Fecha de publicación: 25/07/2019 Fuente: Wipo "precision farming" PROBLEM TO BE SOLVED: To address the technical problem of enabling automated inferencing of changes in spatiotemporal images by leveraging the high level robust features extracted from a Convolutional Neural Network (CNN) trained on varied contexts instead of data dependent feature methods.SOLUTION: Unsupervised clustering on the high level features eliminates the cumbersome requirement of labeling the images. Since models are not trained on any specific context, any image may be accepted. Real time inferencing is enabled by a certain combination of unsupervised clustering and supervised classification. A cloud-edge topology ensures real time inferencing even when connectivity is not available by ensuring that updated classification models are deployed on the edge. Creating a knowledge ontology on the basis of adaptive learning enables inferencing of an input image with varying levels of precision. Precision farming is an application of the present disclosure.SELECTED DRAWING: Figure 7COPYRIGHT: (C)2019,JPO&INPIT