US 12,456,191 B2
Non-contact, non-invasive, and quantitative agricultural monitoring devices and systems
Mitchell Robert Harrah, Tampa, FL (US); and Abdul Mohaimen Safi, Tampa, FL (US)
Assigned to UNIVERSITY OF SOUTH FLORIDA, Tampa, FL (US)
Filed by UNIVERSITY OF SOUTH FLORIDA, Tampa, FL (US)
Filed on Oct. 5, 2022, as Appl. No. 17/960,758.
Claims priority of provisional application 63/262,101, filed on Oct. 5, 2021.
Prior Publication US 2023/0103532 A1, Apr. 6, 2023
Int. Cl. G06K 9/00 (2022.01); G06T 7/00 (2017.01); G06V 10/145 (2022.01); G06V 10/44 (2022.01); G06V 10/774 (2022.01); G06V 20/68 (2022.01)
CPC G06T 7/0012 (2013.01) [G06V 10/145 (2022.01); G06V 10/44 (2022.01); G06V 10/7747 (2022.01); G06V 20/68 (2022.01); G06T 2207/30004 (2013.01); G06T 2207/30188 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A method for agricultural monitoring, comprising:
projecting, by a light source, a coherent light output on at least a part of a plant material;
acquiring, by an imaging device, one or more speckle images based on the coherent light output backscattered by at least the part of the plant material;
generating a red color image, a green color image, and a blue color image for each of the one or more speckle images;
determining a plurality of bioactivity levels corresponding to each of the red color image, the green color image, and the blue color image;
providing the one or more speckle images and the plurality of bioactivity levels to a trained machine learning algorithm;
identifying one or more healthy status indications of at least the part of the plant material based on one or more outputs from the trained machine learning algorithm, the one or more outputs corresponding to the one or more speckle images and the plurality of bioactivity levels; and
providing plant health information based on the healthy status indication.