LiDAR Raised Boundary Detection Using Break Point Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting raised boundaries and lanes, such as kerbs, in routeways face challenges due to sensor errors, varying routeway markings and shapes, and complex environments, particularly failing to accurately detect shorter kerb structures and curved surfaces.
Innovation Solution
A method and system utilizing LiDAR data to identify break points and locate edge points of raised boundaries by determining consecutive projected points, filtering based on height variations, and fitting parallel linear models to generate accurate lane and raised boundary models using Random Sample Consensus (RANSAC).
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing detection methods are used to determine the two nearest kerbs along the driving direction, then the detection process is simple, but the detection accuracy is insufficient and complex raised boundary environments cannot be accurately detected
Solution Approach 1:
The detection process is segmented into multiple distinct steps: receiving LiDAR data, identifying candidate edge points, determining break points in linearity, filtering based on height variations, and fitting parallel linear models. This segmentation transforms a simple but inaccurate single-step detection into a multi-step process that achieves pixel-level accuracy while maintaining systematic organization.
Solution Approach 2:
The method performs preliminary actions by first identifying candidate edge points and then determining break points in the linearity of consecutive projected points before final filtering and model fitting. This preliminary processing of the data enables more accurate detection of complex raised boundary environments including shorter kerb structures and curved surfaces.
2Measurement precision
If pixel-level detection accuracy is pursued for precise manoeuvring near raised boundaries, then navigation precision is improved, but sensor errors and non-ideal routeway surfaces make such accuracy difficult to achieve
Solution Approach 1:
The method incorporates feedback mechanisms through iterative filtering based on height variations and parallel linear model fitting. The system continuously refines the detection results by comparing detected edge points against expected geometric constraints, thereby maintaining pixel-level accuracy even in the presence of sensor errors and non-ideal routeway surfaces.
Solution Approach 2:
The detection method changes parameters by filtering candidate edge points based on height variations and adjusting the linearity criteria for break point identification. These parameter changes enable the system to distinguish true raised boundaries from sensor noise and surface irregularities, achieving reliable pixel-level detection accuracy.
3Measurement precision
If comprehensive filtering and model fitting processes are applied to achieve accurate detection of diverse raised boundaries, then detection accuracy is improved, but computational complexity increases
Solution Approach 1:
The computational process is segmented into distinct filtering stages and model fitting steps, allowing the system to process LiDAR data efficiently by handling different aspects of detection separately. This segmentation reduces overall computational complexity while maintaining high detection accuracy for diverse raised boundary types.
Solution Approach 2:
The method applies partial filtering actions by focusing computational resources on identifying and processing only the relevant break points and edge points that contribute to raised boundary detection. This selective approach achieves accurate detection of diverse raised boundaries without requiring excessive computational power for processing all LiDAR data points.
Data Source
AI summary
A method of detecting a raised boundary of a routeway for a mobile object 100 is disclosed herein. In a specific embodiment, the method comprises receiving LiDAR data of an environment of the mobile object captured by a LiDAR device 101, the LiDAR data comprising a plurality of beams, each beam comprising a plurality of projected points each captured according to a common pitch angle of the LiDAR device 101; identifying a plurality of break points, each break point of the plurality of break points being in a linearity 501, 1501, 2501 of consecutive projected points of at least one beam from the plurality of beams; and locating edge points of the raised boundary from the plurality of identified break points. A system for detecting a raised boundary of a routeway for a mobile object 100 is also disclosed herein.