Laser Crop Row Recognition Using Bird's-Eye Distance Mapping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing crop row recognition systems using camera images struggle with accuracy due to varying lighting conditions and seasonal changes in crop branches and leaves, making it difficult to stably recognize crop rows.

Innovation Solution

A work vehicle equipped with a distance sensor that uses laser light to acquire distance information and generate a bird's eye image, combined with a crop row recognition program that identifies straight lines corresponding to crop rows using detection points within row candidate regions, reducing the influence of non-crop objects and environmental factors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a camera is used to photograph field images for crop row recognition, then the system can capture visual information, but the recognition accuracy deteriorates under varying lighting conditions and seasonal changes

Engineering Contradiction:
Improvecrop row recognition accuracyVSAvoidlighting conditions and seasonal changes
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent replaces the optical camera-based recognition system with a laser-based distance measurement system. Instead of using light to capture images that are affected by lighting conditions, the system uses laser ranging to directly measure distances to crop rows, converting an optical problem into a geometric measurement problem that is immune to lighting and seasonal variations.

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

Solution Approach 2:

The patent introduces laser distance measurements as an intermediary to indirectly determine crop row positions. Rather than directly imaging the crops, the system measures distances to multiple points and reconstructs the crop row geometry through coordinate calculation, using distance information as a mediator that is not affected by visual appearance changes.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If camera images are used for crop row recognition, then the system can identify crop rows, but stability deteriorates when crop branches and leaves change with seasons

Engineering Contradiction:
Improvecrop row recognition stabilityVSAvoidcrop branches and leaves condition
Core Design Contradiction:
ReliabilityVSStability of the object's composition

Solution Approach 1:

The system replaces image-based visual recognition with laser-based geometric measurement. By measuring actual distances to crop rows and calculating positions through coordinate geometry, the system obtains physical measurement data that remains consistent regardless of how the visual appearance of crops changes with seasons.

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

Solution Approach 2:

The patent changes the measurement parameter from visual appearance (image intensity, color, texture) to physical distance (range measurement). This parameter transformation makes the measurement invariant to seasonal changes in crop morphology, as distance measurements remain consistent even when branches and leaves change.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If laser distance measurement is used instead of camera imaging, then environmental stability improves, but device complexity increases

Engineering Contradiction:
Improveenvironmental stabilityVSAvoiddistance sensor and processing system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces a camera system with a laser distance sensor system. While both are optical devices, the laser ranging system uses time-of-flight or phase-shift measurement principles that are fundamentally different from image capture, providing environmental stability at the cost of requiring specialized distance measurement electronics and signal processing.

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

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables stable and accurate recognition of crop rows regardless of environmental conditions, such as lighting and seasonal changes, by using laser-based distance information and advanced image processing techniques to filter out non-crop objects.

Implementation Method 1

a distance sensor configured to irradiate a plurality of objects present in the field with laser light and receive reflected light from the objects to thereby acquire distance information of each of the objects

Methodology Applied
Scientific EffectLaser: Laser

Implementation Method 2

receive reflected light from the objects

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentEP3766320B1Work vehicle and crop row recognition program
Publication Date: 2023.03.01 YANMAR POWER TECH CO LTD
  • EP3766320B1 patent drawingFigure 1
  • EP3766320B1 patent drawingFigure 2
  • EP3766320B1 patent drawingFigure 3

AI summary

A work vehicle includes a distance sensor configured to irradiate a plurality of objects present in a field with laser light and receive reflected light from the objects to thereby acquire distance information of each of the objects; a bird's eye image generation unit 51 configured to detect a position of each of the objects on a basis of the distance information and generate a bird's eye image, including the detected position of each of the objects as a detection point; a row candidate region generation unit 52 configured to generate one or more row candidate regions including two or more detection points located within a predetermined distance, on a basis of the bird's eye image, and a crop row recognition unit 53 configured to recognize a straight line corresponding to a crop row using all of the detection points included in the row candidate regions.