X Development LLC

Sensus Usa, Inc.

Alex Wilson

Jie Yang

Cheng-en Guo

James Donaldson

Alexander Matthews

Christopher Edward Bacon

Semen Trygubenko

Implementations relate to improved crop field segmentation and crop classification in which boundaries between crop fields are more accurately detected. In various implementations, high-elevation image(s) that capture an area containing multiple demarcated fields may be applied as input across one or more machine learning models to generate a boundary enhancement channel. Each pixel of the boundary enhancement channel may be spatially aligned with a corresponding pixel of the one or more high-elevation images. Moreover, each pixel of the boundary enhancement channel may be classified with a unit angle to a reference location of the field of the multiple demarcated fields that contains the pixel. Based on the boundary enhancement channel, pixel-wise field memberships of pixels of the one or more high-elevation images in the multiple demarcated fields may be determined.

Field segmentation and classification

A method of identifying consumption of a utility by devices in a group of devices, wherein each device in the group of devices has a plurality of device-states and is arranged to consume the utility, the method comprising, for a given measurement period in a supply of the utility to the group of devices: obtaining a time-based vector of total levels of consumption of the utility by the group of devices during the given measurement period; for each of a plurality of group-states, wherein each group-state corresponds to each device in the group of devices being in a corresponding device-state, calculating a score representing a likelihood that the group of devices is in the group-state during the given measurement period, wherein said score is based on a likelihood of the obtained vector occurring based on a multivariate statistical model, corresponding to the group-state, of the total level of consumption of the utility by the group of devices during a measurement period in the supply of the utility to the group of devices when the group of devices is in the group-state; and identifying, based at least in part on the calculated scores, a most likely group-state for the group of devices.

Utility consumption identification

Growing community of inventors

Oxford, United Kingdom

Alex Wilson