Abstract: A set of geometric shapes to be applied by a machine learning model to objects identified in image data is defined. A learning rate of the machine learning model is updated in response to external events. The machine learning model is used to estimate spatial parameters for each of the objects identified in the image data. The spatial parameters are estimated by fitting the objects to the set of geometric shapes. Updates to the spatial parameters are temporally integrated. A spatial estimate of the objects identified in the image data is generated.

Abstract: A supply chain (or other process) visibility solution combines RFID technology with a data visibility architecture to provide real-time or near real-time supply chain information at various stages of the supply chain (or other process). The system uses a data gathering architecture which collects data from multiple sources about an object. The sources of data include RFID tags, scanners and manual input. The data from the RFID tags is used to correlate the gathered data to attributes associated with the object (e.g., name, description or price). The gathered data and attributes are stored in a data store according to a customizable schema and published for consumption by one or more business processes.