Roadwork Zone Detection Using Lane Marking Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies face challenges in accurately detecting the start and end positions of roadwork zones for autonomous and semi-autonomous vehicles, leading to incomplete assessments and potential navigation issues due to environmental conditions and discrete lane marking observations.
Innovation Solution
A method and system that cluster lane marking observations based on location and heading, map-match them to links, and generate roadwork extension data by identifying start and end positions of roadwork zones using upstream nodes of roadwork links, thereby determining the extent of roadwork zones for safe navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If lane marking observations are used to detect roadwork zones, then roadwork zone detection capability is improved, but detection accuracy deteriorates when lane markings are incomplete or obscured
Solution Approach 1:
The patent combines multiple discrete lane marking observations from multiple vehicles into clusters to form comprehensive roadwork zone detections. By merging observations that are spatially and temporally correlated, the system overcomes individual observation limitations caused by incomplete or obscured lane markings, thereby improving detection accuracy while maintaining versatility.
Solution Approach 2:
The system performs preliminary clustering and validation of lane marking observations before final roadwork zone detection. By pre-processing observations to identify patterns and correlations across multiple vehicles, the system prepares refined data that improves detection accuracy even when individual lane markings are incomplete or obscured.
2Area of stationary object
If discrete lane marking observations are collected from multiple vehicles, then roadwork zone detection coverage is improved, but determination of start and end positions deteriorates
Solution Approach 1:
The system uses feedback mechanisms to iteratively refine roadwork zone boundary determination. By continuously comparing clustered lane marking observations against expected roadwork zone patterns and adjusting boundary predictions accordingly, the system improves start and end position determination accuracy while maintaining comprehensive detection coverage from multiple vehicle observations.
3Measurement precision
If lane marking clustering is performed based on location and heading, then roadwork zone extent determination is improved, but processing complexity increases
Solution Approach 1:
The patent segments the lane marking observation dataset into distinct clusters based on location and heading parameters. By dividing the comprehensive dataset into manageable spatial and directional groups, the system determines roadwork zone extent more accurately while reducing processing complexity through organized, modular analysis of clustered data.
Data Source
AI summary
A method, a system, and a computer program product are provided for determining roadwork extension data for identification of at least one roadwork extension. The method, for example, includes clustering a first plurality of lane marking observations captured by a plurality of vehicles, based on a lane marking location and a lane marking heading of each of the first plurality of lane marking observations to generate at least one lane marking cluster and map-matching the lane marking cluster to one or more links to obtain one or more map-matched links. The method further includes searching for one or more missing links associated with each of the map-matched links based on link attributes of the map-matched links and a distance threshold and generating the roadwork extension data based on the map matched links and the missing links.