Crop Discrimination System Using Preliminary Image Capture

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current machine-based systems for agricultural use face challenges in accurately distinguishing between crops and non-crops while moving, due to limitations in camera-based recognition systems and environmental fluctuations, leading to inaccuracies in task execution and positioning.

Innovation Solution

A machine-based system equipped with multiple image capture devices, georeferencing, and inertial measurement units processes images and spatial data to identify and georeference the 'area of interest', generating actuation signals for precise task execution and repositioning, using algorithms for real-time data processing and geospatial alignment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the machine-assisted system moves at higher speed across the crop field, then productivity is improved, but the measurement precision of crop and non-crop plants deteriorates due to limited frame rate of camera systems

Engineering Contradiction:
Improvespeed of machine operationVSAvoidaccuracy of crop identification
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system performs preliminary actions by capturing images at multiple positions before the actual task execution point. The image capture device takes pictures at first, second, and third positions along the movement path, allowing the system to predict and prepare for upcoming crop areas, thus maintaining identification accuracy even at higher speeds.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system transitions from two-dimensional image analysis to three-dimensional spatial reasoning by incorporating position information from the position detection device. This adds the time/space dimension to the analysis, allowing the system to correlate images taken at different positions and maintain accurate crop identification despite motion.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Device complexity

If the machine-assisted system uses traditional camera-based recognition systems, then device complexity is reduced, but measurement precision deteriorates due to environmental variations and positioning inaccuracies

Engineering Contradiction:
Improvesystem configurationVSAvoidaccuracy of area of interest determination
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The system merges multiple data sources including images from the image capture device, position information from the position detection device, and terrain data from the terrain data acquisition device. This combination of multiple simple components creates a robust system that overcomes the limitations of individual sensors and maintains high precision in crop identification despite environmental variations.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system implements feedback by continuously comparing detected crop positions with expected positions based on movement data and terrain information. The control device uses this feedback to adjust and refine the determination of the area of interest, improving measurement precision through iterative correction.

Inventive Principle:
Principle #23Feedback

3Measurement precision

If the machine-assisted system captures images at multiple positions, then measurement precision is improved, but loss of time increases due to additional image processing requirements

Engineering Contradiction:
Improveaccuracy of crop identificationVSAvoidimage processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary image capture and processing at multiple positions before reaching the task execution point. By capturing images at first, second, and third positions in advance, the system processes data proactively rather than reactively, maintaining precision without delaying the actual task execution.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts the processing priority and depth of analysis for images captured at different positions. Images from positions closer to the current location receive higher processing priority, while distant positions undergo lighter processing, optimizing the balance between precision and time consumption.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4480292A1A machine-based crop and non-crop discrimination system and method for performing actions and action execution, and computer-aided modification unit
Publication Date: 2024.12.25 DAHLIA ROBOTICS GMBH
  • EP4480292A1 patent drawingFigure 1
  • EP4480292A1 patent drawingFigure 2
  • EP4480292A1 patent drawing

AI summary

The invention relates to a machine-assisted system for agricultural use, wherein the system is set up and prepared to perform a task (24) such as distinguishing between crop plants (27) and non-crop plants (28) and/or changing the position (26) of a device designed to perform a task (24) on crop plants (27) and/or non-crop plants (28). It also relates to a method for performing a task (24) as well as a method for changing the position (26) of a device designed to perform a task (24) on crop plants (27) and/or non-crop plants (28). The invention further relates to a computer-aided change unit (10) with commands for carrying out the methods.