Plant group identification

Patent metadata

Field	Value
Publication number	US-11580718-B2
Application number	US-202016995618-A
Country	US
Kind code	B2
Filing date	Aug 17, 2020
Priority date	Aug 19, 2019
Publication date	Feb 14, 2023
Grant date	Feb 14, 2023

Abstract

A farming machine moves through a field and includes an image sensor that captures an image of a plant in the field. A control system accesses the captured image and applies the image to a machine learned plant identification model. The plant identification model identifies pixels representing the plant and categorizes the plant into a plant group (e.g., plant species). The identified pixels are labeled as the plant group and a location of the pixels is determined. The control system actuates a treatment mechanism based on the identified plant group and location. Additionally, the images from the image sensor and the plant identification model may be used to generate a plant identification map. The plant identification map is a map of the field that indicates the locations of the plant groups identified by the plant identification model.

First claim

What is claimed is:

1. A method for treating a plant in a field by a farming machine that moves through the field, the farming machine including a plurality of treatment mechanisms:
receiving information describing (1) a plurality of weed groups and a crop group to be identified in the field by a plant identification model, (2) a treatment to be applied to plants in the crop group, and (3) treatments to be applied to weed groups in the plurality of weed groups, each weed group comprising one or more weeds;
accessing an image of the field captured by an image sensor, the image comprising a group of pixels representing the plant;
applying the plant identification model to the image, the plant identification model configured to:
determine, based on the group of pixels representing the plant, that the plant is a weed in a weed group of the plurality of weed groups described in the received information;
classify the group of pixels representing the plant as the determined weed group; and
determine a representative location of the classified group of pixels in the image;

generating a plant treatment instruction for treating the plant with a treatment mechanism of the plurality of treatment mechanisms based on the received information describing a treatment to be applied to plants in the determined weed group and the representative location; and
actuating the plant treatment mechanism using the plant treatment instruction such that the plant is treated with the plant treatment mechanism as the farming machine moves past the plant in the field.

2. The method of claim 1 , wherein the plurality of weed groups corresponds to one or more plants in the field.

3. The method of claim 1 , wherein the plurality of weed groups describe families of plants in the weed groups.

4. The method of claim 1 , wherein the plurality of weed groups describe genera of plants in the weed groups.

5. The method of claim 1 , wherein the plurality of weed groups describe species of plants in the weed groups.

6. The method of claim 1 , wherein each weed group in the plurality of weed groups describes a plant characteristic of plants in the weed group.

7. The method of claim 6 , wherein the plant characteristic includes at least one of a leaf shape, a leaf size, or a leaf color.

8. The farming machine of claim 1 , wherein the treatments include at least one of a herbicide treatment, a pesticide treatment, a fungicide treatment, or a fertilizer treatment.

9. The method of claim 1 , wherein the image of the field is captured by the image sensor at a first time and the plant treatment mechanism is actuated at a second time after the first time.

10. The method of claim 1 , wherein the image sensor is coupled to the farming machine and the image sensor captures the image of the field as the farming machine moves through the field.

11. A farming machine comprising:
a plurality of plant treatment mechanisms for treating plants as the farming machine travels past the plants in a field;
a control system configured to:
receive information describing (1) a plurality of weed groups and a crop group to be identified in the field by a plant identification model, (2) a treatment to be applied to plants in the crop group, and (3) treatments to be applied to weed groups in the plurality of weed groups, each weed group comprising one or more weeds;

access an image of a plant captured by an image sensor, the image comprising a group of pixels representing the plant;
apply the plant identification model to the image, the plant identification model configured to:
determine, based on the group of pixels representing the plant, that the plant is a weed in a weed group of the plurality of weed groups described in the received information;
classify the group of pixels representing the plant as the determined weed group; and
determine a representative location of the classified group of pixels;

generate a plant treatment instruction for treating the plant with a treatment mechanism of the plurality of plant treatment mechanisms based on the received information describing a treatment to be applied to plants in the determined weed group and the representative location; and
actuate the plant treatment mechanism using the plant treatment instruction such that the plant is treated with the plant treatment mechanism as the farming machine moves past the plant in the field.

12. The farming machine of claim 11 , wherein the plurality of weed groups correspond to one or more plants planted in the field.

13. The farming machine of claim 11 , wherein the plurality of weed groups describe species of plants in the weed groups.

14. The farming machine of claim 11 , wherein the plurality of weed groups describe genera of plants in the weed groups.

15. The farming machine of claim 11 , wherein each weed group in the plurality of weed groups describes a corresponding plant characteristic of plants in the weed group.

16. The farming machine of claim 15 , wherein plant characteristics include at least one of a leaf shape, a leaf size, or a leaf color.

17. A method comprising:
accessing images of a field that were captured by an image sensor, the images including groups of pixels representing one or more plants in the field, each group of pixels classified as a plant group from a plurality of plant groups by a plant identification model;
accessing information indicating plant treatment actions applied to the field by a farming machine based on the plant groups classified by the plant identification model;
combining the accessed images to generate a plant identification map, wherein the plant identification map is a geographic map of the field indicating locations of individual plants of plant groups in the field and locations of plant treatment actions applied to one or more of the individual plants; and
sending the plant identification map to a device for display.

18. The method of claim 17 , further comprising:
generating a heat map on plant groups in the field by applying a color scheme to the plant identification map, wherein a color intensity of the heat map indicates a spatial density of a plant group in the field.

19. The method of claim 17 , further comprising: displaying an accuracy metric determined by comparing the locations of the plant treatment actions in the field relative to the locations of individual plants in the field.

Assignees

• Blue River Tech Inc

Inventors

• Padwick Christopher Grant
• Patzoldt William Louis
• Cline Benjamin Kahn
• Denas Olgert
• Tanna Sonali Subhash

Classifications

• G06V10/751

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

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06V10/255 Primary

  Detecting or recognising potential candidate objects based on visual cues, e.g. shapes · CPC title

• G06T7/11 Primary

  Region-based segmentation · CPC title

• G06T2207/20164

  Salient point detection; Corner detection · CPC title