Blue River Technology Inc.

Deere & Company

Chia-Chun Fu

James Patrick Ostrowski

Christopher Grant Padwick

Olgert Denas

Lee Kamp Redden

Andrei Polzounov

Chris Padwick

Kent M Anderson

Benjamin Kahn Cline

A method for calibrating performance characteristics of a farming machine using a performance report is described. The farming machine accesses images of plants in a field captured during the calibration pass. The images are input into a performance model to generate a performance report by identifying plants in the images using a plurality of identification sensitivities and determining expected performance characteristics of the farming machine for each of the identification sensitivities. As such, the performance report includes expected performance characteristics for each identification sensitives. The farming machine accesses a target performance characteristic (e.g., from an operator) for the farming machine corresponding identification sensitivity. Images are input into a plant identification model during a treatment pass which identify a plant in the field using the identification sensitivity corresponding to the target performance characteristic. The farming machine treats the plant in the field using a treatment array of the farming machine.

Estimating performance and selecting operating parameters for a farming machine using a calibration pass

A farming machine including a number of treatment mechanisms treats plants according to a treatment plan as the farming machine moves through the field. The control system of the farming machine executes a plant identification model configured to identify plants in the field for treatment. The control system generates a treatment map identifying which treatment mechanisms to actuate to treat the plants in the field. To generate a treatment map, the farming machine captures an image of plants, processes the image to identify plants, and generates a treatment map. The plant identification model can be a convolutional neural network having an input layer, an identification layer, and an output layer. The input layer has the dimensionality of the image, the identification layer has a greatly reduced dimensionality, and the output layer has the dimensionality of the treatment mechanisms.

Semantic segmentation to identify and treat plants in a field and verify the plant treatments

A farming machine includes one or more image sensors for capturing an image as the farming machine moves through the field. A control system accesses an image captured by the one or more sensors and identifies a distance value associated with each pixel of the image. The distance value corresponds to a distance between a point and an object that the pixel represents. The control system classifies pixels in the image as crop, plant, ground, etc. based on depth information in in the pixels. The control system generates a labelled point cloud using the labels and depth information, and identifies features about the crops, plants, ground, etc. in the point cloud. The control system generates treatment actions based on any of the depth information, visual information, point cloud, and feature values. The control system actuates a treatment mechanism based on the classified pixels.

Identifying and avoiding obstructions using depth information in a single image

A farming machine includes one or more image sensors for capturing an image as the farming machine moves through the field. A control system accesses the image(s) and creates a labelled three-dimensional point cloud representing the field. The control system identifies and treats plants based on the labelled point cloud. To do so, the control system applies pre-processing functions to the labelled point cloud to determine characteristics of the field and/or modify labels in the point cloud. Point clusters in the point cloud are identified as plants, crops, weeds, ground, etc., using the determined characteristics and modified labels. The control system derives feature values for the plants based on the determined characteristics and labels. If the feature value indicates that the plant should be treated, the farming machine actuates a treatment mechanism to treat the plant.

Extracting feature values from point clouds to generate plant treatments

A farming machine including a number of treatment mechanisms treats plants as the farming machine moves through the field. The control system of the farming machine executes a plant identification model configured to identify plants in the field for treatment. The plant identification model is also configured to identify plants in non-ideal operating conditions. For example, the control system can identify and treat plants in non-ideal operating conditions where airborne particulates are present in an accessed image. The plant identification model is also configured to determine a particulate level in an accessed image and transmit a notification of the particulate level to an operator of the farming system. The control system generates a treatment map identifying which treatment mechanisms to actuate to treat the plants in the field. The farming machine treats the plants in the field according to the treatment map.

Plant identification in the presence of airborne particulates

A farming machine includes one or more image sensors for capturing an image as the farming machine moves through the field. A control system accesses an image captured by the one or more sensors and identifies a distance value associated with each pixel of the image. The distance value corresponds to a distance between a point and an object that the pixel represents. The control system classifies pixels in the image as crop, plant, ground, etc. based on the visual information in the pixels. The control system generates a labelled point cloud using the labels and depth information, and identifies features about the crops, plants, ground, etc. in the point cloud. The control system generates treatment actions based on any of the depth information, visual information, point cloud, and feature values. The control system actuates a treatment mechanism based on the classified pixels.

Growing community of inventors

Sunnyvale, CA, United States of America

Chia-Chun Fu