CN112307861A

CN112307861A - System, method and apparatus for shelf condition monitoring

Info

Publication number: CN112307861A
Application number: CN201910992339.7A
Authority: CN
Inventors: 刘维
Original assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Current assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Priority date: 2019-10-18
Filing date: 2019-10-18
Publication date: 2021-02-02

Abstract

The invention discloses a system, a method and a device for monitoring shelf states, and relates to the technical field of warehousing management. A system for shelf condition detection comprising: the shooting module is configured to shoot images of one or more shelves and acquire depth information of objects in the images, wherein one or more columns of goods are placed on each shelf, and the goods in each column are arranged along the depth direction of the shelf; and the communication module is configured to send the shot image and the depth information corresponding to the image to the processing module, so that the processing module determines the depth information corresponding to the article in the image and further determines the goods shelf needing replenishment. Thereby improving the efficiency and flexibility of shelf condition monitoring.

Description

System, method and apparatus for shelf condition monitoring

Technical Field

The invention relates to the technical field of warehousing management, in particular to a system, a method and a device for monitoring shelf states.

Background

In a shop, warehouse, etc., it is necessary to periodically check whether the number of items on the shelf is sufficient. If not, replenishment is required. Currently, there are several ways to monitor whether a shelf is out of stock.

For example, a gravity sensor may be added under each shelf deck. When the change value of the weight detected by the gravity sensor exceeds a preset threshold value, the current goods shelf can be judged to have a shortage problem. For another example, several infrared sensors or ultrasonic sensors may be installed on opposite sides of each shelf, so that the measured value returned by each sensor can be used to determine whether the shelf is out of stock.

Disclosure of Invention

After analysis, the inventor finds that the requirement of the sensor on the installation condition is higher. Therefore, the shelf state monitoring mode in the related art is difficult to deploy, so that the monitoring efficiency is low and the flexibility is poor.

The embodiment of the invention aims to solve the technical problem that: how to improve the efficiency and flexibility of shelf condition monitoring.

According to a first aspect of some embodiments of the present invention there is provided a system for shelf status detection, comprising: the shooting module is configured to shoot images of one or more shelves and acquire depth information of objects in the images, wherein one or more columns of goods are placed on each shelf, and the goods in each column are arranged along the depth direction of the shelf; and the communication module is configured to send the shot image and the depth information corresponding to the image to the processing module, so that the processing module determines the depth information corresponding to the article in the image and further determines the goods shelf needing replenishment.

In some embodiments, the processing module is located at the server, and the photographing module and the communication module are located at the mobile device; alternatively, the processing module, the photographing module and the communication module are located on a movable device.

In some embodiments, the system further comprises: and the processing module is configured to determine depth information corresponding to the items in the image and further determine a shelf needing replenishment.

In some embodiments, the processing module is further configured to determine, according to the depth information, a region in the image having a depth value greater than a preset threshold; performing image recognition on the acquired image to determine an item in the image; and under the condition that the area with the depth value larger than the preset threshold value comprises the article, judging that the corresponding shelf in the image needs to be restocked.

In some embodiments, the processing module is further configured to perform image recognition on the acquired image, determine a shelf area in the image, and determine an area with a depth value greater than a preset threshold value in the shelf area according to the depth information.

In some embodiments, the processing module is further configured to stitch some or all of the plurality of images according to the matching result of the feature points in the plurality of images acquired continuously, so as to perform image recognition on the stitched images.

In some embodiments, a shelf indicia is provided on each shelf; the processing module is further configured to perform image recognition on the acquired image, obtain a shelf identifier corresponding to the shelf mark in the image, so as to determine depth information corresponding to the article in the image, and further determine a shelf needing replenishment according to the shelf identifier.

In some embodiments, a shelf indicia is provided on each shelf; the processing module is further configured to perform image recognition on the acquired image to obtain a shelf identifier corresponding to the shelf mark in the image; and determining the position information of the movable device according to the corresponding relation between the pre-stored shelf mark and the position information.

In some embodiments, the system further comprises: a navigation module configured to guide travel of the movable device according to the position information of the movable device.

In some embodiments, the system further comprises: a storage module configured to store the operation trajectory so that the movable apparatus travels according to the operation trajectory.

In some embodiments, the system further comprises: and a height adjusting part for fixing the photographing module on the movable device and adjusting the height of the photographing module.

In some embodiments, the system further comprises: and the vehicle body is used for bearing the shooting module and driving along the goods shelf channel.

In some embodiments, there are multiple camera modules.

According to a second aspect of some embodiments of the present invention there is provided a method for shelf status detection, comprising: acquiring images of one or more shelves and depth information of objects in the images, wherein one or more columns of goods are placed on each shelf, and the goods in each column are arranged along the depth direction of the shelf; and determining depth information corresponding to the articles in the image, and further determining a shelf needing replenishment.

In some embodiments, determining depth information corresponding to the items in the image, and thus determining the shelves that need restocking, comprises: determining an area with a depth value larger than a preset threshold value in the image according to the depth information; performing image recognition on the acquired image to determine an item in the image; and under the condition that the area with the depth value larger than the preset threshold value comprises the article, judging that the corresponding shelf in the image needs to be restocked.

In some embodiments, determining, from the depth information, a region of the image having a depth value greater than a preset threshold comprises: carrying out image recognition on the acquired image, and determining a shelf area in the image; and determining the area with the depth value larger than the preset threshold value in the shelf area according to the depth information.

In some embodiments, image recognition of the acquired image comprises: and according to the matching results of the feature points in the continuously acquired multiple images, splicing part or all of the multiple images so as to perform image recognition on the spliced images.

In some embodiments, a shelf indicia is provided on each shelf; the method further comprises the following steps: and carrying out image recognition on the acquired image to obtain a shelf mark corresponding to the shelf mark in the image so as to determine depth information corresponding to the article in the image and further determine the shelf needing replenishment according to the shelf mark.

In some embodiments, a shelf indicia is provided on each shelf; a shooting module on the movable device acquires images of one or more shelves and depth information of objects in the images; the method further comprises the following steps: carrying out image recognition on the obtained image to obtain a shelf mark corresponding to the shelf mark in the image; and determining the position information of the movable device according to the corresponding relation between the pre-stored shelf mark and the position information.

In some embodiments, the method further comprises: and guiding the traveling of the movable device according to the position information of the movable device.

In some embodiments, the method further comprises: and guiding the running of the movable device according to the pre-stored running track.

According to a third aspect of some embodiments of the present invention there is provided an apparatus for shelf status detection, comprising: a memory; and a processor coupled to the memory, the processor configured to perform any of the foregoing methods for shelf state detection based on instructions stored in the memory.

According to a fourth aspect of some embodiments of the present invention, there is provided a computer readable storage medium having a computer program stored thereon, wherein the program when executed by a processor implements any of the aforementioned methods for shelf status detection.

Some embodiments of the above invention have the following advantages or benefits: the embodiment of the invention provides a novel shelf state detection mode. Through the acquired image of the shelf and the depth information of the object in the image, the shelf needing replenishment can be determined. The mode has low requirement on the use environment and is easy to deploy and use, so that the efficiency and the flexibility of shelf state monitoring can be improved.

Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

FIG. 1 is a block diagram of a system for shelf status detection according to some embodiments of the invention.

FIG. 2 is a block diagram of a system for shelf status detection according to further embodiments of the present invention.

Fig. 3A and 3B are schematic diagrams of a system for shelf status detection according to further embodiments of the invention.

FIG. 4 is a schematic diagram of an apparatus for shelf condition detection according to further embodiments of the present invention.

FIG. 5 is a flow diagram of a method for shelf status detection according to some embodiments of the invention.

FIG. 6 is a flow diagram of a shelf-state determination method according to some embodiments of the invention.

FIG. 7 is a flow diagram illustrating a method for mobile device booting according to some embodiments of the invention.

FIG. 8 is a schematic diagram of an apparatus for shelf condition detection according to some embodiments of the invention.

Fig. 9 is a schematic structural diagram of an apparatus for shelf status detection according to further embodiments of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. 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 invention.

The relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.

Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.

In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.

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, further discussion thereof is not required in subsequent figures.

The shelves in embodiments of the invention may be shelves located in a store or warehouse. One or more columns of goods are placed on each shelf, and the goods in each column are arranged in the depth direction of the shelf. When the item closest to the outside of the shelf in a row of items is removed, the distance from the edge of the ply to the item closest to the outside of the shelf in the remaining items in the row becomes longer. Thus, the remaining condition of each column of articles can be determined by capturing an image of the shelf and obtaining depth information of the object in the image.

FIG. 1 is a block diagram of a system for shelf status detection according to some embodiments of the invention. As shown in fig. 1, the system 10 for shelf status detection of this embodiment includes a photographing module 110 and a communication module 120.

The photographing module 110 is configured to photograph an image of one or more shelves each having one or more columns of goods placed thereon and the goods in each column being arranged in a depth direction of the shelf, and acquire depth information of an object in the image. The depth information of the object in the image includes a depth value corresponding to each pixel point in the image or each subregion in the image, and reflects a distance from the object corresponding to each pixel point or each subregion to the distance sensing device in the camera module.

During the photographing process, the distance of the photographing module 110 from the edge of the shelf deck may be fixed so that the depth information corresponding to different images is in a comparable state. Of course, the distance may be variable, and one skilled in the art may select the distance as desired.

In some embodiments, the photographing module 110 may be a three-dimensional (3D) camera or a depth camera. For example, an infrared sensor, a color sensor, an infrared laser emitter, a real sensor (RealSense) image processing chip, and the like may be integrated in the three-dimensional camera.

In some embodiments, a shelf indicia may be provided on each shelf. The shelf label may be presented in the form of a preset graphic, color, font, etc., and may include an identification of the serial number, etc. of the shelf. Thus, the processing module may determine the shelf that needs restocking based on the depth information and the shelf label in the image.

The communication module 120 is configured to transmit the photographed image and the depth information corresponding to the image to the processing module. The processing module may determine depth information corresponding to items in the image, and further determine shelves that need replenishment. When the depth value of a certain area in the image is larger than the preset threshold value, the distance between the area and the camera module is far, and the situation that the goods shortage exists in the area of the shelf can be judged.

The above-described embodiments provide a new shelf-state detection approach. Through the acquired image of the shelf and the depth information of the object in the image, the shelf needing replenishment can be determined. The mode has low requirement on the use environment and is easy to deploy and use, so that the efficiency and the flexibility of shelf state monitoring can be improved.

In some embodiments, the system may further include a processing module. An embodiment of the system for shelf status detection of the present invention is described below with reference to fig. 2.

FIG. 2 is a block diagram of a system for shelf status detection according to further embodiments of the present invention. As shown in fig. 2, the system 20 for shelf state detection of this embodiment includes a photographing module 210, a communication module 220, and a processing module 230. The processing module 230 is configured to determine depth information corresponding to items in the image, and thus determine shelves that need replenishment.

In some embodiments, the processing module 230 is further configured to determine, according to depth information of an object in the image, a region in the image having a depth value greater than a preset threshold; carrying out image recognition on the obtained image, and determining an article in the image; and under the condition that the area with the depth value larger than the preset threshold value comprises the article, judging that the corresponding shelf in the image needs to be restocked.

In some embodiments, the processing module 230 is further configured to perform image recognition on the acquired image, and determine a shelf area in the image, so as to determine an area with a depth value greater than a preset threshold value in the shelf area according to the depth information.

Thus, when the image acquired by the photographing module 210 includes regions other than shelves, these regions may be excluded from consideration.

In some embodiments, the processing module 230 is further configured to stitch some or all of the plurality of images according to the matching result of the feature points in the plurality of images acquired consecutively so as to perform image recognition on the stitched images.

Therefore, when the shooting module 210 can only shoot a part of the shelf at each time, a plurality of images can be spliced into a complete shelf, so that the accuracy of shelf state detection is further improved.

In some embodiments, the processing module 230 is further configured to perform image recognition on the acquired image, obtain a shelf identifier corresponding to a shelf mark in the image, so as to determine depth information corresponding to an item in the image, and further determine a shelf that needs replenishment according to the shelf identifier. Thus, it is possible to determine which shelf needs replenishment directly from the image.

When the shelf mark is not provided on the shelf, it is also possible to determine which shelf is out of stock from the correspondence between the product identified from the image and the product placement position stored in advance.

Fig. 3A and 3B are schematic diagrams of a system for shelf status detection according to further embodiments of the invention. In the

systems

31, 32 shown in fig. 3A and 3B, the

camera modules

312, 322 and the

communication modules

313, 323 may be carried by the

bodies

311, 321, respectively, of a movable device, which may be, for example, a cart. The mobile device may carry the camera module, travel along the shelf aisle, so that the camera module may acquire images of different shelves, or different parts of the shelves. A shelf aisle refers to the traversable path around a shelf.

The processing module 314 may be located on the server 315, as shown in FIG. 3A, or on the vehicle body 321, as shown in FIG. 3B. In the embodiment of fig. 3A, the processing module 314 located in the server 315 can process more complex calculations, so that the detection efficiency can be improved. In the embodiment of fig. 3B, the processing module 324 on the vehicle body 321 can process simpler calculation, so that the detection process can be implemented without connecting to a network, and energy consumption and network resources are saved. The particular implementation can be selected as desired by those skilled in the art.

In some embodiments, the processing module may be further configured to perform image recognition on the acquired image, and obtain a shelf identifier corresponding to the shelf label in the image; and determining the position information of the movable device according to the corresponding relation between the pre-stored shelf mark and the position information. The communication module may be further configured to acquire location information of the movable apparatus. The location information is determined by the server from the shelf labels in the image and may be a physical coordinate. For example, the correspondence between the shelf identifier and the position of the shelf may be stored in advance in a database of the server. When the server recognizes the shelf mark corresponding to the shelf mark in the image, the position of the shelf can be determined, and the position of the device for detecting the shelf state can be determined. Therefore, the position information can be determined through image recognition, and the positioning cost is reduced.

Other ways of determining the position information of the mobile device may be used by those skilled in the art, as desired. For example, a mobile device may be configured with a positioning module.

In some embodiments, the system 32 may also include a navigation module 325 configured to direct travel of the mobile device based on the location information of the mobile device.

In some embodiments, the system 32 may further include a storage module 326 configured to store the travel trajectory such that the movable device travels according to the travel trajectory.

The movable device may be driven at a preset time, or when a preset condition is satisfied, or periodically according to a preset running track, as needed, so that the shelf state can be obtained in time.

Of course, the system 31 may also include a navigation module and a storage module, which are not described in detail herein.

Through the embodiment, the movable device in the system can realize autonomous driving so as to collect data and detect the state of the goods shelf in the autonomous driving process. Thus, the efficiency of shelf state detection is improved.

The device for detecting the shelf state provided by the invention can also adjust the height of the shooting module according to the height of the shelf. An embodiment of the apparatus for shelf state detection of the present invention is described below with reference to fig. 4.

FIG. 4 is a schematic diagram of a system for shelf status detection according to further embodiments of the present invention. As shown in fig. 4, the system 40 for shelf state detection of this embodiment includes a vehicle body 410, a photographing module 420, a communication module 430, and a height adjusting part 440. The height adjusting member 440 is used to fix the photographing module 420 to the vehicle body 410 and adjust the height of the photographing module 420. The height adjustment member 440 may be, for example, a retractable adjustment lever.

The length of the height adjusting part 440 can be adjusted manually or automatically according to the instruction of the processing module. When the height adjusting member 440 adjusts the length by itself, it can be driven by a motor.

In some embodiments, the processing module may determine the current field of view of the capture module based on the recognition of the image. In the event that the image in the current field of view does not include an image of the top of the shelf, the height adjustment component 440 may be instructed to continue to be raised; in the event that the image in the current field of view includes an image of the top of the shelf, the height adjustment component 440 may be instructed to fall back to the initial height.

In some embodiments, the system may also have multiple camera modules, each arranged at a different height, or arranged to take different angles, etc. For example, the number of camera modules in the system may be equal to the number of levels of the shelf, and the difference in height of adjacent camera modules is equal to the level height of each level of the shelf. Thus, each camera module may be primarily responsible for the taking of some or all of the items in a layer.

An embodiment of the method for shelf-state detection of the present invention is described below with reference to fig. 5.

FIG. 5 is a flow diagram of a method for shelf status detection according to some embodiments of the invention. As shown in fig. 5, the method for shelf state detection of this embodiment includes steps S502 to S504.

In step S502, an image of one or more shelves each having one or more rows of goods placed thereon and the goods in each row arranged in the depth direction of the shelf is acquired, and depth information of the object in the image is acquired.

In step S504, depth information corresponding to the item in the image is specified, and a shelf to be restocked is specified.

In some embodiments, a shelf indicia may be provided on each shelf. Therefore, the acquired image can be subjected to image recognition, the shelf mark corresponding to the shelf mark in the image is obtained, the depth information corresponding to the article in the image is determined, and the shelf needing replenishment is determined according to the shelf mark.

After obtaining the status of the shelf, the system may generate a replenishment order based on the identification.

An embodiment of the shelf-state determination method of the present invention is described below with reference to fig. 6.

FIG. 6 is a flow diagram of a shelf-state determination method according to some embodiments of the invention. As shown in fig. 6, the shelf-state determination method of this embodiment includes steps S602 to S606.

In step S602, according to the depth information of the object in the image, a region in the image having a depth value greater than a preset threshold is determined.

In some embodiments, image recognition may be performed on the acquired image to determine a shelf area in the image; and determining the area with the depth value larger than the preset threshold value in the shelf area according to the depth information of the object in the image.

In step S604, the acquired image is subjected to image recognition, and an article in the image is determined.

In some embodiments, image recognition may be performed on the captured image to obtain the shelf identifier corresponding to the shelf label in the image and the item in the image.

In some embodiments, some or all of the plurality of images may be stitched according to matching results of feature points in the plurality of images acquired continuously, so as to perform image recognition on the stitched images. In the splicing process, the same characteristic point of different images can be matched, so that a plurality of images with small visual angles are spliced into one image with a large visual angle.

In step S606, in the case where an item is included in the area whose depth value is larger than the preset threshold value, it is determined that the corresponding shelf in the image needs to be restocked.

In some embodiments, in order to visually display the out-of-stock condition, an article state depth map may be generated according to depth information corresponding to an area where each article is located. The legend may be presented, for example, in the form of a two-dimensional graph, with the horizontal axis being the item identification and the vertical axis being the depth information corresponding to the area in which the respective item is located. Therefore, the current stock shortage situation on the shelf can be intuitively browsed.

In some embodiments, an image of one or more shelves and depth information of objects in the image may be acquired by a camera module on the mobile device. And the mobile device can operate autonomously to improve detection efficiency. An embodiment of the mobile device guiding method of the present invention is described below with reference to fig. 7.

FIG. 7 is a flow diagram illustrating a method for mobile device booting according to some embodiments of the invention. As shown in fig. 7, the movable apparatus guiding method of this embodiment includes steps S702 to S706.

In step S702, image recognition is performed on the acquired image, and a shelf identifier corresponding to the shelf label in the image is obtained.

In step S704, the position information of the mobile device is determined based on the correspondence between the shelf mark and the position information stored in advance.

In step S706, the travel of the movable device is guided in accordance with the position information of the movable device.

In addition, the storage module on the movable device can also store the running track in advance. The movable device may travel according to a pre-stored travel trajectory.

Therefore, the movable device can realize autonomous operation, and the efficiency of shelf state detection is improved.

FIG. 8 is a schematic diagram of an apparatus for shelf condition detection according to some embodiments of the invention. As shown in fig. 8, the apparatus 80 for shelf state detection of this embodiment includes: a memory 810 and a processor 820 coupled to the memory 810, the processor 820 being configured to perform a method for shelf status detection in any of the preceding embodiments based on instructions stored in the memory 810.

Memory 810 may include, for example, system memory, fixed non-volatile storage media, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader (Boot Loader), and other programs.

Fig. 9 is a schematic structural diagram of an apparatus for shelf status detection according to further embodiments of the present invention. As shown in fig. 9, the apparatus 90 for shelf state detection of this embodiment includes: the memory 910 and the processor 920 may further include an input/output interface 930, a network interface 940, a storage interface 950, and the like. These

interfaces

930, 940, 950 and the memory 910 and the processor 920 may be connected, for example, by a bus 960. The input/output interface 930 provides a connection interface for input/output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 940 provides a connection interface for various networking devices. The storage interface 950 provides a connection interface for external storage devices such as an SD card and a usb disk.

Embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements any of the aforementioned methods for shelf status detection.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims

1. A system for shelf condition detection, comprising:

the shooting module is configured to shoot images of one or more shelves and acquire depth information of objects in the images, wherein one or more columns of goods are placed on each shelf, and the goods in each column are arranged along the depth direction of the shelf; and the number of the first and second groups,

the communication module is configured to send the shot image and the depth information corresponding to the image to the processing module, so that the processing module determines the depth information corresponding to the article in the image and further determines the goods shelf needing replenishment.

2. The system of claim 1, wherein,

the processing module is positioned at the server, and the shooting module and the communication module are positioned at the movable device; alternatively, the first and second electrodes may be,

the processing module, the shooting module and the communication module are located on the movable device.

3. The system of claim 1 or 2, further comprising:

and the processing module is configured to determine depth information corresponding to the items in the image and further determine a shelf needing replenishment.

4. The system of claim 3, wherein the processing module is further configured to determine, according to the depth information, a region in the image having a depth value greater than a preset threshold; performing image recognition on the acquired image to determine an item in the image; and under the condition that the area with the depth value larger than the preset threshold value comprises the article, judging that the corresponding shelf in the image needs to be restocked.

5. The system of claim 4, wherein the processing module is further configured to perform image recognition on the acquired image, determine a shelf area in the image, and determine an area with a depth value greater than a preset threshold in the shelf area according to the depth information.

6. The system of claim 4, wherein the processing module is further configured to stitch some or all of the plurality of images according to the matching result of the feature points in the plurality of images acquired continuously, so as to perform image recognition on the stitched images.

7. The system of claim 4, wherein a shelf marker is disposed on each shelf;

the processing module is further configured to perform image recognition on the acquired image, obtain a shelf identifier corresponding to a shelf mark in the image, so as to determine depth information corresponding to an article in the image, and further determine a shelf which needs to be restocked according to the shelf identifier.

8. The system of claim 3, wherein each shelf has a shelf label disposed thereon;

the processing module is further configured to perform image recognition on the acquired image to obtain a shelf identifier corresponding to the shelf mark in the image; and determining the position information of the movable device according to the corresponding relation between the pre-stored shelf mark and the position information.

9. The system of claim 2 or 8, further comprising:

a navigation module configured to guide travel of the movable apparatus according to the position information of the movable apparatus.

10. The system of claim 2 or 8, further comprising:

a storage module configured to store a travel trajectory so that the movable apparatus travels according to the travel trajectory.

11. The system of claim 2, further comprising:

and the height adjusting component is used for fixing the shooting module on the movable device and adjusting the height of the shooting module.

12. The system of claim 1, further comprising:

and the vehicle body is used for bearing the shooting module and driving along the goods shelf channel.

13. The system of claim 1, wherein there are a plurality of said capture modules.

14. A method for shelf status detection, comprising:

acquiring images of one or more shelves and depth information of objects in the images, wherein one or more columns of goods are placed on each shelf, and the goods in each column are arranged along the depth direction of the shelf;

and determining depth information corresponding to the articles in the image, and further determining a shelf needing replenishment.

15. The method of claim 14, wherein the determining depth information corresponding to the items in the image to determine shelves requiring restocking comprises:

determining an area with a depth value larger than a preset threshold value in the image according to the depth information;

performing image recognition on the acquired image to determine an item in the image;

and under the condition that the area with the depth value larger than the preset threshold value comprises the article, judging that the corresponding shelf in the image needs to be restocked.

16. The method of claim 15, wherein the determining, according to the depth information, a region in the image having a depth value greater than a preset threshold value comprises:

carrying out image recognition on the acquired image, and determining a shelf area in the image;

and determining the area with the depth value larger than a preset threshold value in the shelf area according to the depth information.

17. The method of claim 15, wherein the image recognizing the acquired image comprises:

and according to the matching results of the feature points in the continuously acquired multiple images, splicing part or all of the multiple images so as to perform image identification on the spliced images.

18. The method of claim 15, wherein a shelf marker is provided on each shelf;

the method further comprises the following steps:

and carrying out image recognition on the acquired image to obtain a shelf mark corresponding to the shelf mark in the image so as to determine depth information corresponding to the article in the image and further determine the shelf needing replenishment according to the shelf mark.

19. The method of claim 14, wherein a shelf marker is provided on each shelf; a shooting module on the movable device acquires images of one or more shelves and depth information of objects in the images;

the method further comprises the following steps: carrying out image recognition on the obtained image to obtain a shelf mark corresponding to the shelf mark in the image; and determining the position information of the movable device according to the corresponding relation between the pre-stored shelf mark and the position information.

20. The method of claim 19, further comprising:

guiding the travel of the movable device according to the position information of the movable device.

21. The method of claim 19, further comprising:

and guiding the running of the movable device according to the pre-stored running track.

22. An apparatus for shelf condition detection, comprising:

a memory; and

a processor coupled to the memory, the processor configured to perform the method for shelf state detection of any of claims 14-21 based on instructions stored in the memory.

23. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method for shelf status detection of any one of claims 14 to 21.