Virtual SPAD meter

Patent metadata

Field	Value
Publication number	US-11937528-B2
Application number	US-202016854258-A
Country	US
Kind code	B2
Filing date	Apr 21, 2020
Priority date	Apr 21, 2020
Publication date	Mar 26, 2024
Grant date	Mar 26, 2024

Abstract

Systems and methods are provided for enhancing identification of crop conditions and execution of remedial actions in near real-time. An agricultural vehicle may include a crop analysis system having a computing device and an imaging array for capturing a set of images of a crop. The computing device analyzes images acquired by the imaging array to determine whether a crop experiences a particular condition. The computing device, when a condition is identified, can signal an agriculture machine to perform a remedial action.

First claim

The invention claimed is:

1. A crop analysis system, comprising:
an imaging array configured to acquire a set of images of a crop;
a computing device having a processor executing computer-readable instructions to configure the computing device to:
identify a condition of the crop based on the set of images acquired by the imaging array, wherein the computing device is further configured to select a feature of an image of the set of images corresponding to a portion of the crop and analyze the pixels of the image associated with the portion of the crop to identify the condition of the crop, and wherein the computing device is further configured to select, as the feature of the image corresponding to the portion of the crop, at least one mature leaf with a broad surface generally directed to the imaging array, and wherein the computing device is further configured to select one or more positions on the portion of the crop selected and analyze respective sets of pixels associated with the one or more positions selected to provide respective measurements for identifying the condition of the crop; and
signal an agricultural machine to perform an action based on the condition identified,
wherein the system is coupled to an agricultural vehicle and wherein the imaging array is further configured to acquire the set of images as the agricultural vehicle traverses a field including the crop.

2. The crop analysis system of claim 1 , wherein the imaging array includes a plurality of imaging elements, wherein an imaging element of the imaging array is configured to capture an image having a respective modality.

3. The crop analysis system of claim 2 , wherein the plurality of imaging elements include at least a digital camera and a near-infrared camera.

4. The crop analysis system of claim 1 , wherein the condition relates to nutrient stress of the crop and the agricultural machine is configured to apply fertilizer to the crop.

5. The crop analysis system of claim 4 , wherein the agricultural machine applies the fertilizer in real-time following acquisition of the set of images by the imaging array.

6. The crop analysis system of claim 1 , wherein the computing device is further configured to utilize one or more machine learning models to facilitate selection of the feature of the image and identification of the condition of the crop.

7. A crop analysis method, comprising:
acquiring a set of images of a crop, wherein the set of images include one or more images of the crop having different modalities;
processing the set of images to determine a condition of the crop, wherein processing the set of images includes:
registering images of the set of images;
segmenting the images of the set of images;
selecting at least one part of the crop based on segmented images, wherein selecting the at least on part includes selecting one or more positions of the crop including at least one mature leaf with a broad surface generally directed to an imaging array acquiring the set of images; and
evaluating the at least one part of the crop selected based on corresponding image data to determine the condition of the crop, wherein evaluating includes analyzing respective sets of pixels associated with the one or more positions selected to provide respective measurements for identifying the condition of the crop; and signaling an action in accordance with the condition determined, wherein acquiring the set of image and signaling the action are performed while an agricultural vehicle traverses a field including the crop.

8. The crop analysis method of claim 7 , wherein the set of images include at least a digital image and a near-infrared image of the crop.

9. The crop analysis method of claim 8 , further comprising generating a NDVI image based on at least one of the digital image or the near-infrared image.

10. The crop analysis method of claim 9 , further comprising acquiring a measurement of chlorophyll health of the crop based on the NDVI image.

11. The crop analysis method of claim 10 , further comprising determining whether the crop is experiencing nutrient stress based on the measurement.

12. The crop analysis method of claim 11 , further comprising signaling an agricultural machine to apply fertilizer to the crop when the crop is determined to be experiencing nutrient stress.

13. The crop analysis method of claim 7 , further comprising applying machine learning models to at least one of segmenting the images, selecting the at least one part of the crop, or evaluating the at least one part of the crop.

14. The crop analysis method of claim 13 , further comprising building the machine learning models based on training input received based on the set of images acquired.

15. A non-transitory, computer-readable storage medium having stored thereon computer-executable instructions for an image processing application, the image processing application, when executed by a processor, configure the processor to:
acquire a set of images of a crop, the set of images being captured by an imaging array coupled to an agricultural vehicle while the agricultural vehicle traverse a field including the crop;
select a crop feature included in one or more images from the set of images, wherein the crop feature selecting includes at least one mature leaf with a broad surface generally directed to an imaging array capturing the set of images;
analyze image data, associated with the crop feature, from the set of images to determine a condition of the crop; and
signal an agricultural machine to execute an action based on the condition of the crop determined,
wherein the condition determined relates to nutrient stress, the image data analyzed is NDVI information based on the set of images, and agricultural machine is configured to apply fertilizer to the crop.

Assignees

• Deere & Co

Inventors

• Pickett Terence D
• Boydell Broughton C
• Humpal Richard A
• Rees Steven

Classifications

• H04N23/11

  for generating image signals from visible and infrared light wavelengths · CPC title

• A01B79/005 Primary

  Precision agriculture · CPC title

• A01B69/001

  Steering by means of optical assistance, e.g. television cameras (steering devices for road marking vehicles E01C23/163) · CPC title

• A01B79/02

  combined with other agricultural processing, e.g. fertilising, planting · CPC title

• G06N20/00

  Machine learning · CPC title