Sentera, Inc.

Andrew Muehlfeld

Eric Taipale

Brian Eickhoff

Ryan Lee Nelson

Elliott Imhoff

Joe Tinguely

Henry Nelson

Nicholas Witthoeft

Devon Libby

Joseph Franck

Justin Hui

Reid Plumbo

Precision agriculture methods and systems where drone images of an agricultural field are captured by a UAV and analyzed to generate information regarding the agricultural field. Items of interest are identified in the images, the pixel-space locations of the items of interest are determined, and the world-space locations of the items of interest are then determined using the pixel-space locations. The transformation from pixel-space location to world-space location occurs without transforming the images or processing transformed images.

Precision agriculture using pose georeferenced analytics

Techniques are described for generating population counts for seed production plants based on one or more images obtained from a camera on an aerial vehicle including, but not limited to, UAVs. The image(s) is processed to identify the plurality of rows of seed production plants, classify each one of the identified rows as either male or female, and produce a count of the number of seed production plants in the male rows and produce a count of the number of seed production plants in the female rows. The seed production plants can be corn seed plants or any other type of seed production plant in which male and female seed production plants can be distinguished from one another based on one or more aerial images.

Systems and methods of seed production plant counting using aerial images

Aerial imagery may be captured from an unmanned aircraft or other aerial vehicle. The use of aerial vehicle imagery provides greater control over distance from target and time of image capture, and reduces or eliminates imagery interference caused by clouds or other obstacles. Images captured by the aerial vehicle may be analyzed to provide various agricultural information, such as vegetative health, plant counts, population counts, plant presence estimation, weed presence, disease presence, chemical damage, wind damage, standing water presence, nutrient deficiency, or other agricultural or non-agricultural information. Georeference-based mosaicking may be used to process and combine raw image files into a direct georeferenced mosaic image.

Multiple georeferenced aerial image crop analysis and synthesis

An agricultural zone management system and methods where a variable rate prescription (VRP) includes a plurality of equipment zones of the agricultural field that are generated based on at least one treatment dimension of a farm implement to be used in the agricultural field, and each one of the equipment zones is further defined based on one or more of an intended direction of travel of the farm implement in the agricultural field, and an intended travel path of the farm implement in the agricultural field. In addition, a treatment plan, such as a treatment rate, can be generated based on the needs of plants, soil or the like in each equipment zone.

Agricultural zone management system and variable rate prescription generation

An agricultural zone management system and methods where agricultural management zones can be generated based on point samples generated from images of a field. The images can be captured by a camera on a UAV flown over the field. The point samples are used to generate the management zones of the agricultural field, where each management zone encompasses at least one of the point samples. The management zones are then stored in at least one non-transitory computer readable storage medium. The management zones can then be used to, for example, treat the field using a prescription that has been developed for each management zone, make yield predictions of a crop grown or to be grown in the field, perform analysis of crops or soil in the field, make plans for the future use of the field, and others.

Zone management generation from point samples

Autonomous vehicles may include one or more onboard devices to perform various actions, such as a still image capture device. In contrast with using an auxiliary communication system to control a payload, a vehicle navigation sensor is used to monitor autonomous vehicle movements to match a predefined vehicle maneuver event, and trigger a payload event based on identification of the vehicle maneuver event. For example, this allows an autopilot system or a remote drone pilot to initiate an image capture device or send other commands based on vehicle maneuver event recognition.

Autonomous vehicle maneuver recognition

The present subject matter provides a technical solution for various technical problems associated with precision agriculture imagery. One solution to improving precision agriculture imagery includes identification and use of ground control points. A ground control point may include the association of a visible feature in an image of an agricultural field with a geospatial coordinate. A ground control point may be used as a common reference point between two aerial images, thereby improving alignment between the two images during stitching. The ground control points may be generated using planting prescription data or as-planted data, which may include one or more intentionally unplanted regions within an agricultural filed. Multiple aerial images may be stitched together using these ground control points to generate a precisely georeferenced output image, thereby improving the accuracy of the precision agriculture output image.

Ground control point extraction from planting data

Index-based geospatial analysis may include applying a first and second index-based analysis for a set of imagery. The set of imagery may include a location-specific index values used to form a histogram for a single index image (e.g., for a single surveyed field). This first analysis may be referred to as an 'acre-to-acre' mapping, which may be useful for identifying differences in indices (e.g., NDVI vegetative health) of different parts of the field from a single day. A second 'day-to-day' index-based analysis may be performed by calculating a histogram for each set of imagery from multiple days, combining the histograms, and generating a single equal-area index map. The index map can be applied to redistribute the histogram values within multiple days of data, which may provide a more useful map of variation in each individual image and changes between images.

Growing community of inventors

Minneapolis, MN, United States of America

Andrew Muehlfeld