Capture of ground truthed labels of plant traits method and system

Patent metadata

Field	Value
Publication number	US-10492374-B2
Application number	US-201715857512-A
Country	US
Kind code	B2
Filing date	Dec 28, 2017
Priority date	Dec 28, 2017
Publication date	Dec 3, 2019
Grant date	Dec 3, 2019

Abstract

In embodiments, acquiring sensor data associated with a plant growing in a field, and analyzing the sensor data to extract, while in the field, one or more phenotypic traits associated with the plant from the sensor data. Indexing, while in the field, the one or more phenotypic traits to one or both of an identifier of the plant or a virtual representation of a part of the plant, and determining one or more plant insights based on the one or more phenotypic traits, wherein the one or more plant insights includes information about one or more of a health, a yield, a planting, a growth, a harvest, a management, a performance, and a state of the plant. One or more of the health, yield, planting, growth, harvest, management, performance, and the state of the plant are included in a plant insights report that is generated.

First claim

What is claimed is:

1. A method comprising:
acquiring sensor data associated with a plant growing in a field, wherein the sensor data is acquired from one or more of an optical sensor, an acoustic sensor, a chemical sensor, a geo-location sensor, an environmental sensor, and a weather sensor;
analyzing the sensor data to extract, while in the field, one or more phenotypic traits associated with the plant from the sensor data;
indexing, while in the field, the one or more phenotypic traits to one or both of an identifier of the plant or a virtual representation of a part of the plant;
determining one or more plant insights based on the one or more phenotypic traits, wherein the one or more plant insights includes information about one or more of a health, a yield, a planting, a growth, a harvest, a management, a performance, and a state of the plant; and
generating a plant insights report that includes one or more of the health, the yield, the planting, the growth, the harvest, the management, the performance, and the state of the plant;
wherein analyzing the sensor data includes:
predicting the one or more phenotypic traits based on the sensor data and a computerized model;
displaying indications of the one or more phenotypic traits predicted; and
obtaining a confirmation, modification, or addition indication from the user for at least one of the indications of the one or more phenotypic traits predicted based on direct observation of the plant in the field by the user; and
wherein the one or more phenotypic traits extracted comprises the one or more phenotypic traits predicted as confirmed, modified or added in accordance with the obtained confirmation, modification, or addition indication.

2. The method of claim 1 , wherein the computerized model includes a machine learning system, a deep learning system, an optical flow technique, a computer vision technique, a convolutional neural network (CNN), a recurrent neutral network (RNN), or a machine learning dataflow library, and wherein analyzing the sensor data comprises autonomously predicting the one or more phenotypic traits.

3. The method of claim 1 , wherein determining the one or more plant insights comprising determining the one or more plant insights while in the field.

4. The method of claim 1 , further comprising identifying, while in the field, one or more metadata associated with the plant or a condition of an environment proximate to the plant based on the sensor data.

5. The method of claim 4 , wherein the condition of the environment proximate to the plant comprises soil properties, soil chemical composition, light, solar characteristics, temperature, or humidity, and wherein determining the one or more plant insights comprises determining the one or more plant insights based on the one or more phenotypic traits and the condition of the environment proximate to the plant.

6. The method of claim 1 , wherein the one or more phenotypic traits comprises physical attributes of the plant, and wherein the plant comprises a crop plant, a fruit bearing plant, a vegetable bearing plant, or a seed bearing plant.

7. The method of claim 1 , wherein acquiring the sensor data comprises acquiring the sensor data using a human-operated vehicle, an unmanned aerial vehicle (UAV), or an unmanned ground vehicle (UGV).

8. One or more computer-readable storage media comprising a plurality of instructions to cause an apparatus, in response to execution by one or more processors of the apparatus, to:
acquire sensor data associated with a plant growing in a field, wherein the sensor data is acquired from one or more of an optical sensor, an acoustic sensor, a chemical sensor, a geo-location sensor, an environmental sensor, and a weather sensor;
analyze the sensor data to extract, while in the field, one or more phenotypic traits associated with the plant from the sensor data;
index, while in the field, the one or more phenotypic traits to one or both of an identifier of the plant or a virtual representation of a part of the plant; and
determine one or more plant insights based on the one or more phenotypic traits, wherein the one or more plant insights includes information about one or more of a health, a yield, a planting, a growth, a harvest, a management, a performance, and a state of the plant;
wherein analyzing the sensor data includes:
predicting the one or more phenotypic traits based on the sensor data and a computerized model;
displaying indications of the one or more phenotypic traits predicted; and
obtaining a confirmation, modification, or addition indication from the user for at least one of the indications of the one or more phenotypic traits predicted based on direct observation of the plant in the field by the user; and

wherein the one or more phenotypic traits extracted comprises the one or more phenotypic traits predicted as confirmed, modified or added in accordance with the obtained confirmation, modification, or addition indication.

9. The computer-readable storage medium of claim 8 , further comprising to cause the apparatus, in response to execution by the one or more processors of the apparatus, to generate a plant insights report that includes one or more of the health, the yield, the planting, the growth, the harvest, the management, the performance, and the state of the plant.

10. The computer-readable storage medium of claim 8 , wherein the computerized model includes a machine learning system, a deep learning system, an optical flow technique, a computer vision technique, a convolutional neural network (CNN), a recurrent neutral network (RNN), or a machine learning dataflow library, and wherein analyzing the sensor data comprises autonomously predicting the one or more phenotypic traits.

11. The computer-readable storage medium of claim 8 , further comprising to cause the apparatus, in response to execution by the one or more processors of the apparatus, to identify, while in the field, one or more metadata associated with the plant or a condition of an environment proximate to the plant based on the sensor data.

12. The computer-readable storage medium of claim 11 , wherein the condition of the environment proximate to the plant comprises soil properties, soil chemical composition, light, solar characteristics, temperature, or humidity, and wherein determining the one or more plant insights comprises determining the one or more plant insights based on the one or more phenotypic traits and the condition of the environment proximate to the plant.

13. The computer-readable storage medium of claim 8 , wherein the one or more phenotypic traits comprises physical attributes of the plant, and wherein the plant comprises a crop plant, a fruit bearing plant, a vegetable bearing plant, or a seed bearing plant.

14. The computer-readable storage medium of claim 8 , wherein to acquire the sensor data comprises to acquire the sensor data using a human-operated vehicle, an unmanned aerial vehicle (UAV), or an unmanned ground vehicle (UGV).

Assignees

• X Dev Llc

Inventors

• Regan William R
• Bitterman Matthew A
• Schillings Benoit G
• Brown David R
• Grant Elliott

Classifications

• A01G7/00 Primary

  Botany in general · CPC title

• G06V10/774 Primary

  Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06N3/045

  Combinations of networks · CPC title