Search International and National Patent Collections

1. (WO2018057796) HI-FIDELITY COMPUTER OBJECT RECOGNITION BASED HORTICULTURAL FEEDBACK LOOP

Pub. No.:    WO/2018/057796    International Application No.:    PCT/US2017/052800
Publication Date: Fri Mar 30 01:59:59 CEST 2018 International Filing Date: Fri Sep 22 01:59:59 CEST 2017
IPC: G05B 6/02
G05B 23/02
Applicants: IUNU, LLC
Inventors: GREENBERG, Adam Phillip Takla
KING, Matthew Charles
Title: HI-FIDELITY COMPUTER OBJECT RECOGNITION BASED HORTICULTURAL FEEDBACK LOOP
Abstract:
Infrastructure and methods to implement a feedback loop for a horticultural operation are disclosed. Image capture devices are deployed on a per plant or near per plant basis, and upload images to image analysis server. The image analysis server applies image preprocessing to the uploaded images, and then applies image analysis to identify plants and plant artifacts. Where artifacts indicate an issue with a plant, a course of action to remediate is identified. Static analysis techniques, sequential analysis techniques, and adaptive techniques are some of the techniques enabled and disclosed by the application of object recognition techniques to horticultural applications. Images may be associated with a plant state vector to enable complex comparison operations.