System and method for automated odometry calibration for precision agriculture systems
US-11197409-B2 · Dec 14, 2021 · US
US11510355B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11510355-B2 |
| Application number | US-202117497868-A |
| Country | US |
| Kind code | B2 |
| Filing date | Oct 8, 2021 |
| Priority date | Mar 7, 2012 |
| Publication date | Nov 29, 2022 |
| Grant date | Nov 29, 2022 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A method of real-time plant selection and removal from a plant field including capturing a first image of a first section of the plant field, segmenting the first image into regions indicative of individual plants within the first section, selecting the optimal plants for retention from the first image based on the first image and the previously thinned plant field sections, sending instructions to the plant removal mechanism for removal of the plants corresponding to the unselected regions of the first image from the second section before the machine passes the unselected regions, and repeating the aforementioned steps for a second section of the plant field adjacent the first section in the direction of machine travel.
Opening claim text (preview).
What is claimed is: 1. A method comprising: accessing an image of a field comprising a plurality of plants, the image comprising a plurality of pixels and captured by a farming machine moving through the field; segmenting the image into a plurality of regions, each region of the plurality of regions comprising pixels representing a plant of the plurality of plants; identifying, by a computer, a first plant of the plurality of plants that overlaps a second plant of the plurality of plants by: classifying a first set of pixels in the plurality of pixels in a first region of the plurality of regions as the first plant by identifying plant features in the first set of pixels, classifying a second set of pixels in the pluarlity of pixels in a second region of the plurality of regions as the second plant by identifying plant features in the second set of pixels, and determining the classified first plant at least partially overlaps the classified second plant; and generating treatment instructions for the first plant based on identified features of the first plant and an amount of overlap between the first plant and the second plant, the treatment instructions indicating a directional electromagnetic energy treatment configured to eliminate the first plant from the field; generating, using the treatment instructions, the directional electromagnetic energy treatment with an elimination mechanism of the farming machine to eliminate the first plant from the field as the farming machine moves through the field. 2. The method of claim 1 , wherein eliminating the first plant from the field with the directional electromagnetic energy treatment comprises heating at least some portion of the plant to necrose the plant. 3. The method of claim 1 , wherein segmenting the image into a plurality of regions further comprises: identifying a point of interest within a region of the plurality of regions; determining that the point of interest indicates a unique feature of a plant; classifying first set of pixels as the first plant based on the point of interest indicating the unique feature; and determining treatment instructions for the first plant based on a set of cultivation parameters indicating which plants to retain or eliminate in the field. 4. The method of claim 1 , wherein classifying pixels in the first set of pixels in the first region as the first plant comprises: accessing a machined learned model configured to classify pixels as plants; applying the machine learned model to the image, the machine learned model extracting one or more features values indicating one are more pixels in the image represent the first plant; and classifying the pixels in the image as the first plant based on the extracted features. 5. The method of claim 1 , wherein the farming machine comprises an additional elimination mechanism and wherein generating treatment instructions further comprises selecting the elimination mechanism rather than the additional elimination mechanism to treat the first plant based on the identified plant features. 6. The method of claim 1 , wherein generating treatment instructions for the first plant comprises: accessing target plant parameters for the field; and generating the treatment instructions based on the target plant parameters for the field. 7. The method of claim 1 , further comprising: accessing a virtual map of the field; and modifying the virtual map to include a position of the first plant in the virtual map. 8. A farming machine comprising: a camera system configured to capture an image of a field of plants as the farming machine travels through the field of plants; an elimination mechanism configured to generate directional electromagnetic energy treatments to eliminate plants in the field; one or more processors physically attached to the farming machine; a non-transitory computer readable storage medium storing computer program instructions that, when executed by the one or more processors, cause the one or more processors to: segment the image into a plurality of regions, each region of the plurality of regions comprising pixels representing a plant of the plurality of plants; identify a first plant of the plurality of plants overlaps a second plant of the plurality of plants by: classifying a first set of pixels in the plurality of pixels in a first region of the plurality of regions as the first plant by identifying plant features in the first set of pixels, classifying a second set of pixels in the pluarlity of pixels in a second region of the plurality of regions as the second plant by identifying plant features in the second set of pixels, and determining the classified first plant at least partially overlaps the classified second plant; and generate treatment instructions for the first plant overlapping the second plant based on identified features of the first plant and an amount of overlap between the first plant and the second plant, the treatment instructions indicating a directional electromagnetic energy treatment configured to eliminate the first plant from the field; generate, using the treatment instructions, the directional electromagnetic energy treatment with an elimination mechanism of the farming machine to eliminate the first plant overlapping the second plant from the field as the farming machine moves through the field. 9. The system of claim 8 , wherein eliminating the first plant from the field with the directional electromagnetic energy treatment causes the elimination mechanism to heat at least some portion of the first plant to necrose the first plant. 10. The system of claim 8 , wherein executing the computer program instructions to segment the image into a plurality of regions further causes the one or more processors to: identify a point of interest within a region of the plurality of regions; determine that the point of interest indicates a unique feature of a plant; classifying the first set of pixels as the first plant based on the point of interest indicating the unique feature; and determining treatment instructions for the first plant based on a set of cultivation parameters indicating which plants to retain or eliminate in the field. 11. The system of claim 8 , wherein executing the computer program instructions to classify pixels in the first region as the first plant further causes the one or more processors to: access a machined learned model configured to classify pixels as plants; apply the machine learned model to the image, the machine learned model extracting one or more features values indicating one are more pixels in the image represent the plant; and classify the pixels in the image as the first plant based on the extracted features. 12. The system of claim 8 , wherein the farming machine comprises an additional elimination mechanism and wherein executing the computer program instructions to generate treatment instructions further causes the one or more processors to select the elimination mechanism rather than the additional elimination mechanism to necrose the first plant based on the identified first plant features. 13. The system of claim 8 , wherein executing the computer program instructions to generate instructions for the first plant further causes the one or more processors to: access target plant parameters for the field; and generate the treatment instructions based on the target plant parameters for the field. 14. The system of claim 8 , wherein the computer program instructions, when executed by the one or more processors, cause the one or more processors to: access a virtual map of the field; and m
with electric, e.g. photo-electric control of thinning operations · CPC title
Detecting or recognising potential candidate objects based on visual cues, e.g. shapes · CPC title
Illumination specially adapted for pattern recognition, e.g. using gratings · CPC title
Region-based segmentation · CPC title
Food products · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.