Apparatus and method for inventorying shelves

Abstract

A device for inventorying shelves comprising a movable base, two or more cameras coupled to the movable base, a processing module, said processing module being electronically coupled to said cameras, a data storage module, which data storage module is electronically coupled to said processing module, a communication module, said communication module being electronically coupled to said data storage module, and a light module, said processing module being configured to locate said movable base in said space and / or identify the item to be inventoried in said shelves, based on a pixel correspondence in said image information, and wherein the light module extends in an emission plane, over a height of at least 100 cm, which light module is configured to produce light with a local luminous flux over 1 cm2 of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane.

Description

[0001] DEVICE AND METHOD FOR INVENTORYING SHELVES

[0002] TECHNICAL FIELD

[0003] The invention relates to a device and method for inventorying shelves.

[0004] PRIOR ART

[0005] Retail environments such as supermarkets, department stores or drug stores can offer thousands of different products, often for sale at the same time. These stores are typically arranged in an aisle structure, with each aisle having shelves with products on one or both sides. However, the store's inventory can be continually adjusted by removing, adding, or repositioning products. In addition, when customers purchase products, they may sell out and may need to be reordered from suppliers.

[0006] Shelves in a store are usually provided with shelf labels. These labels have two purposes. The first is the identification of the product placed near the label on the shelf. For example, the label may contain a barcode or QR code that identifies the product. The label also typically contains the unit price of the product and may contain other specific information relevant to the store.

[0007] The second purpose of the shelf label is to indicate a position on the shelf where the product should be placed. For example, a store may decide to place the labels on the far left side of the shelf where the corresponding product should go. It is therefore important that store staff place the products correctly when restocking the shelves.

[0008] Despite regular restocking schedules, products expected to be in stock may be sold out, reducing both sales and customer satisfaction. Cash register data can be used to provide a rough estimate of stock levels, but it does not help identify misplaced, stolen, or damaged products, all of which impact product availability. However, manually monitoring product inventory and keeping track of product position is often an expensive and time-consuming process.

[0009] One possible solution for product inventorying relies on planograms, typically created manually for each individual store, combined with computer vision technology. Given a planogram, computer vision can be used to assist with stock-taking. In such cases, the planogram needs to be created and updated every time a product is removed, added or repositioned in the store.

[0010] To implement computer vision that relies on a planogram, one or more fixed cameras can be used throughout a store to monitor aisles, checking large gaps in shelf space against the planogram or shelf labels. The disadvantage of this is that many fixed cameras must be provided, usually with high resolution, in order to capture the entire store. Alternatively, several movable cameras can be used to scan a store aisle. Even with such systems, human intervention is generally required to build an initial planogram that correctly represents the product layout, and is sufficiently detailed.

[0011] For example, WO 2020 / 210820 Al attempts to meet this need by deploying a movable robot that moves through the aisles of a store and performs inventory tasks. Although this significantly reduces the amount of human intervention in the inventory process, inventory tasks are performed with low speed, efficiency and accuracy. Fully automatic systems as described in WO '820 therefore have only mediocre reliability.

[0012] The present invention aims to solve at least some of the above problems or drawbacks.

[0013] SUMMARY OF THE INVENTION

[0014] In a first aspect, the invention relates to a device for inventorying shelves according to claim 1.

[0015] The device according to the present invention has the advantage that the light module produces a very homogeneous luminous flux over its entire height, whereby items to be inventoried are well illuminated and thus qualitative imaging can take place. This in turn allows inventory to be made with high accuracy and speed using the device according to the present invention.

[0016] Preferred embodiments of the device are shown in claims 2 to 7.

[0017] A second aspect of the present invention relates to a method for inventorying shelves according to claim 8.

[0018] Preferred embodiments of the method are shown in claims 9 to 15. DESCRIPTION OF THE FIGURES

[0019] Figure 1 shows a perspective view of an embodiment of a device according to the first aspect of the invention.

[0020] Figure 2 shows a side view of an embodiment of a device according to the first aspect of the invention.

[0021] Figure 3 shows an exploded view of an embodiment of a device according to the first aspect of the invention.

[0022] DETAILED DESCRIPTION

[0023] The invention relates to a device and method for inventorying shelves.

[0024] Unless otherwise defined, all terms used in the description of the invention, including technical and scientific terms, have the meaning as commonly understood by a person skilled in the art to which the invention pertains. For a better understanding of the description of the invention, the following terms are explained explicitly.

[0025] In this document, "a" and "the" refer to both the singular and the plural, unless the context presupposes otherwise. For example, "a segment" means one or more segments.

[0026] When the term "around" or "about" is used in this document with a measurable quantity, a parameter, a duration or moment, and the like, then variations are meant of approx. 20% or less, preferably approx. 10% or less, more preferably approx. 5% or less, even more preferably approx. 1% or less, and even more preferably approx. 0.1% or less than and of the quoted value, insofar as such variations are applicable in the described invention. However, this must be understood to mean that the value of the magnitude where the term "approximately" or "around" is used, is itself specifically disclosed.

[0027] The terms "comprise," "comprising," "consist of," "consisting of," "provided with," "have," "having," "include," "including," "contain," "containing" are synonyms and are inclusive or open terms that indicate the presence of what follows, and which do not exclude or prevent the presence of other components, characteristics, elements, members, steps, as known from or disclosed in the prior art.

[0028] Quoting numeric intervals by the endpoints includes all integers, fractions, and / or real numbers between the endpoints, including those endpoints.

[0029] In a first aspect, the present invention relates to a device for inventorying shelves, comprising: a movable base configured for movement between and / or along one or more shelves in a space, two or more cameras coupled to the movable base, for obtaining image information relating to an item to be inventoried in said shelves; a processing module for digitizing and / or analyzing said image information, which processing module is electronically coupled to said cameras; a data storage module for storing said image information and / or data obtained after digitizing and / or analyzing it, which data storage module is electronically coupled to said processing module; a communication module for sending said image information and / or data obtained after digitizing and / or analyzing it to one or more digital locations, which communication module is electronically coupled to said data storage module; and a light module.

[0030] Preferably, the processing module is configured to locate the movable base in said space and / or identify the item to be inventoried in said shelves based on a pixel correspondence in said image information.

[0031] According to a further or other embodiment, said digital locations are configured to locate the movable base in said space and / or identify the item to be inventoried in said shelves based on a pixel correspondence in said image information.

[0032] According to a further or other embodiment, the light module extends in an emission plane, over a height of at least 100 cm, which light module is configured to produce light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane. Preferably, the processing module is configured to locate the movable base in said space and / or identify the item to be inventoried in said shelves based on a pixel correspondence in said image information, and the light module extends in an emission plane, over a height of at least 100 cm, which light module is configured to produce light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane.

[0033] In the context of the present invention, the term "inventorying" refers to the process of systematically recording, categorizing and / or counting goods or articles, preferably in a store, department store, warehouse, or the like, in order to obtain an overview of the goods or articles present, their location and status.

[0034] The term "movable base" should be interpreted as a mechanism or platform designed to move the device. In the context of the present invention, this refers to a device that can move autonomously or manually along shelves in order to perform inventory activities.

[0035] The term "shelf" refers to a storage unit in a store, department store, warehouse, or other space in which goods or articles are stored. Particularly in a retail environment, a shelf is used to display and present goods or articles to customers. A shelf may take the form of one or more shelves, a rack, a box, or the like.

[0036] The term "camera" in the context of the present invention means a device that captures images, either as still photographs or as continuously moving images. In the context of an inventory system, it is used to collect visual information about goods, articles and / or shelves.

[0037] The terminology "image information" refers to visual data captured by a camera. This may include photographs, videos, or other visual representations of products, articles, or shelves.

[0038] In the context of the invention, the terminology "item to be inventoried" should be interpreted as any product or article that forms part of the inventory. This could potentially range from individual retail products to larger units or packages. A "processing module" refers to a part of a system, such as a software or hardware component, that processes data or signals for further analysis, storage, or transmission. The processing module in the context of the present invention is configured for digitizing and / or analyzing, among other things, but not limited to, image information, product information or location.

[0039] The term "data storage module" refers to a hardware component of a system designed to store digital data.

[0040] In the context of the present invention, a "communication module" concerns a component of a system that facilitates the transfer of data between different parts of the system or between the system and external sources.

[0041] In this context, a "digital location" is a location in a digital system, such as a server, cloud environment or database, where data can be stored, retrieved or processed.

[0042] For the purposes of the invention, the term "pixel correspondence" should be understood as the correspondence or correlation between pixels in different images or within parts of the same image, as used in image processing algorithms.

[0043] A "light module" refers to a component of a system that produces and / or manages light. In the context of an inventory system, this may refer to a component that helps optimize lighting for image acquisition. The light module according to the present invention extends in an "emission plane", over a height of at least 100 cm. One or more individual light sources or light points may be located in this emission plane. In particular, the emission plane is defined as the smallest rectangle that encompasses all individual light sources or light points. The term "luminous flux" in this context refers to the degree of intensity of the light module expressed in lumens per unit of surface area of the emission plane. In English, the term "luminous exitance (Mv)" is commonly used, or "luminous flux emitted from a surface". More specifically, the term "local luminous flux" is used for the luminous flux of the light module radiated over 1 cm2of the emission plane. The term "average luminous flux" is used for the luminous flux of the light module radiated over the entire surface of the emission plane. By defining a deviation of the local luminous flux from the average luminous flux, a measure of homogeneity of the luminous flux can be defined. Luminous flux can be measured according to ISO / CIE 23539, edition 2023-03. According to the present invention, the light module is configured to produce light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane. The device satisfying this feature constitutes an independent inventive aspect of the present invention. This has the advantage that the light module produces a very homogeneous luminous flux over its entire height, whereby the item to be inventoried is well illuminated and thus qualitative imaging can take place. This in turn allows inventory to be made with high accuracy and speed using the device according to the present invention.

[0044] According to the present invention, the processing module is configured to locate the movable base in said space and / or identify the item to be inventoried in said shelves, based on a pixel correspondence in said image information. The device satisfying this feature constitutes an independent inventive aspect of the present invention. To locate the movable base in the mentioned space, the processing module uses the image information obtained by the cameras to determine the exact location of the movable base within the space. This can be done through techniques such as image recognition, where the module identifies specific features or markers in the space and uses them to determine the position of the base. This functionality is essential for accurately navigating and positioning the device, which in turn ensures efficient and effective inventorying. Such pixel correspondence markers relate to, for example, specific QR codes or barcodes on certain shelves or groups of shelves. The processing module also uses the image information obtained from the cameras to identify the item to be inventoried on the mentioned shelves. This is done through pixel correspondence, a technique in which the module analyzes the received images to recognize patterns, shapes, colors, or barcodes of products. Through this recognition, the system can accurately determine the presence, quantity, and preferably even the condition of the products on the shelves. In particular, pixel correspondence of electronic shelf labels (ESLs), preferably comprising barcodes or QR codes, associated with a specific product can be used for product identification. However, it is possible that photos or models of goods to be inventoried are used in a database for the identification of these goods. In this case, it works on the basis of pixel correspondence between the item to be inventoried and its corresponding photos or models. According to a preferred embodiment, the processing module is configured to both locate the movable base in said space and identify the item to be inventoried in said shelves, based on a pixel correspondence in said image information. Preferably, the light module produces light with a local luminous flux over 1 cm2of the emission plane which deviates by a maximum of 15% from the average luminous flux over the entire surface of the emission plane. More preferably, the light module produces light with a local luminous flux over 1 cm2of the emission plane which deviates by a maximum of 10% from the average luminous flux over the entire surface of the emission plane. Even more preferably, the light module produces light with a local luminous flux over 1 cm2of the emission plane which deviates by a maximum of 9, 8, 7, 6, 5, 4, 3, 2, most preferably a maximum of 1%, from the average luminous flux over the entire surface of the emission plane.

[0045] Higher light uniformity further promotes the illumination of the items to be inventoried and thus further increases the accuracy and speed with which the device can inventory these items.

[0046] According to some embodiments, the light module extends in the emission plane, over a height of at least 110 cm. Preferably, the light module extends in the emission plane over a height of at least 120 cm, more preferably over a height of at least 130 cm, at least 140 cm, most preferably at least 150 cm. According to some embodiments, the light module extends in the emission plane, over a height of up to 300 cm. Preferably, the light module extends in the emission plane over a height of maximum 290 cm, more preferably over a height of maximum 280 cm, maximum 270 cm, maximum 260 cm, most preferably maximum 250 cm.

[0047] According to some embodiments, the light module extends in the emission plane, over a height between 100 and 500 cm. Preferably, the light module extends in the emission plane over a height between 100 and 400 cm, between 100 and 350 cm, or between 100 and 300 cm. More preferably, the light module extends in the emission plane over a height between 110 and 290 cm, between 120 and 280 cm, between 130 and 270 cm, between 140 and 260 cm, most preferably over a height between 150 and 250 cm.

[0048] As the height of the emission plane increases, larger shelves can also be inventoried.

[0049] According to some embodiments, the light module is configured to produce light having an average luminous flux ranging from 2000 to 20000 lm / m2. The light module as described herein is advantageous for obtaining high quality image information, while making inventorying efficient. Preferably, the light module is configured to produce light with an average luminous flux comprised between 5000 and 19000 lm / m2, more preferably between 7500 and 18000 lm / m2, even more preferably between 10000 and 17000 lm / m2, most preferably between 14000 and 16000 lm / m2, such as for example 15000 lm / m2.

[0050] According to some embodiments, the light module is configured to produce light with an illuminance on the item to be inventoried between 2000 and 20000 lm / m2.

[0051] The term "illuminance" refers to the luminous flux incident on a surface, in this case the surface of an item to be inventoried. In English this is commonly referred to as "illuminance" or "luminous flux incident on a surface (Ev)".

[0052] Preferably, the light module is configured to produce light with an illuminance on the item to be inventoried of between 5000 and 19000 lm / m2. More preferably, the light module is configured to produce light with an illuminance on the item to be inventoried of between 7500 and 18000 lm / m2, more preferably between 1000 and 17000 lm / m2, most preferably between 14000 and 16000 lm / m2, such as for example 15000 lm / m2. Illuminance can be measured according to ISO / CIE 23539, edition 2023-03.

[0053] According to a further or other embodiment, the light module is configured to produce light having a color temperature comprised between 5472 and 5500 K. Preferably, the light module is configured to produce light with a color temperature ranging between 5472 and 5492 K, most preferably between 5492 and 5500 K. The color temperature can be measured according to NEN-EN-IEC 61000-3-2:2019 / Al :2021.

[0054] According to a further or other embodiment, the light module is configured to produce light having a wavelength comprised between 400 and 800 nm. Preferably, the light module is configured to produce light having a wavelength between 420 and 480 nm. More preferably, the light module is configured to produce light having a wavelength ranging between 440 and 445 nm, between 420 and 480 nm, between 440 and 460 nm, or between 445 and 450 nm. Even more preferably, the light module is configured to produce light having a wavelength comprised between 440 and 450 nm, most preferably between 443 and 447 nm. The wavelength can be measured according to NEN-EN-IEC 61000-3-2:2019 / Al:2021. According to some embodiments, the light module is configured to generate a total luminous flux of greater than 40,000 lumens. The energy efficiency of the light module is further determined by a power consumption of 20 to 25 W per meter, resulting in a total power of 300 to 400 W, preferably 325 to 375 W. This configuration ensures optimally consistent and powerful illumination over the entire operating height, with the light being distributed homogeneously in an emission plane to guarantee optimal inventory performance.

[0055] According to a further or other embodiment, the light module comprises a single, continuous light source extending over the entire said height. Such a light source contributes to a reduced complexity of the device as a whole, compared to devices comprising multiple light sources.

[0056] Preferably, said single, continuous light source is selected from the group of LED strip lighting, linear LED lighting, TL lighting or fluorescent lighting, linear halogen lighting, or combinations thereof.

[0057] An "LED (Light Emitting Diode)" is a semiconductor light source that emits light when an electrical current passes through it. LED lighting is known for its high efficiency and long lifespan. An "LED strip" is a flexible strip on which LED lights are mounted in a series. These strips are versatile in use and can be bent and cut to size. They are often used for decorative lighting, accent lighting, and in some cases as main lighting. "Linear LED lighting" refers to LED lights that are designed in long, narrow panels or tubes. This form of lighting is often used to illuminate large areas such as offices, shops, and industrial spaces. They provide an even, diffuse light distribution and are more energy efficient than traditional fluorescent linear lighting. "TL lighting" or "fluorescent lighting" uses a chemical process to convert UV light into visible light. This process takes place in a glass tube filled with a small amount of mercury and an inert gas. When electric current passes through the tube, the tube lights up. "Linear halogen lighting" uses halogen gas to extend the life of the filament in this type of lamp. Linear halogen lamps are usually long and thin, similar to fluorescent lamps, but they use a different lighting mechanism.

[0058] More preferably, said single, continuous light source is selected from the group of LED strip lighting, linear LED lighting, or combinations thereof. According to some embodiments, the single, continuous light source is LED strip lighting. According to some embodiments, the single, continuous light source is linear

[0059] LED lighting.

[0060] According to a preferred embodiment, the light module comprises at least one LED strip. According to a further preferred embodiment, the light module comprises at least two LED strips, at least three LED strips, or at least four LED strips. The said LED strips are preferably oriented parallel to each other and extend in the height direction of the light module. More preferably, said LED strips are parallel and next to each other, and all extend over the same height. According to some embodiments, said LED strips are located on opposite longitudinal sides of the two or more cameras. According to a particular embodiment, at least two LED strips are located on one longitudinal side of the two or more cameras and at least two LED strips are located on another longitudinal side of the two or more cameras.

[0061] According to a further or other embodiment, the light module comprises a plurality of light points, spread over the entire said height. Preferably, such light points are selected from the group of LED lighting, halogen lighting, or combinations thereof. Preferably, each of these light points produces light with the same luminous flux, color temperature, wavelength, or combinations thereof.

[0062] According to some embodiments, said light points are positioned at a mutual distance between 0.5 and 50 cm. Preferably, the said light points are positioned at a mutual distance of between 5 and 40 cm. More preferably, said light points are positioned at a mutual distance of between 5 and 30 cm, between 5 and 25 cm, between 5 and 20 cm, between 6 and 20 cm, between 7 and 20 cm, between 8 and 20 cm, between 9 and 20 cm, most preferably between 10 and 20 cm.

[0063] According to some embodiments, said light points are light points which produce light according to a beam angle comprised between 10 and 160°. Preferably, said light points are light points which produce light according to a beam angle between 20 and 150°. More preferably, said light points are light points which produce light according to a beam angle comprised between 30 and 140°, between 40 and 120°, between 50 and 120°, or between 60 and 120°. Even more preferably, said light points are light points which produce light according to a beam angle between 70 and 110°, most preferably between 80 and 100°. The beam angle can be measured according to NEN-EN-IEC 61000-3-2:2019 / Al:2021. According to some embodiments, said light module is configured to adjust light intensity, beam angle, color temperature, wavelength, or combinations thereof. Preferably, said light module is configured to adjust light intensity, beam angle, color temperature, wavelength, or combinations thereof, for each of said light points separately. According to a further or other embodiment, said light module is configured to dynamically adjust light intensity, beam angle, color temperature, wavelength, or combinations thereof based on camera feedback. According to some embodiments, said light source is an energy-efficient light source. According to a further or other embodiment, the light module includes a heat dissipation system. In the context of the present invention, the terminology "heat dissipation system" refers to a system that allows the temperature to be kept within optimum operating limits.

[0064] Each of the aforementioned embodiments of the device allows the inventory of goods in a space, preferably in a shelf, to be further optimized. The device is able to collect high-quality image information, partly due to the homogeneous lighting conditions, and this with high accuracy and speed. As a result, the entire inventory process can also run optimally.

[0065] According to a further or other embodiment, said cameras are selected from the group of stereo vision cameras, Time-of-Flight (ToF) cameras, structured light cameras, monocular vision cameras, monochromatic cameras, or combinations thereof.

[0066] "Stereo vision cameras", or also called "stereo cameras", are imaging systems that use two or more lenses with separate image sensors for each lens. This setup mimics human binocular vision, with each lens capturing images from slightly different angles. By comparing these two images, the system can calculate depth information for each point in an image, effectively creating a three-dimensional representation of the area being viewed.

[0067] "Time-of-Flight (ToF) cameras" measure the time it takes for light to travel from the camera to the object and back, allowing them to accurately calculate depth information. This technology is useful for understanding the volume and position of objects in a space. They are especially effective in environments where maintaining consistent lighting is challenging. The term "structured light cameras" refers to cameras that project a known pattern of light (such as grids or dots) onto a scene and then capture the reflected light with a camera. The distortion in the pattern is used to calculate depth information. This type of camera is particularly effective in controlled environments where the projected pattern is easily discernible.

[0068] The term "monocular vision cameras" refers to single-lens cameras that, through advanced algorithms, can derive depth information from visual cues in the environment. They are less accurate in depth measurement compared to stereo or ToF cameras, but are often more cost-efficient and easier to integrate into existing systems.

[0069] A "monochromatic camera" according to the invention is a camera that captures images exclusively in one color or different shades of one color (usually gray tones).

[0070] When selecting the cameras, particular attention was paid to their ability to capture a complete set of visual and spatial information related to a shelf and the products contained therein. This includes not only the identification and positioning of products, but also the perception of features that a human observer would normally detect when standing in front of the shelf. The device according to the present invention is configured to realize this perception during a passing movement of the device, whereby an accurate and efficient inventory of the shelf content is guaranteed.

[0071] According to some embodiments, said cameras include at least one stereo vision camera. Preferably, said cameras comprise at least two stereo vision cameras, or even at least three stereo vision cameras.

[0072] According to some embodiments, said cameras comprise at least one monochromatic camera. Preferably, said cameras comprise at least two monochromatic cameras, at least three monochromatic cameras, or even at least four monochromatic cameras.

[0073] The camera configurations described herein enable the reading of data matrices, such as barcodes or QR codes, on electronic shelf labels (ESLs) for product identification, while taking into account a variable distance between the device and the shelf or the electronic shelf label. To ensure the most reliable detection and reading, four monochromatic cameras are preferably used. To achieve a sufficiently large depth of field, where objects at different distances are captured sharply, the aperture of the cameras is preferably closed as much as possible. This requires an increased light intensity to optimize image quality, and the light module according to the invention proved to be sufficient.

[0074] Preferably, the monochromatic camera has a resolution of 3088 pixels and a sensor size of 7.41 mm with a pixel size of 2.4 pm. According to some embodiments, the monochromatic camera has a focal length of 9 mm. According to some embodiments, the angle of view is 0.78 rad, corresponding to a field of view of 44.8°.

[0075] According to some embodiments, the device is configured for use at a distance from the shelf or electronic shelf label of between 1000 and 2000 mm, preferably between 1100 and 1900 mm, more preferably between 1200 and 1800 mm from the shelf or electronic shelf label. This enables the monochromatic camera to correctly read a data matrix from the electronic shelf label. Such a data matrix is, for example, a two- dimensional barcode or QR code comprising 14 modules. The said data matrix preferably has a size of at least 11 by 11 mm. Ideally, the device should be located no further than 1800 mm from the shelf or electronic shelf label. In this way, a resolution of 1.64 pixels per module of the data matrix can be obtained. In the various embodiments described herein, a lower limit of 1.5 pixels per module of the data matrix is guaranteed in order to achieve correct reading.

[0076] According to some embodiments, the monochromatic camera is configured to obtain a minimum pixel density of 3.125 pixels per mm when the device is located at a distance of 1200 mm from the shelf or electronic shelf label.

[0077] According to some embodiments, the monochromatic camera is configured to obtain a Field of View (FOV) comprised between 988 mm and 1482 mm, respectively, when the device is located at a distance comprised between 1200 and 1800 mm from the shelf or electronic shelf label.

[0078] Most preferably, said cameras include two stereo vision cameras and between two and four monochromatic cameras. Even more preferably, said cameras comprise at least two stereo vision cameras and at least one monochromatic camera. Most preferably, said cameras include two stereo vision cameras and four monochromatic cameras.

[0079] These cameras are particularly useful in applications where depth perception is important. For example, stereo vision cameras can be used for navigation, object recognition and obstacle avoidance in robotics. In retail, they can accurately determine the position and volume of products on shelves. Stereo vision technology is also used in 3D modeling, autonomous vehicles, and various augmented and / or virtual reality applications.

[0080] The main advantage of stereo vision cameras over other depth sensing technologies is their ability to capture depth information in a wide range of lighting conditions and over various distances.

[0081] The use of stereo vision cameras allows to achieve complete coverage of the shelf with a minimum number of cameras, so that all obtained image information can be processed efficiently, in particular it is possible to image the entire shelf with just two cameras.

[0082] According to some embodiments, the stereo vision cameras are configured to obtain depth information and visual data with a resolution ranging from 720 to 1600 pixels, have a sensor size ranging from 3 to 4 mm, and / or a pixel size ranging from 4 to 5 pm. According to some embodiments, the stereo vision cameras have a focal length ranging from 1 to 3 mm.

[0083] Preferably, the stereo vision cameras are configured to acquire depth information and visual data with a resolution of 1280 pixels, have a sensor size of 3.84 mm and / or a pixel size of 3 pm. According to some embodiments, the stereo vision cameras have a focal length of 1.93 mm. According to some embodiments, the Angle of Field (AOF) of the stereo vision cameras is 1.57 rad, corresponding to a field of view of 89.7°.

[0084] According to some embodiments, the stereo vision cameras are configured to obtain a minimum pixel density of 0.536 pixels per mm when the device is located at a distance of 1200 mm from the shelf or electronic shelf label.

[0085] According to some embodiments, the stereo vision cameras are configured to obtain a Field of View (FOV) comprised between 2388 mm and 3581 mm, respectively, when the device is located at a distance comprised between 1200 and 1800 mm from the shelf or electronic shelf label.

[0086] According to a further or other embodiment, the light module comprises two stereo vision cameras positioned relative to the full height of the light module, so that they divide the light module into 3 equal parts. In particular, said stereo vision cameras are positioned at 1 / 3 and 2 / 3 of the full height of the light module, respectively. Preferably, the light module comprises two stereo vision cameras positioned respectively at a relative height comprised between 550 and 650 mm, and at a relative height comprised between 1200 and 1300 mm, more preferably at a relative height of 608 and 1260 mm.

[0087] According to a further or other embodiment, the light module comprises four monochromatic cameras positioned relative to the full height of the light module, so that they divide the light module into 5 equal parts. In particular, said monochromatic cameras are positioned at 1 / 5, 2 / 5, 3 / 5 and 4 / 5 of the full height of the light module, respectively. Preferably, the light module comprises four monochromatic cameras positioned respectively at a relative height comprised between 40 and 60 mm, at a relative height comprised between 615 and 635 mm, at a relative height comprised between 1190 and 1210 mm, and at a relative height comprised between 1765 and 1785 mm. More preferably, the light module comprises four monochromatic cameras positioned at a relative height of 50, 625, 1199 and 1774 mm respectively.

[0088] According to a further or other embodiment, the light module and the cameras are directed towards only one side of the aisle. Preferably, the light module and the cameras are directed in a direction perpendicular to the direction of movement of the movable base, or thus perpendicular to a viewing plane of a shelf to be inventoried.

[0089] According to another embodiment, the light module and the cameras are directed towards two opposite sides of the aisle. Preferably, the light module and the cameras are directed in directions perpendicular to the direction of movement of the movable base, or thus perpendicular to the viewing planes of two opposite shelves.

[0090] According to some embodiments, the movable base of the device is an autonomously movable base, preferably a motorized and / or movable base. According to some embodiments, the movable base of the device is a manually movable base, preferably a pushable base. According to some embodiments, the movable base is configured to move along one or more fixed rails. The movable base may comprise one or more guide wheels for this purpose, configured for movement along said rails. In some embodiments, the movable base is configured to move freely on a surface, particularly a ground or floor. The movable base may comprise one or more rollers and / or wheels. Preferably, at least one of said rollers and / or wheels is furthermore positionable and / or rotatable along an axis perpendicular to said surface. Thus, the positionable and / or rotatable wheels allow the movable base to move freely in two dimensions over the surface.

[0091] According to some embodiments, the communication module sends and / or receives data via one or more communication techniques chosen from the group of Bluetooth, Wi-Fi, NFC, loT, Ethernet, mobile internet, or a combination thereof. According to some embodiments, mobile internet includes: 3G, 4G, 5G, or further iterations thereof.

[0092] In a second aspect, the present invention relates to a method for inventorying shelves, the method comprising the steps of: illuminating an item to be inventoried in a shelf; obtaining visual information relating to the item to be inventoried; the digitization and / or analysis of said image information; the sending of said image information and / or data obtained after digitizing and / or analyzing it to one or more digital locations.

[0093] Preferably, the digitizing and / or analyzing of said image information comprises locating the obtained image information in said space and / or identifying the item to be inventoried in said shelves based on a pixel correspondence in said image information.

[0094] According to a further or other embodiment, the item to be inventoried is illuminated by means of a light module, which extends in an emission plane, over a height of at least 100 cm, which light module produces light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane.

[0095] Preferably, the digitizing and / or analyzing of said image information comprises locating the obtained image information in said space and / or identifying the item to be inventoried in said shelves on the basis of a pixel correspondence in said image information, and the item to be inventoried is illuminated by means of a light module, which extends in an emission plane, over a height of at least 100 cm, which light module produces light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane.

[0096] According to the present invention, the light module is configured to produce light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane. This has the advantage that the light module produces a very homogeneous luminous flux over its entire height, whereby the item to be inventoried is well illuminated and thus qualitative imaging can take place. This in turn allows inventory to be made with high accuracy and speed using the device according to the present invention.

[0097] According to the present invention, the obtained image information is located in said space and / or products in said shelves are identified, based on a pixel correspondence in said image information. This can be done through techniques such as image recognition, where the module identifies specific features or markers in space and uses them to determine the position of the acquired image information. Such pixel correspondence markers relate to, for example, specific QR codes or barcodes on certain shelves or groups of shelves. Pixel correspondence is also used to identify the item to be inventoried on the said shelves, a technique in which the images are analyzed to recognize patterns, shapes, colors, or barcodes of products. This recognition allows the presence, quantity and preferably even the condition of the products on the shelves to be accurately determined. In particular, pixel correspondence of electronic shelf labels (ESLs), preferably comprising barcodes or QR codes, associated with a specific product can be used for product identification. However, it is possible that photos or models of goods to be inventoried are used in a database for the identification of these goods. In this case, it works on the basis of pixel correspondence between the item to be inventoried and its corresponding photos or models. According to a preferred embodiment, both the obtained image information is located and items to be identified in said shelves are identified, based on a pixel correspondence in said image information.

[0098] Preferably, the light module produces light with a local luminous flux over 1 cm2of the emission plane which deviates by a maximum of 15% from the average luminous flux over the entire surface of the emission plane. More preferably, the light module produces light with a local luminous flux over 1 cm2of the emission plane which deviates by a maximum of 10% from the average luminous flux over the entire surface of the emission plane. Even more preferably, the light module produces light with a local luminous flux over 1 cm2of the emission plane which deviates by a maximum of 9, 8, 7, 6, 5, 4, 3, 2, most preferably a maximum of 1%, from the average luminous flux over the entire surface of the emission plane.

[0099] Higher light uniformity further promotes the illumination of the items to be inventoried and thus further increases the accuracy and speed with which items are inventoried.

[0100] According to some embodiments, the light module extends in the emission plane, over a height of at least 110 cm. Preferably, the light module extends in the emission plane over a height of at least 120 cm, more preferably over a height of at least 130 cm, at least 140 cm, most preferably at least 150 cm. According to some embodiments, the light module extends in the emission plane, over a height of up to 300 cm. Preferably, the light module extends in the emission plane over a height of maximum 290 cm, more preferably over a height of maximum 280 cm, maximum 270 cm, maximum 260 cm, most preferably maximum 250 cm.

[0101] According to some embodiments, the light module extends in the emission plane, over a height between 100 and 500 cm. Preferably, the light module extends in the emission plane over a height between 100 and 400 cm, between 100 and 350 cm, or between 100 and 300 cm. More preferably, the light module extends in the emission plane over a height between 110 and 290 cm, between 120 and 280 cm, between 130 and 270 cm, between 140 and 260 cm, most preferably over a height between 150 and 250 cm.

[0102] As the height of the emission plane increases, larger shelves can also be inventoried.

[0103] According to some embodiments, the light module is configured to produce light having an average luminous flux ranging from 2000 to 20000 lm / m2. The light module as described herein is advantageous for obtaining high quality image information, while making inventorying efficient. Preferably, the light module is configured to produce light with an average luminous flux comprised between 5000 and 19000 lm / m2, more preferably between 7500 and 18000 lm / m2, even more preferably between 10000 and 17000 lm / m2, preferably between 14000 and 16000 lm / m2, such as for example 15000 lm / m2.

[0104] According to some embodiments, the light module is configured to produce light with an illuminance on the item to be inventoried between 2000 and 20000 lm / m2.

[0105] Preferably, the light module is configured to produce light with an illuminance on the item to be inventoried of between 5000 and 19000 lm / m2. More preferably, the light module is configured to produce light with an illuminance on the item to be inventoried of between 7500 and 18000 lm / m2, more preferably between 10000 and 17000 lm / m2, most preferably between 14000 and 16000 lm / m2, such as for example 15000 lm / m2.

[0106] According to a further or other embodiment, the light module is configured to produce light having a color temperature comprised between 5472 and 5500 K. Preferably, the light module is configured to produce light with a color temperature ranging between 5472 and 5492 K, most preferably between 5492 and 5500 K.

[0107] According to a further or other embodiment, the light module is configured to produce light having a wavelength comprised between 400 and 800 nm. Preferably, the light module is configured to produce light having a wavelength between 420 and 480 nm. More preferably, the light module is configured to produce light having a wavelength ranging between 440 and 445 nm, between 420 and 480 nm, between 440 and 460 nm, or between 445 and 450 nm. Even more preferably, the light module is configured to produce light having a wavelength comprised between 440 and 450 nm, most preferably between 443 and 447 nm.

[0108] According to some embodiments, the method according to the second aspect is carried out using embodiments of the device according to the first aspect of the invention.

[0109] According to some embodiments, locating the movable base in said space and / or locating the obtained image information based on pixel correspondence is achieved by means of a computer vision model. According to some embodiments, the computer vision model reads a barcode or QR code, where the read barcode or QR code is associated with an x and y coordinate. In this way, the barcode or QR code is linked to the position in the building where the barcode or QR code was read. According to some embodiments, the computer vision model hereby searches for barcodes or QR codes with a length comprised between 6 and 40 mm, and a width comprised between 6 and 40 mm. Since the barcodes or QR codes have an exact length and width, the computer vision model only looks for those barcodes or QR codes that match the exact length and width of the barcodes and QR codes as used in the space in question. Preferably, the computer vision model searches for barcodes or QR codes with a length between 10 and 40 mm, more preferably between 10 and 25 mm or between 25 and 40 mm, even more preferably between 10 and 20 mm, and with a width preferably between 10 and 40 mm, more preferably between 10 and 25 mm or between 25 and 40 mm, even more preferably between 10 and 20 mm.

[0110] According to a further or other embodiment, the locating of the movable base in said space and / or the locating of the obtained image information based on pixel correspondence is obtained by means of a computer vision model, the computer vision model reading out one or more location markers, preferably by means of the cameras. The location markers in the building may be known based on a floor plan. The barcodes or QR codes that are read are also linked to a location marker after passing this location marker. Possible location markers are barcodes or QR codes that are not linked to a product or electronic shelf label (ESL), but are linked to an entire shelf.

[0111] According to a further or other embodiment, the position of the movable base and / or the obtained image information based on pixel correspondence is obtained by means of a comparison between a recognized product or a group of recognized products on the one hand, and a database containing the expected location of the recognized product or the group of recognized products on the other hand. Preferably, the group of recognized products concerns a consecutive series of three to five products. In these embodiments, it is therefore not necessary to provide location markers on shelves, but it is the products themselves that form the location marker.

[0112] According to some embodiments, where barcodes or QR codes are located relative to each other is determined by measuring the number of pixels located between consecutive barcodes or QR codes. This allows determining the position of barcodes or QR codes relative to each other. All barcodes or QR codes that are detected are thus linked to the position in the building from a location marker, or from another barcode or QR code on which the position in the building is recognized.

[0113] According to some embodiments, the sending of said image information and / or data obtained after digitizing and / or analyzing it to one or more digital locations includes sending recognized barcodes or QR codes, recognized location markers, linking data between the recognized barcodes or QR codes and the recognized location markers, x and y coordinates of the recognized barcodes or QR codes and / or of the recognized location markers, or combinations thereof.

[0114] The article number of the product associated with the barcode or QR code is, according to some embodiments, requested from one or more digital locations.

[0115] According to some embodiments, subsequent processing steps are performed, preferably on the processing module of the device itself, or alternatively on one or more digital locations, such as on an external computer or in the cloud, which give rise to determining the product width of a group of the same products. In a first processing step, an algorithm and / or model is used to detect differences between successive products. In a second step, a link is made between a detected product and an ESL, preferably comprising a barcode or QR code, to identify the detected product. This second step preferably only takes place if it was established in the first processing step that a product deviates from a previous product. The link with the ESL, preferably comprising a barcode or QR code, signals the algorithm and / or model that a new product has been recognized and thus links the correct identification to this product. All the same products that have been recognized are then assembled so that the product width can be determined. Incorrect product placement can also be determined via the steps mentioned.

[0116] According to some embodiments, the device and / or method of the present invention provide for detecting sold out goods and / or low inventory of goods. The device and / or method of the present invention are capable of automatically identifying when a product is sold out or when inventory levels are low. This is achieved by analyzing the image information to determine the presence and quantity of products on the shelves. This contributes to timely replenishment and helps prevent loss of turnover due to stock shortages. According to some embodiments, the device and / or method of the present invention provide for determining product location and / or position within a shelf. The method can accurately determine the location and position of each product on the shelves. This is important for keeping track of where products are located in the space and for efficient navigation for both staff and customers.

[0117] According to some embodiments, the device and / or method of the present invention provide for determining the width of shelf occupancy by a particular product. The device and / or method provides for the analysis of the shelf space occupied by each product in order to determine the width of the shelf occupancy. This is useful for space management and product placement optimization, efficiently utilizing available shelf space.

[0118] According to some embodiments, the device and / or method of the present invention provide for identifying product misplacement. The device and / or method may detect deviations between actual and expected product placement. This helps maintain the planned layout of the space and ensures products are easy for customers to find.

[0119] According to some embodiments, the device and / or method of the present invention provide for checking the orderliness and / or neatness of a shelf. The device and / or method can assess the condition of the shelves, such as whether products are neatly arranged and whether there is no clutter or disruption. This contributes to an attractive and inviting space, for example a shopping environment.

[0120] According to some embodiments, the device and / or method of the present invention provide for checking the proper functioning of electronic shelf labels (ESLs). The device and / or method may verify the functionality of ESLs, such as checking for defects or incorrect information. This ensures accurate price and product information for customers.

[0121] According to some embodiments, the device and / or method of the present invention provide for checking pricing on electronic shelf labels (ESLs) or other data sources. The device and / or method may check and / or verify the pricing information as displayed on ESLs or other price indications, which helps prevent pricing inconsistencies. According to some embodiments, the device and / or method of the present invention provide for controlling the presentation of a product. The device and / or method can control whether products are displayed correctly, for example whether labels are facing forward, which is important for both visual merchandising and customer convenience.

[0122] A third, independent aspect of the present invention, however, relates to a device for inventorying shelves which does not itself comprise a movable base, but which does comprise coupling means configured for coupling the device to a movable base suitable for this purpose. Thus, this third aspect concerns a device for inventorying shelves, comprising: one or more coupling means for coupling the device to a movable base; two or more cameras coupled to the movable base, for obtaining image information relating to an item to be inventoried in said shelves; a processing module for digitizing and / or analyzing said image information, which processing module is electronically coupled to said cameras; a data storage module for storing said image information and / or data obtained after digitizing and / or analyzing it, which data storage module is electronically coupled to said processing module; a communication module for sending said image information and / or data obtained after digitizing and / or analyzing it to one or more digital locations, which communication module is electronically coupled to said data storage module; and a light module; wherein the processing module is configured to locate the device in said space and / or identify the item to be inventoried in said shelves based on a pixel correspondence in said image information, and wherein the light module extends in an emission plane, over a height of at least 100 cm, which light module is configured to produce light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane.

[0123] The device according to the third aspect, by means of its coupling means, thus allows it to be coupled to a movable base which is separate from the device itself. Such a movable base may already be operational in the space, for example a cleaning robot. Thus, the device according to the third aspect allows an already operational movable base to be used additionally for inventorying shelves. The emphasis in the device according to the invention is therefore on a compact and modular design, allowing the device to be easily mounted on different devices. This modularity makes it possible to deploy the device flexibly and future-oriented, without the need for complex adjustments for integration with various systems.

[0124] A fourth, independent aspect of the present invention, however, concerns a device for inventorying shelves, in which the analysis of the image information obtained is carried out at one or more digital locations, for example on an external computer or in the cloud, and therefore not by means of the processing module. Thus, this fourth aspect concerns a device for inventorying shelves, comprising: one or more coupling means for coupling the device to a movable base, or alternatively, a movable base configured for movement between and / or along one or more shelves in a space; two or more cameras coupled to the movable base, for obtaining image information relating to an item to be inventoried in said shelves; a processing module for digitizing said image information, which processing module is electronically coupled to said cameras; a data storage module for storing said image information and / or data obtained after digitizing it, which data storage module is electronically coupled to said processing module; a communication module for sending said image information and / or data obtained after digitizing it to one or more digital locations, which communication module is electronically coupled to said data storage module; and a light module; wherein said digital locations are configured to locate the movable base in said space and / or identify the item to be inventoried in said shelves based on a pixel correspondence in said image information, and wherein the light module extends in an emission plane, over a height of at least 100 cm, which light module is configured to produce light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane.

[0125] The device according to the fourth aspect thus allows image processing to be carried out at an external, digital location, such as on an external computer or in the cloud. However, a fifth, independent aspect of the present invention relates to a device for inventorying shelves, wherein the light module is configured to produce light with an average luminous flux comprised between 2000 and 20000 lm / m2. Thus, this fifth aspect concerns a device for inventorying shelves, comprising: one or more coupling means for coupling the device to a movable base, or alternatively, a movable base configured for movement between and / or along one or more shelves in a space; two or more cameras coupled to the movable base, for obtaining image information relating to an item to be inventoried in said shelves; a processing module for digitizing and / or analyzing said image information, which processing module is electronically coupled to said cameras; a data storage module for storing said image information and / or data obtained after digitizing and / or analyzing it, which data storage module is electronically coupled to said processing module; a communication module for sending said image information and / or data obtained after digitizing and / or analyzing it to one or more digital locations, which communication module is electronically coupled to said data storage module; and a light module; wherein the processing module and / or said digital locations are configured to locate the movable base in said space and / or identify the item to be inventoried in said shelves based on a pixel correspondence in said image information, and wherein the light module extends in an emission plane, over a height of at least 100 cm, wherein the light module is configured to produce light with an average luminous flux comprised between 2000 and 20000 lm / m2.

[0126] The various embodiments as described in the first and / or second aspect of the present invention also relate to further or other embodiments of the device according to the third, fourth and / or fifth aspects, where compatible.

[0127] In what follows, the invention is described by way of non-limiting drawings illustrating the invention, and which are not intended to and should not be interpreted as limiting the scope of the invention.

[0128] DESCRIPTION OF THE FIGURES 1

[0129] Figures 1 and 2 show, respectively, a perspective view and a side view of an embodiment of a device for inventorying shelves according to the first aspect of the invention. The device comprises a movable base (1) configured to move between and / or along one or more shelves in a space, two or more cameras (2) coupled to the movable base (1), for obtaining image information relating to an item to be inventoried in said shelves. The device further comprises a processing module, a data storage module, and a communication module, which are not explicitly shown here. The device is also equipped with a light module (3) which extends into an emission plane. The processing module is configured to locate the movable base (1) in said space and / or to identify the item to be inventoried in said shelves, based on a pixel correspondence in said image information, and the light module (3) extends in the emission plane, over a height of at least 100 cm, the light module being configured to produce light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane. The light module (3) for this purpose comprises two separate LED strips (4), which are oriented substantially parallel to each other. The cameras (2) as shown herein consist of three separate stereo vision cameras (2), each comprising two lenses (5) with separate image sensors. As shown here, the various cameras (2) are located between the two separate LED strips (4). As shown in Figures 1 and 2, the movable base (1) is configured to move freely over a floor surface. The movable base (1) comprises the wheels (6) for this purpose.

[0130] Figure 3 shows an exploded view of an embodiment of a device for inventorying shelves according to the first aspect of the invention. The device comprises a movable base (1) configured to move between and / or along one or more shelves in a space, two or more cameras (2) coupled to the movable base (1), for obtaining image information relating to an item to be inventoried in said shelves. The device further comprises a processing module, a data storage module, and a communication module, which are shown grouped together as electronics (7). These parts are contained in an electronics housing (8). The device is also equipped with a light module (3), which extends into an emission plane. The processing module is configured to locate the movable base (1) in said space and / or to identify the item to be inventoried in said shelves, based on a pixel correspondence in said image information, and the light module (3) extends in the emission plane, over a height of at least 100 cm, the light module being configured to produce light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane. The light module (3) for this purpose comprises two separate LED strips (4), which are oriented substantially parallel to each other. The cameras (2) as shown herein consist of three separate stereo vision cameras (2), each comprising two lenses (5) with separate image sensors. As shown herein, the movable base (1) is configured to move freely over a floor surface. The movable base (1) comprises the wheels (6) for this purpose. The exploded view in Figure 3 also shows the cameras (2) attached to a camera base (8). The LED strips (4) are attached to the light module (3) using mounting elements (9). The cameras (2) and LED strips (4) are enclosed in a housing consisting of a front (10) and a back (11). The front (10) has respective cutouts (12) and (13) for the cameras (2) and LED strips (4).

Claims

CLAIMS1. A device for inventorying shelves, comprising: a movable base (1) configured for movement between and / or along one or more shelves in a space, two or more cameras (2) coupled to the movable base, for obtaining image information relating to an item to be inventoried in said shelves; a processing module for digitizing and / or analyzing said image information, which processing module is electronically coupled to said cameras (2); a data storage module for storing said image information and / or data obtained after digitizing and / or analyzing it, which data storage module is electronically coupled to said processing module; a communication module for sending said image information and / or data obtained after digitizing and / or analyzing it to one or more digital locations, which communication module is electronically coupled to said data storage module; and a light module (3); characterized in that the processing module is configured to locate the movable base (1) in said space and / or to identify the item to be inventoried in said shelves, based on a pixel correspondence in said image information, and wherein the light module (3) extends in an emission plane, over a height of at least 100 cm, which light module (3) is configured to produce light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane.

2. The device according to claim 1, characterized in that the light module (3) is configured to produce an average luminous flux comprised between 2000 and 20000 lm / m2.

3. The device according to claim 1 or 2, characterized in that the light module (3) is configured to produce light with an illuminance on the item to be inventoried of between 2000 and 20000 lm / m2.

4. The device according to any one of the preceding claims 1-3, characterized in that the light module (3) is configured to produce light with a color temperature ranging between 5472 and 5500 K.

5. The device according to any one of the preceding claims 1-4, characterized in that the light module (3) comprises a single, continuous light source (4), which extends over the entire said height.

6. The device according to claim 5, characterized in that said single, continuous light source is selected from the group of LED strip lighting, linear LED lighting, TL lighting or fluorescent lighting, linear halogen lighting, or combinations thereof.

7. The device according to any one of the preceding claims 1-6, characterized in that said cameras (2) are selected from the group of stereo vision cameras, Time-of-Flight (ToF) cameras, structured light cameras, monocular vision cameras, monochromatic cameras, or combinations thereof.

8. A method for inventorying shelves, the method comprising the steps: illuminating an item to be inventoried in a shelf; obtaining visual information relating to the item to be inventoried; the digitization and / or analysis of said image information; sending said image information and / or data obtained after digitizing and / or analyzing it to one or more digital locations; where the digitizing and / or analyzing of said image information comprises: locating the obtained image information in said space and / or identifying the item to be inventoried in said shelves, based on a pixel correspondence in said image information, and wherein the item to be inventoried is illuminated by means of a light module, which extends in an emission plane, over a height of at least 100 cm, which light module produces light with a local luminous flux over 1 cm2of the emission plane, which deviates by a maximum of 20% from the average luminous flux over the entire surface of the emission plane.

9. The method according to claim 8, characterized in that the locating of the obtained image information based on pixel correspondence is achieved by means of a computer vision model, wherein the computer vision model reads a barcode or QR code, and wherein the read barcode or QR code is linked to an x and y coordinate.

10. The method according to claim 9, characterized in that the computer vision model for reading a barcode or QR code searches for barcodes or QR codes with a length between 6 and 40 mm and a width between 6 and 40 mm.

11. The method according to any one of the preceding claims 8-10, characterized in that the locating of the obtained image information based on pixel correspondence is achieved by means of a computer vision model, the computer vision model reading out one or more location markers.

12. The method according to any one of the preceding claims 8-11, characterized in that locating the obtained image information based on pixel correspondence is achieved by means of a comparison between a recognized product or a group of recognized products on the one hand, and a database containing the expected location of the recognized product or the group of recognized products on the other hand.

13. The method according to any one of the preceding claims 8-12, characterized in that locating the obtained image information based on pixel correspondence comprises determining where barcodes or QR codes are located relative to each other by measuring the number of pixels located between successive barcodes or QR codes.

14. The method according to any one of the preceding claims 8-13, characterized in that sending said image information and / or data obtained after digitizing and / or analyzing it to one or more digital locations comprises: sending recognized barcodes or QR codes, recognized location markers, linking data between the recognized barcodes or QR codes and the recognized location markers, x and y coordinates of the recognized barcodes or QR codes and / or of the recognized location markers, or combinations thereof.

15. The method according to any of the preceding claims 8-14, wherein the method is carried out by means of a device according to any of claims 1-7.

Images