Agricultural Sprayer Camera Control for ROI-Aligned Nozzle Targeting

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Agricultural sprayers face challenges in precise application of substances due to misalignment of regions of interest (ROIs) in image processing, leading to over-spraying or under-spraying, which increases costs and environmental impact.

Innovation Solution

The implementation of a visualization and control system in agricultural sprayers that uses cameras and image processing components to identify and align ROIs, allowing for precise control of nozzles to apply substances only where needed, with features like camera calibration, ROI normalization, and nozzle-to-ROI mapping.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If image processing is used to control spraying, then spraying precision can be improved, but misalignment of regions of interest (ROIs) causes over-spraying or under-spraying

Engineering Contradiction:
Improvespraying precisionVSAvoidsubstance waste
Core Design Contradiction:
Manufacturing precisionVSLoss of substance

Solution Approach 1:

The system continuously captures images of the field, processes them to identify ROIs, and uses this information to adjust nozzle operation in real-time. This closed-loop feedback mechanism ensures that spraying is precisely controlled based on actual field conditions, preventing both over-spraying and under-spraying.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent replaces traditional mechanical spray control with an image processing and computer vision system. Cameras capture visual information, which is then processed algorithmically to determine precise spray locations, substituting mechanical positioning with optical-digital control for higher precision.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Area of stationary object

If multiple cameras are used to cover the entire field, then coverage can be improved, but alignment and calibration of multiple ROIs becomes complex

Engineering Contradiction:
Improvefield coverageVSAvoidsystem complexity
Core Design Contradiction:
Area of stationary objectVSDevice complexity

Solution Approach 1:

The system merges data from multiple cameras into a unified coordinate system through calibration. By combining the fields of view and aligning the ROIs from different cameras, the system achieves comprehensive field coverage while maintaining consistent positioning across all camera views.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The calibration process establishes a universal coordinate system that all cameras reference. This allows each camera to perform the same function of identifying ROIs while contributing to a unified spray control system, making the multi-camera setup manageable and effective.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Measurement precision

If real-time image processing is performed, then spraying control accuracy can be improved, but processing time and computational load increase

Engineering Contradiction:
Improveplant detection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary calibration of cameras and establishes processing algorithms before actual spraying begins. This pre-processing work, including coordinate system setup and parameter optimization, reduces the computational burden during real-time operation, allowing fast processing during actual spraying.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The image processing focuses on specific regions of interest (ROIs) rather than analyzing entire images. By concentrating computational resources on detecting and processing only the relevant plant areas within each camera's field of view, the system achieves high accuracy with reduced processing time.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4005379B1Camera system visualization and control for an agricultural spraying machine
Publication Date: 2024.04.24 DEERE & CO
  • EP4005379B1 patent drawingFigure 1
  • EP4005379B1 patent drawingFigure 2
  • EP4005379B1 patent drawingFigure 3-1

AI summary

An agricultural machine includes a product application system comprising a plurality of actuatable applicator mechanisms, each actuatable applicator mechanism configured to apply a substance on an agricultural surface, an imaging system configured to obtain image data indicative of an image of plant matter on the agricultural surface, and a control system configured to determine a characteristic of the plant matter in an image region defined within the image, control one or more of the actuatable applicator mechanisms to apply the substance on the agricultural surface based on the determined characteristic, and generate a user interface display that displays the image and includes a display element that visually represents the image region within the image.