Plot gap identification

{
  "publication_number": "US10192112B2",
  "country": "US",
  "kind": "B2",
  "title": "Plot gap identification",
  "abstract": "Field data is collected of a field. Each instance of field data contains information that can be used to determine a value corresponding to whether or not a plant is present or absent in a particular location and is referred to as a plant presence value. The plant presence values are aggregated using the position data associated with each instance of field data to generate aggregated plant presence values. Gaps between plots are identified based partly on variations in the plant presence values within the aggregated field data. Information known about a field can be used to heuristically identify gaps in a seed line or used to eliminate locations on a seed line that may look like a gap based on low plant presence values. The aggregated plant presence values can be presented as a heat map of plant presence values showing the relative plant density of the field.",
  "claims": [
    "1. A method comprising: receiving, from a camera mounted to a vehicle navigating through the field, one or more images representing field data, the field including a plurality of seed lines and one or more plots within the plurality of seed lines; determining a plant presence value for each instance of field data, each instance of field data corresponding to a portion of the field and each plant presence value corresponds to a portion of the field and numerically representing a measure of plant matter density associated with each portion of the field; identifying plant presence values below a threshold density as candidate gaps; comparing plant presence values associated the candidate gaps to plant presence values associated with portions of the field adjacent to the candidate gaps to eliminate candidate gaps associated with plant presence values within a threshold difference of the adjacent plant presence values; identifying remaining candidate gaps as the one or more gaps between plots of the plurality of plots within the field; and segmenting the plant presence values into the one or more plots based on the one or more gaps.",
    "2. The method of claim 1, wherein identifying remaining candidate gaps as the one or more gaps between plots further comprises: determining an average row plant presence value for each row of a plurality of rows perpendicular to the plurality of seed lines, the average row plant presence value including at least one plant presence value from two or more parallel seed lines of the plurality of seed lines; and identifying one or more rows with an average row plant presence value below an average row plant presence value threshold as the one or more gaps.",
    "3. The method of claim 1, wherein the field data is at least one of thermal image data, color image data, plant height data, or plant volume data received from at least one of a vehicle or unmanned aerial vehicle (UAV) capturing the field data.",
    "4. The method of claim 1, wherein the field data is image data captured using a camera, and wherein determining the plant presence value for each instance of the field data further comprises: determining an amount of green colored pixels in each instance of the field data; and assigning the plant presence value to each instance of field data based at least in part on the amount of green colored pixels in each instance of field data.",
    "5. The method of claim 4, wherein the amount of green pixels is at least one of a total number of green pixels, a percentage of green pixels, or a ratio of green pixels to brown pixels in the field data.",
    "6. The method of claim 1, further comprising: obtaining position data for each instance of field data, the plant presence values being arranged as the function of position within the field based on the obtained position data.",
    "7. The method of claim 6, wherein the plant presence values are arranged into a plant presence heat map representing varying measures of plant matter density for the field, wherein dark areas on the plant presence heat map represent portions of the field with low plant matter density and light areas on the plant presence heat map represent portions of the field with relatively high plant matter density.",
    "8. The method of claim 1, wherein the field data is at least one of position data for plots in the field provided by a grower, field boundary data, plot length, gap length, or seed line length.",
    "9. The method of claim 1, wherein the camera is oriented non-orthogonally to the surface of the field.",
    "10. The method of claim 1, wherein each image captured by the camera represents a portion of the plot.",
    "11. A non-transitory computer readable storage medium including instructions that, when executed by a processor, cause the processor to: receive, from a camera mounted to a vehicle navigating through the field, one or more images representing field data, the field including a plurality of seed lines and one or more plots within the plurality of seed lines; determine a plant presence value for each instance of field data, each instance of field data corresponding to a portion of the field and each plant presence value corresponds to a portion of the field and numerically representing a measure of plant matter density associated with each portion of the field; identify plant presence values below a threshold density as candidate gaps; compare plant presence values associated the candidate gaps to plant presence values associated with portions of the field adjacent to the candidate gaps to eliminate candidate gaps associated with plant presence values within a threshold difference of the adjacent plant presence values; identify remaining candidate gaps as the one or more gaps between plots of the plurality of plots within the field; and segment the plant presence values into the one or more plots based on the one or more gaps.",
    "12. The non-transitory computer readable storage medium of claim 11, wherein identifying remaining candidate gaps as the one or more gaps between plots further comprises: determining an average row plant presence value for each row of a plurality of rows perpendicular to the plurality of seed lines, the average row plant presence value including at least one plant presence value from two or more parallel seed lines of the plurality of seed lines; and identifying one or more rows with an average row plant presence value below an average row plant presence value threshold as the one or more gaps.",
    "13. The non-transitory computer readable storage medium of claim 11, wherein the instructions that, when executed by the processor, further cause the processor to: obtain position data for each instance of field data, the plant presence values being arranged as the function of position within the field based on the obtained position data.",
    "14. The non-transitory computer readable storage medium of claim 11, wherein identifying the one or more gaps in the aggregated plant presence values further comprises: identifying plant presence values below a plant presence value threshold as candidate gaps; comparing characteristics of the candidate gaps to field characteristic data associated with the field to eliminate candidate gaps with characteristics failing to match the field characteristic data within a threshold; and identifying remaining candidate gaps as the one or more gaps between plots of the plurality of plots within the field.",
    "15. The non-transitory computer readable storage medium of claim 11, wherein the field data is at least one of position data for plots in the field provided by a grower, field boundary data, plot length, gap length, or seed line length.",
    "16. The non-transitory computer readable storage medium of claim 11, wherein the field data is at least one of thermal image data, color image data, plant height data, or plant volume data received from at least one of a vehicle or unmanned aerial vehicle (UAV) capturing the field data."
  ],
  "description_excerpt": "Crop growers plant different seed variants by genotype in individual plots of a field and often record the location of each different seed variant by plot to track, measure, and be able to compare the potentially different growth performances among the different seed variants. In order to measure and compare physiological parameters that determine growth performance, information of the plants or crops at various stages of growth must be collected and accurately mapped to their actual location in the grower's field. Mapping this collected information to a field, however, is not a straightforward process. For example, a grower may record the location of a plot with a positioning system that records slightly different measurements relative to another positioning system used to collect the information, the plot lengths may not be the same length (relative to a recorded theoretical plot length provided by the grower) across all plots in the field, among other variations and anomalies. Further, collection of the information could fail for a portion of the field (e.g., a seed line was inadvertently skipped, etc.) that could inadvertently and incorrectly map information of the plants to incorrect plots, thereby, rending all subsequently collected field data incorrect from that point. Thus, any error however small can result in significant measurement and comparison error in the aggregate across a field.",
  "cpc": [
    "G06V 20/188",
    "G06K 9/00657",
    "G06T 2207/10004",
    "G06T 7/0042",
    "G06T 7/0081",
    "G06T 7/11",
    "G06T 7/73"
  ],
  "ipc": [
    "G06K 9/00",
    "G06T 7/00"
  ],
  "assignees": [
    "Blue River Technology Inc"
  ],
  "inventors": [
    "Lee Kamp Redden",
    "James Patrick Ostrowski",
    "James Willis",
    "Zeb Wheeler"
  ],
  "filing_date": "2016-11-02",
  "publication_date": "2019-01-29",
  "grant_date": "2019-01-29",
  "priority_date": "2016-11-02",
  "application_number": "US-201615341883-A",
  "family_id": "62021661",
  "cited_by_count": 3,
  "citations": [
    "US5764819A",
    "US6390387B1",
    "US20010000806A1",
    "US7058197B1",
    "US20070044445A1",
    "US20130066666A1",
    "US20130124055A1",
    "US20140012732A1",
    "US20170181372A1",
    "US9251420B2",
    "US20150015697A1",
    "US20140379228A1",
    "US20150264881A1",
    "US20150278640A1",
    "US20160050840A1",
    "US20160078570A1",
    "WO2016090414A1",
    "US20160224703A1",
    "US20180022208A1",
    "WO2016123656A1",
    "WO2016191825A1",
    "EP3316673A1",
    "WO2017214686A1",
    "US20180027725A1"
  ]
}