Agricultural Machine Attachment Recognition via 3D Projection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current agricultural machines, such as self-propelled harvesters, face challenges in accurately determining and controlling the components of their attachments, especially under adverse environmental conditions like dust and varying lighting, which affects the precision and reliability of crop flow monitoring and processing.

Innovation Solution

The implementation of a control device with a sensor unit and image processing unit that uses a two-dimensional projection of a three-dimensional model to recognize and identify image areas related to the attachment, allowing for improved component differentiation and process sequence regulation, even when components are not optically detectable or are obscured by crop flow.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If optical sensors are used to detect crop flow and attachment components, then real-time monitoring capability is improved, but detection accuracy deteriorates under adverse environmental conditions like dust and varying lighting

Engineering Contradiction:
Improvereal-time monitoring capabilityVSAvoiddetection accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent transitions from two-dimensional image data to three-dimensional point cloud data by introducing LIDAR technology. This dimensional change enables accurate detection of attachment components and crop flow characteristics even under adverse environmental conditions, as the depth information from LIDAR penetration through dust and varying lighting provides robust spatial data that overcomes the limitations of optical cameras

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

2Reliability

If multiple sensor types are integrated to improve detection reliability, then measurement accuracy is improved, but device complexity increases

Engineering Contradiction:
Improvedetection reliabilityVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines LIDAR and optical camera sensors into an integrated sensor system with a unified control unit. This merging approach maintains high detection reliability by utilizing complementary strengths of both sensor types while reducing overall system complexity through integrated data processing and coordinated operation under single control

Inventive Principle:
Principle #5Merging (Combining)

3Measurement precision

If three-dimensional models are used to recognize image areas, then component identification accuracy is improved, but data processing time increases

Engineering Contradiction:
Improvecomponent identification accuracyVSAvoiddata processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent pre-generates three-dimensional models of attachment components before operation and stores them in the control unit. During operation, the system performs template matching between pre-stored models and real-time LIDAR point cloud data, which significantly reduces processing time compared to generating models in real-time, while maintaining high identification accuracy through precise model matching

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4360418A1Agricultural machine
Publication Date: 2024.05.01 CLAAS SELBSTFAHRENDE ERNTEMASCHINEN GMBH
  • EP4360418A1 patent drawingFigure 1
  • EP4360418A1 patent drawingFigure 2
  • EP4360418A1 patent drawingFigure 3

AI summary

The present invention relates to an agricultural machine (1), in particular a self-propelled harvester. The present invention is based on the general concept of recognizing an image area (15), in particular at least one image area or several image areas, with respect to the attachment (2) by means of a two-dimensional projection of a three-dimensional model of an attachment (2) in the images (14).