IP Library Granted Patent US 10,942,113
Granted Patent B2
US 10,942,113 · App. 16/295,756 · Granted Mar 9, 2021

Methods, systems, and components thereof relating to using multi-spectral imaging for improved cultivation of cannabis and other crops

Inventors: Chris Rushing (Lake Oswego, OR); Robert McCorkle (Colton, OR); Brendan Joyce (Lake Park, FL)
Assignee: Emerald Metrics
G01N21/274A01G22/00G01J3/0297G01N21/3563G01N21/84G06T7/0004G01J2003/2826G01N2021/8466G06T2207/30188
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,942,113
App. No.
16/295,756
Granted
Mar 9, 2021
Kind
B2
Abstract

A method for assessing at least one condition of a plant material is provided. The method may include providing a spectral image, normalizing the spectral image to generate a normalized spectral image, processing the normalized spectral image to generate at least one processed spectral image, providing a palette file, and generating a displayable false color image from the at least one processed spectral image and the palette file. The method may include capturing a multi-spectral image of the plant material with a multi-spectral imager. The plant material may be a portion of a cannabis plant and the condition may be one of, or relating to, health. A non-transitory computer readable storage medium storing a computer program for performing the method is also provided.

Claims (86)

1. A method for assessing at least one condition of a plant material, comprising:

providing a spectral image;

normalizing the spectral image to generate a normalized spectral image;

processing the normalized spectral image to generate at least one processed spectral image;

providing a palette file;

generating a displayable false color image from the at least one processed spectral image and the palette file; and

providing a calibration file,

wherein:

the step of normalizing the spectral image comprises normalizing the spectral image with the calibration file; and

the step of providing the calibration file comprises:

using the multi-spectral imager to capture reflectance values of a calibration target under lighting conditions similar to that of the spectral image;

providing color processing values; and

generating the calibration file based on the captured reflectance values and the color processing values;

the plant material is a portion of a cannabis plant; and

the step of providing color processing values comprises selecting color processing values based on at least one of a strain of the cannabis plant and a life cycle stage of the cannabis plant.

2. The method of claim 1 , wherein the step of processing the normalized spectral image to generate at least one processed spectral image comprises:

generating a first processed spectral image based on at least one of NDVI, SAVI, GNDVI, NDVI, and NIR.

3. The method of claim 2 , wherein the step of processing the normalized spectral image to generate at least one processed spectral image further comprises:

generating a second processed spectral image based on RGB.

4. The method of claim 1 , wherein the step of providing the palette file comprises:

providing the palette file with a grey-red-yellow-green palette rubric.

5. The method of claim 2 , wherein the step of providing the palette file further comprises:

providing the palette file that assigns a grey color to pixels of the first processed spectral image with a value at or below 0.000.

6. The method of claim 2 , wherein:

the at least one condition of plant material includes a health measurement as a first condition;

the first processed spectral image reflects the health measurement; and

the step of providing a palette file further comprises providing a palette file that:

assigns a green color to very healthy plant material;

assigns a yellow color to midline healthy plant material;

assigns a red color to unhealthy plant material; and

assigns a grey color to inert material.

7. The method of claim 1 , further comprising:

screening the normalized spectral image for a first multi-spectral code set.

8. The method of claim 1 , further comprising:

evaluating at least one of the at least one processed spectral image and the normalized spectral image to recognize patterns indicative of plant health related anomalies.

9. A method for assessing at least one condition of a plant material, comprising:

providing a spectral image;

normalizing the spectral image to generate a normalized spectral image;

processing the normalized spectral image to generate at least one processed spectral image;

providing a palette file;

generating a displayable false color image from the at least one processed spectral image and the palette file;

overlaying a plurality of assessment squares on the displayable false color image;

calculating an assessment value for each of the plurality of assessment squares; and

coloring each of the plurality of assessment squares based at least in part on its assessment value,

wherein the step of providing a spectral image comprises capturing a multi-spectral image of the plant material with a multi-spectral imager.

10. The method of claim 9 , further comprising:

providing a health threshold percentage, wherein:

the at least one condition of plant material includes a health measurement as a first condition;

the first processed spectral image reflects the health measurement; and

the step of coloring each of the plurality of assessment squares based at least in part on its assessment value comprises:

overlaying a first color on each assessment square that is not predominately inert and has an assessment value greater than the health threshold percentage; and

overlaying a second color on each assessment square that is not predominately inert and has an assessment value below than the health threshold percentage.

11. The method of claim 10 , wherein the step of coloring each of the plurality of assessment square based at least in part on its assessment value further comprises:

overlaying a third color on each assessment square that is predominately inert.

12. The method of claim 10 , wherein the step of providing a health threshold percentage comprises:

receiving user input to determine the health threshold.

13. The method of claim 9 , further comprising:

providing a background surface with a grid,

wherein:

the step of capturing the spectral image comprises capturing at least a portion of the grid in the multi-spectral image; and

the step of overlaying the plurality of assessment squares on the displayable false color image comprises overlaying the plurality of assessment squares in alignment with the grid.

14. The method of claim 9 , wherein:

the plant material is seeds;

the at least one condition is seed viability; and

the step of processing the normalized spectral image to generate at least one processed spectral image further comprises generating a first processed spectral image based on at least one of NDVI, SAVI, GNDVI, NDWI, and NIR.

15. The method of claim 9 , wherein the step of processing the normalized spectral image to generate at least one processed spectral image comprises:

generating a first processed spectral image based on at least one of NDVI, SAVI, GNDVI, NDVI, and NIR.

16. The method of claim 9 , further comprising:

screening the normalized spectral image for a first multi-spectral code set.

17. The method of claim 9 , further comprising:

evaluating at least one of the at least one processed spectral image and the normalized spectral image to recognize patterns indicative of plant health related anomalies.

18. A method for assessing at least one condition of a plant material, comprising:

providing a spectral image;

normalizing the spectral image to generate a normalized spectral image;

processing the normalized spectral image to generate at least one processed spectral image;

providing a palette file; and

generating a displayable false color image from the at least one processed spectral image and the palette file,

wherein:

the step of providing a spectral image comprises capturing a multi-spectral image of the plant material with a multi-spectral image;

the plant material is cannabis flowers;

the at least one condition is curing completeness; and

the step of processing the normalized spectral image to generate at least one processed spectral image comprises generating a first processed spectral image based on at least one of NDWI and GNDVI.

19. The method of claim 18 , further comprising:

screening the normalized spectral image for a first multi-spectral code set.

20. The method of claim 18 , further comprising:

evaluating at least one of the at least one processed spectral image and the normalized spectral image to recognize patterns indicative of plant health related anomalies.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 7, 2019
From: RUSHING, CHRIS; MCCORKLE, ROBERT; JOYCE, BRENDAN
To: EMERALD METRICS
Reel/Frame 048534/0216 →
Continuity (5)
Provisional Application 62649583 · Mar 29, 2018
Provisional Application 62639990 · Mar 7, 2018
Provisional Application 62714492 · Aug 3, 2018
Provisional Application 62649580 · Mar 29, 2018
Related Publication 20190277749A1 · Sep 12, 2019