Soil Clod Detection via Ray Intersection Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for detecting soil clods in agricultural fields are time-consuming, expensive, and ineffective in identifying small clods or those embedded within larger clods or hollow borders.

Innovation Solution

A method and system using computer vision techniques and image processing algorithms to classify soil pixels, identify local maxima as candidate soil clods, and determine the presence of soil clods based on ray intersections and pixel heights, with the option to adjust agricultural machine operations accordingly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional soil analysis methods are used to identify and characterize clods, then measurement precision may be adequate, but the process becomes time-consuming and expensive

Engineering Contradiction:
Improveclod detection accuracyVSAvoidanalysis time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces traditional mechanical/manual soil analysis methods with an automated image processing system. The system uses computers to capture images of the soil surface and automatically processes these images to identify and characterize clods, eliminating the need for time-consuming manual analysis while maintaining detection accuracy.

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

Solution Approach 2:

The patent creates a digital copy of the soil surface through image capture. Instead of directly analyzing physical soil samples, the system captures visual representations (images) of the soil surface and processes these copies to identify clods, significantly reducing analysis time while preserving measurement precision.

Inventive Principle:
Principle #26Copying

2Measurement precision

If traditional clod identification methods based on a priori models are used, then large clods with closed elevation contours can be identified, but small clods and embedded clods are missed

Engineering Contradiction:
Improveclod detection completenessVSAvoiddetection method flexibility
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent inverts the traditional approach by not requiring clods to fit predefined models. Instead of checking if soil features match expected clod patterns, the system identifies all potential clod candidates and then validates them, allowing detection of small clods and embedded clods that were previously missed by model-based methods.

Inventive Principle:
Principle #13The other way round (Inversion)

Solution Approach 2:

The patent changes the detection parameters from requiring closed elevation contours with high gradient values to using a more flexible approach that considers local maxima and validates clod characteristics through multiple parameters including area, depth, and shape factors. This allows detection of various clod types including small and embedded clods.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If detailed soil analysis is performed to accurately characterize all clods, then detection precision improves, but data processing requirements and system complexity increase

Engineering Contradiction:
Improveclod characterization accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the clod detection process into distinct stages: image capture, preprocessing, clod candidate identification, validation, and characterization. Each stage processes specific aspects of the data independently, reducing overall system complexity while maintaining precision through systematic progression through the analysis pipeline.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs self-validation through automated algorithms that check clod characteristics against predefined criteria. The computer automatically validates detected clods and filters out false positives without requiring external intervention, maintaining detection precision while simplifying the overall system architecture.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4042851B1Systems and methods for soil clod detection
Publication Date: 2025.01.29 CNH IND BELGIUM NV
  • EP4042851B1 patent drawingFigure 1
  • EP4042851B1 patent drawingFigure 2
  • EP4042851B1 patent drawingFigure 3

AI summary

In one aspect, a method for determining soil clods within a field includes receiving one or more images depicting an imaged portion of an agricultural field. The method also includes classifying a portion of the plurality of pixels that are associated with soil within the imaged portion of the field as soil pixels with each soil pixel being associated with a respective pixel height. The method also includes generating a first ray from a local maximum in a first direction and a second ray from the local maximum in a second direction that is perpendicular to the first ray until opposing endpoints are determined based on a detected edge condition. Lastly, the method includes determining whether a soil clod based at least in part the first ray or the second ray of the candidate soil clod.