Position determination method or system, for determining the position of objects

Abstract

The invention relates to a method for determining the position of at least one object (P1–P6) in a space (2), in particular of at least one product positioned on a shelf (7), wherein the method includes: emitting a light signal, encoded with identification information for identifying the object, from a light-emitting device (6) positioned adjacent to the object, and capturing a scene with the aid of at least one freely movable camera (10), wherein a digital scene image generated with the aid of the camera represents the scene, and generating object position data on the basis of a computer-determined position of the light signal appearing in the digital scene image in relation to the camera and the identification information emitted with the light signal, and on the basis of an automatically determined orientation and position of the camera in the space when the scene is captured, wherein the object position data represents the position of the object in the scene with respect to the space.

Description

[0001] title

[0002] Position determination method or system for determining the position of objects

[0003] Description

[0004] Technical field

[0005] The invention relates to a method and a system for determining the position of objects, in particular for detecting the position of products.

[0006] background

[0007] US2021073489A1 discloses a system for recording the position of a large number of products in a store. However, the system, as well as the method disclosed in connection with the system, have proven to be extremely complicated, time-consuming, and costly in practice because all shelves must be equipped with a special device for identifying a shelf, namely a so-called "identity information provision apparatus." This special device is generally disclosed as a wireless communication device that can be used as a separate device or as part of an electronic price display. This device, or the information it provides for identifying a shelf, must be recorded in the method.

[0008] The invention therefore has the object of avoiding the problems discussed in a system or the method carried out therewith.

[0009] Summary of the invention

[0010] This object is achieved by a method according to claim 1. The subject of the invention is therefore a method for determining the position of at least one object in space, in particular of at least one product positioned on a shelf, wherein the method comprises emitting a light signal, which is coded with identification information for identifying the object, from a light emitting device positioned adjacent to the object, and capturing a scene with the aid of at least one freely movable camera, wherein a digital scene image generated with the aid of the camera represents the scene,and generating object position data based on a computer-determined position of the light signal occurring in the digital scene image with respect to the camera and the identification information transmitted with the light signal, and with knowledge of an automatically determined orientation and position of the camera in space when capturing the scene, wherein the object position data represents the position of the object in the scene with respect to space.

[0011] This object is further achieved by a freely movable device according to claim 12. The invention therefore relates to a freely movable device, in particular a shopping trolley or a pair of glasses or a mobile phone or a tablet computer, for determining the position of at least one object in space, in particular of at least one product positioned on a shelf, wherein this position is indicated by a light signal emitted by a light emitting device positioned adjacent to the object, which light signal encodes identification information with the aid of which the object can be identified, wherein the device carries at least one camera which is designed to generate a digital scene image of a scene captured by it, and wherein the device, in particular the camera,for the computerized determination of the position of the light signal occurring in the digital scene image in relation to the camera and the identification information emitted with the light signal, and wherein the device, in particular the camera, is designed to at least support an automated determination of the orientation and position of the camera in space when capturing the scene.

[0012] This object is further achieved by a light emitting device according to claim 13. The invention therefore relates to a light emitting device, in particular a shelf label designed to display product and / or price information, or a product separator designed to separate different products, wherein the light emitting device comprises: a storage stage for storing identification information with the aid of which an object, in particular a product positioned on a shelf, can be identified, in the vicinity of which the light emitting device is positioned, and a light signal generation stage designed to encode a light signal according to the identification information and to emit this encoded light signal.

[0013] This object is further achieved by a system according to claim 14. The invention therefore relates to a system for determining the position of at least one object in space, in particular of at least one product positioned on a shelf, the system comprising: at least one light emitting device according to the invention and at least one freely movable device according to the invention.

[0014] The measures according to the invention have the advantage of creating a more powerful and cost-effective system that is both implementable and operable, because, compared to the system discussed at the outset, fewer devices are required that are permanently installed on shelves and that must be separately provided and maintained. This primarily concerns the omission of the device discussed at the outset, which provides information for identifying the shelf on which it is mounted. Furthermore, a significantly more efficient method is created because the full focus is placed on the emitted light signal, which is spatially localized corresponding to the respective location of an object or product on the shelf or has its origin there and is suitable for identifying the object. Furthermore, the freely movable camera enables temporally dynamic and location-variable recording of the positioning of the objects present in a store.The position detection of the objects in the store therefore does not require any camera-based detection of the objects themselves or any camera-based detection and evaluation of the product-specific information conveyed with the help of the objects or a shelf label, which would have to be found, for example, in a digital recording (digital photo or video) of the object or in a digital recording of a paper-based shelf label or in a digital recording of the screen content of an electronic shelf label with a large amount of digital processing effort.

[0015] Further, particularly advantageous embodiments and developments of the invention emerge from the dependent claims and the following description.

[0016] In general, the invention makes it possible to determine the position of an object within a store based on the light signal, i.e., to locate the object. To identify the object, the aforementioned identification information, which is communicated using the light signal, is used. This identification information is obtained by a prior logical link between the object and a light-emitting device assigned to it. Specifically, this logical link is known as "binding." This creates a unique identification of the object with a unique identification of, for example, an electronic shelf label (ESL). For this purpose, the barcode displayed on the object and the barcode displayed on the ESL screen are typically scanned using a manually operated barcode scanner and stored in a database as belonging together.The same also applies to a so-called shelf divider or product divider, which separates different items, products, or product groups on a shelf. The barcode that uniquely identifies the divider can be shown on a label on the divider or on a screen on the divider. Typically, either the ESLs or the dividers are installed on shelves, although mixed configurations are also possible. Accordingly, the identification information can be a unique identifier for the ESL or divider, or a unique identifier for the product. Of course, other information can also be used here, such as meta information, which represents the logical connection created during the binding. This meta information can then be used to identify the product or product group.

[0017] The light emitting device which emits the light signal is therefore designed here as an ESL or isolator. The light emitting device stores the respective identification information using identification data in its memory stage, which is implemented, for example, by an EEPROM. The identification data can be transmitted from a central data processing device, for example, wirelessly or wired, to the respective light emitting device. In addition to other electronic components required for the respective functionality, the light emitting device has a light signal generation stage with the aid of which the coded light signal can be emitted. For this purpose, the light generated using, for example, a light-emitting diode is modulated according to the applicable (pre-defined) coding. In this case, the intensity or, in the case of an RGB LED, also the color, i.e. the spectral characteristics of the light, can be influenced.The light signal can be located in the visible spectral range of light. However, the non-visible spectral range is preferred to avoid unnecessary distraction of customers and employees from their usual activities with light signals. The light signal is emitted for at least the period of time necessary to transmit all the identification information. This transmission can occur once or several times in succession, particularly upon external request (e.g., by a control signal from a central data processing device or the camera), or several times automatically, for example, controlled by an internal timer of the light-emitting device.

[0018] The camera can be a still-image camera or a video camera, which is designed to create a two-dimensional digital image of the scene within its detection range, i.e., a digital scene image. Regardless of whether it is a still-image camera or a video camera, at least enough individual scene images or a sufficiently long video are captured as a scene image to enable evaluation of the identification information, which occurs over a period of time. Therefore, when determining the minimum recording duration, the time period required at least for transmitting the identification information is taken into account.In the case of a light signal in which the identification information is coded over a time period, in the case of a still image camera, for example, at least so many images are captured within the time period intended for transmission that the identification information can be easily determined from the changes in the light signal in the scene image.

[0019] The real scene captured by the camera includes the objects in the scene and, if applicable, their temporal or spatial changes.

[0020] The digital scene image is the optical imaging of the real scene via the camera's optics (a lens system, also called an objective) onto the camera's digital image capture unit, which typically uses a so-called CCD (charge-coupled device), which digitizes the image of the scene. The scene image is thus mapped onto a pixel matrix of this image capture unit.

[0021] The digital scene image is therefore a two-dimensional data structure obtained from the matrix of pixels of the CCD. Depending on the design of the electronic sensor and the additional camera electronics for post-processing, a digital still image or a digital video sequence of the scene is generated. The resolution of the electronic image sensor and / or the digital post-processing defines the image resolution (total number of pixels or the number of columns (width) and rows (height) of a raster graphic) of the digital scene image. The digital scene image generated by the camera for further processing is therefore made up of a matrix of pixels, for example 1500 pixels in the x-direction and 1000 pixels orthogonal to this in the y-direction.Each of these pixels has a defined (i.e. known) pixel dimension (or in other words, the center of neighboring pixels has a defined (i.e. known) pixel distance).

[0022] During the computerized determination of the identification information, the digital scene image is first searched for the light signal. This is relatively easy to find because the light signal is fundamentally different from the otherwise rather dark background of the digital scene image. For this purpose, for example, pixels of this digital scene image can be examined for a characteristic color or a characteristic intensity or brightness. The search for the light signal can also be based on its temporal change in color or brightness or intensity expected according to the coding. Once such a light signal has been found, the temporal change (modulation) of a light signal parameter is analyzed using knowledge of the coding scheme used when the light signal was emitted in order to decode the identification information.

[0023] For further processing of the light signal, the position of the detected light signal in the digital scene image, i.e. the pixel coordinates, and also a data representation of the determined identification information are stored as belonging together.

[0024] By capturing the digital scene image with a freely moving camera, different digital scene images of the real scene or the surroundings of the camera are created over time from positions and with different orientations, which can all be evaluated individually or in a temporal and spatial context in order to determine the position of one, but preferably several, objects.

[0025] In the system primarily used in a supermarket, a relatively large number of light emitting devices are typically used, depending on the number of different products. In the maximum expansion stage, this will be at least as many light emitting devices as there are products or product groups in the store. In such a system, the position of the products or product groups is determined entirely based on the position determination of the light signals and their identification using the identification information in the digital scene images, which are acquired over time using the moving camera or camera moving around the store.The light signal, which can be clearly identified using the identification information in the respective digital scene image, allows the assignment of a real object that is, by definition, positioned near the light-emitting device in a room. To locate the object in the room (such as a business premises) from which one or more digital scene images were captured using the camera, i.e., to obtain the object position data relative to the room, the position of the respective light signal is first determined in relation to the camera (the camera coordinate system) and then transformed into the coordinate system of the room (the room coordinate system), which has its origin at a defined location in the room and is located there with a defined orientation.

[0026] The various aspects of this generation of object position data are discussed below.

[0027] According to one aspect of the invention, only a single freely movable camera can be used, which is carried, for example, by an employee through the space, such as the store. Preferably, the method is carried out with the aid of several independently moving cameras. These cameras can be moved independently of one another by the store's employees, which accelerates the capture process for capturing the various scene images throughout the entire space.

[0028] To capture the largest possible spatial area per camera, a so-called fisheye lens can be used. Of course, the lens itself can also be designed to be movable, meaning it can be pivoted relative to the camera. Alternatively, the camera can also be pivoted relative to the freely movable device. Alternatively, an omnidirectional camera can be used.

[0029] To move the camera, employees can be equipped with (protective) goggles, for example, to which the respective camera is attached. However, it has proven particularly advantageous if the freely movable camera is attached to a shopping cart. This has the advantage that the number of image-capturing cameras is no longer limited to the number of employees moving around the store, but rather the individual movements of the number of customers—which usually far exceeds the number of employees—can be used to capture images. The customers move a swarm of image-capturing cameras around the store.Customer involvement also has the advantage of allowing image capture to identify those retail zones where products attract increased customer attention or where customers actually pick products from the shelves. Based on the captured scenes, it can be determined that these retail zones occur more frequently or because customers spend longer there. This can provide important insights for warehousing, inventory tracking, shelf replenishment planning, as well as for target group or product-specific marketing.

[0030] Regardless of whether the freely movable device is a pair of glasses or the like, or a shopping cart, it has proven particularly advantageous if several cameras are provided on the freely movable device, which are moved together, i.e. grouped, with this freely movable device and generate individual digital scene images from different detection positions and / or with different detection orientations. This makes it possible for each camera to generate digital scene images of different scenes at the respective position in which the freely movable device is currently located. In this way, the shelves bordering the aisle on the left and right sides of the aisle can actually be detected simultaneously, for example ifWith respect to the direction of travel of the shopping cart, one of the cameras is directed to the left and the other to the right, meaning their respective detection areas are directed towards the shelves next to the shopping cart. The same applies, of course, to the glasses mentioned. To ensure problem-free and therefore reliable detection of the full height of shelves, several individual cameras can be provided on one or each side, particularly in the case of a shopping cart. In the case of a shopping cart, these cameras can be arranged one above the other, e.g., mounted on a pole, or they can be oriented differently, i.e., detecting an upper shelf area, a middle shelf area, and a lower shelf area.Even with glasses, the cameras facing one side can have different, stacked detection areas, capturing the entire image area from the bottom shelf to the top shelf. Optionally, wide-angle cameras can also be used to cover the same or a similar overall detection area. The individual detection areas can also overlap. The ESLs, or the separators that form the light emitting device, are often battery-operated.It has therefore proven particularly advantageous if a control signal transmitter moving along with the at least one freely movable camera emits a control signal, in particular a radio-based control signal, and the light emitting device located in the reception range of the control signal, which is equipped with a receiver to receive the control signal, only emits the light signal upon receipt of the control signal. To receive the control signal, a relatively simple receiver is required, which can also evaluate a unique identifier of the control signal if necessary, in order not to react to other radio signals. This allows the light emission by a wide variety of light emitting devices to be restricted to a defined spatial area around the control signal transmitter. For example,A control signal range of five to ten meters should be sufficient to activate only those light signal generation stages located in the vicinity of at least one camera to emit the respective light signal. The control signal range should be dimensioned such that the camera's detection range can be optimally utilized. Therefore, at least those light signal generation stages should be active whose light signal can reasonably be detected by the camera. This has the advantage that other light signal generation stages can remain inactive, which has a positive influence on the energy balance of the respective light emission device, and in particular on the energy balance of the entire system.

[0031] For this purpose, for example, a radio technology can be used in which the transmitted control signal is at least partially shielded by the shelves, which are often made of metal, so that mainly those light emitting devices located in the same shelf aisle as the freely movable device can receive the control signal.

[0032] Instead of using the radio control signal, or in addition to using the radio control signal, the light-emitting device can be configured to emit the light signal only when certain (time-dependent) criteria are met. To apply these criteria, the light-emitting device has a timing control stage configured to control the temporal behavior, i.e., the activity or inactivity phase(s), of the light signal generation stage. The light signal generation stage is, of course, configured to be controllable by the timing control stage and can be triggered by it.

[0033] For example, the timing control stage can receive time data containing information about the current time and / or have a clock generator with which the timing control stage determines the current time or date. However, this information can also be obtained in other ways, such as a system clock or a system time or date globally available in the system.

[0034] The criteria can, for example, include that the light signal is only emitted if it has not already been emitted within a certain time period. The criteria can also, for example, include that the light signal may only be emitted within a certain time range. This time range can, for example, contain one or more fixed, predefined time windows during a day, week, or month. For example, the system can be set up so that light signals are only emitted on certain days of the week. For example, the entire store can be scanned once a week to check the consistent positioning of the products. The light signals in different shelf aisles in the store can also be assigned to different days of the week, so that aisles that are close together do not emit light signals at the same time.When using the glasses, the criterion can also be defined in such a way that the light signal is only emitted during the time period in which the employees usually, i.e. predictably, walk through the business premises with the glasses in order to prepare it for operations the next day, for example.

[0035] The method has proven to be particularly advantageous if the determination of the position in relation to the camera comprises an automatic determination of a scale derivable from the digital scene image, wherein the scale is determined with knowledge of the real dimensions of a reference object identified in the digital scene image, in particular designed as an electronic shelf label, and the scale is used for the conversion between position information or dimensions that are determined in the digital scene image and position information or dimensions in the scene captured with the aid of the camera.

[0036] For this purpose, a reference object contained in the scene image, preferably identically formed reference objects, can be identified, whereby the actual dimensions are known and the scale for the scene image is determined with knowledge of the actual dimensions.

[0037] In the context of the present invention, however, the reference object is particularly preferably the light-emitting device itself, which is implemented as an ESL or separator with conventionally defined, i.e., pre-known dimensions. These reference objects can be easily located in the digital scene image due to the "inherent" light signals they emit, i.e., localized or delimited, and subsequently analyzed to determine the scale. To identify or locate the reference object in the digital scene image, pattern recognition can be used, which examines the digital scene image for the characteristic appearance (such as rectangular or square, or even proportions) of the reference object.In any case, the starting point for the search for the reference object(s) is the light signal that is usually emitted by the reference objects and therefore makes them particularly easy to find in the digital scene image.

[0038] However, the reference object can also be a "composite" reference object, which is composed of a collection of light signals from different light emitting devices. For example, the light signals from two light signal emitting devices positioned essentially exactly above each other on different shelves can also form such a "composite" reference object, whereby in this situation the distance between the shelves is the known real dimension used to determine the scale.

[0039] As already mentioned, the invention in question is primarily used in retail. In retail, such a reference object can take on a variety of forms. For example, it can be an entire shelf whose length and height are precisely known. Using the shelf can be advantageous because it often plays a dominant role in a scene. However, smaller objects, such as a shelf rail that forms the front end of a shelf, can also be used as a reference object. Shopping baskets that are set up to present goods in a store are also suitable, provided they are positioned within the detection range of the respective camera.However, in retail, shelves, shelf rails, and shopping baskets are often provided by a wide variety of manufacturers in a wide variety of dimensions for the respective stores of various retailers, often subject to specific structural specifications. Therefore, they are only suitable as reference objects in a very narrow application.

[0040] The use of an electronic shelf label as the reference object is also advantageous because such electronic shelf labels essentially have uniform dimensions. Of course, electronic shelf labels exist in a wide variety of dimensions, some of which vary considerably. In practice, however, it has been shown that the dimensions used vary hardly at all, or only within a predefined range, between different stores or even different retailers. This is particularly true for the large number of electronic shelf labels that are installed on a shelf rail or the shelf rails of that shelf in a single store and that come from a single manufacturer, which is usually the case. Such electronic shelf labels usually only occur in one or two (perhaps even three) different dimensions on a shelf.Since each of these electronic shelf labels must fit into the same shelf rail, their dimensions often differ only in width, whereas the height is often identical for two different types of electronic shelf labels, for example. However, the opposite can also occur. Their actual dimensions can therefore be considered essentially homogeneous across different types of shelf labels and across installation locations.

[0041] Furthermore, the choice of electronic shelf labels as a reference object has proven particularly advantageous for another reason. Unlike the shelves themselves or the shelf rails, etc., shelf labels are always attached to the very front of a shelf and can therefore be easily and clearly identified using digital image processing in the scene image captured by the camera, and thus reliably analyzed.

[0042] The basis for determining the scale is counting the relevant pixels assigned to the reference object. The number of pixels determined in this way can be related to the actual area or length of a reference object, allowing scaling from the pixel system of the CCD sensor to the real scene. Knowledge of the precise physical parameters of the CCD sensor can also be used for determining the scale, as the actual distances between the pixels in the pixel matrix or their size are precisely known. In this way, the counted pixels can be converted to an actual length or area measurement for the reference object imaged on the CCD sensor, from which the current scale can be calculated, and then scaling can be performed between the length and area measurements of an image on the CCD sensor and the real scene.

[0043] In concrete terms, the determination of those pixels in the scene image assigned to the image of the reference object, i.e. the pixels of the reference object image, can be carried out using at least one of the following measures, namely:

[0044] - Determination of the number of pixels occupied by the image of the reference object. This allows the area occupied by the reference object image (specify the area as the sum of the counted pixels or the area as the total pixel area of ​​the counted pixels) to be determined in the scene image by counting the pixels. Knowing the actual surface area of ​​the reference object (e.g., the surface area of ​​the front surface of the reference object, expressed in square millimeters), the scale can be calculated.

[0045] - Determination of the number of pixels circumferentially occupied by the reference object image or the number of pixels circumferentially enclosing the reference object image. The circumference of the reference object image in the scene image is thus determined by counting the pixels either based on the pixels just barely occupied by the reference object image at the edges or based on the pixels immediately adjacent to the reference object image. Knowing the actual circumference of the reference object (e.g., the circumference of the front of the reference object), the scale can be calculated.

[0046] - Determination of the number of pixels occupied by the reference object image along one of its boundary lines or the number of pixels enclosing the reference object image adjacent to one of its boundary lines. The length of an edge line is therefore used as the basis for determining the scale. This can in particular be a straight edge line, such as a side of a rectangular or square structure of the reference object, which can be defined by housing edges, for example. The pixels occupied along such a boundary line are therefore counted, or the pixels enclosing the reference object image adjacent to one of its boundary lines are counted. Knowing the actual length of the boundary line of the reference object, the scale can be calculated.

[0047] However, using the measures described, a scale can also be defined that scales along the scene image, i.e. a scale that depends on the location in the scene image. This location-dependent scale can be necessary if, for example, the scene image distorts the proportions of the reference objects depicted there. Such a situation can arise, for example, if the camera is used to record a scene that extends far to the left or right of the camera, which can happen, for example, in shelf aisles in retail companies if the camera is not positioned well. The reference objects that are close to the camera are then depicted larger than reference objects that are positioned further away from the camera.

[0048] In the context of such perspective images, it might also be possible to derive the scale progression along the scene image from the distortion of a single reference object. However, if the length of this reference object along the perspective to be evaluated is relatively short and, unfortunately, only a few pixels are assigned to the reference object, this can often only lead to a result that can be improved. Therefore, it is preferable to use several such reference objects, which ideally appear fairly evenly distributed along the perspective image, which is often the case with ESLs, in order to be able to define the function describing the location-dependent scale as precisely as possible. Such a scale is also referred to as a metric.

[0049] Based on the totality of the light signals detected in the digital scene image, an initial data structure can be generated using the scale for the scene image. This first data structure represents a two-dimensional digital map of the light signals in the real scene, specifying the actual measurement(s) required for two-dimensional cartography (e.g. measured in millimeters). For this purpose, for example, only chained measurements (i.e. relative measurements between neighboring light signals) can be created to determine the positions of the light signals. Absolute measurements measured from a reference point in the scene image can also be created. This two-dimensional map obtained in this way, which is stored digitally, is subsequently used to place it in a three-dimensional context in relation to the camera, which will be discussed below.

[0050] According to this aspect, determining the position relative to the camera involves automatically determining the distance between the camera and the scene captured by it. This allows the light signals identified in the digital scene image to be located three-dimensionally relative to the camera, i.e., in the camera coordinate system. Thus, the already known two-dimensional location of the light signals in the scene is expanded by a third coordinate.

[0051] The distance can be estimated in an essentially known spatial arrangement, such as a shelf aisle, i.e., using approximately half the aisle width. This distance can also be well delimited using the so-called lens equation, because the scale or metric can be defined with good accuracy using the reference object found in the digital scene image, the dimensions of which are known very precisely. The distance between the camera and the respective light-emitting device can therefore be determined by automatic calculation using knowledge of the parameters of the camera's optical imaging system. This can be done fully automatically, for example, by the camera's computer, because it can retrieve the parameters of the optical imaging system from its memory, where they were previously programmed (e.g.,during manufacture of the camera or during commissioning), and because the computer knows the actual dimensions of the reference object, which are also available, e.g. as programmed in advance. For example, using the well-known lens equation, the distance from the camera to the real object from which the light signal is emitted, i.e. ultimately the distance to the light signal source, in the scene can be calculated, whereby the imaging function corresponding to the actual lens of the camera must of course be applied. In this way, the positions of the light signals can be determined in the spatial context of the camera coordinate system. It should also be mentioned here that the distance between the camera and the light emitting device can also be determined automatically using a distance sensor, for which purpose a LIDAR sensor or similar can be used.This enables precise, direct distance measurements, with the camera's computer further processing the data transmitted by the LIDAR sensor to obtain the third coordinate in the spatial context of the camera's coordinate system. It should also be mentioned that so-called "time-of-flight" sensors can also be used to automate this distance measurement.

[0052] Since this camera coordinate system changes its position and orientation according to the camera movement in space, but at the same time the position of the light emitting device in space remains unchanged, the three-dimensional coordinate information calculated in the camera coordinate system for a specific light emitting device exhibits a variability or dynamics that is determined by the movement of the camera.

[0053] According to a further aspect, it has proven advantageous if the method step of emitting the light signal is carried out essentially simultaneously by several light-emitting devices, and wherein the method step of computer-based determination of the position of the light signal occurring in the digital scene image with respect to the camera and of the identification information emitted with the light signal is carried out for all of the light signals occurring in the digital scene image. This is accompanied by the advantage that the multitude of light signals contained in a scene image are used collectively in order to perform the position determination for the multitude of light signals in a single detection area of ​​the camera. This accelerates and optimizes the position determination process.

[0054] After receiving the three-dimensional position data of the light signals in the camera coordinate system, these are transformed into the spatial coordinate system of the room to obtain the object position data, since each light signal identifies an object adjacent to the location where the light signal was emitted. According to a further aspect of the method, supplementary data is taken into account for generating the object position data, which comprises at least one of the following types of data, namely:

[0055] - Orientation data describing the orientation of the camera with respect to a reference orientation in space;

[0056] - Tilt data describing the tilt of the camera relative to a reference plane in space;

[0057] - Position data that describes the position of the camera relative to a reference point in space.

[0058] This supplementary data can be generated using a variety of sensors that exist on the camera or the freely moving device, such as the shopping cart or the glasses, which is discussed below.

[0059] The orientation of the camera in the spatial coordinate system can be determined automatically using an orientation sensor. For this purpose, an electronic compass can be used, for example, and a camera computer further processes the data transmitted by the electronic compass or makes this data available for conversion between the coordinate systems. Furthermore, the inclination of the camera relative to the horizontal, represented by inclination data, can also be understood as a component of the orientation. It can be detected automatically using an inclination sensor. For this purpose, an electronic gyroscope can be used, for example, and the camera computer further processes the data transmitted by the electronic gyroscope or makes this data available for conversion between the coordinate systems.

[0060] The position of the camera in the spatial coordinate system can be determined by automatic radio-based positioning, in particular with the aid of "ultra-wideband radio technology" (UWB radio technology for short). For this purpose, UWB transmitters with a known position in the spatial coordinate system are preferably installed at various points in the relevant spatial area. The camera is equipped with a UWB radio module. With the aid of this module, the position of the camera in relation to the UWB transmitter is determined for the respective UWB transmitters in UWB radio communication with the camera. This data is used to generate position data that is further processed by the camera's computer or provided for conversion between the coordinate systems.Since the camera used is preferably miniaturized, the resulting position of the camera in the spatial coordinate system can be equated to the origin of the camera coordinate system to a good approximation. Otherwise, a correction that takes this difference into account would have to be implemented.

[0061] The distance traveled can also be recorded using a sensor (e.g., attached to the rollers of a shopping cart, which detects the rolling motion of the rollers or wheels) or a sensor for detecting acceleration, from which the distance traveled and the direction taken can be determined. These sensors can be used to generate data describing the distance traveled, which is then further processed by the camera's computer or made available for conversion between the coordinate systems. However, this requires a known starting point in the spatial coordinate system in order to be able to describe the path.

[0062] With the help of the supplementary data, which describes different characteristics depending on the system configuration, the conversion to the spatial coordinate system can be performed directly in the camera, and the resulting object position data of the real scene in the spatial coordinate system can be transmitted by the camera for further processing, for example, by a central data processing device. On the other hand, the camera can also transmit the position data of the light signals in the spatial context of the camera coordinate system together with the supplementary data available at the camera, and the conversion to the spatial coordinate system can be performed by a central data processing device, for example.

[0063] Thus, the three-dimensional positions of the individual light-emitting devices, as well as the identification information they convey, are now known in the spatial coordinate system. Using the identification information, the actually affected objects for the respective position are retrieved from a database of, for example, the (central) data processing device. Subsequently, the (central) data processing device generates a data structure for all objects from the object position data determined for each object. This data structure contains the three-dimensional position of each object in the store in the spatial coordinate system. In technical jargon, this is also referred to as a three-dimensional floor plan of a store, which represents the position of all products in the store as accurately as possible.

[0064] In the present case, as discussed, this floor plan is not generated manually but fully automatically based on the light signals of the electronic shelf labels or dividers installed in the store and with the help of freely moving cameras that capture the light signals over time as they move around the store.

[0065] It can also be provided that sequences of scene images are used together to determine the position of objects. These sequences can also affect overlapping detection areas. This allows positions for one and the same light emitting device to be determined in, for example, consecutive scene images, and thus the scene images can be linked by superimposing the positions of the light signals in the different scene images. This coupling of the scene images leads to an expansion of the detection range of one or more cameras used.

[0066] Already generated data, which locates light signals and provides their identification information, can be used to interpret newly generated scene images. By utilizing already generated image position data, i.e., the position and identification of the previously detected light-emitting device, newly generated scene images in which the same light-emitting device is depicted can be easily interpreted. Light-emitting devices that have not yet been detected can simply be described relative to the position of the known light-emitting device. This also enables dynamic light signal detection, in which the depicted light signals move in a temporal sequence of scene images. The positions of light signals newly appearing in the sequence of scene images are described based on the already known positions of light signals.The coupling therefore allows a dynamic and at the same time safe and reliable capture and description of the scene.

[0067] This makes it easy to capture all the light emitting devices installed along a shelf aisle, even if the camera in use cannot capture an entire image of the aisle due to its detection range or its positioning or orientation relative to the shelf. This measure allows a complete digital scene image of the light emitting devices installed along the aisle to be generated.

[0068] It should also be mentioned that multiple fixed-position coordinate systems can be used to describe the object position data. For example, a local fixed-position coordinate system can be defined in each aisle, so that the object position data is described in this coordinate system. The dimensions and / or positions, etc., described in the individual coordinate systems can then be easily converted into one another if the relationship between the coordinate systems is known. In this way, the object position data can be transferred from the local fixed-position coordinate systems to the fixed spatial coordinate system that encompasses or describes the entire store.

[0069] It should also be mentioned that, in addition to the components already discussed, the freely movable device can also have a rechargeable battery or a battery for supplying the electronic components with energy. The freely movable device can also have a generator for converting kinetic energy into electrical energy. The electrical power provided by the generator can be used directly to power the electronic components or temporarily stored in the rechargeable battery or a battery. When using a shopping cart as a freely movable device, this generator is preferably connected to or integrated with at least one wheel of the shopping cart, so that the rotational movement of the wheel drives the generator. In this way, the camera can also be operated autonomously on the freely movable device.Equipped with its own power source, the shopping cart can also power its own drive to provide autonomous assistance to the customer. In this context, it can also be provided that the power source is recharged contactlessly, for example, at the usual collection points for such shopping carts.

[0070] It should also be mentioned that when using a shopping cart, it can have a screen, in particular a touch screen, and an associated data processing unit that allows the customer to interact with the shopping cart. For example, a digital shopping cart can be displayed on the screen, showing which items have been placed in the shopping cart. The customer's shopping list can also be displayed. Detailed information about products can also be provided. For this purpose, the shopping cart can have a barcode scanner or an NFC communication module, with which the products placed in the shopping cart can be scanned or recorded. The shopping cart can also have another camera or use the previously discussed camera to record products placed in the shopping cart.The camera captures the product placed in the shopping cart and creates a product image. Products can be identified using a barcode, QR code, or similar, for example. The object position data, which is essentially available in real time, also allows the product to be identified based on its structure in the product image. The currently generated object position data allows the product image to be compared with a reduced selection of possible products that are located in the scene or surroundings according to the object position data. The object position data thus allows for faster and more reliable processing of the product image and recognition of the products contained therein. Such a shopping cart can also have a scale designed to weigh products in the shopping cart.The data generated from this can, for example, be used to determine a weight-based price. The inventory in the shopping cart thus recorded can also be used for a reliable self-checkout process, including payment for all items, especially those that are weight-based. For this purpose, an NFC payment terminal can be installed on the shopping cart, which can be used to process payments using, for example, the NFC functionality of a mobile phone. To also be able to record items that are not equipped with an NFC chip, a barcode scanner can be installed in the shopping cart, allowing the self-checkout process to be carried out in any case.

[0071] The shopping cart can also be equipped with an NFC communication module for inventory tracking on the shelves, for example, to detect NFC tags attached to items as the shopping cart passes by. In this configuration, the shopping cart can be used not only to determine the position of items, but also to simultaneously record the number of items actually present at each (shelf) location. This allows the inventory in the store to be continuously monitored via the swarm of shopping carts moving around the store. A wireless communication module transmits the recorded inventory data from the shopping cart to the server, where it is incorporated into the floor plan and can be visualized there.

[0072] When the shopping cart is moved, location-specific marketing information can also be provided to the customer via the screen, because the server 8 is always informed about the location of the shopping cart with the help of the supplementary data.

[0073] Furthermore, a customer behavior analysis can be carried out in server 8 because the movement patterns of the shopping cart are available to server 8 in real time, possibly even with data that represents or indicates the inventory in the shopping cart.

[0074] The shopping cart may also have a visual signaling device (e.g. an LED or screen) that can be used to indicate that the shopping cart is occupied or that the user of the shopping cart requires assistance from the staff in the store.

[0075] The shopping cart can also be equipped with a cost-effective LIDAR system, which can be used to attract the customer's attention in a specific environment, e.g. by providing environment-related information on the screen.

[0076] Finally, it should be generally mentioned that the electronic devices and equipment discussed here naturally contain electronics. The electronics can be discrete or integrated, or even a combination of both. Microcomputers, microcontrollers, and Application Specific Integrated Circuits (ASICs), possibly in combination with analog or digital electronic peripherals, can also be used. Many of the device functionalities mentioned are implemented—possibly in conjunction with hardware components—with the help of software running on an electronics processor. Devices designed for radio communication usually have an antenna configuration for transmitting and receiving radio signals, as well as a modulator and / or demodulator, as part of a transceiver module.The electronic devices can also have an internal electrical power supply, which can be implemented, for example, with a replaceable or rechargeable battery. The devices can also be powered wired, either via an external power supply or via "Power over LAN." A wireless power supply can also be provided via "Power over WiFi."

[0077] These and other aspects of the invention are apparent from the figures discussed below.

[0078] Short character description

[0079] The invention is explained in more detail below with reference to the accompanying figures using exemplary embodiments, to which, however, the invention is not limited. In the various figures, identical components are provided with identical reference numerals. They show schematically: Fig. 1 shows a basic structure of a system for carrying out a method according to the invention;

[0080] Fig. 2 shows the occurrence of identification information in different light signals over time;

[0081] Fig. 3 an application of the system in a shelf aisle in a shop.

[0082] Description of the embodiments

[0083] Figure 1 shows a system 1 for implementing a method for determining the position of object-forming products PI to P6 in a retail outlet, hereinafter referred to as room 2. A stationary, orthogonal, right-handed spatial coordinate system 3 with its coordinate axes XR, YR, and ZR is drawn in room 2, so that the three-dimensional positions of the products PI to P6 can be specified in this spatial coordinate system 3. A digital representation of these three-dimensional positions is hereinafter referred to as object position data for the respective product PI - P6.

[0084] In room 2, only two shelves 7A and 7B of a shelf 7 are visible, to the front edge of which three electronic shelf labels 4A - 4C and 4D - 4F are attached, corresponding to or adjacent to the products P1 - P6, with which they are logically linked and for which they each display product and / or price information on their screen 5. Each shelf label 4A - 4F also has a light-emitting diode 6 located on the front adjacent to the screen 5, which is designed to emit a light signal. When emitted, the light signal is encoded according to individual identification information, and the identification information serves to uniquely identify the respective product P1 - P6. In the present case, a binary code forming the identification information is transmitted, with the current through the light-emitting diode 6 being either switched on or off depending on the respective bit value.This transmission can also be embedded in defined start and stop bit(s), etc.

[0085] The system 1 also has a server 8 that stores the logical connection between each product P1 - P6 and the shelf label 4A - 4F assigned to it. The shelf labels 4A - 4F receive their respective product and / or price information to be displayed from the server 8, which is transmitted to the respective shelf label 4A - 4F using a wireless shelf label access point 9. Since the server 8 knows the identity of each shelf label 4A - 4F and the product P1 - P6 assigned to the respective shelf label 4A - 4F, it is generally sufficient for the light signal to transmit only the identification information of the respective shelf label 4A - 4F as identification information in order for the server 8 to be able to uniquely identify the respective product P1 - P6 concerned based on the identification information.

[0086] The system 1 also has a camera 10 that is freely movable in the room 2, so that it can basically be moved into all areas of the room 2 in order to capture the respective scene there using a digital scene image. The scene captured by the camera 10 can be described in three-dimensional coordinates XK, YK, ZK using a camera coordinate system 11, wherein the camera coordinate system 11 is located at the center of the image-capturing pixels of the CCD sensor of the camera 10, i.e., has its origin there, and wherein the plane spanned by the coordinates XK and ZK runs in the image capture plane of the CCD sensor and has a granularity corresponding to the pixels of the CCD sensor. In the pixel matrix of the CCD sensor, each pixel can be specified by a two-dimensional pixel coordinate system with the axes XKP and ZKP, where the XKP axis runs and is oriented according to the XK axis and the ZKP axis according to the ZK axis.For the sake of simplicity of discussion, it is assumed here that the pixels of the digital scene image, i.e. the result of the digitization of the scene image using the CCD sensor, are also addressable according to the two-dimensional pixel coordinate system.

[0087] Furthermore, it should be noted that the third coordinate YK of the camera coordinate system 11 points through an optics (or lens - not shown) of the camera 10 in the direction of the scene to be captured. The lens essentially defines a detection range E of the camera. If a digital zoom is present, this detection range can of course also depend on the digital zoom setting. The spatial orientation and location of the camera coordinate system 11 in space 2, i.e., in the spatial coordinate system 3, therefore depends on the respective position as well as the orientation of the camera 10 in space 2.

[0088] In the present case, it is assumed that the floor area of ​​room 2 coincides with the plane defined by the coordinate axes XR and YR. For ease of explanation, the camera's inclination is also aligned parallel to the floor area, meaning that the area defined by the coordinate axes XK and YK of the camera coordinate system 11 runs parallel to the floor area. It is thus aligned without inclination. If inclination were to be taken into account, inclination data representing the determined inclination would be generated using a sensor on camera 10.

[0089] In the present case, it is further assumed that a reference orientation in space 2 is given by the direction of the coordinate axis XR of the spatial coordinate system 3. The current orientation of the camera 10 is thus specified with respect to this direction. This can be done with the aid of an electronic compass of the camera 10, which is set or programmed to this direction as the reference orientation. An electronic magnetic compass can also be used, whereby the orientation determined with its aid with respect to north can be converted with respect to the reference orientation. Regardless of the method of determining the current orientation, the orientation data thus obtained are provided by the camera 10 for further processing.

[0090] System 1 also includes a wireless camera access point 12, which is connected to server 8 and used to transmit the orientation data from camera 10 to server 8. For this purpose, camera 10 has a corresponding camera data wireless communication stage 12A (not shown in detail), of which only a first antenna configuration is shown. Camera data wireless communication stage 12A is used to transmit the orientation data, possibly also the inclination data, if these need to be taken into account, and also other image processing data that are to be transmitted as a result of image processing using a computer of camera 10, hereinafter referred to as the camera computer (not shown).

[0091] In this case, the position of camera 10 in room 2 is determined using UWB radio, and this position is assigned, with a good approximation, to the origin of camera coordinate system 11. For this purpose, a UWB radio system 13 is provided, whose position is uniquely defined in room 2 and which is coupled to server 8 in order to transmit the camera position data determined via UWB radio to server 8, which indicates the position of camera 10 in room 2 (specifically, in relation to the position of UWB radio system 13, from which, in turn, can be converted to the position determined by spatial coordinate system 3). Of course, the origin of spatial coordinate system 3 can also be located at the location of the UWB radio system in order to avoid the conversion discussed above. For the purpose of UWB radio communication, the camera 10 has a corresponding camera UWB radio communication stage 13A (not shown in detail), of which only a second antenna configuration is shown.

[0092] The following describes in detail the method performed using system 1. It is assumed that camera 10 is currently located at location S1 along its path S and is aligned with its detection range E toward shelf 7. It creates a series of still images, hereinafter referred to as a still image series, of the scene present within the detection range E. Each still image forms a digital scene image whose pixels, as discussed, are essentially determined by the pixel matrix of the CCD sensor of camera 10.

[0093] In the still image series, which is represented by image data, in addition to the shelf labels 4A - 4F, the coded light signal of each shelf label 4A - 4F at the respective pixel coordinates XKP and ZKP is now included.

[0094] Reduced to the shelf labels 4A - 4F and the respective light signal, Figure 2 now visualizes the image of the scene on the level of the pixel matrix of the CCD sensor of the camera 10 and shows the brightness present at the image location for the respective light signal at five different times t1 to t5 using the symbols "circle" and "star". In this representation, a "circle" symbolizes darkness, i.e., that the LED 6 emitting the respective coded light signal is currently switched off. Furthermore, in this representation, in contrast to the "circle", a "star" symbolizes brightness, i.e., that the LED 6 emitting the respective coded light signal is currently switched on.

[0095] With the help of the camera's computer, it is now determined, by recognizing the coding of the respective light signal, that it is a light signal to be considered in the present context and that no other light signals are present that have nothing to do with the objective of the invention. For such a light signal to be considered, the position in the pixel matrix is ​​determined, and the respective identification information is determined. This detection data at the pixel level is temporarily stored. At this point, the determined identification information can already be used to identify the associated product PI - P6.

[0096] In a further process step, it is determined how far apart the light signals are in the real scene. For this purpose, a scale is determined which results from knowledge of the real dimensions (e.g. edge length of the front border) of the shelf labels 4A - 4F present in the digital image. The positions of the respective shelf labels 4A - 4F can be easily determined in the digital scene image with computer support because the light signal is located within the visible front or front border of the respective shelf label 4A - 4F. The camera's computer also knows the real dimensions (i.e. the actual length of the sections of the front border) of these shelf labels 4A - 4F used as reference objects. Using pattern recognition, the respective front border is determined in the digital image and the number of corresponding pixels along this (along the longer and / or shorter side) is determined.Since the physical pixel pitches of the CCD sensor are known, the scale for converting counted pixels (i.e., distances or lengths in the pixel system of the digital scene image) into real length units (e.g., millimeters) in the scene can now be calculated. This allows the relative distances of the light signals in the real scene to be determined, i.e., specified in the XK-ZK plane of the camera coordinate system 11. This essentially defines the positions of the Rega I et i chains 4A - 4F and, subsequently, the positions of the corresponding products P1 - P6 in this XK-ZK plane.

[0097] In a further method step, the distance from the camera 10 to the scene is determined in order to supplement the two-dimensional location in the camera coordinate system 11 with the third dimension. Once the physical parameters of both the CCD sensor and the lens are known, i.e. the length of an object imaged on the CCD sensor can be determined in, for example, millimeters at the CCD sensor, and the dimensions of the respective reference object in the real scene are also known, this distance between the camera and the real scene can be easily calculated using the lens equation with the help of the computer of the camera 10, which stores the necessary data, so that the position of the light signals in the camera coordinate system 11 along the coordinates XK, YK and ZK can be specified in, for example, metric measurements (e.g. millimeters).

[0098] Subsequently, the object position data determined in the camera coordinate system 11 (which here are still present in the coordinates XK, YK, and ZK) for each light signal (in a broader sense, of course, also for each shelf label 4A - 4F) are transmitted from the camera 10 to the server 8 along with the respective identification information. The orientation data determined at location S1 are also transmitted to the server 8. Server 8 also has the camera position data that was determined for location S1 at the time the image series was taken using UWB radio communication.The orientation data and the camera position data together form supplementary data, with the aid of which the position information of the light signals valid for the camera coordinate system 11 is transferred to the spatial coordinate system 3 by conversion (coordinate transformation taking into account the fact that the position of the UWB radio system 13 does not coincide with the origin of the spatial coordinate system 3) at the server 8. The object position data then defines the respective position of the light signals in the coordinates XR, YR, and ZR.

[0099] As can be seen from Figure 2, the camera 10 can, in principle, be freely movable. Depending on the implementation, it can therefore be mounted, for example, on glasses or on a shopping cart 14, as shown in Figure 3.

[0100] Specifically, Figure 3 shows a shelf aisle flanked on both sides by shelves 7, in which the shopping cart 14, which carries the camera 10 on an upstanding pole 15, moves along the path S. For reasons of clarity, only the first six shelf labels 4A - 4F and the first six products P1 - P6 have been provided with reference symbols, with the products P1 - P6 being merely indicated by dashed frames that indicate the position of the products P1-P6 on the shelf 7. In the present case, it is assumed that the camera 10 is oriented towards the left side of the cart 14, i.e. the left shelf 7 lies within the detection range E of the camera 10, with the length of the shelf 7 exceeding the width of the detection range E. Along the path S, the camera 10 therefore records the respective scene located in its detection area E several times, for example a first time at a position S1 and a second time at a position S2.The still image series generated at each location SI or S2 is processed by the camera 10 computer in accordance with the previously discussed procedures and subsequently transmitted to the server 8, which, with the aid of the conversion, completes the localization of the light signals, and ultimately the products, in the spatial coordinate system. If, as can be seen in the present example, the series images captured from neighboring positions PI and P2 exhibit an overlap of shelf areas, this can be used to improve the results of determining the item position data, because these are generated multiple times for one and the same light signal in the overlap area. The same also applies to multiple captures at completely different times with one and the same camera 10 or with different cameras 10 competing with different shopping carts 14.In larger stores, the large number of shopping carts 14 in motion also ensures that the entire store is mapped with the assistance of customers, i.e. that the item position data for all of the products is recorded over time.

[0101] In order to capture the right shelf 7 shown in Figure 3, the shopping cart 14 must be turned around and moved along the aisle again or have two cameras 10, of which a first camera 10 is oriented to the left and a second camera 10 to the right.

[0102] The entirety of the individual object position data in the spatial coordinate system 3 for the respective products P1, P2, etc., which gradually become available at the server 8, is ultimately used by the server s to create a digital three-dimensional map of the product positions, which is referred to in technical jargon as a floor plan. The creation or update of this three-dimensional map of the products P1, P2, etc. can occur after a certain recording period or successively, i.e., each time new object position data becomes available.

[0103] Alternatively, it should be mentioned that the freely movable device (i.e., the glasses or the shopping cart) can have a computer that receives raw data from the camera 10 and performs the processing of this raw data described in connection with the camera 10. In this case, the freely movable device can also have the camera data radio communication stage 12A and the camera UWB radio communication stage 13A.

[0104] According to a further embodiment, a mobile phone or a tablet computer can also be used as a freely web-based device carrying the camera. Modern devices of this type are usually already equipped with an excellent camera system including a sensor (often implemented as a flight-of-time sensor) for detecting the distance between the camera and an object captured by the camera. They also have powerful computers that can easily implement the previously discussed computing tasks (particularly in real time) with suitable programming. Such devices use a so-called app, i.e., software that provides the functionalities discussed in the context of this invention as soon as it is executed on the device's computer. The position determination of these devices in the space of the business premises or warehouse can also be carried out using the radio device integrated in the respective device (such as, for example,WLAN or BlueTooth ®), for example, can be easily carried out using triangulation or even using UWB radio, provided that this functionality is also implemented in the respective device. If such devices are not equipped with an integrated UWB radio device ex works, they can be retrofitted with UWB radio devices that can be plugged into the USB port of the device (e.g. designed as a UWB radio dongle or USB-capable UWB radio device). In the context of this invention, such devices are predominantly used by store or warehouse staff. They are held towards the shelves, carried past or along the shelves, and the respective scene is recorded. The use of such devices has also proven particularly advantageous because they have an integrated screen, with the help of which the staff can always visually observe and evaluate the recorded scene on site and, if necessary,the orientation or alignment, and if necessary also the anger setting or even the exposure, etc., can be adjusted to ensure optimized capture in a single work pass. If a just-in-time visual check of the scene captured by the camera is not to be carried out by the staff, automatic image or video analysis (e.g. on the server) can subsequently identify which areas of the business premises or warehouse may require a repeat capture of the scene in order to obtain a complete picture of the situation there. However, since the devices themselves also have a powerful computer, the respective device can also automatically check during capture whether the digital scene image is suitable for further processing or whether the scene should be captured again. This can be communicated to the staff acoustically, for example, using the audio module integrated in the device.by means of "spoken" instructions from the device or in the form of a dialogue, in such a way that the personnel are given unambiguous instructions for action, such as holding the device higher or lower, or changing the inclination or orientation in a given direction, etc.

[0105] Finally, it should be noted once again that the figures described in detail above are merely exemplary embodiments that can be modified in a variety of ways by those skilled in the art without departing from the scope of the invention. For the sake of completeness, it should also be noted that the use of the indefinite articles "a" or "an" does not exclude the possibility that the relevant features may be present multiple times.

Claims

Claims 1. Method for determining the position of at least one object (P1-P6) in space (2), in particular of at least one product (P1-P6) positioned in a shelf (7), wherein the method comprises: - the emission of a light signal encoded with identification information for identifying the object (P1-P6) from a light emission device (4A - 4F) positioned adjacent to the object (P1-P6), and - capturing a scene using at least one freely movable camera (10), wherein a digital scene image generated using the camera (10) represents the scene, and - a generation of object position data based on a computerized determined position of the light signal appearing in the digital scene image in relation to the camera (10) and the identification information emitted with the light signal and with knowledge of an automatically determined orientation and position of the camera (10) in space (2) when capturing the scene, wherein the object position data represent the position of the object (P1-P6) in the scene in relation to space (2).

2. Method according to claim 1, wherein the method is carried out using several independently moving cameras (10).

3. Method according to one of the preceding claims, wherein the at least one freely movable camera (10) is attached to a shopping cart (14) or to a pair of glasses.

4. Method according to claim 3, wherein several cameras (10) are provided which are moved together, i.e., grouped, and from different detection positions and / or with Different capture orientations generate individual digital scene images.

5. Method according to one of the preceding claims, wherein a control signal transmitter moving with the at least one freely movable camera (10) emits a control signal, in particular a radio-based control signal, and the light emission device (4A - 4F) located in the reception area of ​​the control signal, which is designed to receive the control signal, emits the light signal only when the control signal is received.

6. Method according to one of the preceding claims, wherein determining the position with respect to the camera (10) comprises automatically determining a scale derivable from the digital scene image, wherein the scale is determined with knowledge of the real dimension of a reference object (4A - 4F) identified in the digital scene image, in particular designed as an electronic shelf label (4A - 4F), and serves for the conversion between position data or dimensions determined in the digital scene image and position data or dimensions in the scene captured by the camera (10).

7. Method according to one of the preceding claims, wherein determining the position with respect to the camera (10) comprises automatically determining the distance between the camera (10) and the scene captured by it.

8. Method according to one of the preceding claims, wherein determining the identification information comprises analyzing the temporal change of a light signal parameter with knowledge of a coding scheme used when emitting the light signal.

9. Method according to one of the preceding claims, wherein the method step of emitting the light signal is carried out substantially simultaneously by several light emission devices (4A - 4F), and wherein the method step of computerized determination of the Position of the light signal appearing in the digital scene image in relation to the camera (10) and the identification information transmitted with the light signal for the entirety of the light signals appearing in the digital scene image is carried out.

10. Method according to one of the preceding claims, wherein supplementary data are taken into account for the generation of the object position data, which includes at least one of the following types of data, namely: - Orientation data which describe the orientation of the camera (10) in relation to a reference orientation in space (2); - Inclination data describing the inclination of the camera (10) with respect to a reference plane in space (2); - Position data describing the position of the camera (10) in relation to a reference point in space (2).

11. Method according to one of the preceding claims, wherein a data processing device generates a data structure from the object position data determined for each object (P1-P6), which specifies the three-dimensional position of each object (P1-P6) in the space (2).

12. Freely movable device (14), in particular a shopping cart or glasses or a mobile phone or a tablet computer, for determining the position of at least one object (P1-P6) in the space (2), in particular of at least one product (P1-P6) positioned in a shelf (7), wherein this position is indicated by a light signal emitted by a light emission device (4A - 4F) positioned adjacent to the object (P1-P6), which encodes identification information by which the object (P1-P6) can be identified, - wherein the device includes at least one camera (10) designed to generate a digital scene image of a scene captured by it, - and wherein the device, in particular the camera (10), is used for computerized determination of the position of the object in the digital scene image is designed with regard to the light signal appearing in relation to the camera (10) and the identification information emitted with the light signal, - and wherein the device, in particular the camera (10), is designed to at least assist an automated determination of the orientation and position of the camera (10) in the room (2) when capturing the scene.

13. Light emission device (4A - 4F), in particular a shelf label (4A - 4F), which is designed to display product and / or price information, or a product separator designed to separate different products (P1-P6), having the light emission device (4A - 4F): - a storage stage for storing identification information by which an object (P1-P6), in particular a product (P1-P6) positioned in a shelf (7), can be identified in the vicinity of which the light emission device (4A - 4F) is positioned, and - a light signal generation stage (6) configured to encode a light signal according to the identification information and to emit this encoded light signal.

14. System (1) for determining the position of at least one object (P1-P6) in space (2), in particular of at least one product (P1-P6) positioned in a shelf (7), wherein the system (1) comprises: - at least one light emission device (4A - 4F) according to claim 13 and - at least one freely movable device (14) according to claim 12.

Images