Method for automatic phenotype measurement and selection

Patent metadata

Field	Value
Publication number	US-9658201-B2
Application number	US-201414329161-A
Country	US
Kind code	B2
Filing date	Jul 11, 2014
Priority date	Mar 7, 2013
Publication date	May 23, 2017
Grant date	May 23, 2017

Abstract

A system for plant parameter detection, including: a plant morphology sensor having a first field of view and configured to record a morphology measurement of a plant portion and an ambient environment adjacent the plant, a plant physiology sensor having a second field of view and configured to record a plant physiology parameter measurement of a plant portion and an ambient environment adjacent the plant, wherein the second field of view overlaps with the first field of view; a support statically coupling the plant morphology sensor to the physiology sensor, and a computing system configured to: identify a plant set of pixels within the physiology measurement based on the morphology measurement; determine physiology values for each pixel of the plant set of pixels; and extract a growth parameter based on the physiology values.

First claim

We claim:

1. A system for plant parameter detection, comprising:
a plant morphology sensor directed in a first direction toward a volume and configured to record a morphology measurement of a plant, the plant including a plant portion, the volume including an ambient environment adjacent the plant, the morphology measurement including data describing a structure or geometry of the plant;
a plant physiology sensor directed in a second direction toward the volume and configured to record a plant physiology measurement of the plant portion and an ambient environment adjacent the plant, the plant physiology measurement including data describing a functionality of a plant and comprising a set of physiology pixels;
a computing system configured to:
identify a subset of the set of physiology pixels based on the structure or geometry described by the morphology measurement, the subset of physiology pixels being associated with the plant portion within the physiology measurement;
determine physiology values for each pixel of the subset of physiology pixels; and
extract a plant index based on the physiology values of the subset.

2. The system of claim 1 , further comprising an ambient environment sensor, the ambient environment sensor comprising a photosensor configured to measure incident sunlight parameters, wherein the computing system is further configured to adjust the physiology values based on the incident sunlight parameters measured by the ambient environment sensor.

3. The system of claim 2 , wherein the photosensor comprises a pyranometer.

4. The system of claim 2 , wherein the system further comprises a light source arranged proximal to the physiology sensor and configured to emit light along a vector along the second direction, wherein the morphology measurement and the physiology measurement are based on reflected emitted light.

5. The system of claim 2 , wherein the ambient environment sensor further comprises a plant thermal sensor and an ambient temperature sensor.

6. The system of claim 1 , wherein the plant morphology sensor comprises an RGB camera and the physiology sensor comprises a narrow band multispectral camera.

7. The system of claim 6 , wherein the physiology sensor comprises:
a first narrow band multispectral camera configured to capture image data at a 550 nm band;
a second narrow band multispectral camera configured to capture image data at a 650 nm band; and
a third narrow band multispectral camera configured to capture image data at a 800 nm band.

8. The system of claim 1 , further comprising a second plant morphology sensor configured to record a second morphology measurement, wherein the computing system is further configured to:
identify a plant feature within the second morphology measurement;
determine a set of geographic locations associated with the plant feature; and
determine the subset of pixels based on pixels in the set of physiology pixels associated with the set of geographic locations.

9. The system of claim 8 , wherein the second plant morphology sensor is arranged in a position within a field of view of the first plant morphology sensor.

10. The system of claim 1 , wherein the computing system is further configured to:
generate a three-dimensional model of a plant portion based on the morphology measurement; and
identify the subset of physiology pixels by comparing the set of physiology pixels with the three-dimensional model generated based on the morphology measurement.

11. The system of claim 10 , wherein the computing system identifies the subset of physiology pixels by:
determining a geographic volumetric identifier for each of a set of points within the three-dimensional model; and
identifying a set of pixels within the physiology measurement sharing the determined geographic volumetric identifiers.

12. The system of claim 10 , wherein the computing system is further configured to:
determine ambient environment pixels within the set of physiology pixels corresponding to an ambient environment of the plant, based on the three-dimensional model of the plant portion;
determine ambient environment index values for the ambient environment pixels based on the physiology measurement; and
correct the physiology value for the set of physiology pixels based on the ambient environment index values.

13. The system of claim 10 , wherein the computing system is further configured to:
calculating the plant index at first and second timepoints for the plant;
determining a growth parameter value for the plant based on changes in the plant index between the first and second timepoints.

14. The system of claim 13 , wherein the growth parameter value for the plant is determined based on changes in the three-dimensional model of the plant portion between the first and second timepoints, determined from respective morphology measurements.

15. The system of claim 1 , wherein the morphology measurement comprises a color image, and the physiology measurement comprises a set of narrow-band spectral images.

16. The system of claim 1 , wherein the morphology measurement and the physiology measurement are recorded concurrently.

17. A method for plant parameter determination, comprising:
receiving a morphology measurement of a first geographic area from a morphology sensor, the morphology measurement indicative of plant structure or geometry;
generating a three-dimensional model of a plant portion based on the morphology measurement;
receiving a physiology measurement of the first geographic area from a physiology sensor, the physiology measurement indicative of a plant functionality and comprising a set of physiology pixels;
identifying a subset of the set of physiology pixels from the physiology measurement by comparing the set of physiology pixels with the three-dimensional model generated based on the morphology measurement, the subset of physiology pixels corresponding to the plant portion;
determining physiology values for each pixel of the subset of physiology pixels; and
calculating a plant index value for the plant portion based on the physiology values for each pixel of the subset of physiology pixels.

18. The method of claim 17 , wherein, wherein identifying the subset of physiology pixels corresponding to the plant portion comprises:
determining a geographic volumetric identifier for each of a set of points within the model; and
identifying a set of pixels within the physiology measurement sharing the determined geographic volumetric identifiers.

19. The method of claim 17 , further comprising:
determining ambient environment pixels within the set of physiology pixels corresponding to an ambient environment of the plant, based on the three-dimensional model of the plant portion;
determining ambient environment index values for the ambient environment pixels based on the physiology measurement; and
correcting the physiology value for the set of physiology pixels based on the ambient environment index values.

20. The method of claim 17 , further comprising:
repeating the method at first and second timepoints for the plant;
determining a growth parameter value for the plant based on changes in the plant index value between the first and second timepoints.

21. The method of claim 20 , further comprising determining the growth parameter value for the plant based on changes in the three-dimensional model of the plant portion between the first and second timepoints, determined from the respective morphology measurements.

Assignees

• Blue River Tech Inc

Inventors

• Redden Lee Kamp
• Colgan Matthew

Classifications

• G06V10/751

  Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching · CPC title

• G01B11/24

  for measuring contours or curvatures · CPC title

• A01G7/06

  Treatment of growing trees or plants, e.g. for preventing decay of wood, for tingeing flowers or wood, for prolonging the life of plants · CPC title

• A01C21/007

  Determining fertilization requirements · CPC title

• G01N33/0098 Primary

  Plants or trees (wood G01N33/46) · CPC title