Abstract: A system for capturing images for training an item identification model obtains an identifier of an item. The system detects a triggering event at a platform, where the triggering event corresponds to a user placing the item on a platform. At least one camera to captures at least one image of the item. The system extracts a set of features associated with the item from the at least one image. The system associates the item to the identifier and the set of features. The system adds a new entry to a training dataset of the item identification model, where the new entry represents the item labeled with the identifier and the set of features.

Abstract: An apparatus includes a base having a platform configured for placement of one or more items on a surface of the platform, a frame coupled to the base, and a plurality of camera units coupled to the frame. Each camera unit is configured to capture images of at least a portion of the platform and the plurality of camera units includes a plurality of side-view camera units arranged above the platform along a horizontal plane, wherein each camera unit of the side-view camera units comprises two vertically stacked cameras and is configured to capture perspective images of at least a portion of the platform. An overhead-view camera unit is positioned over the platform, wherein the overhead-view camera unit comprises two cameras and is configured to capture top view images of the platform.

Abstract: A device configured to receive a rack identifier for a rack that is configured to hold items. The device is further configured to identify a master template that is associated with the rack. The device is further configured to receive images of the plurality of items on the rack and to combine the images into a composite image of the rack. The device is further configured to identify shelves on the rack within the composite image and to generate bounding boxes that correspond with an item on the rack. The device is further configured to associate each bounding box with an item identifier and an item location. The device is further configured to generate a rack analysis message based on a comparison of the item locations for each bounding box and the rack positions from the master template and to output the rack analysis message.

Abstract: A system for refining an item identification model detects a triggering event at a platform. The system captures images of the item. The system extracts a set of features from at least one of the images. The system identifies the item based on the set of features. The system receives an indication that the item is not identified correctly. The system receives an identifier of the item. The system identifies the item based on the identifier of the item. The system feeds the identifier of the item and the images to the item identification model. The system retrains the item identification model to learn to associate the item to the images. The system updates the set of features based on the determined association between the item and the images.

Abstract: In response to detecting a triggering event corresponding to placement of a first item on a platform, a plurality of images of the first item are captured. For each image of the first item, a cropped image is generated including a bounding box around the first item depicted in the image. For each cropped image, a ratio is calculated between a portion of a total area within the bounding box occupied by the first item and the total area. If the ratio equals or exceeds a minimum threshold, an item identifier associated with the first item is identified based on the cropped image. On the other hand, if the ratio is below the threshold, the cropped image is discarded. A particular item identifier is selected from a set of cropped images that were not discarded.

Abstract: A system determines an interaction period during which a fuel dispensing operation is performed at a fuel dispensing terminal. The system determines a measured volume per unit time parameter associated with fuel dispensed from the fuel dispensing terminal by dividing the determined volume for fuel by the interaction period. The system compares the measured volume per unit time parameter with a threshold volume per unit time parameter. In response to determining that the measured volume per unit time parameter is less than the threshold volume per unit time parameter, the system retrieves a video feed that shows the fuel dispensing terminal during the fuel dispensing operation. The system creates a file for the fuel dispensing operation. The system stores the video feed in the created file.

Abstract: A device detects a triggering event that corresponds to a placement of a first item on a platform. In response, the device captures an image of the first item and generates a first encoded vector for the image. The first encoded vector describes one or more attributes of the first item. The device determines a height of the first item. The device identifies one or more items in an encoded vector library that are associated with average heights within a threshold range from the determined height of the first item. The device compares the first encoded vector with a second encoded vector associated with a second item from among the one or more items. The device determines that the first encoded vector corresponds to the second encoded vector. In response, the device determines that the first item corresponds to the second item.

Abstract: A device detects a triggering event that corresponds to a placement of an item on a platform. In response, the device captures an image of the item and generates a first encoded vector for the image. The first encoded vector describes one or more attributes of the item. The device determines that the item is associated with a first container category based on the one or more attributes of the item. The device identifies one or more items that have been identified as having placed inside a container associated with the first container category. The device displays a list of item options that comprises the one or more items on a graphical user interface (GUI). The device receives a selection of a first item from along the list of item options and identifies the first item as being inside the container.

Abstract: A system for identifying items based on aggregated metadata obtains images of an item. The system extracts a set of features from images of the item. The system identifies a first value of a first feature associated with a first image of the item. The system identifies a second value of the first feature associated with a second image of the item. The system aggregates the first value and the second value. The system associates the item to the aggregated first value and the second value, where the aggregated first value and the second value represent the first feature of the item. The system adds a new entry for each image of the item to a training dataset associated with an item identification model.

Abstract: A device for object tracking receives an image from a camera, where the image shows a set of points on a calibration board placed on a platform. The device determines a pixel location array that comprises pixel locations associated with the points in the image. The device determines, by applying a first homography to the pixel location array, a calculated location array identifying calculated physical location coordinates of the set of points in the global plane. The device determines that the difference between a reference location array and the calculated location array is more than a threshold value. In response, the device determines that the camera and/or the platform has moved from a respective initial location when the first homography was determined. The device determines a second homography by multiplying an inverse of the pixel location array by the reference location array and calibrates the camera using the second homography.

Abstract: In response to detecting a triggering event corresponding to placement of a first item on a platform, a plurality of images are captured of the first item and a plurality of cropped images are generated based on the images. For each cropped image, a first encoded vector is generated and compared to encoded vectors in an encoded vector library that are tagged as a front image. Based on the comparison, a second encoded vector is selected from the encoded vector library that most closely matches with the first encoded vector. An item identifier is identified that is associated with the second encoded vector. A particular item identifier is selected that is identified for a particular cropped image.

Abstract: A system includes a plurality of racks each storing packs of cigarettes, a display device associated with each rack and a master controller coupled to the racks and the display devices. A processor of the master controller is configured to receive a first indication that a scanner has scanned a first code associated with a first rack of the plurality of racks while the scanner is in a product checking mode. In response, the processor obtains from a memory a first rack number of the first rack and a first UPC associated with the rack number based on a planogram. The processor subsequently receives a second UPC scanned by the scanner of a pack actually stored in the first rack. Based on determining that the first and second UPCs do not match, the processor transmits an alert message indicating incorrect product placement in the first rack.

Abstract: In response to detecting a first triggering event corresponding to placement of a first item on a platform, a plurality of first images are captured of the first item and a plurality of cropped first images are generated based on the first images. A first item identifier associated with the first item is identified based on the cropped first images. In response to detecting a second triggering event corresponding to placement of a second item on the platform, a plurality of second images of the first item are captured and a plurality of cropped second images are generated from the second images. In response to determining that the cropped first images match with the cropped second images, the first item identifier is assigned to the first item depicted in the second images.

Abstract: In response to detecting a triggering event corresponding to placement of a first item on a platform, a plurality of images are captured of the first item and a plurality of cropped images are generated based on the first images. An item identifier is identified based on each cropped image, wherein each item identifier is associated with a numerical similarity value. Each cropped image is further tagged as a front image or a back image. A particular item identifier identified for a corresponding cropped image tagged as a front image is selected and associated with the first item. An indicator of the particular item identifier is displayed on a user interface device.

Abstract: In response to detecting a first triggering event corresponding to placement of a first item on a platform, a plurality of first images are captured of the first item. An item identifier associated with the first item is identified based on the first images and assigned to the first item. In response to detecting a second triggering event corresponding to placement of a second item on the platform, a plurality of second images are captured of the second item, a plurality of cropped images are generated based on the second images, and a plurality of item identifiers are determined for the second item based on the cropped images. When a process for selecting a particular item identifier from the plurality of item identifiers fails, a second item identifier is assigned to the second item based on an association between the first item identifier and the second item identifier.

Abstract: A system includes a longitudinal rack storing a plurality of items, a shoe movably attached to the rack, a magnet coupled to the shoe and a longitudinal circuit board arranged along the length of the rack. The circuit board includes an array of sensors along the length of the rack. Each sensor generates a voltage value depending on a position of the magnet in relation to the sensor. The circuit board further includes a memory storing voltage values generated by the sensors, and a processor configured to monitor voltage values generated by the sensors, detect that a particular sensor has generated a maximum voltage value and determine a number of items stored in the rack based at least in part upon a particular number of items corresponding to the particular sensor.

Abstract: In response to detecting a first triggering event corresponding to placement of a first item on a platform, a first image of the platform is captured. A first item identifier of the first item is identified and stored in a memory. In response to detecting a second triggering event corresponding to placement of a second item on the platform, a second image of the platform is captured. The second image is compared with the first image. Upon determining that the first item depicted in the second image overlaps with the first item depicted in the first image and the overlap equals or exceeds a threshold, the first item identifier is assigned to the first item depicted in the second image. A second item identifier of the second item is identified, and information associated with the first item identifier and the second item identifier is displayed on a user interface device.

Abstract: A device captures an image of a first item and generates a first encoded vector for the image. The device identifies a set of items that have at least one attribute in common with the first item. The device determines the identity of the first item based at least on attributes of the first item. The device determines that a confidence score associated with the identity of the first item is less than a threshold percentage. In response, the device determines a height of the first item. The device identifies item(s) with average heights within a threshold range from the height of the first item. The device compares the first encoded vector with a second encoded vector associated with a second item from the identified item(s). If the first encoded vector corresponds to the second encoded vector, the device determines that the first item corresponds to the second item.

Abstract: An item tracking system comprises a plurality of cameras, a memory storing associations between item identifiers of respective items, and a processor configured to capture a plurality of first images of a first item and identify a first item identifier of the first item based on the first images. The processor captures a plurality of second images of a second item, generates cropped image of the second item from each second image, and identifies an item identifier for each cropped image. Based on the associations stored in the memory, the processor determines that an association exists between the first item identifier of the first item and a second item identifier, and assigns the second item identifier to the second item when at least one of the item identifiers corresponding to the cropped images is the second item identifier.

Abstract: An event tracking subsystem detects events for the removal of items at a plurality of locations. A data prediction subsystem receives event data based on the detected events that indicates an amount of an item removed from each of the plurality of locations over a previous period of time. The data prediction subsystem determines a prediction data value for each item at each of the plurality of locations. The prediction data is used to proactively request items with improved communication and computational efficiency.