Abstract: Commercial interactions with non-discretized items such as liquids in carafes or other dispensers are detected and associated with actors using images captured by one or more digital cameras including the carafes or dispensers within their fields of view. The images are processed to detect body parts of actors and other aspects therein, and to not only determine that a commercial interaction has occurred but also identify an actor that performed the commercial interaction. Based on information or data determined from such images, movements of body parts associated with raising, lowering or rotating one or more carafes or other dispensers may be detected, and a commercial interaction involving such carafes or dispensers may be detected and associated with a specific actor accordingly.

Abstract: Where an event is determined to have occurred at a location within a vicinity of a plurality of actors, imaging data captured using cameras having the location is processed using one or more machine learning systems or techniques operating on the cameras to determine which of the actors is most likely associated with the event. For each relevant pixel of each image captured by a camera, the camera returns a set of vectors extending to pixels of body parts of actors who are most likely to have been involved with an event occurring at the relevant pixel, along with a measure of confidence in the respective vectors. A server receives the vectors from the cameras, determines which of the images depicted the event in a favorable view, based at least in part on the quality of such images, and selects one of the actors as associated with the event accordingly.

Abstract: As agents move about a materials handling facility, tracklets representative of the position of each agent are maintained along with a confidence score indicating a confidence that the position of the agent is known. If the confidence score falls below a threshold level, image data of the agent associated with the low confidence score is obtained and processed to generate one or more embedding vectors representative of the agent at a current position. Those embedding vectors are then compared with embedding vectors of other candidate agents to determine a set of embedding vectors having a highest similarity. The candidate agent represented by the set of embedding vectors having the highest similarity score is determined to be the agent and the position of that candidate agent is updated to the current position, thereby re-identifying the agent.

Abstract: Commercial interactions with non-discretized items such as liquids in carafes or other dispensers are detected and associated with actors using images captured by one or more digital cameras including the carafes or dispensers within their fields of view. The images are processed to detect body parts of actors and other aspects therein, and to not only determine that a commercial interaction has occurred but also identify an actor that performed the commercial interaction. Based on information or data determined from such images, movements of body parts associated with raising, lowering or rotating one or more carafes or other dispensers may be detected, and a commercial interaction involving such carafes or dispensers may be detected and associated with a specific actor accordingly.

Abstract: Where an event is determined to have occurred at a location within a vicinity of a plurality of actors, imaging data captured using cameras having the location is processed using one or more machine learning systems or techniques operating on the cameras to determine which of the actors is most likely associated with the event. For each relevant pixel of each image captured by a camera, the camera returns a set of vectors extending to pixels of body parts of actors who are most likely to have been involved with an event occurring at the relevant pixel, along with a measure of confidence in the respective vectors. A server receives the vectors from the cameras, determines which of the images depicted the event in a favorable view, based at least in part on the quality of such images, and selects one of the actors as associated with the event accordingly.

Abstract: Where an event is determined to have occurred at a location within a vicinity of a plurality of actors, imaging data captured using cameras having the location is processed using one or more machine learning systems or techniques operating on the cameras to determine which of the actors is most likely associated with the event. For each relevant pixel of each image captured by a camera, the camera returns a set of vectors extending to pixels of body parts of actors who are most likely to have been involved with an event occurring at the relevant pixel, along with a measure of confidence in the respective vectors. A server receives the vectors from the cameras, determines which of the images depicted the event in a favorable view, based at least in part on the quality of such images, and selects one of the actors as associated with the event accordingly.

Abstract: As agents move about a materials handling facility, tracklets representative of the position of each agent are maintained along with a confidence score indicating a confidence that the position of the agent is known. If the confidence score falls below a threshold level, image data of the agent associated with the low confidence score is obtained and processed to generate one or more embedding vectors representative of the agent at a current position. Those embedding vectors are then compared with embedding vectors of other candidate agents to determine a set of embedding vectors having a highest similarity. The candidate agent represented by the set of embedding vectors having the highest similarity score is determined to be the agent and the position of that candidate agent is updated to the current position, thereby re-identifying the agent.

Abstract: This disclosure describes, in part, systems for enabling physical retail stores and other facilities to implement automated-checkout techniques for the purchase of customizable and/or made-to-items items by customers of the stores and/or facilities. For example, the described systems may enable a retail store to implement technology where users are able to order customizable items from an ordering location, an inventory location, or an associate of the facility, and exit the store without performing manual checkout of the items. The systems described herein thus enable customized retail facilities, as opposed to a retail facility that allows automated-checkout only for prepackaged-type or otherwise non-customizable merchandise.

Abstract: Systems and methods are provided for detecting target object(s) within image(s) based on selective template matching. More specifically, the systems and methods relate to template generation, selection and matching based on the identification of regions of interest within image(s). Training images showing target object(s) can be obtained and regions of interest that are deemed more likely to contain part(s) of the target object can be identified based on the training images. Subsequent to the identification of regions of interest, templates for target object detection can be generated based thereon. Templates can be applied on testing images. Based on the test application of templates, a subgroup of templates can be selected to serve as a basis for target object detection in subsequent images.

Abstract: A global demand forecast is generated for a product group in a computer system, where the product group comprises a plurality of products of a predefined genre. A historical relationship between an aggregate of product level demand forecasts and actual demand for the products in the product group, and the global demand forecast are used to adjust a critical ratio employed to generate a product level demand forecast in the computer system for a product in the product group. The critical ratio expresses a probability that the product level demand forecast will exceed an actual demand for a corresponding product.

Abstract: Various embodiments of the present invention are provided to adjust a product demand forecast. In one embodiment, a value is determined of an aggregation of a plurality of product level demand forecasts for a respective plurality of products in a product group at a desired value of a critical ratio. The critical ratio expresses a probability that a forecast will exceed a demand for a given product. A ratio is determined of the aggregation of the product level demand forecasts to a global demand forecast for the product group in the computer system. The ratio is verified as to whether it is congruous with a historical ratio of past aggregate product level demand forecasts to actual product demand.

Abstract: Computer processes are disclosed for identifying and informing users of early adopter items. In one embodiment, scores are generated for particular items represented in an electronic catalog, with each score reflecting an extent to which a corresponding item has been ordered by customers who tend to order items promptly after they become available. Information pertaining to such scores may be incorporated into item detail pages of the electronic catalog to assist customers in making item selection decisions. For example, the electronic catalog may identify specific items as early adopter items, and/or may display information pertaining to the degree to which specific items are early adopter items.