A COMPLEX ACTIVITY RECOGNITION AND RECOMMENDER SYSTEM FOR PRECISION FARMING WITH TEMPORALLY CORRELATED GESTURES

Fecha de publicación: 13/10/2017
Fuente: Wipo "precision farming"
A system and method for recognizing a plurality of permissible gesture sequences of a complex agricultural activity and recommending a set of ideal practices of farming in the real time to an individual working in the field. The permissible gesture sequences are recognized by using a state machine model of the agricultural activity. The set of ideal practices are based on analysis of at least one of a plurality of spatio-temporal parameters of the field and the plurality of permissible gesture sequences of the individual. The system receives an information of the spatio-temporal parameters and agricultural activity on an electronic device by using sensors. A sequence of repetitive gestures of the activity and pre-defined constraints pertaining to the agricultural parameters are analyzed on an n-dimensional space model of the system to recommend a set of ideal farming practices of the activity to the individual working in the field.