechanism 320 to move the bucket 310 to the exit of the target cargo way 200 according to the received instruction (for example, an inventory instruction input by the user through the human-computer interaction device 121), and then controls the camera 400 to shoot an image of the cargo way 200, where the image of the cargo way 200 includes the image of the target cargo way 200. The image of the lane 200 is then analyzed to obtain the distance between the exit of the target lane 200 (i.e., the forward-most end of the floor 210) and the target commodity.

Fig. 9 is a schematic diagram of an image of a target lane 200 in an embodiment of the present application. Referring to fig. 9, further, calculating a first distance from a target commodity in the target cargo way 200 to an exit of the target cargo way 200 according to the image of the cargo way 200 may include: determining a plurality of pixel points P on an intersection line of a target commodity and a bottom plate 210 of the target cargo way 200 according to the image of the cargo way 200; respectively calculating a second distance L between a target commodity and the outlet of the target goods way 200 according to each pixel point P; the minimum value of the second distances L corresponding to the pixel points P is used as the first distance from the target commodity to the exit of the target cargo way 200.

The intersection line of the target commodity and the bottom plate 210 of the target commodity channel 200 is a line formed by the intersection of the target commodity and the bottom plate 210 of the target commodity channel 200, and the intersection line may be a straight line or a curved line, for example, when the target commodity includes a rectangular parallelepiped packing box, the intersection line is a straight line, and when the target commodity is a bottled beverage, the intersection line is a curved line. In the image of the commodity passage 200, an intersection line of the target commodity and the bottom plate 210 of the target commodity passage 200 is composed of pixel points P, and it can be understood that each pixel point P on the intersection line in the image corresponds to a physical point on the actual target commodity. In this embodiment, the distance from the physical point corresponding to each pixel point P to the foremost end of the bottom plate 210 along the length direction of the cargo way 200 is calculated according to each pixel point P, and the distance is used as the second distance L between the target commodity corresponding to the pixel point P and the outlet of the target cargo way 200.

In some cases, the image of the cargo way 200 captured by the camera 400 is a distorted image (as shown in fig. 11), and therefore, the distance between the pixel point P in the image and the front end of the bottom plate 210 cannot truly represent the distance between the physical point corresponding to the pixel point P on the actual target product and the front end of the actual bottom plate 210. For example, a pixel point P closest to the front end of the bottom plate 210 on the image does not necessarily have to be the physical point closest to the front end of the bottom plate 210, and the physical point corresponding to the pixel point P on the actual target product is the physical point closest to the front end of the bottom plate 210. Therefore, in this embodiment, optionally, the distance from the physical point corresponding to each pixel point P to the foremost end of the bottom plate 210 along the length direction of the lane 200 is calculated according to each pixel point P, and the distance is used as the second distance L between the target commodity corresponding to the pixel point P and the outlet of the target lane 200, and since the second distance L can truly reflect the distance from each physical point on the actual target commodity to the foremost end of the bottom plate 210 of the lane 200, the first distance can accurately reflect the distance from the foremost end of the edge where the target commodity intersects with the bottom plate 210 of the target lane 200 to the outlet of the target lane 200 by determining the minimum value of the plurality of second distances L as the first distance from the target commodity to the outlet of the target lane 200. By driving the commodities in the target commodity channel 200 to move a first distance, the foremost end of the target commodity can be positioned at the outlet of the target commodity channel 200, so that the target commodity is not dropped from the target commodity channel 200, the commodity identification accuracy and the commodity total length measurement accuracy can be improved, and the commodity checking accuracy is improved.

Further, the step of calculating a second distance L between a target commodity and the exit of the target cargo way 200 according to each pixel point P may specifically include:

determining the position of the pixel point P in the image of the cargo way 200 along the width direction of the cargo way 200; determining a conversion polynomial of the pixel point P according to the position of the pixel point P in the image of the cargo way 200 along the width direction of the cargo way 200 and a pre-stored conversion comparison table, wherein the conversion polynomial is used for calculating a second distance L corresponding to the pixel point P according to the position of the pixel point P; and calculating a second distance L corresponding to the pixel point P according to the position of the pixel point P in the image of the cargo way 200 along the width direction of the cargo way 200 and the conversion polynomial corresponding to the pixel point P.

It is understood that since the image captured by the camera 400 is prone to distortion, the distances reflected by different positions in the image or the size ratios in the image may not be consistent with the actual situation. Therefore, in order to ensure that the second distance L calculated for each pixel point P at different positions can more accurately reflect the distance from the physical point corresponding to the pixel point P to the front end of the bottom plate 210, the second distance L corresponding to the pixel point P at different positions is calculated by different conversion polynomials in this embodiment, so as to obtain the second distance L which can more accurately reflect the real situation. It can be understood that due to image distortion, the conversion polynomial adopted by the pixel point P at different positions may be different.

Specifically, the conversion polynomial includes an input parameter and an output value, the input parameter includes a coordinate position of the pixel point P along the width direction of the cargo way 200, and the output value is a second distance L corresponding to the pixel point P. By converting the polynomial, under the condition that the coordinate position of a pixel point P along the width direction of the cargo way 200 is known according to the image of the cargo way 200, the second distance L from the physical point of the pixel point P corresponding to the target commodity to the foremost end of the bottom plate 210 of the target cargo way 200 can be calculated. Specifically, in this embodiment, the position of the pixel point P in the image of the cargo way 200 along the width direction of the cargo way 200 refers to the position of the pixel point P along the width direction of the cargo way 200 on the bottom plate 210 located between the first partition 211 and the second partition 212.

It should be understood that fig. 9 is only a schematic diagram of an image of the cargo way 200, and for convenience of illustration, the straight line contour of the actual cargo way 200 is correspondingly represented as a straight line in the figure; in the image actually captured by the camera 400, the straight line in the figure may be distorted and bent.

FIG. 10 is a schematic diagram of the distribution of test marks in a pre-defined lane 200 according to an embodiment of the present application. Referring to fig. 10, optionally, the conversion look-up table may be obtained in advance by:

the control camera 400 shoots an image of the preset cargo way 200, wherein a test mark is arranged in the preset cargo way 200, the test mark is positioned on the bottom plate 210 of the preset cargo way 200, the test mark comprises M first dividing lines 230 and N second dividing lines 240, the first dividing lines 230 extend along the length direction of the cargo way 200, the second dividing lines 240 extend along the width direction of the cargo way 200, and the M first dividing lines 230 and the N second dividing lines 240 divide the bottom plate 210 of the preset cargo way 200 into a plurality of areas; for each first dividing line 230, selecting a plurality of intersections on the first dividing line 230, and obtaining a conversion polynomial of the first dividing line 230 according to the position of each intersection in the image of the preset cargo way 200 and the actual position of the intersection; wherein the intersection point refers to a point where the first dividing line 230 and the second dividing line 240 intersect; the correspondence of each first dividing line 230 to its conversion polynomial is stored as a conversion look-up table.

Specifically, a plurality of intersection points are selected on each first dividing line 230, and a polynomial coefficient of the first dividing line 230 is generated by polynomial fitting according to a coordinate position of each intersection point in the image of the preset cargo way 200 and an actual position of each intersection point, so as to obtain a conversion polynomial of the first dividing line 230. The preset lane 200 may be the target lane 200, or may be another lane 200 having the same width as the target lane 200.

Further, the step of determining the conversion polynomial of the pixel point P according to the position of the pixel point P in the image of the lane 200 along the width direction of the lane 200 and a pre-stored conversion look-up table may specifically include:

determining a first dividing line 230 closest to the pixel point P according to the position of the pixel point P in the image of the cargo way 200 along the width direction of the cargo way 200; and determining the conversion polynomial corresponding to the nearest first dividing line 230 according to a pre-stored conversion look-up table, and taking the conversion polynomial corresponding to the nearest first dividing line 230 as the conversion polynomial of the pixel point P.

Wherein, according to the position of the pixel point P in the image of the cargo way 200 along the width direction of the cargo way 200 and the position of each first dividing line 230 in the image of the preset cargo way 200 along the width direction of the cargo way 200, the first dividing line 230 closest to the pixel point P is determined. Because the image of the cargo way 200 shot by the camera 400 is a distorted image, the image is calibrated in advance by using the test mark, different positions along the width direction of the cargo way 200 can be obtained, and the influence of image distortion on distance conversion is caused, that is, conversion polynomials of different positions are obtained, after the conversion polynomial of the pixel point P is determined, the second distance L from the physical point corresponding to the pixel point P on the actual target commodity to the foremost end of the bottom plate 210 of the target cargo way 200 can be obtained by calculating by using the conversion polynomial according to the coordinate position of the pixel point P in the image, and the calculation accuracy of the second distance L is ensured. It can be seen that, when the density of the first dividing line 230 in the test mark is higher, the corresponding conversion polynomial is more, the expected value of the distance between the selected first dividing line 230 closest to the pixel point P and the pixel point P is smaller, and the second distance L obtained by calculating the pixel point P by using the conversion polynomial of the first dividing line 230 is more accurate.

Further, the test mark may be disposed on the bottom plate 210 of the preset cargo way 200 in an adhesive manner, or may be disposed on the bottom plate 210 of the preset cargo way 200 in a printing manner. In general, the width of the cargo channel 200 is adjustable, that is, the distance between the first partition 211 and the second partition 212 is adjustable, before the vending machine 010 leaves the factory, or after the width of the cargo channel 200 of the vending machine 010 is adjusted, the preset cargo channel 200 needs to be calibrated by using the test mark, so as to obtain the conversion comparison table corresponding to the width of the preset cargo channel 200. Therefore, in order to adapt to the feature that the width of the cargo way 200 is adjustable, it is preferable that the test mark is disposed on the bottom plate 210 of the cargo way 200 in an adhering manner, and after the width of the cargo way 200 is adjusted, a worker may make a test mark adapted to the width of the cargo way 200, adhere the test mark to the bottom plate 210 of the cargo way 200, and obtain the conversion mapping table of the cargo way 200 through the test mark.

Optionally, determining a plurality of pixel points P on an intersection line of the target product and the bottom plate 210 of the target cargo way 200 according to the image of the cargo way 200 may further include:

analyzing and processing the image of the cargo way 200, and determining a detection area of the target cargo way 200 in the image of the cargo way 200, wherein the detection area of the target cargo way 200 is an area defined by the edge of the bottom plate 210 of the target cargo way 200; and detecting the pixel points P of the detection area line by line along the set direction, determining the mutation points in the detection area, and taking the mutation points in the detection area as the pixel points P on the intersection line of the target commodity and the bottom plate 210 of the target goods way 200.

Specifically, since the image of the cargo way 200 captured by the camera 400 is often a distorted image, the detection area of the target cargo way 200 determined from the image of the cargo way 200 is often not a regular rectangle. For convenience of processing, after the detection area of the target cargo way 200 in the image of the cargo way 200 is determined, other areas except for the detection area of the target cargo way 200 in the image of the cargo way 200 may be shielded, or the detection area of the target cargo way 200 in the image of the cargo way 200 may be extracted by image segmentation. Thus, the interference of other mutation points outside the detection area of the target cargo way 200 in the image of the cargo way 200 can be eliminated, and the mutation points obtained by detection can be ensured to be pixel points P on the intersection line of the target commodity and the bottom plate 210 of the target cargo way 200.

It should be noted that, under the influence of the field of view of the camera 400, the installation position, and the width of the cargo way 200, one or more complete cargo ways 200 may be included in the image of the cargo way 200. For example, when the width of the target cargo way 200 is wide, the image captured by the camera 400 includes only one complete cargo way 200, that is, the target cargo way 200; when the width of the target aisle 200 is narrow, the image captured by the camera 400 may include other complete aisles 200 in addition to the target aisle 200. In the embodiment of the present application, the camera 400 is disposed on the bucket 310, and when the bucket 310 is located at the exit of the target cargo channel 200, the view range and the installation position of the camera 400 and the relative position relationship between the bucket 310 and the target cargo channel 200 can ensure that the image of the target cargo channel 200 captured by the camera 400 is captured based on a partition of the target cargo channel 200. Fig. 11 is a schematic diagram of an image of a cargo way captured by a camera in an embodiment of the present application, and as shown in fig. 11, the camera 400 captures an image of a target cargo way 200 based on a first partition 211 located on the left side of a bottom plate 210, that is, in the captured image of the cargo way 200, a left vertex angle of a front end of the first partition 211 is located at an edge of the image of the cargo way 200, and with such a configuration, the camera 400 can capture a complete image of the target cargo way 200, and in a process of analyzing and processing the image of the cargo way 200, edge detection can be performed based on one side edge of the image, so as to determine a detection area of the target cargo way 200.

In an optional embodiment, analyzing and processing the image of the cargo way 200 to determine the detection area of the target cargo way 200 in the image of the cargo way 200 may specifically include:

obtaining the width of the target lane 200; determining a plurality of positioning points in the image of the cargo way 200 according to the width of the target cargo way 200; the detection area of the target lane 200 in the image of the lane 200 is determined based on the plurality of anchor points.

In this embodiment, according to the width of the cargo way 200, the coordinate positions of a plurality of positioning points in the corresponding image are predefined, after the width of the target cargo way 200 is obtained, the coordinate positions of the plurality of positioning points corresponding to the cargo way 200 with the width are obtained through table lookup, and then drawing is performed according to the plurality of positioning points, so as to obtain the detection area of the target cargo way 200. As described above, optionally, the image of the target cargo way 200 captured by the camera 400 is captured based on one partition of the target cargo way 200, for example, as shown in fig. 11, the left vertex angle of the front end of the first partition 211 is located at the edge of the image of the cargo way 200, so that after the width of the cargo way 200 is determined, the position of the cargo way 200 in the image of the cargo way 200 is also determined, and therefore, the detection area of the target cargo way 200 can be quickly and accurately obtained according to a plurality of positioning points corresponding to the width of the target cargo way 200.

In another alternative embodiment, analyzing and processing the image of the cargo way 200 to determine the detection area of the target cargo way 200 in the image of the cargo way 200 may specifically include:

segmenting the image of the cargo way 200 by adopting a deep learning algorithm through a pre-trained feature file, and extracting a partition plate area of the target cargo way 200 in the image of the cargo way 200; the front ends of the first partition board 211 and the second partition board 212 of the target cargo way 200 are determined from the partition board area, the rear end of each partition board is calculated by taking an adjacent distance fit line corresponding to the front end of the partition board as a reference line, and the detection area of the target cargo way 200 is obtained by calculating according to the front end and the rear end of the first partition board 211 and the front end and the rear end of the second partition board 212.

In this embodiment, an image segmentation algorithm based on deep learning is adopted, sample images of multiple commodities are labeled in advance, and a feature file is generated according to sample image training of the multiple commodities. For the image of the cargo way 200 to be processed, the image segmentation processing is carried out by adopting a deep learning algorithm through a pre-trained feature file, and a commodity region and a partition plate region of the target cargo way 200 are extracted.

And step S200, driving the commodity in the target commodity channel to move for a first distance, so that the target commodity is positioned at an outlet of the target commodity channel.

Taking the vending machine 010 provided in the embodiment of the present application as an example, after obtaining the first distance between the target commodity and the outlet of the target commodity channel 200, the control device 600 controls the driving motor 314 on the bucket 310 to rotate, and drives the driving gear 313, the transmission gear 222, and the transmission belt 224 to move, so as to drive the push plate 220 to move the first distance to the outlet of the target commodity channel 200, and finally, to move the target commodity to the outlet of the target commodity channel 200. Since the goods in the target lane 200 are already as close as possible to the exit of the target lane 200, that is, the goods are as close as possible to the camera 400, the recognition accuracy is higher when the camera 400 recognizes the type of the goods in the target lane 200. At this time, since the target product is located at the exit of the lane and the position of the target product is determined, a more accurate result can be obtained even when the total length of the product in the target lane 200 is calculated from the distance between the target product and the detection unit 221, which is obtained by the distance measuring sensor 500.

And step S300, checking the commodities in the target goods channel.

Optionally, the checking the goods in the target goods passage includes detecting the type and the number of the goods in the target goods passage. Taking the vending machine 010 provided in the embodiment of the present application as an example, the control device 600 may calculate the number of the commodities in the target track 200 after acquiring the type of the commodities in the target track 200 and the distance between the distance measuring sensor 500 and the detection portion 221. Specifically, the image of each type of article and the length of the individual article may be stored in advance in the memory of the vending machine 010. Therefore, after acquiring the image of the product, the control device 600 may compare the acquired image with the image in the product image library in the memory to determine the type of the product, and further acquire the length of the single product corresponding to the product. The distance between the distance measuring sensor 500 and the detecting unit 221 can be regarded as the distance between the last product in the cargo way 200 and the distance measuring sensor 500. Since the distance between the distance measuring sensor 500 and the outlet of the cargo channel 200 in the longitudinal direction of the cargo channel 200 is a fixed value, the distance between the outlet of the target cargo channel 200 and the push plate 220 can be calculated by subtracting the fixed value from the measured value of the distance measuring sensor 500. Since the target commodity has been moved to the exit of the target cargo way 200 before the distance between the push plate 220 and the exit of the target cargo way 200 is calculated, the distance between the exit of the target cargo way 200 and the push plate 220 can be regarded as the total length of the commodity in the target cargo way 200. It can be seen that moving the target product to the exit of the target lane 200 in step S200 is a prerequisite for accurately calculating the total length of the product in the lane 200. After the total length of the commodities in the target commodity channel 200 is obtained through calculation, the total length of the commodities in the target commodity channel 200 is divided by the length of a single commodity, so that the number of the commodities in the target commodity channel 200 can be obtained, and the counting of the commodities in the target commodity channel 200 is realized.

To sum up, the commodity checking method provided by the embodiment of the application can acquire the first distance from the target commodity in the target commodity channel to the outlet of the target commodity channel before checking the commodity in the target commodity channel, and drive the commodity in the target commodity channel to move the first distance so that the target commodity is located at the outlet of the target commodity channel, thereby being beneficial to improving the accuracy of identifying the commodity type through the image of the commodity channel and the accuracy of measuring the total length of the commodity in the commodity channel through the distance measuring sensor, and further improving the accuracy of automatic checking of the vending machine. The self-service vending machine provided by the embodiment of the application is used for realizing the commodity checking method, and therefore the self-service vending machine also has the advantage of high automatic checking accuracy.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. A commodity checking method is applied to a vending machine, the vending machine comprises a cabinet, a plurality of commodity channels used for storing commodities are arranged in the cabinet, each commodity channel is provided with an outlet used for outputting the commodities, each commodity channel is provided with a conveying mechanism, each conveying mechanism is arranged for conveying the commodities in the corresponding commodity channel to the outlet of the corresponding commodity channel, and the commodity checking method comprises the following steps:

acquiring a first distance from a target commodity in a target commodity channel to an outlet of the target commodity channel; the target commodity is a commodity which is closest to an outlet of the target commodity in the target commodity channel;

driving the goods in the target goods channel to move the first distance, so that the target goods are positioned at the outlet of the target goods channel;

and checking the commodities in the target goods channel.

2. The method of claim 1, wherein a camera is further disposed within the cabinet of the vending machine, the camera configured to acquire an image of the lane; the step of obtaining a first distance from a target commodity in a target commodity channel to an outlet of the target commodity channel comprises:

controlling the camera to shoot the image of the goods channel;

and calculating a first distance from the target commodity in the target commodity channel to an outlet of the target commodity channel according to the image of the commodity channel.

3. The article counting method according to claim 2, wherein the lane comprises a floor for supporting the articles, and the step of calculating a first distance from a target article in the target lane to an exit of the target lane from the image of the lane comprises:

determining a plurality of pixel points on an intersection line of the target commodity and a bottom plate of the target cargo channel according to the image of the cargo channel;

respectively calculating to obtain a second distance between the target commodity and the outlet of the target goods channel according to each pixel point;

and taking the minimum value in the second distances corresponding to the pixel points as the first distance from the target commodity to the outlet of the target goods channel.

4. The method of claim 3, wherein said step of calculating a second distance between said target product and an exit of said target lane according to each of said pixel points comprises:

determining the position of the pixel point in the image of the cargo channel along the width direction of the cargo channel;

determining a conversion polynomial of the pixel point according to the position of the pixel point in the image of the cargo channel along the width direction of the cargo channel and a pre-stored conversion comparison table; wherein the conversion polynomial is used for calculating the second distance corresponding to the pixel point according to the position of the pixel point;

and calculating the second distance corresponding to the pixel point according to the position of the pixel point in the image of the cargo channel along the width direction of the cargo channel and the conversion polynomial corresponding to the pixel point.

5. The merchandise inventory method according to claim 4, wherein the conversion look-up table is obtained in advance by:

the method comprises the steps that a camera is controlled to shoot an image of a preset goods channel, wherein a test mark is arranged in the preset goods channel and is located on a bottom plate of the preset goods channel, the test mark comprises M first dividing lines and N second dividing lines, the first dividing lines extend along the length direction of the preset goods channel, the second dividing lines extend along the width direction of the preset goods channel, and the M first dividing lines and the N second dividing lines divide the bottom plate of the preset goods channel into a plurality of areas;

for each first dividing line, selecting a plurality of intersections on the first dividing line, and obtaining a conversion polynomial of the first dividing line according to the position of each intersection in the image of the preset cargo way and the actual position of the intersection; wherein the intersection point is a point where the first dividing line and the second dividing line intersect;

and storing the corresponding relation of each first dividing line and the conversion polynomial thereof as the conversion comparison table.

6. The merchandise checking method according to claim 5, wherein the step of determining the conversion polynomial of the pixel point according to the position of the pixel point in the image of the lane along the width direction of the lane and a conversion look-up table stored in advance comprises:

determining the first dividing line closest to the pixel point according to the position of the pixel point in the image of the cargo way along the width direction of the cargo way;

and determining a conversion polynomial corresponding to the latest first dividing line according to the prestored conversion comparison table, and taking the conversion polynomial corresponding to the latest first dividing line as the conversion polynomial of the pixel point.

7. The method of claim 3, wherein the step of determining a plurality of pixel points on an intersection of the target commodity and a bottom plate of the target lane from the image of the lane comprises:

analyzing and processing the image of the goods channel, and determining a detection area of the target goods channel in the image of the goods channel; wherein the detection area of the target lane is an area defined by edges of a floor of the target lane;

and carrying out line-by-line detection on the pixel points of the detection area along a set direction, determining the mutation points in the detection area, and taking the mutation points in the detection area as the pixel points on the intersection line of the target commodity and the bottom plate of the target goods way.

8. The method of claim 7, wherein analyzing the image of the lane to determine the detection area of the target lane in the image of the lane comprises:

acquiring the width of the target cargo channel;

determining a plurality of positioning points in the image of the cargo channel according to the width of the target cargo channel;

and determining the detection area of the target cargo channel in the image of the cargo channel according to the positioning points.

9. The method for checking the commodities as claimed in claim 7, wherein said commodity passage comprises a bottom plate, a first partition and a second partition, said first partition and said second partition are oppositely disposed on said bottom plate along the width direction of said commodity passage and are parallel to each other, a receiving space of said commodity passage is formed among said bottom plate, said first partition and said second partition, said step of analyzing and processing the image of said commodity passage to determine the detection area of said target commodity passage in the image of said commodity passage comprises:

segmenting the image of the cargo channel by adopting a deep learning algorithm through a pre-trained feature file, and extracting a partition plate area of the target cargo channel in the image of the cargo channel;

determining the front ends of a first partition plate and a second partition plate of the target cargo way from the partition plate area, calculating the rear end of each partition plate by taking an adjacent distance fit line corresponding to the front end of each partition plate as a reference line, and calculating according to the front end and the rear end of the first partition plate and the front end and the rear end of the second partition plate to obtain the detection area of the target cargo way.

10. An automatic vending machine, includes controlling means and rack, be provided with a plurality of goods way that are used for saving commodity in the rack, the goods way has the export that is used for exporting commodity, just the goods way is provided with conveying mechanism, conveying mechanism sets up to the export of goods way is carried the commodity in the goods way, controlling means sets up to:

acquiring a first distance from a target commodity in a target commodity channel to an outlet of the target commodity channel; the target commodity is a commodity which is closest to an outlet of the target commodity in the target commodity channel;

driving the goods in the target goods channel to move the first distance, so that the target goods are positioned at the outlet of the target goods channel;

and checking the commodities in the target goods channel.

Images