Abstract: A tracking system includes a set of cameras, a kiosk, and a tracking server. The kiosk receives a payment amount from a person. The tracking server extracts features of the person from an image feed received from the set of cameras. The tracking server generates a session identifier that is associated with the payment amount and a unique code. The unique code represents at least one of the payment amount and features of the person. The tracking server sends a message to the kiosk to provide a ticket corresponding to the payment amount and the unique code to the person. The tracking server receives a digital cart associated with the person comprising items and a total cash value of the items. The tracking server concludes a transaction by deducting the total cash value from the payment amount.

Abstract: A tracking system includes a camera subsystem that includes cameras that capture vide of a space. Each camera is coupled with a camera client that determines local coordinates of people in the captured video. The camera clients generate frames that include color frames and depth frames labeled with an identifier number of the camera and their corresponding timestamps. The camera clients generate tracks that include metadata describing historical people detections, tracking identifications, timestamps, and the identifier number of the camera. The camera clients send the frames and tracks to cluster servers that maintain the frames and tracks such that they are retrievable using their corresponding labels. A camera server queries the cluster servers to receive the frames and tracks using their corresponding labels. The camera server determines the physical positions of people in the space based on the determined local coordinates.

Abstract: A tracking system includes a camera subsystem that includes cameras that capture vide of a space. Each camera is coupled with a camera client that determines local coordinates of people in the captured video. The camera clients generate frames that include color frames and depth frames labeled with an identifier number of the camera and their corresponding timestamps. The camera clients generate tracks that include metadata describing historical people detections, tracking identifications, timestamps, and the identifier number of the camera. The camera clients send the frames and tracks to cluster servers that maintain the frames and tracks such that they are retrievable using their corresponding labels. A camera server queries the cluster servers to receive the frames and tracks using their corresponding labels. The camera server determines the physical positions of people in the space based on the determined local coordinates.

Abstract: An apparatus includes a memory and processor. The memory stores a machine learning algorithm configured to decide between using an algorithmic and a virtual cart to process a transaction. The processor receives feedback for a decision made by the algorithm, indicating whether the algorithmic and virtual carts match. The processor assigns a reward to the feedback. A first positive reward is assigned when the algorithmic cart is selected, and the feedback indicates that the carts match. A second positive reward is assigned when the virtual cart is selected, and the feedback indicates that the carts do not match. A first negative reward is assigned when the algorithmic cart is selected, and the feedback indicates that the carts do not match. A second negative reward is assigned when the virtual cart is selected, and the feedback indicates that the carts match. The processor uses the reward to update the algorithm.

Abstract: A sensor calibration system configured to receive a first frame of one or more markers on a repositionable platform at a first location within a space from a sensor. The system is further configured to determine pixel locations in the first frame for a first marker and a second marker from among the one or more markers. The system is further configured to receive distance information that corresponds with a distance between the platform and distance measuring devices. The system is further configured to determine (x,y) coordinates for the first marker and the second marker based on the distance information. The system is further configured to generate a homography based on the (x,y) coordinates and pixel locations of the first marker and the second marker. The homography includes coefficients that translate between pixel locations in the first frame of the sensor and (x,y) coordinates in the global plane.

Abstract: An apparatus includes a memory and a processor. The memory stores a set of inputs, an algorithmic shopping cart, and a machine learning algorithm. The set of inputs includes information collected from sensors located in a physical store during a shopping session of a person. The algorithmic shopping cart includes items determined by an algorithm, based on the set of inputs, to have been selected during the shopping session. The machine learning algorithm is configured to use the set of inputs to select between using the algorithmic shopping cart and using a virtual shopping cart to process a transaction associated with the shopping session. The processor uses the machine learning algorithm to determine, based on the set of inputs, to use the algorithmic shopping cart to process the transaction.

Abstract: An apparatus includes a memory and processor. The memory stores a machine learning algorithm configured to decide whether to use a virtual shopping cart to verify all or a portion of a transaction performed with an algorithmic shopping cart. The processor receives feedback for a decision made by the algorithm, indicating whether the algorithmic and virtual carts match. The processor assigns a reward to the feedback. A first positive reward is assigned when the virtual shopping cart is not used for verification, and the feedback indicates that the carts match. A second positive reward is assigned when the virtual cart is used for verification, and the feedback indicates that the carts do not match. A first negative reward is assigned when the virtual shopping cart is not used for verification, and the feedback indicates that the carts do not match. A second negative reward is assigned when the virtual cart is used for verification, and the feedback indicates that the carts match.

Abstract: A sensor calibration system configured to receive a first frame of one or more markers on a repositionable platform at a first location within a space from a sensor. The system is further configured to determine pixel locations in the first frame for a first marker and a second marker from among the one or more markers. The system is further configured to receive distance information that corresponds with a distance between the platform and distance measuring devices. The system is further configured to determine (x,y) coordinates for the first marker and the second marker based on the distance information. The system is further configured to generate a homography based on the (x,y) coordinates and pixel locations of the first marker and the second marker. The homography includes coefficients that translate between pixel locations in the first frame of the sensor and (x,y) coordinates in the global plane.

Abstract: An apparatus includes a memory and processor. The memory stores a machine learning algorithm configured to decide between using an algorithmic and a virtual cart to process a transaction. The processor receives feedback for a decision made by the algorithm, indicating whether the algorithmic and virtual carts match. The processor assigns a reward to the feedback. A first positive reward is assigned when the algorithmic cart is selected, and the feedback indicates that the carts match. A second positive reward is assigned when the virtual cart is selected, and the feedback indicates that the carts do not match. A first negative reward is assigned when the algorithmic cart is selected, and the feedback indicates that the carts do not match. A second negative reward is assigned when the virtual cart is selected, and the feedback indicates that the carts match. The processor uses the reward to update the algorithm.

Abstract: A tracking system includes a set of cameras, a kiosk, and a tracking server. The kiosk receives a payment amount from a person. The tracking server extracts features of the person from an image feed received from the set of cameras. The tracking server generates a session identifier that is associated with the payment amount and a unique code. The unique code represents at least one of the payment amount and features of the person. The tracking server sends a message to the kiosk to provide a ticket corresponding to the payment amount and the unique code to the person. The tracking server receives a digital cart associated with the person comprising items and a total cash value of the items. The tracking server concludes a transaction by deducting the total cash value from the payment amount.

Abstract: A sensor calibration system configured to receive a first frame of one or more markers on a repositionable platform at a first location within a space from a sensor. The system is further configured to determine pixel locations in the first frame for a first marker and a second marker from among the one or more markers. The system is further configured to receive distance information that corresponds with a distance between the platform and distance measuring devices. The system is further configured to determine (x,y) coordinates for the first marker and the second marker based on the distance information. The system is further configured to generate a homography based on the (x,y) coordinates and pixel locations of the first marker and the second marker. The homography includes coefficients that translate between pixel locations in the first frame of the sensor and (x,y) coordinates in the global plane.

Abstract: An image sensor is positioned such that a field-of-view of the image sensor encompasses at least a portion of a rack storing items. The image sensor generates angled-view images of the items stored on the rack. A tracking subsystem determines that a person is within a threshold distance of the rack and receives image frames of the angled-view images. A pixel position of a wrist of the person is determined in at least a subset of the received image frames, thereby determining a set of pixel positions of the wrist. An aggregated wrist position is determined based on the set of pixel positions. If the aggregated wrist position is determined to correspond to a position on a shelf of the rack, a trigger signal is provided indicating a shelf-interaction event has occurred.

Abstract: An apparatus includes a memory and a processor. The memory stores a set of inputs, an algorithmic shopping cart, and a machine learning algorithm. The set of inputs includes information collected from sensors located in a physical store during a shopping session of a person. The algorithmic shopping cart includes items determined by an algorithm, based on the set of inputs, to have been selected during the shopping session. The machine learning algorithm is configured to use the set of inputs to select between using the algorithmic shopping cart and using a virtual shopping cart to process a transaction associated with the shopping session. The processor uses the machine learning algorithm to determine, based on the set of inputs, to use the algorithmic shopping cart to process the transaction. In response, the processor generates a receipt based on the algorithmic shopping cart. The processor sends the receipt to the person.

Abstract: A system includes sensors and a tracking subsystem. The subsystem tracks a first object and one or more other objects in a space. After determining that re-identification of the first object is needed, candidate identifiers are determined for the first object. The candidate identifiers include a subset of the identifiers of all tracked objects in the space. The subset includes possible identifiers of the first object based on a history of movements of the first object and interactions of the first object with the other objects in the space. Based on a top-view image, a first descriptor is determined for the first object. The first descriptor is associated with a characteristic of the first object. Based on results of comparing the first descriptor to a set of predetermined descriptors, an updated identifier is determined for the first object.

Abstract: An object tracking system includes a first sensor, a second sensor, and a tracking system. The tracking system is configured to determine that the first current pixel location for the shelf marker does not match a first expected pixel location for the shelf marker. The tracking system is further configured to determine a second current pixel location for the shelf marker within a second frame from the second sensor, to recalibrate the first sensor when the second current pixel location for the shelf marker matches the second pixel location for the shelf marker and to update the first pixel location with the first current pixel location and the second pixel location with the second current pixel location when the second current pixel location for the shelf marker does not match the second pixel location for the shelf marker.

Abstract: An image sensor is positioned such that a field-of-view of the image sensor encompasses at least a portion of a rack storing items. The image sensor generates angled-view images of the items stored on the rack. A tracking subsystem determines that a person is within a threshold distance of the rack and receives image frames of the angled-view images. A pixel position of a wrist of the person is determined in at least a subset of the received image frames, thereby determining a set of pixel positions of the wrist. An aggregated wrist position is determined based on the set of pixel positions. If the aggregated wrist position is determined to correspond to a position on a shelf of the rack, a trigger signal is provided indicating a shelf-interaction event has occurred.

Abstract: A system includes sensors and a tracking subsystem. The subsystem tracks a first object and one or more other objects in a space. After determining that re-identification of the first object is needed, candidate identifiers are determined for the first object The candidate identifiers include a subset of the identifiers of all tracked objects in the space. The subset includes possible identifiers of the first object based on a history of movements of the first object and interactions of the first object with the other objects in the space. Based on a top-view image, a first descriptor is determined for the first object. The first descriptor is associated with a characteristic of the first object. Based on results of comparing the first descriptor to a set of predetermined descriptors, an updated identifier is determined for the first object.

Abstract: An apparatus includes a display, interface, and processor. The interface receives a camera feed from a camera directed at a first physical rack located in a physical store. The processor displays, in a first region of the display, a virtual layout of a virtual store, configured to emulate a physical layout of the physical store. The virtual layout includes virtual racks assigned to physical racks. The virtual layout emulates the physical layout of the physical store. The processor receives an indication of an event associated with the first physical rack and accordingly displays the first virtual rack, which includes first and second virtual shelves. The first and second virtual shelves include virtual items that emulate physical items located on physical shelves of the first physical rack. The processor additionally displays a recording of the camera feed, which depicts the event associated with the first physical rack.

Abstract: An apparatus includes a display and a processor. The processor displays a virtual shopping cart. The processor also receives information indicating that an algorithm determined that a physical item was selected by a person during a shopping session in a physical store, based on a set of inputs received from sensors located within the store. In response, the processor displays a virtual item, which includes a graphical representation of the physical item. The processor additionally displays a rack video captured during the shopping session by a rack camera located in the store. The rack camera is directed at a physical rack located in the store, which includes the physical item. In response to displaying the rack video, the processor receives information identifying the virtual item, where the rack video depicts that the person selected the physical item. The processor then stores the virtual item in the virtual shopping cart.

Abstract: An object tracking system includes a sensor, a weight sensor, and a tracking system. The sensor is configured to capture a frame of at least a portion of a rack within a global plane for a space. The tracking system is configured to detect a weight decrease on the weight sensor. The tracking system is further configured to receive the frame of the rack, to determine a pixel location for a person, to determine the person is within a predefined zone associated with the rack. The tracking system is further configured to identify the item associated with the weight sensor and to add the identified item to a digital cart associated with the person.