Work Vehicle Road-Area Recognition Using 3D Point Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing work vehicles face challenges in accurately distinguishing between roads and non-road areas, particularly when weeds grow on farm fields, leading to potential self-driving interruptions due to erroneous recognition.
Innovation Solution
An area recognition system with a first discrimination processor using image information and a second discrimination processor utilizing height, width, and three-dimensional point group data to re-discriminate areas, enhancing accuracy by confirming the vehicle's position on a road or non-road area.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If a work vehicle uses image information from a camera to discriminate road areas, then the system can perform automatic navigation, but the discrimination accuracy deteriorates when weeds grow on farm fields causing erroneous recognition
Solution Approach 1:
The patent transitions from two-dimensional image information from cameras to three-dimensional point group data from LiDAR sensors. This dimensional change enables the system to capture height information, allowing it to distinguish between road surfaces and weeds by detecting the vertical profile of objects, thereby resolving the discrimination accuracy issue when weeds are present on farm fields
Solution Approach 2:
The patent changes the detection parameters from purely visual features (color, texture, shape in 2D) to spatial geometric features (x, y, z coordinates, height, width, depth) obtained from three-dimensional point group data. This parameter transformation enables reliable discrimination of road areas even when visual appearance is confounded by growing weeds
2Measurement precision
If the work vehicle uses multiple sensors and processing steps to improve discrimination accuracy, then road identification accuracy improves, but the system complexity increases
Solution Approach 1:
The patent combines multiple data sources (image information from cameras and three-dimensional point group data from LiDAR sensors) into a unified discrimination process. The controller integrates these different types of information to perform comprehensive road area discrimination, achieving high accuracy while managing system complexity through coordinated processing of multiple sensor inputs
Solution Approach 2:
The patent divides the discrimination process into two distinct processing stages: a first discrimination processor that performs initial road area identification, and a second discrimination processor that performs verification using three-dimensional data. This segmentation allows each processor to specialize in specific aspects of the discrimination task, improving overall accuracy while maintaining manageable complexity through modular architecture
Data Source
AI summary
An area recognition system includes a first discrimination processor configured or programmed to discriminate whether an area is a road based on first information obtained by setting a surrounding area of a work vehicle as a detection target, and a second discrimination processor configured or programmed to discriminate between a road and a non-road area by using identification information on a height or a width based on second information obtained for a range overlapping a range discriminated by using the first information.