US20210272316A1 - Method, System and Apparatus for Object Detection in Point Clouds - Google Patents

Abstract

A method of detecting objects on a support structure includes: obtaining a point cloud of the support structure supporting an object; obtaining a position of a back of the support structure in the point cloud; discarding a portion of the point cloud based on the position of the back of the support structure; generating a three-dimensional occupancy grid from the point cloud, the occupancy grid having a plurality of cells each indicating whether the cell is one of occupied and unoccupied; identifying a contiguous region of occupied cells in the occupancy grid corresponding to the object; and generating a detected object position based on the contiguous region.

Description

BACKGROUND
• Environments in which inventories of objects are managed, such as products for purchase in a retail environment, may be complex and fluid. For example, a given environment may contain a wide variety of objects with different attributes (size, shape, price and the like). Further, the placement and quantity of the objects in the environment may change frequently. Still further, imaging conditions such as lighting may be variable both over time and at different locations in the environment. These factors may reduce the accuracy with which such objects can be detected in data captured within the environment.
BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS
• 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.
• FIG. 1 is a schematic of a mobile automation system.
• FIG. 2A depicts a mobile automation apparatus in the system ofFIG. 1.
• FIG. 2B is a block diagram of certain internal hardware components of the mobile automation apparatus in the system ofFIG. 1.
• FIG. 3 is a flowchart of a method for detecting objects in a point cloud.
• FIG. 4A is a diagram illustrating data obtained atblock305 of the method ofFIG. 3.
• FIG. 4B is a diagram illustrating the transformation of the data obtained atblock305 of the method ofFIG. 3 to a secondary frame of reference.
• FIG. 5A is a diagram illustrating the removal of a portion of the point cloud atblock315 of the method ofFIG. 3
• FIGS. 5B and 6A-6B are diagrams illustrating the generation of an occupancy grid atblock320 of the method ofFIG. 3.
• FIG. 7 is a diagram illustrating contiguous sub-regions identified in the occupancy grid atblock330 of the method ofFIG. 3.
• FIGS. 8 and 9A are diagrams illustrating the performance of blocks340-350 of the method ofFIG. 3.
• FIG. 9B is a diagram illustrating detected object positions generated atblock355 of the method ofFIG. 3.
• FIG. 10 is a diagram illustrating the segmentation of a point cloud prior to object detection.
• 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.
• 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
• Examples disclosed herein are directed to a method of detecting objects on a support structure, the method comprising: obtaining a point cloud of the support structure supporting an object; obtaining a position of a back of the support structure in the point cloud; discarding a portion of the point cloud based on the position of the back of the support structure; generating a three-dimensional occupancy grid from the point cloud, the occupancy grid having a plurality of cells each indicating whether the cell is one of occupied and unoccupied; identifying a contiguous region of occupied cells in the occupancy grid corresponding to the object; and generating a detected object position based on the contiguous region.
• Additional examples disclosed herein are directed to a computing device for detecting objects on a support structure, comprising: a memory storing (i) a point cloud of the support structure supporting an object, and (ii) a position of a back of the support structure in the point cloud; an imaging controller connected to the memory, the imaging controller configured to: retrieve, from the memory, the point cloud and the position of the back of the support structure in the point cloud; discard a portion of the point cloud based on the position of the back of the support structure; generate a three-dimensional occupancy grid from the point cloud, the occupancy grid having a plurality of cells each indicating whether the cell is one of occupied and unoccupied; identify a contiguous region of occupied cells in the occupancy grid corresponding to the object; and generate a detected object position based on the contiguous region.
• Further examples disclosed herein are directed to a non-transitory computer-readable medium storing a plurality of computer-readable instructions executable by a processor of a computing device, wherein execution of the instructions configures the computing device to: obtain a point cloud of a support structure supporting an object; obtain a position of a back of the support structure in the point cloud; discard a portion of the point cloud based on the position of the back of the support structure; generate a three-dimensional occupancy grid from the point cloud, the occupancy grid having a plurality of cells each indicating whether the cell is one of occupied and unoccupied; identify a contiguous region of occupied cells in the occupancy grid corresponding to the object; and generate a detected object position based on the contiguous region.
• FIG. 1 depicts amobile automation system100 in accordance with the teachings of this disclosure. Thesystem100 is illustrated as being deployed in a retail environment, but in other embodiments can be deployed in a variety of other environments, including warehouses, hospitals, and the like. Thesystem100 includes aserver101 in communication with at least one mobile automation apparatus103 (also referred to herein simply as the apparatus103) and at least oneclient computing device105 viacommunication links107, illustrated in the present example as including wireless links. In the present example, thelinks107 are provided by a wireless local area network (WLAN) deployed within the retail environment by one or more access points (not shown). In other examples, theserver101, theclient device105, or both, are located outside the retail environment, and thelinks107 therefore include wide-area networks such as the Internet, mobile networks, and the like. Thesystem100 also includes adock108 for theapparatus103 in the present example. Thedock108 is in communication with theserver101 via alink109 that in the present example is a wired link. In other examples, however, thelink109 is a wireless link.
• Theclient computing device105 is illustrated inFIG. 1 as a mobile computing device, such as a tablet, smart phone or the like. In other examples, theclient device105 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. Thesystem100 can include a plurality ofclient devices105 in communication with theserver101 viarespective links107.
• Thesystem100 is deployed, in the illustrated example, in a retail environment including a plurality of support structures such as shelf modules110-1,110-2,110-3 and so on (collectively referred to as shelves110, and generically referred to as a shelf110—this nomenclature is also employed for other elements discussed herein). In other examples, additional types of support structures may also be present, such as pegboards. Each shelf module110 supports a plurality ofproducts112. Each shelf module110 includes a shelf back116-1,116-2,116-3 and a support surface (e.g. support surface117-3 as illustrated inFIG. 1) extending from the shelf back116 to a shelf edge118-1,118-2,118-3.
• The shelf modules110 are typically arranged in a plurality of aisles, each of which includes a plurality of modules110 aligned end-to-end. In such arrangements, the shelf edges118 face into the aisles, through which customers in the retail environment as well as theapparatus103 may travel. As will be apparent fromFIG. 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 surfaces117) refers to a surface bounded by adjacent surfaces having different angles of inclination. In the example illustrated inFIG. 1, the shelf edge118-3 is at an angle of about ninety degrees relative to each of the support surface117-3 and the underside (not shown) of the support surface117-3. In other examples, the angles between the shelf edge118-3 and the adjacent surfaces, such as the support surface117-3, is more or less than ninety degrees. The shelf edges118 define a front of the shelves110, separated from the shelf backs116 by a shelf depth. A common frame ofreference102 is illustrated inFIG. 1. In the present example, the shelf depth is defined in the Y dimension of the frame ofreference102, while the shelf backs116 and shelf edges118 are shown as being parallel to the XZ plane.
• Theapparatus103 is deployed within the retail environment, and communicates with the server101 (e.g. via the link107) to navigate, autonomously or partially autonomously, along a length119 (illustrated inFIG. 1 as being parallel to the X axis of the frame of reference102) of at least a portion of the shelves110. Theapparatus103, autonomously or in conjunction with theserver101, is configured to continuously determine its location within the environment, for example with respect to a map of the environment. Theapparatus103 may also be configured to update the map (e.g. via a simultaneous mapping and localization, or SLAM, process).
• Theapparatus103 is equipped with a plurality of navigation anddata capture sensors104, 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). Theapparatus103 can be configured to employ thesensors104 to both navigate among the shelves110 (e.g. according to the paths mentioned above) and to capture shelf data, such as point cloud and image data, during such navigation.
• Theserver101 includes a special purpose imaging controller, such as aprocessor120, specifically designed to control and/or assist themobile automation apparatus103 to navigate the environment and to capture data. Theprocessor120 can be further configured to obtain the captured data via acommunications interface124 for storage in arepository132 and subsequent processing (e.g. to detect objects such as shelvedproducts112 in the captured data, and detect status information corresponding to the objects). Theserver101 may also be configured to transmit status notifications (e.g. notifications indicating that products are out-of-stock, low stock or misplaced) to theclient device105 responsive to the determination of product status data. Theclient device105 includes one or more controllers (e.g. central processing units (CPUs) and/or field-programmable gate arrays (FPGAs) and the like) configured to process (e.g. to display) notifications received from theserver101.
• Theprocessor120 is interconnected with a non-transitory computer readable storage medium, such as the above-mentionedmemory122, having stored thereon computer readable instructions for performing various functionality, including control of theapparatus103 to capture shelf data, post-processing of the shelf data, and generating and providing certain navigational data to theapparatus103, such as target locations at which to capture shelf data. Thememory122 includes a combination of volatile (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). Theprocessor120 and thememory122 each comprise one or more integrated circuits. In some embodiments, theprocessor120 is implemented as one or more central processing units (CPUs) and/or graphics processing units (GPUs).
• Theserver101 also includes the above-mentionedcommunications interface124 interconnected with theprocessor120. Thecommunications interface124 includes suitable hardware (e.g. transmitters, receivers, network interface controllers and the like) allowing theserver101 to communicate with other computing devices—particularly theapparatus103, theclient device105 and thedock108—via thelinks107 and109. Thelinks107 and109 may be direct links, or links that traverse one or more networks, including both local and wide-area networks. The specific components of thecommunications interface124 are selected based on the type of network or other links that theserver101 is required to communicate over. In the present example, as noted earlier, a wireless local-area network is implemented within the retail environment via the deployment of one or more wireless access points. Thelinks107 therefore include either or both wireless links between theapparatus103 and themobile device105 and the above-mentioned access points, and a wired link (e.g. an Ethernet-based link) between theserver101 and the access point.
• Thememory122 stores a plurality of applications, each including a plurality of computer readable instructions executable by theprocessor120. The execution of the above-mentioned instructions by theprocessor120 configures theserver101 to perform various actions discussed herein. The applications stored in thememory122 include an object detection application128 (also referred to herein as the application128), which may also be implemented as a suite of logically distinct applications. In general, via execution of theapplication128 or subcomponents thereof and in conjunction with the other components of theserver101, theprocessor120 is configured to implement various functionality related to obtaining captured data from theapparatus103 and performing various post-processing operations on the captured data. In the present example, as discussed below in greater detail, execution of theapplication128 configures theserver101 to detect objects (e.g. the products112) on the shelves110 from point cloud data, such as a point cloud generated from data captured by theapparatus103.
• Theprocessor120, as configured via the execution of thecontrol application128, is also referred to herein as the above-mentionedimaging controller120. As will now be apparent, some or all of the functionality implemented by thecontroller120 described below may also be performed by preconfigured special purpose hardware controllers (e.g. one or more FPGAs and/or Application-Specific Integrated Circuits (ASICs) having logic circuit arrangements configured to enhance the processing speed of imaging computations) rather than by execution of theapplication128 by theprocessor120.
• Turning now toFIGS. 2A and 2B, themobile automation apparatus103 is shown in greater detail. Theapparatus103 includes achassis201 containing a locomotive mechanism203 (e.g. one or more electrical motors driving wheels, tracks or the like). Theapparatus103 further includes asensor mast205 supported on thechassis201 and, in the present example, extending upwards (e.g., substantially vertically) from thechassis201. Themast205 supports thesensors104 mentioned earlier. In particular, thesensors104 include at least oneimaging sensor207, such as a digital camera, as well as at least onedepth sensor209, such as a 3D digital camera. Theapparatus103 also includes additional depth sensors, such asLIDAR sensors211. In other examples, theapparatus103 includes additional sensors, such as one or more RFID readers, temperature sensors, and the like.
• In the present example, themast205 supports seven digital cameras207-1 through207-7, and two LIDAR sensors211-1 and211-2. Themast205 also supports a plurality ofillumination assemblies213, configured to illuminate the fields of view of therespective cameras207. That is, the illumination assembly213-1 illuminates the field of view of the camera207-1, and so on. Thesensors207 and211 are oriented on themast205 such that the fields of view of each sensor face a shelf110 along thelength119 of which theapparatus103 is travelling. Theapparatus103 is configured to track a location of the apparatus103 (e.g. a location of the center of the chassis201) in the common frame ofreference102 previously established in the retail facility, permitting data captured by themobile automation apparatus103 to be registered to the common frame of reference.
• Themobile automation apparatus103 includes a special-purpose controller, such as aprocessor220, as shown inFIG. 2B, interconnected with a non-transitory computer readable storage medium, such as amemory222. Thememory222 includes a combination of volatile (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). Theprocessor220 and thememory222 each comprise one or more integrated circuits. Thememory222 stores computer readable instructions for execution by theprocessor220. In particular, thememory222 stores acontrol application228 which, when executed by theprocessor220, configures theprocessor220 to perform various functions related to the navigation of theapparatus103 and capture of data for subsequent processing, e.g. by theserver101. In some embodiments, such subsequent processing can be performed by theapparatus103 itself via execution of theapplication228. Theapplication228 may also be implemented as a suite of distinct applications in other examples.
• Theprocessor220, when so configured by the execution of theapplication228, may also be referred to as animaging controller220. Those skilled in the art will appreciate that the functionality implemented by theprocessor220 via the execution of theapplication228 may also be implemented by one or more specially designed hardware and firmware components, such as FPGAs, ASICs and the like having logic circuit arrangements configured to enhance the processing speed of navigational and/or imaging computations in other embodiments.
• Thememory222 may also store arepository232 containing, for example, one or more maps representing the environment in which theapparatus103 operates, for use during the execution of theapplication228. Theapparatus103 may communicate with theserver101, for example to receive instructions to navigate to specified locations and initiate data capture operations, via acommunications interface224 over thelink107 shown inFIG. 1. Thecommunications interface224 also enables theapparatus103 to communicate with theserver101 via thedock108 and thelink109.
• As will be apparent in the discussion below, other examples, some or all of the processing performed by theserver101 may be performed by theapparatus103, and some or all of the processing performed by theapparatus103 may be performed by theserver101. That is, although in the illustrated example theapplication128 resides in theserver101, in other embodiments some or all of the actions described below to detect objects on the shelves110 from captured data may be performed by theprocessor220 of theapparatus103, either in conjunction with or independently from theprocessor120 of theserver101. As those of skill in the art will realize, distribution of such computations between theserver101 and themobile automation apparatus103 may depend upon respective processing speeds of theprocessors120 and220, the quality and bandwidth of thelink107, as well as criticality level of the underlying instruction(s).
• The functionality of theapplication128 will now be described in greater detail. In particular, the detection of objects on the shelves110 (or other suitable support structures) will be described as performed by theserver101. Turning toFIG. 3, amethod300 of detecting objects is shown. Themethod300 will be described in conjunction with its performance by theserver101, with reference to the components illustrated inFIG. 1.
• Atblock305, theserver101 is configured to obtain a point cloud of the support structure, as well as a plane definition corresponding to the front of the support structure. In the present example, in which the support structures are shelves such as the shelves110 shown inFIG. 1, the point cloud obtained atblock305 therefore represents at least a portion of a shelf module110 (and may represent a plurality of shelf modules110), and the plane definition corresponds to a shelf plane that corresponds to the front of the shelf modules110. In other words, the plane definition defines a plane that contains the shelf edges118.
• The point cloud and plane definition obtained atblock305 can be retrieved from therepository132. For example, theserver101 may have previously received captured data from theapparatus103 including a plurality of lidar scans of the shelf modules110, and generated a point cloud from the lidar scans. Each point in the point cloud represents a point on a surface of the shelves110,products112, and the like (e.g. a point that the scan line of alidar sensor211 impacted), and is defined by a set of coordinates (X, Y and Z) in the frame ofreference102. The plane definition may also be previously generated by theserver101 and stored in therepository132, for example from the above-mentioned point cloud. For example, theserver101 can be configured to process the point cloud, the raw lidar data, image data captured by thecameras207, or a combination thereof, to identify shelf edges118 according to predefined characteristics of the shelf edges118. Examples of such characteristics include that the shelf edges118 are likely to be substantially planar, and are also likely to be closer to theapparatus103 as theapparatus103 travels thelength119 of a shelf module110) than other objects (such as the shelf backs116 and products112). The plane definition can be obtained in a variety of suitable formats, such as a suitable set of parameters defining the plane. An example of such parameters includes a normal vector (i.e. a vector defined according to the frame ofreference102 that is perpendicular to the plane) and a displacement (indicating the distance along the normal vector from the origin of the frame ofreference102 to the plane).
• Atblock305 theserver101 is also configured to obtain a depth of the back116 of the shelf110, also referred to herein as the shelf depth. The shelf depth may be determined previously at theserver101 and therefore retrieved from therepository132. The shelf depth can be determined, for example, by processing the point cloud, images of the shelf110, or a combination thereof, to identify portions of the point cloud that are likely to correspond to the shelf back116. An example of such processing includes decomposing an image of the shelf110 into patches, and classifying each patch as depicting the shelf back116 or not according to a similarity between the patch and a reference image of the shelf back116. Theserver101 can then be configured to identify points in the point cloud that correspond to the patches classified as depicting the shelf back116, and to average the depth of such points to determine the shelf depth.
• Further, atblock305 theserver101 is configured to obtain shelf edge positions. The shelf edge positions can be determined previously by the server (e.g. based on the characteristics noted above), and retrieved from therepository132 atblock305. Shelf edge positions can be defined as bounding boxes in the frame ofreference102, relative to the plane definition, or the like.
• Referring toFIG. 4A, apoint cloud400 is illustrated, depicting the shelf module110-3. The shelf back116-3, the shelf117-3 and the shelf edge118-3 are therefore represented in thepoint cloud400, as are theproducts112. Also shown inFIG. 4A is aplane definition404 corresponding to the front of the shelf module110-3 (that is, theplane definition404 contains the shelf edges118-3).FIG. 4A also illustrates the remaining inputs obtained atblock305, including ashelf depth408 and shelf edge positions412-1 and412-2 (shown as bounding boxes overlaid on the portions of thepoint cloud400 representing shelf edges118).
• Thepoint cloud400,plane definition404,shelf depth408 and shelf edge positions412 need not be obtained in the graphical forms shown inFIG. 4A. As will be apparent to those skilled in the art, the point cloud may be obtained as a list of coordinates. Theplane definition404 can be obtained as the above-mentioned parameters defining a normal vector and displacement. Theshelf depth408 can be obtained as a scalar quantity, a vector, or the like, and the shelf edge positions412 can be obtained as sets of coordinates (e.g. in the frame of reference102) defining the corners of the bounding boxes shown inFIG. 4A.
• Returning toFIG. 3, atblock310 theserver101 can be configured to transform thepoint cloud400 to a secondary frame of reference based on theshelf plane404. As shown inFIG. 4B, a transformedpoint cloud400′ in shown, in which the coordinates of each point of thepoint cloud400′ are expressed in a secondary frame ofreference416. The secondary frame ofreference416 has an origin on theplane404 and thus, for each point in the point cloud, defines a planar position (in the X and Z dimensions, in the illustrated example) on theshelf plane404 as well as a depth (in the Y dimension as illustrated) orthogonal to theshelf plane404.Block310 may reduce the computational load imposed by the remaining blocks of themethod300. However, in other embodiments, block310 can be omitted.
• Referring again toFIG. 3, atblock315, theserver101 is configured to discard a portion of the point cloud based on the position of the shelf back116, as defined by theshelf depth408. For example, theserver101 can be configured to discard any points in the point cloud with depths equal to or greater than theshelf depth408. In other examples theserver101 is configured to discard any points in the point cloud with depths that are within a threshold (e.g. 10% below or above the shelf depth408) of theshelf depth408. Turning briefly toFIG. 5A, a further modifiedpoint cloud500 is illustrated following the performance ofblock310, at which the points corresponding to the shelf back116-3 were discarded.
• Atblock320, theserver101 is configured to generate a three-dimensional occupancy grid from the point cloud as modified atblocks305 and310 (i.e. thepoint cloud500, in the present example). The occupancy grid defines a plurality of cells, arranged according to the frame ofreference416. Anexample grid502 is shown inFIG. 5B. In particular, thecells504 of thegrid502 are arranged in depthwise layers or slices, as will be discussed below in greater detail. As also seen inFIG. 5B, in the present example, thecells504 have a lower resolution than thepoint cloud500. That is, eachcell504 represents a larger portion of the shelf module110-3 than each point in the point cloud. For example, the point cloud may include points spaced apart by about 2 mm, while eachcell504 may have dimensions of about 2 cm×2 cm×2 cm. As will be apparent to those skilled in the art, a wide variety of other dimensions may also be employed for thepoint cloud500 and thecells504.
• Theoccupancy grid502 is generated by assigning each point of the point cloud to one of the cells504 (specifically, to the cell encompassing a volume on the shelf module110 that contains that point). Eachcell504 is then assigned a value indicating that the cell is either occupied (if any points were assigned to the cell504) or unoccupied (if no points were assigned to the cell504). In addition, theserver101 can be configured to store the assignment of points tocells504, for example in the form of a list of points with a cell identifier corresponding to each point. The generation of the occupancy grid will be described below, for aportion508 of thepoint cloud500, as indicated inFIG. 5B
• Turning toFIG. 6A, theportion508 of thepoint cloud500 is shown in isolation, along with three layers600-1,600-2 and600-3 of thegrid502. To generate the first layer600-1, theserver101 is configured to determine, for eachcell504 in the layer600-1, whether thecell504 contains any points from thepoint cloud500. Thus, anexample cell504ais assigned an occupied value (e.g. a value of one) because thecell504acontains points corresponding to aproduct112. Anotherexample cell504b,on the other hand, is assigned an unoccupied value because thecell504bdoes not contain any points in the point cloud500 (that is, the volume contained within thecell504bis empty).
• FIG. 6B illustrates, in two dimensions, each layer600 mentioned above in thegrid502. In particular, in the illustrated example, cells assigned an occupied value are illustrated in white, while cells assigned an unoccupied value are illustrated in black. As will be apparent, other values may also be selected to indicate that a cell is occupied or unoccupied. Thecell504amentioned in connection withFIG. 6A is occupied, while thecell504bis unoccupied.
• In the present example, theserver101 is configured, upon setting the value of a cell to “occupied”, to automatically set the value of every cell with the same planar position (i.e. in the and Z dimension) but a greater depth (in the Y dimension) to unoccupied, whether or not those cells contain points of thepoint cloud500. Thus, in the layers600-2 and600-3, the cells at the same planar position as thecell504abut at greater depths are assigned unoccupied values, even though they may contain points corresponding to aproduct112. As also seen inFIG. 6B, the layers600-1,600-2 and600-3 each contain occupied cells corresponding to different portions of thecylindrical product112. Further, the layer600-1 contains occupied cells that correspond to the shelf edge118-3.
• Returning toFIG. 3, atblock325 theserver101 is configured to discard, e.g. by setting cell values to unoccupied, any cells corresponding to the shelf edge positions412-1 and412-2. For example, theserver101 can be configured to identify any cells (e.g. at any depth) having the same planar positions (i.e. in the XZ plane) as the shelf edge positions412, and to update the values of such cells to unoccupied. Thus, returning toFIG. 6B, theserver101 is configured to update the layer600-1 of the grid to generate a later600-1′ in which the cells coinciding with the shelf edge position412-2 are set to unoccupied. Updated versions of the layers600-2 and600-3 may also be generated, but their content is identical to the layers600-2 and600-3 as shown inFIG. 6B. In other embodiments, the performance ofblock325 may be delayed until later in themethod300, as will be discussed below.
• Following the performance ofblock325, theserver101 is configured to detect contiguous regions in theoccupancy grid502. Each contiguous region so detected corresponds to an object, such as aproduct112. In the present example, theserver101 is configured to detect contiguous regions beginning atblock330. Atblock330, theserver101 is configured to select a layer of the grid502 (e.g. the layer closest to the shelf plane404), and to detect contiguous sub-regions in the selected layer. Atblock335, theserver101 is configured to determine whether any layers remain to be processed. When the determination atblock335 is affirmative, the next layer600 is selected and contiguous sub-regions detected, atblock330. When the determination atblock335 is negative, the performance of themethod300 proceeds to block340.
• Referring toFIG. 7, three sets of contiguous sub-regions are illustrated, arising from three performances of block330 (for each of the layers600-1,600-2 and600-3). In particular, a first set of contiguous sub-regions700-1 and700-2 are identified in the layer600-1. A second set of contiguous sub-regions704-1 and704-2 are identified in the layer600-2, and a third set of contiguous sub-regions708-1 and708-2 are identified in the layer600-3. Identification of contiguous sub-regions700,704,708 and the like can be implemented via a suitable blob extraction (also referred to as connected-component analysis) algorithm. In general, the detection of contiguous sub-regions is configured to detect regions of cells in each layer600 with the same value. More specifically, in the present example theserver101 is configured to identify regions of cells in each layer600 with “occupied” values.
• Atblock340, following a negative determination atblock335, theserver101 is configured to continue the identification of contiguous regions by determining, for each sub-region detected atblock330, whether any adjacent layers600 (to the layer containing the current sub-region) contain abutting sub-regions. As noted in connection withFIG. 6B and as seen inFIG. 7, certain objects (e.g. thecylindrical product112 shown inFIG. 6A), particularly those with surfaces that are not parallel to theshelf plane404, appear segmented between layers600 of thegrid502, and may therefore be represented by a plurality of sub-regions. In other words, atblock340, theserver101 is configured to determine whether any sub-regions detected through one or more performances of blocks330-335 correspond to a single object.
• Turning toFIG. 8, the determination atblock340 for a selected sub-region includes determining whether the planar position of the selected sub-region and the planar position of another sub-region in an adjacent layer600 of thegrid502 abut each other. For example, beginning with the sub-region700-2, which resides in the layer600-1, theserver101 is configured to determine whether the sub-region700-2 shares a boundary in the XZ plane of the frame ofreference416 with a boundary of any sub-region in the layer600-2 (which is adjacent in depth to the layer600-1). In the present example, the determination is affirmative for both the sub-regions704-1 and704-2 in the layer600-2. Theserver101 is therefore configured, atblock345, to merge the sub-regions700-2,704-1 and704-2, e.g. by assigning a common region identifier to all three sub-regions.
• Atblock350, theserver101 is configured to determine whether any sub-regions remain to be assessed via a further performance ofblock340. In the present example, the determination is affirmative, and block340 is repeated, for example by selecting the sub-region700-1. As there are no sub-regions in the layer600-2 with planar positions abutting the planar position of the sub-region700-1, the determination atblock340 is negative.
• In a further example performance ofblock340, theserver101 may be configured to select the sub-region704-1 of the layer600-2. As is evident inFIG. 8, the boundary of the sub-region708-1 (in the layer600-3) coincides with the boundary of the sub-region704-1 in the XZ plane. The determination atblock340 is therefore affirmative, and the sub-regions704-1 and708-1 are merged (i.e. assigned the same region identifier). As will now be apparent, repeated performances ofblock340,345 and350 result in the sub-regions700-2,704-1,704-2,708-1 and708-2 being merged and assigned one region identifier, and in the sub-region700-1 assigned another region identifier. In other words, following a negative determination at block350 (i.e. when all sub-regions have been assessed via block340), twocontiguous regions800 and804 have been detected within thegrid502.FIG. 9A illustrates thecontiguous regions800 and804 in an overhead view.
• Atblock355, theserver101 is configured to generate detected object positions based on the contiguous regions detected at blocks330-350. For each detected contiguous region, theserver101 is configured to generate one detected object position. Various forms of object position are contemplated. In the present example, as illustrated inFIG. 9B, the detected object positions are generated as bounding boxes containing the volumes encompassed by the cells of the corresponding contiguous regions. Thus, afirst bounding box900 is generated from thecontiguous region800, and asecond bounding box904 is generated from thecontiguous region804.
• In other examples, the detected object positions can be generated as the centroids of each contiguous region (e.g. a single point in the frame of reference416). In further examples, the above-mentioned bounding boxes can be generated based on thepoint cloud500 rather than based directly on thecontiguous regions800 and804. For example, as noted above, the allocation of points to the cells of theoccupancy grid502 can be stored in thememory122. Atblock355, for each contiguous region the points associated with the cells of that contiguous region are retrieved from thememory122 and a bounding box is fitted to the retrieved cells.
• The detected object positions generated atblock355 can be stored in the memory122 (e.g. in the repository132), and can also be transmitted to a further computing device such as theclient device105, e.g. for presentation on a display thereof. The detected object positions generated atblock355 may also be employed by theserver101 itself or by another computing device for the detection of gaps betweenproducts112. For example, theserver101 can be configured to retrieve label positions on the shelf edges118, indicating the expected position forproducts112, and to determine whether a detected object position was generated in association with each label position (e.g. above each label position, indicating the presence of aproduct112 above the corresponding label). Any label positions without corresponding detected object positions may be detected as gaps (e.g. out of stock products112) by theserver101.
• Variations to the above systems and methods are contemplated. For example, as noted earlier, in some embodiments, block325 may be performed following a negative determination at block335 (i.e. betweenblocks335 and340). In such embodiments, the presence of occupied cells corresponding to shelf edges may lead to the detection of a single contiguous sub-region that in fact corresponds to distinct objects as a result of the shelf edge extending between the portions of the sub-region corresponding to each object. Responsive to discarding cells corresponding to the shelf edges118, theserver101 may therefore be configured to relabel remaining sub-regions where such sub-regions have been separated (i.e. are no longer contiguous).
• In further embodiments, theserver101 can be configured, prior to the performance ofblock310, to segment the point cloud obtained atblock305. Specifically, referring toFIG. 10, anexample point cloud1000 obtained atblock305 is shown. Thepoint cloud1000 represents two distinct shelf modules, separated by amodule boundary1004. Theserver101 can be configured, in such embodiments, to retrieve module boundary positions (e.g. in the frame of reference102) from therepository132, or to detect themodule boundary1004, for example via image gradients or the like, and to segment thepoint cloud1000 into first and second segments1008-1 and1008-2. Theserver101 can then be configured to perform the remainder of themethod300 separately for each segment1008.
• 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.
• 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.
• 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.
• 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.
• 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.
• 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.

Claims (20)

1. A method of detecting objects on a support structure, the method comprising:

obtaining a point cloud of the support structure supporting an object;

obtaining a position of a back of the support structure in the point cloud;

discarding a portion of the point cloud based on the position of the back of the support structure;

generating a three-dimensional occupancy grid from the point cloud, the occupancy grid having a plurality of cells each indicating whether the cell is one of occupied and unoccupied;

identifying a contiguous region of occupied cells in the occupancy grid corresponding to the object; and

generating a detected object position based on the contiguous region.

2. The method ofclaim 1, wherein the detected object positions comprises a bounding box.

3. The method ofclaim 1, wherein obtaining the position of the back of the support structure includes:

obtaining (i) a plane definition corresponding to a front of the support structure, and (ii) a depth from the plane definition to the back of the support structure.

4. The method ofclaim 3, wherein discarding the portion of the point cloud at the position of the back of the support structure includes discarding points within a threshold depth matching the depth from the plane definition to the back of the support structure.

5. The method ofclaim 3, wherein the point cloud defines a plurality of points according to a common frame of reference; the method further comprising:

before discarding the portion, transforming the points from the common frame of reference to a secondary frame of reference defining, for each point, a position on the plane definition and a depth orthogonal to the plane definition.

6. The method ofclaim 5, wherein generating the occupancy grid comprises, for each position on the plane definition:

determining a first depth of a point nearest to the plane definition; and

storing, in a cell of the occupancy grid containing the point, an occupied indicator, and storing, in each cell of the occupancy grid having the position on the plane definition and a greater depth than the first depth, an unoccupied indicator.

7. The method ofclaim 6, wherein identifying the contiguous region comprises:

in a first set of cells having a first common depth, identifying a first contiguous sub-region;

in a second set of cells having a second common depth, identifying a second contiguous sub-region;

determining whether to merge the first and second contiguous sub-regions; and

when the determination is affirmative, merging the first and second contiguous sub-regions to generate the contiguous region.

8. The method ofclaim 7, wherein determining whether to merge the first and second contiguous sub-regions comprises: determining whether a first position on the plane definition of the first contiguous sub-region abuts a second position on the plane definition of the second contiguous sub-region.

9. The method ofclaim 1, further comprising:

prior to identifying the contiguous region, discarding a portion of the cells corresponding to support structure edge positions.

10. A computing device for detecting objects on a support structure, comprising:

a memory storing (i) a point cloud of the support structure supporting an object, and (ii) a position of a back of the support structure in the point cloud;

an imaging controller connected to the memory, the imaging controller configured to:

retrieve, from the memory, the point cloud and the position of the back of the support structure in the point cloud;

discard a portion of the point cloud based on the position of the back of the support structure;

generate a three-dimensional occupancy grid from the point cloud, the occupancy grid having a plurality of cells each indicating whether the cell is one of occupied and unoccupied;

identify a contiguous region of occupied cells in the occupancy grid corresponding to the object; and

generate a detected object position based on the contiguous region.

11. The computing device ofclaim 10, wherein the detected object positions comprises a bounding box.

12. The computing device ofclaim 10, wherein the imaging controller is further configured, to obtain the position of the back of the support structure, to:

retrieve from the memory (i) a plane definition corresponding to a front of the support structure, and (ii) a depth from the plane definition to the back of the support structure.

13. The computing device ofclaim 12, wherein the imaging controller is further configured, to discard the portion of the point cloud at the position of the back of the support structure, to: discard points within a threshold depth matching the depth from the plane definition to the back of the support structure.

14. The computing device ofclaim 12, wherein the point cloud defines a plurality of points according to a common frame of reference; and wherein the imaging controller is further configured to:

before discarding the portion, transform the points from the common frame of reference to a secondary frame of reference defining, for each point, a position on the plane definition and a depth orthogonal to the plane definition.

15. The computing device ofclaim 14, wherein the imaging controller is further configured, to generate the occupancy grid, to:

for each position on the plane definition:

determine a first depth of a point nearest to the plane definition; and

store, in a cell of the occupancy grid containing the point, an occupied indicator, and storing, in each cell of the occupancy grid having the position on the plane definition and a greater depth than the first depth, an unoccupied indicator.

16. The computing device ofclaim 15, wherein the imaging controller is further configured, to identify the contiguous region, to:

in a first set of cells having a first common depth, identify a first contiguous sub-region;

in a second set of cells having a second common depth, identify a second contiguous sub-region;

determine whether to merge the first and second contiguous sub-regions; and

when the determination is affirmative, merge the first and second contiguous sub-regions to generate the contiguous region.

17. The computing device ofclaim 16, wherein the imaging controller is further configured, to determine whether to merge the first and second contiguous sub-regions, to:

determine whether a first position on the plane definition of the first contiguous sub-region abuts a second position on the plane definition of the second contiguous sub-region.

18. The computing device ofclaim 10, wherein the imaging controller is further configured to:

prior to identifying the contiguous region, discard a portion of the cells corresponding to support structure edge positions.

19. A non-transitory computer-readable medium storing a plurality of computer-readable instructions executable by a processor of a computing device, wherein execution of the instructions configures the computing device to:

obtain a point cloud of a support structure supporting an object;

obtain a position of a back of the support structure in the point cloud;

discard a portion of the point cloud based on the position of the back of the support structure;

generate a three-dimensional occupancy grid from the point cloud, the occupancy grid having a plurality of cells each indicating whether the cell is one of occupied and unoccupied;

identify a contiguous region of occupied cells in the occupancy grid corresponding to the object; and

generate a detected object position based on the contiguous region.

20. The non-transitory computer-readable medium ofclaim 19, wherein the detected object positions comprises a bounding box.

Images