BACKGROUND

[0001] In facilities supporting material handling activities, such as warehouses, retail facilities such as grocers, and the like, the physical placement of items within the facility (e.g. the location of each item within the facility) can affect the performance of the facility, for example in terms of the volume of materials handled in a given time frame. Such facilities may be large and complex, with hundreds or thousands of distinct items handled therein, however, complicating accurate assessments of current item placements and facility performance.

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0002] The accompanying figures, where like reference numerals refer to identical or functionally similar elements throughout the separate views, together with the detailed description below, are incorporated in and form part of the specification, and serve to further illustrate embodiments of concepts that include the claimed invention, and explain various principles and advantages of those embodiments.

[0003] FIG. l is a schematic of a mobile automation system.

[0004] FIG. 2 is a side view of a mobile automation apparatus in the system of FIG. 1. [0005] FIG. 3 is a flowchart of a method of item placement detection and optimization.

[0006] FIG. 4 is a diagram illustrating a shelf module.

[0007] FIG. 5 is a diagram illustrating example item regions obtained at block 310 of the method of FIG. 3.

[0008] FIG. 6 is a diagram illustrating example overlay regions generated at block 330 of the method of FIG. 3.

[0009] FIG. 7 is a diagram illustrating an example performance of block 345 of the method of FIG. 3.

[0010] FIG. 8 is a flowchart of a method for generating performance metrics.

[0011] FIG. 9 is a diagram illustrating an example performance of the method of FIG. 9. [0012] FIG. 10 is a flowchart of a method of generating relocation indicators.

[0013] FIG. 11 is a diagram illustrating an example performance of block 345 of the method of FIG. 3 after the performance of the method of FIG. 10.

[0014] FIG. 12. is a diagram illustrating a set of overlays generated via successive performances of the method 300.

[0015] FIG. 13. is a diagram illustrating an additional item overlay corresponding to a rate of change in performance metrics.

[0016] Skilled artisans will appreciate that elements in the figures are illustrated for simplicity and clarity and have not necessarily been drawn to scale. For example, the dimensions of some of the elements in the figures may be exaggerated relative to other elements to help to improve understanding of embodiments of the present invention.

[0017] The apparatus and method components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

DETAILED DESCRIPTION

[0018] Examples disclosed herein are directed to a method, comprising: obtaining, from an image sensor mounted on a mobile automation apparatus, an image representing a plurality of items on a support structure in a facility; responsive to detection of the items in the image, for each item: obtaining an item region defining an area of the image containing the item; obtaining a performance metric corresponding to the item; encoding the performance metric as a visual attribute; and generating an item overlay using the visual attribute; and controlling a display to present the image, and each of the item overlays placed over the corresponding item regions.

[0019] Additional examples disclosed herein are directed to a computing device, comprising: a communications interface, and; a processor configured to: obtain, from an image sensor mounted on a mobile automation apparatus, an image representing a plurality of items on a support structure in a facility; responsive to detection of the items in the image, for each item: obtain an item region defining an area of the image containing the item; obtain a performance metric corresponding to the item; encode the performance metric as a visual attribute; and generate an item overlay using the visual attribute; and control a display to present the image, and each of the item overlays placed over the corresponding item regions.

[0020] FIG. 1 depicts a mobile automation system 100 in accordance with the teachings of this disclosure. The system 100 includes a server 101 in communication with at least one mobile automation apparatus 103 (also referred to herein simply as the apparatus 103) and at least one client computing device 104 via communication links 105, illustrated in the present example as including wireless links. In the present example, the links 105 are provided by a wireless local area network (WLAN) deployed via one or more access points (not shown). In other examples, the server 101, the client device 104, or both, are located remotely (i.e. outside the environment in which the apparatus

103 is deployed), and the links 105 therefore include wide-area networks such as the Internet, mobile networks, and the like. The system 100 also includes a dock 106 for the apparatus 103 in the present example. The dock 106 is in communication with the server 101 via a link 107 that in the present example is a wired link. In other examples, however, the link 107 is a wireless link.

[0021] The client computing device 104 is illustrated in FIG. 1 as a mobile computing device, such as a tablet, smart phone or the like. In other examples, the client device

104 is implemented as another type of computing device, such as a desktop computer, a laptop computer, another server, a kiosk, a monitor, and the like. The system 100 can include a plurality of client devices 104 in communication with the server 101 via respective links 105.

[0022] The system 100 is deployed, in the illustrated example, in a retail facility including a plurality of support structures such as shelf modules 110-1, 110-2, 110-3 and so on (collectively referred to as shelf modules 110 or shelves 110, and generically referred to as a shelf module 110 or shelf 110 - this nomenclature is also employed for other elements discussed herein). Each shelf module 110 supports a plurality of products 112, which may also be referred to as items. Each shelf module 110 includes a shelf back 116-1, 116-2, 116-3 and a support surface (e.g. support surface 117-3 as illustrated in FIG. 1) extending from the shelf back 116 to a shelf edge 118-1, 118-2, 118-3. A variety of other support structures may also be present in the facility, such as pegboards, tables, and the like.

[0023] The shelf modules 110 (also referred to as sub-regions of the facility) are typically arranged in a plurality of aisles (also referred to as regions of the facility), each of which includes a plurality of modules 110 aligned end-to-end. In such arrangements, the shelf edges 118 face into the aisles, through which customers in the retail facility, as well as the apparatus 103, may travel. As will be apparent from FIG. 1, the term “shelf edge” 118 as employed herein, which may also be referred to as the edge of a support surface (e.g., the support surfaces 117) refers to a surface bounded by adjacent surfaces having different angles of inclination. In the example illustrated in FIG. 1, the shelf edge 118-3 is at an angle of about ninety degrees relative to the support surface 117-3 and to the underside (not shown) of the support surface 117-3. In other examples, the angles between the shelf edge 118-3 and the adjacent surfaces, such as the support surface 117-3, is more or less than ninety degrees.

[0024] The apparatus 103 is equipped with a plurality of navigation and data capture sensors 108, such as image sensors (e.g. one or more digital cameras) and depth sensors (e.g. one or more Light Detection and Ranging (LIDAR) sensors, one or more depth cameras employing structured light patterns, such as infrared light, or the like). The apparatus 103 is deployed within the retail facility and, via communication with the server 101 and use of the sensors 108, navigates autonomously or partially autonomously along a length 119 of at least a portion of the shelves 110.

[0025] While navigating among the shelves 110, the apparatus 103 can capture images, depth measurements and the like, representing the shelves 110 and the items 112 supported by the shelves 110 (generally referred to as shelf data or captured data). Navigation may be performed according to a frame of reference 102 established within the retail facility. The apparatus 103 therefore tracks its pose (i.e. location and orientation) in the frame of reference 102.

[0026] The server 101 includes a special purpose controller, such as a processor 120, specifically designed to control and/or assist the mobile automation apparatus 103 to navigate the environment and to capture data. The processor 120 is interconnected with a non-transitory computer readable storage medium, such as a memory 122, having stored thereon computer readable instructions for performing various functionality, including control of the apparatus 103 to navigate the modules 110 and capture shelf data, as well as post-processing of the shelf data. The memory 122 can also store data for use in the above-mentioned control of the apparatus 103 and post-processing of captured data, such as a repository 123. The repository 123 can contain, for example, a map of the facility, operational constraints for use in controlling the apparatus 103, the image and/or depth data captured by the apparatus 103, and the like.

[0027] The memory 122 includes a combination of volatile memory (e.g. Random Access Memory or RAM) and non-volatile memory (e.g. read only memory or ROM, Electrically Erasable Programmable Read Only Memory or EEPROM, flash memory). The processor 120 and the memory 122 each comprise one or more integrated circuits. In some embodiments, the processor 120 is implemented as one or more central processing units (CPUs) and/or graphics processing units (GPUs).

[0028] The server 101 also includes a communications interface 124 interconnected with the processor 120. The communications interface 124 includes suitable hardware (e.g. transmitters, receivers, network interface controllers and the like) allowing the server 101 to communicate with other computing devices - particularly the apparatus 103, the client device 104 and the dock 106 - via the links 105 and 107. The links 105 and 107 may be direct links, or links that traverse one or more networks, including both local and wide-area networks. The specific components of the communications interface 124 are selected based on the type of network or other links that the server 101 is required to communicate over. In the present example, as noted earlier, a wireless local-area network is implemented within the retail facility via the deployment of one or more wireless access points. The links 105 therefore include either or both wireless links between the apparatus 103 and the mobile device 104 and the above-mentioned access points, and a wired link (e.g. an Ethernet-based link) between the server 101 and the access point.

[0029] The processor 120 can therefore obtain data captured by the apparatus 103 via the communications interface 124 for storage (e.g. in the repository 123) and subsequent processing (e.g. to detect objects such as shelved products in the captured data, and detect status information corresponding to the objects). The server 101 maintains, in the memory 122, an application 125 executable by the processor 120 to perform such subsequent processing. In particular, as discussed in greater detail below, the server 101 is configured, via execution of the instructions of the application 125 by the processor 120, to obtain detected positions of the items 112 in images captured by the apparatus 103, as well as to obtain performance metrics associated with the items 112. The performance metrics, as will be discussed in greater detail below, correspond generally to rates at which the items 112 are dispensed from the facility (e.g. rates of consumption of the items 112).

[0030] Having obtained the above information, the application 125 further configures the processor 120 to generate visual representations of the performance metrics, and to detect and present relocation indicators identifying items 112 to be physically repositioned within the facility. Such repositioning may, in turn, increase the performance of the material handling operations within the facility. The server 101 repeats the above functionality periodically based on updated data captured by the apparatus 103, enabling continuous observation of current item locations and corresponding performance metrics.

[0031] In some examples, the server 101 can perform the above functions using data retrieved from other subsystems. For example, the server 101 can communicate, via the interface 124, with a performance monitoring subsystem 128, e.g. via a link 130, to retrieve certain forms of performance data. The subsystem 128 can include any one of, or any combination of, a point of sale (PoS) subsystem, a product category management and/or merchandizing planning system, or the like.

[0032] The server 101 may also transmit status notifications (e.g. notifications indicating that products are out-of-stock, in low stock or misplaced) to the client device 104 responsive to the determination of product status data. In addition, the server 101 can transmit the above-mentioned visual representations and/or relocation identifiers to the client device 104. The client device 104 includes one or more controllers (e.g. central processing units (CPUs) and/or field-programmable gate arrays (FPGAs) and the like) configured to process notifications and other information received from the server 101. For example, the client device 104 includes a display 132 controllable to present information received from the server 101.

[0033] Turning now to FIG. 2, the mobile automation apparatus 103 is shown in greater detail. The apparatus 103 includes a chassis 201 containing a locomotive assembly 203 (e.g. one or more electrical motors driving wheels, tracks or the like). The apparatus 103 further includes a sensor mast 205 supported on the chassis 201 and, in the present example, extending upwards (e.g., substantially vertically) from the chassis 201. The mast 205 supports the sensors 108 mentioned earlier. In particular, the sensors 108 include at least one imaging sensor 207, such as a digital camera. In the present example, the mast 205 supports seven digital cameras 207-1 through 207-7 oriented to face the shelves 110.

[0034] The mast 205 also supports at least one depth sensor 209, such as a 3D digital camera capable of capturing both depth data and image data. The apparatus 103 also includes additional depth sensors, such as LIDAR sensors 211. In the present example, the mast 205 supports two LIDAR sensors 211-1 and 211-2. As shown in FIG. 2, the cameras 207 and the LIDAR sensors 211 are arranged on one side of the mast 205, while the depth sensor 209 is arranged on a front of the mast 205. That is, the depth sensor 209 is forward-facing (i.e. captures data in the direction of travel of the apparatus 103), while the cameras 207 and LIDAR sensors 211 are side-facing (i.e. capture data alongside the apparatus 103, in a direction perpendicular to the direction of travel). In other examples, the apparatus 103 includes additional sensors, such as one or more RFID readers, temperature sensors, and the like.

[0035] The mast 205 also supports a plurality of illumination assemblies 213, configured to illuminate the fields of view of the respective cameras 207. The illumination assemblies 213 may be referred to collectively as an illumination subsystem. That is, the illumination assembly 213-1 illuminates the field of view of the camera 207-1, and so on. The cameras 207 and lidars 211 are oriented on the mast 205 such that the fields of view of the sensors each face a shelf 110 along the length 119 of which the apparatus 103 is traveling. The apparatus 103 is configured to track a pose of the apparatus 103 (e.g. a location and orientation of the center of the chassis 201) in the frame of reference 102, permitting data captured by the apparatus 103 to be registered to the frame of reference 102 for subsequent processing.

[0036] Facilities such as retailers may measure facility performance by assessing various performance metrics associated with the items 112. For example, a quantity of each item 112 removed from the shelves 110 (e.g. for purchase by customers) over a given time period (e.g. a week, although both shorter and longer time periods may also be assessed) may be measured. The quantities of items 112 consumed may be combined with item prices, margins, shelf space (e.g. in square feet or other suitable measurement unit) assigned to an item 112, or the like to assess facility performance in financial terms.

[0037] Further, the above measurements may be employed to alter the physical placement of items 112 in order to increase facility performance. For example, certain locations, such as higher support surfaces 117 (as opposed to support surfaces 117 closer to the ground), may increase the performance metrics associated with an item placed on such support surfaces. Therefore, the performance of the facility as a whole may be improved by further increasing the performance of already high-performing items. Gathering accurate locations of items 112, however, as well as accurate measurements of performance and selection of items to relocate, is typically a timeconsuming manual process. As discussed below, the system 100 enables at least partial automation of this process.

[0038] Turning to FIG. 3, a method 300 of item placement detection and optimization is illustrated. The method 300 will be discussed in conjunction with its performance in the system 100, and in particular by the server 101. In other examples, however, at least some of the functionality implemented via the method 300 can be performed by another computing device, such as the apparatus 103.

[0039] At block 305, the server 101 is configured to obtain image data, and in some examples depth data (i.e. one or more point clouds) depicting a support structure such as one or more shelves 110. The image data, in this example, includes a two- dimensional color image previously captured by the apparatus 103, e.g. while traversing an aisle containing shelves 110. The image may be a composite generated from a plurality of 2D images captured by the apparatus 103 as the apparatus 103 traversed the aisle. In other examples, the image data and/or depth data may also be captured prior to block 305 by at least one fixed camera mounted within the facility, in addition to or instead of the apparatus 103.

[0040] In examples in which the server 101 receives depth data at block 305, the depth data can include a point cloud containing a plurality of points with coordinates defined in three dimensions, e.g. according to the frame of reference 102, captured by the apparatus 103 during the above-mentioned traversal of the support structures. As with the 2D images mentioned above, the point cloud can be a composite generated from multiple point cloud captures taken as the apparatus 103 traversed the aisle. The images and point cloud obtained at block 305 may be retrieved from the repository 123, for example.

[0041] As will be apparent to those skilled in the art, the image obtained at block 305 represents a set of items 112 on the shelves 110. At block 310, the server 101 obtains item regions defining, for each item represented in the image, an area of the image that contains the item. The item regions are obtained in response to detection of the items 112 in the image, e.g. by at least one detection mechanism implemented at the server 101 (e.g. via another application distinct from the application 125) or another computing device. For example, the detection mechanisms can include an item classification mechanism employing a trained classifier (e.g. any suitable machine learning technique, including deep learning mechanisms such as neural networks and the like) to detect image features associated with particular items.

[0042] The detection mechanisms can also include a shelf edge detector, configured to return a region of the image corresponding to a shelf edge 118. The shelf edge detector can be based on any suitable combination of edge detection algorithms, for example. The detection mechanisms may also include a label detector, configured to return regions of the image corresponding to labels (e.g. price labels) that identify the items 112. The label detector can, for example, search the image (e.g. within detected shelf edge region(s)) for text and/or barcodes with predefined characteristics such as font sizes, layouts, and the like.

[0043] The item regions mentioned above can be derived from the detections of items, shelf edges, and labels. The server 101, via the execution of the application 125, may therefore generate the item regions at block 305 based on the above-mentioned item detections, or the item regions may be previously generated and stored in the repository 123, and retrieved at block 305. The server 101 can retrieve detection data 312 defining the item regions and/or the detection data mentioned above at block 310.

[0044] Referring to FIG. 4, an example shelf module 410 is illustrated, with support surfaces 417-1 and 417-2 terminating in aisle-facing shelf edges 418-1 and 418-2, which are substantially as described above in connection with the support surfaces 117 and shelf edges 118. Each support surface 417 supports various items 112. The shelf module 410 also supports, e.g. on the shelf edges 418, a plurality of labels 404 each identifying a corresponding item 112. As will be apparent from FIG. 4, the positions of the labels 404 define spaces on the support surfaces 417 for each item 112. The image obtained at block 305 encompasses a field of view 400, and therefore represents the shelf module 410 and the items 112 thereon.

[0045] Turning to FIG. 5, an image 500 representing the shelf module 410 and items 112 encompassed within the field of view 400 is illustrated. FIG. 5 also illustrates an item region 502-1 defining an area of the image 500 containing an item 112-1. More specifically, in this example the item region 502-1 defines the maximum extent of an area containing the item 112-1, e.g. assuming the item 112-1 is fully stocked. The item region 502-1 extends from the shelf edge 418-2 to an upper structure 502 of the module 410, and from a left edge of the label 404-1 identifying the item 112-1 to a left edge of the adjacent label 404-2, which identifies an item 112-2. The remaining item regions define similar areas for the other items 112 in the image 500.

[0046] The item regions 500 are also shown in isolation within a boundary 504 of the image 500 (with the remainder of the image 500 omitted for clarity). Thus, each of the item regions 500-1, 500-2, 500-3, 500-4, 500-5, and 500-6 defines an area within the image 500 representing the maximum extent of the item 112-1, 112-2, 112-3, 112-4, 112-5, and 112-6, respectively. As will be apparent to those skilled in the art, the items 112 do not necessarily currently occupy the entirety of the corresponding item regions 500 (e.g. because some items have been removed for purchase). Each item region 502 is stored by the server 101 along with an item identifier, such as a stock-keeping unit (SKU) or other suitable identifier.

[0047] Returning to FIG. 3, having obtained the item regions 500, the server 101 is configured to obtain a performance metric for each item detected in the image (i.e. for each item region 502). The server 101 is further configured to process the performance metrics to generate overlay data for the image and/or relocation indicators identifying items to relocate, e.g. from one support surface 417 to another.

[0048] In particular, at block 315, the server 101 is configured to select an item for processing. Blocks 320 to 330 of the method 300 are performed for each item, as will be apparent in the discussion below. [0049] In an example performance of block 315, therefore, the item corresponding to the item region 502-1 is selected. At block 320, the server 101 obtains a performance metric corresponding to the selected item. The performance metric can take a wide variety of forms. In some examples, the performance metric is an indication of revenue associated with sales of the item 112-1 over a predefined time period (e.g. a week, a month, or any other suitable time period). In further examples, the performance metric is an indication of profit margin associated with sales of the item 112-1 over the predefined time period. Other performance metrics are also contemplated, however, such as a rate of consumption of the item 112-1 independent of financial information. That is, the performance metric can include an indication of a number of instances of the item 112-1 removed from the module 410 over the time period (and therefore assumed to have been purchased), a weight of the item 112-1 removed, or the like.

[0050] Performance metric data 322 can be retrieved from the repository 123 in some examples. In other examples, performance metric data 322 can be retrieved from the PoS subsystem 128, which stores data defining sales at the facility. For example, the server 101 may request sales data from the subsystem 128 using the item identifier associated with the item region 502-1 as well as start and end dates and/or times defining the above-mentioned time period. In other examples, e.g. when the server 101 does not have access to sales data from the subsystem 128, the server 101 can generate the performance metric, as will be discussed in greater detail below.

[0051] In the present example performance of the method 300, the server 101 is assumed to retrieve the performance metric from the subsystem 128, e.g. as an amount of revenue associated with the item 112-1 over the time period. At block 325, the server 101 is configured to encode the performance metric as a visual attribute. The visual attribute includes at least one of a color value, a transparency value, a pattern selection, and the like. For example, the performance metric can be encoded to a color value by comparing the performance metric to a set of thresholds.

[0052] Turning to FIG. 6, a set of encoding data 600 is illustrated, defining three visual attributes. In other examples, fewer than three, or more than three visual attributes may be defined. For example, an upper threshold (e.g. a predefined revenue threshold) corresponds to a first color (represented as diagonal hatching), such that any items 112 with performance metrics exceeding the upper threshold are encoded as the first color. The set 600 also includes a lower threshold, such that any items 112 with performance metrics below the lower threshold are encoded as a second color (represented in FIG. 6 as sparse points). Further, the set 600 includes an intermediate visual attribute definition, such that items 112 with performance metrics falling below the upper threshold and above the lower threshold are assigned a third color (represented in FIG. 6 as dense points).

[0053] Other mechanisms for encoding the performance metrics as visual attributes are also contemplated. For example, rather comparing a performance metric to discrete thresholds, the performance metric may be mapped to a color scale defined by first and second colors each associated with minimal and maximal performance metrics. Each performance metric is therefore assigned a color between the first and second colors according to the position of the performance metric relative to the minimal and maximal performance metrics.

[0054] Returning to FIG. 3, at block 330, the server 101 is configured to generate an item overlay corresponding to the item selected at block 315. In particular, the item overlay can have the same dimensions as the corresponding item region 502, as well as the visual attribute(s) encoded at block 325. The right side of FIG. 6 illustrates overlay regions 604, corresponding to the item regions 500 of FIG. 5 and assigned colors (represented as the above-mentioned patterns) based on encoding of their respective performance metrics via the encoding data 600. That is, the regions overlay 604-3 and 604-6 are assigned the first color, the overlay regions 604-2 and 604-4 are assigned the third color, and the region 502-1 and 500-5 are assigned the second color. As will now be apparent, FIG. 6 illustrates multiple performances of blocks 320-330.

[0055] At block 335, the server 101 determines whether there remain items 112 to be processed that correspond to the item regions 500 obtained at block 310. Blocks 315, 320, 325, and 330 are repeated until all items for which an item region 502 was obtained have been processed (i.e. to generate a corresponding item overlay).

[0056] Following a negative determination at block 335, the server 101 may proceed to block 340. At block 340, the server can generate the above-mentioned relocation indicators. The generation of relocation indicators is optional, and may therefore be omitted. Generation of relocation indicators will be discussed below, and in the present example is therefore omitted. [0057] At block 345, the server 101 is configured to control a display to present the image 500 obtained at block 305, along with the overlay regions generated via successive performances of blocks 315-330. Turning to FIG. 7, the image 500 is shown with the overlay regions 604 overlaid thereon. As seen by comparing FIGS. 5 and 7, the overlay regions 604 define the same areas as the item regions 500. Further, the overlay regions 604 have the visual attributes defined by the set of encoding data 600 discussed above. FIG. 7, in other words, illustrates a heat map depicting performance metrics associated with the items 112 via color and/or pattern, or other suitable visual attributes.

[0058] The overlay of the image 500 and the regions 604 generated at block 345 may be presented by transmission to the client device 104 (e.g. for presentation on the display 132), by presentation on a display local to the server 101, or the like. At block 345, the server 101 may also present the relocation indicators, when block 340 is performed.

[0059] Turning to FIG. 8, a method 800 for generating performance metrics at block 320 is illustrated. As noted above, the performance metrics in the form of sales data may not be available to the server 101 in some examples. The server 101 can therefore generate performance metrics from the image 500 and item detections. In particular, at block 805, the server 101 obtains an occupied portion of the item region. For example, along with the item regions 500, the server 101 may obtain (e.g. at block 310) item bounding boxes, indicating the portion(s) of each item region 502 that are actually occupied by the relevant item. For example, turning to FIG. 9, the item region 502-2 is illustrated, along with an occupied region 900a that corresponds to the item 112-2 shown in FIG. 5. The server 101 can determine the occupied portion, for example, by determine a fraction of the area of the region 502-2 represented by the region 900a. In the present example, that fraction is about 20%. In other embodiments, in which depth data is also available, an occupied portion of a volume corresponding to the item region 502-2 may be determined.

[0060] At block 810, the server 101 is configured to retrieve a previous occupied portion of the same item region (e.g. the region 502-2). That is, the server 101 retrieves data from a previous performance of block 805, e.g. from the repository 123. The previous version retrieved corresponds to a predefined time period before the image 500 was captured. Turning again to FIG. 9, a portion of an earlier image, showing four instances of the item 112-2 is also shown. The four instances of the item 112-2 define an occupied region 900b, representing about 80% of the item region 502-2. In other words, during the time period separating the capture operations that yielded the two depictions of the item region 502-2 shown in FIG. 9, three instances of the item 112-2 have been consumed

[0061] Returning to FIG. 8, at block 815 the server 101 generates a consumption rate based on the current occupied portion (e.g. about 20% in the above example), the previous occupied portion (e.g. about 80% in the above example), and the time period separating the current and previous occupied regions. For example, if the time period is five days, the consumption rate is 12% per day. In some embodiments, item dimension data and/or facing detection data enables the server 101 to determine a number of items (e.g. 3 items per five days).

[0062] Turning now to FIG. 10, generation of item relocation indicators will be discussed in greater detail. As will be apparent to those skilled in the art, the performance metrics of the items 112 (e.g. the revenue generated by the items 112 may depend in part on the positioning of the items 112 within the facility. In particular, the height of the support surface 417 on which an item 112 is placed may affect the performance metric of that item 112, with support surfaces 417 further above the ground increasing performance metrics compared to support surfaces 417 closer to the ground. In other words, it may be advantageous to place items 112 with greater performance metrics on support surfaces 417 with higher values (i.e. further above the ground), in order to further increase the performance of such items 112. The server 101 can be configured, at block 340, to perform a method 1000 to identify pairs of items 112 to relocate by swapping locations with one another, e.g. in order to place higher-value items 112 on higher support surfaces 417. The performance of the method 1000 will be discussed in conjunction with the image 500 and overlays 604 described earlier.

[0063] At block 1005, the server 101 selects a support surface to evaluate. In the present example, the method 1000 serves to identify opportunities to relocate high-value items to higher support surfaces 417. The method 1000 therefore begins with the second support surface from the ground, which in the present example is the support surface 417-2. [0064] At block 1010, the server 101 selects a first item 112. The first item is the item 112 that will be compared to a plurality of items on the lowest support surface (i.e. the support surface 417-1 in this example). In this example, the first item is the item 112-1 (corresponding to the overlay region 604-1, which indicates that the item 112-1 is a low-value item). At block 1015, the server 101 selects a second item 112. The second item is selected from the lower support surface 417-1. For example, the second item may be the item 112-4.

[0065] At block 1020, the server 101 determines whether the performance metric of the first item is smaller than the performance metric of the second item. In the present example, the determination is affirmative, as the item 112-4 (as indicated by the overlay region 604-4) has a greater value than the item 112-1. Following an affirmative determination at block 1020, the server 101 stores the first and second item as a relocation candidate pair at block 1025, and then proceeds to block 1030.

[0066] At block 1030, the server 101 determines whether additional second items remain to be compared to the first item from block 1010. In the present example, the non-active support surface (i.e. the support surface 417-1) contains two more items (the items 112-5, and 112-6), and the determination is therefore affirmative. The server 101 therefore proceeds to block 1015 and selects the next second item, e.g. the item 112-5. The comparison at block 1020 is repeated, and in the present example is negative because the items 112-1 and 112-5 both have low values. In this example, the performance metrics of the items 112 are being compared using the visual attributes described earlier, to simplify the comparison, but in some examples the original performance metrics may be compared, which may lead to a determination that the item 112-1, despite having been assigned a low-value visual attribute, nevertheless has a greater performance metric than the item 112-5.

[0067] A third performance of blocks 1015 and 1020 leads to a determination that the item 112-6 has a greater performance metric than the item 112-1. At block 1025 another relocation candidate pair (consisting of the items 112-1, and 112-6) is therefore stored. Following a negative determination at block 1030, because each of the items 112 on the support surface 417-1 have been compared to the item 112-1, the server 101 proceeds to block 1035. [0068] At block 1035, the server 101 selects a relocation indicator for the first item (i.e. the item 112-1 in this example). When there are multiple candidate pairs, as in this example performance, the paired items 112 themselves may be compared. Thus, in this example the items 112-4 andl l2-6 are compared in the same manner as block 1020, with the higher-value item being selected. The relocation indicator selected at block 1035 therefore pairs the items 112-1 and 112-6.

[0069] At block 1040, the server 101 determines whether any first items remain. That is, the server 101 determines whether any items 112 on the support surface selected at block 1005 remain to be processed. The process above is repeated for each such item, and following a negative determination, at block 1045 the process is once again repeated for each item on the next support surface. In this example, the first determination at block 1045 is negative because only two support surfaces 417 are present. However, if the module 410 included a third support surface 417 above the support surface 417-2, the determination at block 1045 would be affirmative, and each item 112 on the third support surface would be compared with every item on the first and second support surfaces 417-1 and 417-2.

[0070] At block 1050, once no further support surfaces 417 remain to be processed, the server 101 returns the selected relocation indicators from successive performances of block 1035, for use in the method 300. Specifically, at block 345 the image 500 may be displayed along with the overlay regions 604 and any relocation indicators arising from the method 1000. Turning to FIG 11, the image 500 and overlay regions 604 are illustrated, along with a relocation indicator 1100 suggesting a swap of the items 112- 1 and 112-6. If such a swap is executed, subsequent performances of the method 300 enable the server 101 to assess the impact of such a swap on the performance metrics of the items 112-1 and 112-6.

[0071] In other examples, the generation of relocation indicators via the method 1000 may operate on groups of items 112, rather than individual items 112 as described above. For example, at block 1010 the first item selected can instead be selected support surface 117 or 417, containing a group of items 112. The selection at block 1015 therefore includes a second support surface 117 or 417, and the performance metrics compared at block 1020 can include the combined performance metrics for all items 112 on each of the first and second support surfaces. [0072] In other examples, the first selected item can instead include a selected module 110 or 410, and the second selected item can include a second module 110 or 410, such that the performance metrics compared at block 1020 include the combined performance metrics of all items 112 on the selected modules 110 or 410. The relocation indicators generated via the method 1000 can therefore identify pairs of support surfaces, or pairs of modules, to swap (including all items 112 thereon), rather than pairs of individual items 112. First and second groups of items 112 selected for comparison via the method 1000 can also include categories of items 112, which may be specified in metadata associated with the items 112 in the repository 123.

[0073] Variations to the above systems and methods are contemplated. For example, at block 305, in addition to the image 500 the server 101 can receive a selection of an area on which to operate. That is, the image 500 may cover a portion of the facility, and the server 101 may receive a selection corresponding to a smaller portion within that portion. In such examples, the server 101 may restrict the remainder of the method 300 to the items 112 within the selected area.

[0074] In some examples, as will be apparent to those skilled in the art, an item 112 may be out of stock when an image is captured. In such examples, to avoid the omission of the relevant item 112 from the processing of the method 300, the server 101 can determine, e.g. at block 310, whether any out of stock (OOS) detections are associated with the image obtained at block 305. When an OOS detection is obtained along with the item detections 312, the server 101 generates a item region for the OOS item based on historical data indicating the location of the item (i.e. from an earlier performance of the method 300). Further, in such examples the server 101 can alter the image 500 prior to display at block 345, e.g. by replacing the portion of the image within the item region 502 with a corresponding portion of an earlier image in which the item 112 is present.

[0075] In further examples, the generation of item overlays at block 330 can include the generation of a plurality of overlays for each item 112. For example, the server 101 can be configured to generate a set of overlays for adjacent one-week periods (or any other suitable time period), rather than a single time period as discussed above. That is, the server 101 can retrieve and encode a performance metric for the item 112 for each of a series of contiguous weeks, months, or the like. A separate overlay may then be generated at block 330 for each encoded performance metric. Together, the series of overlays illustrate the variations in performance metrics associated with that item over time.

[0076] The server 101 can, at block 345, present the above-mentioned series of overlays in various ways. For example, the server 101 can present an animation containing the series of overlays for each item 112 in the image. For example, the overlays generated for a given time period (e.g. a week) may be presented for a predefined number of video frames, followed by a further predefined number of frames displaying the overlays for the subsequent period of time (e.g. the following week), and so on.

[0077] FIG. 12 illustrates a series of three sets of overlays 1200a, 1200b, and 1200c, corresponding to encoded performance metrics for the items 112 for three successive periods of time (e.g. equal periods, such as successive weeks). The sets 1200 may be presented at block 345 in an animation, for example. As seen in FIG. 12, all but one of the overlays remain unchanged over the successive time periods. The overlays 604-3a, 604-3b, and 604-3 c, however, illustrate a decreasing performance metric associated with the underlying item 112.

[0078] In other examples, the server 101 may generate an additional overlay for each item 112, representing a rate of change of the performance metrics discussed above. That is, a rate of change in the performance metric obtained via successive performances of block 320 can be computed and encoded at block 325. For example, a positive or flat (i.e. zero) rate of change may be encoded as a first visual identifier, while a negative rate of change may be encoded as a second visual identifier. Additional visual identifiers may also be employed for more granular representations of the rate of change. The additional overlay can be presented at block 345, in addition to or instead of the overlays discussed earlier.

[0079] Turning to FIG. 13, an example set of overlays 1300 is shown, in which each overlay illustrates the rate of change in performance metrics over the series from FIG. 12. That is, the overlays 1300 depict a performance metric trend over time (e.g. an occupancy trend), derived via the performance of the method 300. Thus, while all but one of the overlays 1300 employs a first visual identifier, indicating no change or positive change in this example, the overlay 1304-3 employs a second visual identifier, indicating a negative rate of change.

[0080] As will now be apparent to those skilled in the art, the system 100 as described above provides a technical improvement by way of processing image sensor data to determine accurate item locations, from which it computes and displays performance metrics for item location optimization, such as occupancy over time, item relocation indicators, as well as the above-mentioned heat maps.

[0081] In the foregoing specification, specific embodiments have been described. However, one of ordinary skill in the art appreciates that various modifications and changes can be made without departing from the scope of the invention as set forth in the claims below. Accordingly, the specification and figures are to be regarded in an illustrative rather than a restrictive sense, and all such modifications are intended to be included within the scope of present teachings.

[0082] The benefits, advantages, solutions to problems, and any element(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential features or elements of any or all the claims. The invention is defined solely by the appended claims including any amendments made during the pendency of this application and all equivalents of those claims as issued.

[0083] Moreover in this document, relational terms such as first and second, top and bottom, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," “has”, “having,” “includes”, “including,” “contains”, “containing” or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises, has, includes, contains a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by “comprises ...a”, “has ...a”, “includes ...a”, “contains ...a” does not, without more constraints, preclude the existence of additional identical elements in the process, method, article, or apparatus that comprises, has, includes, contains the element. The terms “a” and “an” are defined as one or more unless explicitly stated otherwise herein. The terms “substantially”, “essentially”, “approximately”, “about” or any other version thereof, are defined as being close to as understood by one of ordinary skill in the art, and in one non-limiting embodiment the term is defined to be within 10%, in another embodiment within 5%, in another embodiment within 1% and in another embodiment within 0.5%. The term “coupled” as used herein is defined as connected, although not necessarily directly and not necessarily mechanically. A device or structure that is “configured” in a certain way is configured in at least that way, but may also be configured in ways that are not listed.

[0084] It will be appreciated that some embodiments may be comprised of one or more specialized processors (or “processing devices”) such as microprocessors, digital signal processors, customized processors and field programmable gate arrays (FPGAs) and unique stored program instructions (including both software and firmware) that control the one or more processors to implement, in conjunction with certain non-processor circuits, some, most, or all of the functions of the method and/or apparatus described herein. Alternatively, some or all functions could be implemented by a state machine that has no stored program instructions, or in one or more application specific integrated circuits (ASICs), in which each function or some combinations of certain of the functions are implemented as custom logic. Of course, a combination of the two approaches could be used.

[0085] Moreover, an embodiment can be implemented as a computer-readable storage medium having computer readable code stored thereon for programming a computer (e.g., comprising a processor) to perform a method as described and claimed herein. Examples of such computer-readable storage mediums include, but are not limited to, a hard disk, a CD-ROM, an optical storage device, a magnetic storage device, a ROM (Read Only Memory), a PROM (Programmable Read Only Memory), an EPROM (Erasable Programmable Read Only Memory), an EEPROM (Electrically Erasable Programmable Read Only Memory) and a Flash memory. Further, it is expected that one of ordinary skill, notwithstanding possibly significant effort and many design choices motivated by, for example, available time, current technology, and economic considerations, when guided by the concepts and principles disclosed herein will be readily capable of generating such software instructions and programs and ICs with minimal experimentation. [0086] The Abstract of the Disclosure is provided to allow the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, it can be seen that various features are grouped together in various embodiments for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separately claimed subject matter.