Road Linear Feature Reconstruction via Orientation Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Navigation and mapping service providers face challenges in generating accurate representations of road linear features from incomplete and error-prone detections, which are crucial for applications like autonomous driving and lane-level navigation.
Innovation Solution
A method that receives multiple linear feature detections, maps them to a geographic database, determines orientation differences, and constructs a consistent representation of the linear feature by aggregating orientation differences to ensure accurate orientation and location estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple linear feature detections are used to reconstruct road features, then the coverage and data availability improve, but the accuracy and consistency deteriorate due to positioning errors and heading errors in each detection
Solution Approach 1:
The patent merges multiple linear feature detections by aggregating their orientation differences relative to map-matched road link segments. The system combines orientation differences from multiple detections through statistical aggregation (e.g., median or mean) to determine a consolidated feature orientation, thereby resolving individual detection errors through collective data fusion
Solution Approach 2:
The system uses map-matched road link segments as a reference framework to provide feedback on detected linear features. By comparing detected orientations against the known orientations of map-matched road segments, the system identifies and corrects orientation errors, using the map data as a feedback mechanism to improve reconstruction accuracy
2Measurement precision
If map matching is performed to correct positioning errors, then the location accuracy improves, but the processing complexity increases
Solution Approach 1:
The system performs map matching as a preliminary step before orientation aggregation. By pre-aligning detected linear features with map-matched road link segments, the system establishes a reference framework that simplifies subsequent orientation calculations and reduces the complexity of error correction in later processing stages
3Reliability
If orientation differences are aggregated to determine feature orientation, then the robustness against individual detection errors improves, but the computational requirements increase
Solution Approach 1:
The system aggregates orientation differences from multiple detections but uses statistical measures (such as median or mean) that require processing only a subset of the available data to achieve robust results. This partial action approach provides sufficient error robustness without requiring exhaustive processing of all detection data, thereby reducing computational requirements
Data Source
AI summary
An approach is provided for reconstructing a road linear feature. The approach, for example, involves receiving two or more linear feature detections that respectively represent a linear feature of a road as a line segment delimited by two feature points. The approach also involves map matching the two or more linear feature detections to a road link segment of a geographic database. The approach further involves determining an orientation difference for each of the two or more linear feature detections based on an angle difference between each linear feature detection and a link orientation of the map matched road link segment. The approach further involves determining a feature orientation of the linear feature based on an aggregation of the orientation difference for each linear feature detection. The approach further involves constructing a representation of the linear feature based at least in part on the feature orientation.