Work Vehicle Implement Tracking Using 3D Visual Feature Localization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current work vehicles lack efficient methods to track the pose of implements, especially in environments where the contact domain is not visible from the driver cabin, leading to potential accidents and inefficiencies due to sensor drift and shock forces.

Innovation Solution

An image-based tracking method using a feature tracking algorithm to derive 3D map data and implement tracking data, providing positional and arrangement information of implement features within a 3D environment model, with optional benchmark information for absolute scale, allowing for precise tracking of implement movement without direct sensor exposure.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If contact domain sensors are mounted directly on the implement, then measurement precision is improved, but reliability deteriorates due to shock forces and harsh conditions

Engineering Contradiction:
Improveimplement pose measurementVSAvoidsensor durability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent uses visual features on the implement as an intermediary medium. Instead of mounting sensors directly on the implement, the system captures images of visual features and computes pose through image processing. This intermediary approach allows measurement without direct sensor-ex implement contact, resolving the contradiction between measurement precision and reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces mechanical contact sensors with an optical system. By using cameras to capture images of visual features and computing pose through computer vision algorithms, the system substitutes a mechanical sensing approach with an optical-field-based approach, eliminating the need for direct sensor mounting on the implement.

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

2Reliability

If cameras are mounted in protected locations, then reliability is improved, but measurement precision deteriorates due to limited viewing angles

Engineering Contradiction:
Improvecamera protectionVSAvoidimplement pose detection
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent makes the visual features universal by placing them on the implement itself rather than requiring specific sensor mounting locations. The visual features serve multiple purposes: they provide measurement references from various camera angles, enable pose computation, and work with cameras mounted in protected locations. This universality resolves the contradiction between camera protection and measurement precision.

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

3Device complexity

If traditional sensors are used for implement tracking, then device complexity is reduced, but loss of information increases due to sensor drift

Engineering Contradiction:
Improvesensor systemVSAvoidpose accuracy over time
Core Design Contradiction:
Device complexityVSLoss of information

Solution Approach 1:

The patent implements a feedback mechanism where the system continuously captures images of visual features, computes current pose, and compares it with previous pose estimates. This continuous visual feedback loop corrects drift accumulation that would occur with traditional open-loop sensor systems, maintaining accuracy over time without significantly increasing device complexity.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4361355A1Visual localization and feature detection for a work vehicle implement tracking system
Publication Date: 2024.05.01 LEICA GEOSYST TECH
  • EP4361355A1 patent drawingFigure 1~2a
  • EP4361355A1 patent drawingFigure 2b~2c
  • EP4361355A1 patent drawingFigure 3a~3b

AI summary

The present invention relates to a method for tracking a movable implement of a work vehicle. The method comprises the steps of 1.) accessing images during movement of the work vehicle providing a view onto an environment and at least part of the implement, 2.) providing by a feature tracking algorithm a 3D environment model and referencing of the sensor pose to the 3D environment model, 3.) tracking implement features at different poses of the implement and, determining implement tracking data providing positional and arrangement information for the implement features, 4.) accessing benchmark information providing a real distance between two benchmark points, 5.) using the benchmark information to provide the implement tracking data with absolute scale information, and 6.) using the implement tracking data for the tracking of the implement.