IP Library Granted Patent US 12,307,532
Granted Patent B2
US 12,307,532 · App. 18/767,627 · Granted May 20, 2025

Upward facing light sensor for plant detection

Inventors: Matthew Stephen Colgan (San Francisco, CA); Charles McCauley Ross (Los Altos, CA)
Assignee: Deere & Company
G06Q50/02A01M7/0071G01N21/255G06T7/0004G06V10/60G06V20/38G06T2207/30188
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 12,307,532
App. No.
18/767,627
Granted
May 20, 2025
Kind
B2
Abstract

A farming machine is configured to identify and treat plants in a field. The farming machine includes one or more light sensors for measuring a characteristic of light. The one or more light sensors are coupled to the farming machine and are directed a substantially upwards orientation away from the plants. A control system adjusts settings of an image acquisition system based on a characteristic of light measured by the one or more light sensors. The image acquisition system captures an image of a plant using one or more image sensors coupled to the farming machine, the one or more image sensors directed in a substantially downwards orientation towards the plants. The control system identifies a plant in the image and actuates a treatment mechanism to treat the identified plant.

Claims (55)

1. A plant identification system comprising:

an image acquisition system configured to capture an image of a plant in a field, the image acquisition system configured for capturing the image of the plant using an image sensor;

a light measurement system configured to measure a characteristic of incident light on the light measurement system, the light measurement system measuring the incident light using a light sensor; and

a control system including a processor, the processor configured to:

determine an environmental condition of the field;

access a typical characteristic of incident light associated with the environmental condition in the field;

measure, using the light measurement system, a current characteristic of incident light on the light sensor,

capture the image of the plant in the field using the image acquisition system configured to operate based on the environmental condition, wherein capturing the image of the plant comprises adjusting a configuration of the image acquisition system by modifying one or more capture parameters of the image acquisition system based on a difference between the typical characteristic of incident light and the current characteristic of incident light;

identify the plant in the image based on (1) pixels in the image identified as representing the plant, and (2) image properties of the image corresponding to the current characteristic of incident light and configuration of the image acquisition system, and

generate a control signal that, when received by a plant treatment mechanism of a farming machine, actuates the plant treatment mechanism to treat the plant.

2. The plant identification system of claim 1 , wherein the light sensor is coupled to a top surface of the farming machine, and the image sensor is coupled to a bottom surface of the farming machine.

3. The plant identification system of claim 1 , wherein the light sensor of the image acquisition system is one of:

coupled to a front surface of the farming machine and directed downwards,

coupled to a bottom surface of the farming machine and directed downwards,

coupled to the bottom surface of the farming machine and titled forward,

coupled to a top surface of the farming machine and direct downwards, and

coupled to a side of the farming machine and directed downwards.

4. The plant identification system of claim 1 , wherein the environmental condition is a time of day.

5. The plant identification system of claim 1 , wherein the environmental condition is a weather condition.

6. The plant identification system of claim 1 , wherein the characteristic of incident light is one or more of an intensity of light, a brightness of light, or a color temperature of light.

7. The plant identification system of claim 1 , wherein the characteristic of incident light is a reflectance of a plant in the field.

8. The plant identification system of claim 1 , wherein the typical characteristic of light is one or more of an average value for the environmental condition, a default value, or a value determined by the control system.

9. The plant identification system of claim 1 , wherein the plant identification system adjusts the configuration of the image acquisition system by modifying one or more capture parameters of the image acquisition system based on the difference between the typical characteristic of light and the measured characteristic of light in response to the difference being above an adjustment threshold.

10. The plant identification system of claim 1 , wherein modifying one or more capture parameters of the image acquisition system comprises one or more of a balance of the image sensor, a gain of the image sensor, or an exposure time of the image sensor.

11. A farming machine comprising:

a removably couplable light measurement system coupled to the farming machine, the light measurement system configured to measure a characteristic of incident light using a light sensor;

a removably couplable image acquisition system coupled to the farming machine, the image acquisition system configured to capture an image of a plant in a field using an image sensor;

a plurality of plant treatment mechanisms for treating plants in the field; and

a control system for:

determining an environmental condition in the field;

accessing a typical characteristic of incident light associated with the environmental condition of the field;

measuring, using the light measurement system, a current characteristic of incident light on the light sensor,

capturing the image of the plant in the field using the image acquisition system configured to operate based on the environmental condition, wherein capturing the image of the plant comprises adjusting a configuration of the image acquisition system by modifying one or more capture parameters of the image acquisition system based on a difference between the typical characteristic of incident light and the measured characteristic of incident light;

identifying the plant in the image based on (1) pixels in the image identified as representing the plant, and (2) image properties of the captured image corresponding to the measured characteristic of incident light and configuration of the image acquisition system, and

generating a control signal that, when received by a plant treatment mechanism of the plurality of plant treatment mechanisms, actuates the plant treatment mechanism to treat the identified plant.

12. The farming machine of claim 11 , wherein the light sensor is coupled to a top surface of the farming machine, and the image sensor is coupled to a bottom surface of the farming machine.

13. The farming machine of claim 11 , wherein the light sensor of the image acquisition system is one of:

coupled to a front surface of the farming machine and directed downwards,

coupled to a bottom surface of the farming machine and directed downwards,

coupled to the bottom surface of the farming machine and titled forward,

coupled to a top surface of the farming machine and direct downwards, and

coupled to a side of the farming machine and directed downwards.

14. The farming machine of claim 11 , wherein the environmental condition is a time of day.

15. The farming machine of claim 11 , wherein the environmental condition is a weather condition.

16. The farming machine of claim 11 , wherein the characteristic of incident light is one or more of an intensity of light, a brightness of light, or a color temperature of light.

17. The farming machine of claim 11 , wherein the characteristic of incident light is a reflectance of a plant in the field.

18. The farming machine of claim 11 , wherein the typical characteristic of light is one or more of an average value for the environmental condition, a default value, or a value determined by the control system.

19. The farming machine of claim 11 , wherein the control system adjusts the configuration of the image acquisition system by modifying one or more capture parameters of the image acquisition system based on the difference between the typical characteristic of light and the measured characteristic of light in response to the difference being above an adjustment threshold.

20. A method comprising:

determining an environmental condition in a field;

accessing a typical characteristic of incident light associated with the environmental condition of the field;

measuring, using a light measurement system, a current characteristic of incident light on a light sensor of the light measurement system,

capturing an image of a plant in the field using an image acquisition system configured to operate based on the environmental condition, wherein capturing the image of the plant comprises adjusting a configuration of the image acquisition system by modifying one or more capture parameters of the image acquisition system based on a difference between the typical characteristic of incident light and the measured characteristic of incident light;

identifying the plant in the image based on (1) pixels in the image identified as representing the plant, and (2) image properties of the captured image corresponding to the measured characteristic of incident light and configuration of the image acquisition system, and

generating a control signal that, when received by a plant treatment mechanism of a farming machine, actuates the plant treatment mechanism to treat the identified plant.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 11, 2024
From: BLUE RIVER TECHNOLOGY INC.
To: DEERE & COMPANY
Reel/Frame 069164/0195 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 23, 2024
From: COLGAN, MATTHEW STEPHEN; ROSS, CHARLES MCCAULEY
To: BLUE RIVER TECHNOLOGY INC.
Reel/Frame 068665/0494 →
Continuity (4)
Continuation 18360756 · Jul 27, 2023
Continuation 18170551 · Feb 17, 2023
Continuation 16789406 · Feb 12, 2020
Related Publication 20240394807A1 · Nov 28, 2024
References Cited (22)
US 7329168B2 · Hofmann · 2008 [cited by examiner]
US 20040153284A1 · Bernstein · 2004 [cited by examiner]
US 20070035815A1 · Edgar · 2007 [cited by examiner]
US 20070065857A1 · Glaser · 2007 [cited by examiner]
US 20080267445A1 · Capewell · 2008 [cited by examiner]
US 20160255778A1 · Redden · 2016 [cited by examiner]
US 20180330165A1 · Halligan · 2018 [cited by examiner]
US 20190150357A1 · Wu · 2019 [cited by examiner]
US 20190259108A1 · Bongartz · 2019 [cited by examiner]
US 20190261581A1 · Redden · 2019 [cited by examiner]
US 20190362146A1 · Polzounov et al. · 2019 [cited by applicant]
US 20190392239A1 · Ferrari · 2019 [cited by examiner]
US 20200187433A1 · Redden · 2020 [cited by examiner]
JP 2009281931A · 2009 [cited by applicant]
WO WO2016144795A1 · 2016 [cited by applicant]
Dronefly, “Best Drones for Agriculture and Farming: Crop Inspection & Analysis,” Date Unknown, four pages, Retrieved from the Internet <URL:https://www.dronefly.com/blogs/news/how-are-drones-used-for-agriculture/>. [cited by applicant]
European Patent Office, Extended European Patent Application No. 21753713.3, Oct. 26, 2023, 8 pages. [cited by applicant]
PCT International Search Report and Written Opinion, PCT Application No. PCT/US21/17127, Apr. 23, 2021, 14 pages. [cited by applicant]
United States Office Action, U.S. Appl. No. 16/789,406, Jul. 5, 2022, 20 pages. [cited by applicant]
United States Office Action, U.S. Appl. No. 16/789,406, Oct. 11, 2022, 22 pages. [cited by applicant]
United States Office Action, U.S. Appl. No. 18/170,551, Jun. 29, 2023, seven pages. [cited by applicant]
United States Office Action, U.S. Appl. No. 18/360,756, Feb. 16, 2024, seven pages. [cited by applicant]