Deere & Company

Eric M Heien

Noel Wayne Anderson

Nathan R Vandike

Alexander C Reiners

John P Just

Matthew J Burke

Marcos Antonio De Jesus Filho

A computer implemented method includes obtaining, from one or more image providers, a set of one or more overhead images of a worksite, each overhead image including values indicative of a characteristic at different geographic locations across the worksite; identifying an image performance quality metric for each overhead image based on an image performance quality model; determining if at least one overhead image can be selected, as a selected image, based on the identified image performance quality metrics for the one or more overhead images; selecting, in response to determining that at least one overhead image can be selected, as a selected image, the at least one overhead image and outputting the at least one selected image for use in control of the mobile work machine and generating control signals to control the mobile work machine based, at least, on the at least one selected image.

Systems and methods for worksite imagery selection

Historical and seasonal data is obtained by an agricultural work machine. The historical data provides historical values of agricultural characteristics, which may or may not be geolocated, and the seasonal data provides seasonal values of agricultural characteristics corresponding to a current season. A predictive map generator generates a predictive map that predicts an agricultural characteristic, such as crop state, at different locations in the field based on a relationship between the historical values of agricultural characteristics in the historical data and based on the seasonal values of agricultural characteristics in the seasonal data at those different locations. The predictive map can be output and used in automated machine control.

Historical crop state model, predictive crop state map generation and control system

Growing community of inventors

Davis, CA, United States of America

Eric M Heien