Linear Feature Detection Centerline Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in generating accurate and consistent digital map data, particularly in reconstructing linear road features from multiple sources, especially in complex environments like highway interchanges and ramps.
Innovation Solution
A method involving the reception of multiple linear feature detections, clustering these detections into clusters, determining if these clusters form polygons, cutting the polygons at specific locations to form sub-clusters, extracting centerlines for the sub-clusters, and connecting these centerlines to generate a network graph of linear features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple linear feature detections from different sources are used to reconstruct road features, then the completeness and coverage of map data is improved, but the consistency and accuracy of the reconstructed features deteriorate due to deviations between different detection sources
Solution Approach 1:
The patent segments the polygon formed by clustered linear feature detections into multiple sub-polygons by identifying and cutting at diagonal edges. This segmentation resolves the contradiction by dividing the complex polygon (which causes inconsistency) into simpler sub-polygons that can be processed independently, thereby maintaining detection consistency while preserving the completeness of multiple detection sources. The centerlines of these sub-polygons are then extracted and connected to form the final road feature representation.
2Adaptability or versatility
If complex cartographic features such as highway interchanges and ramps are mapped, then the versatility and applicability of the mapping system is improved, but the difficulty of generating consistent linear feature representations increases
Solution Approach 1:
The patent applies segmentation by dividing complex polygons into sub-polygons through diagonal edge identification and cutting. This breaks down the complex feature reconstruction task into manageable sub-tasks, making it feasible to handle diverse cartographic features like highway interchanges and ramps while maintaining systematic processing and consistency.
Solution Approach 2:
The patent applies local quality by treating different regions of the polygon differently - identifying diagonal edges specifically for cutting, while other edges are treated differently in the clustering process. This localized approach allows the system to handle complex features with varying geometries appropriately, improving versatility without uniformly increasing complexity across all processing steps.
3Measurement precision
If polygons with interior areas or holes are formed from clustered detections, then the accuracy of linear feature representation is improved, but the complexity of processing and generating consistent centerlines increases
Solution Approach 1:
The patent resolves this contradiction by segmenting polygons with interior areas or holes into multiple sub-polygons through diagonal edge cutting. This segmentation simplifies the processing by eliminating complex interior geometries, allowing standard centerline extraction algorithms to work effectively on simpler sub-polygons while still preserving the overall accuracy of the linear feature representation through proper connection of centerlines at cut locations.
Data Source
AI summary
An approach is provided for linear feature detection of cartographic features. The approach, for example, involves receiving a plurality of linear feature detections that represent one or more linear features of a geographic environment and are detected using at least one sensor. The approach also involves clustering the plurality of linear feature detections into at least one cluster and determining that the at least one cluster forms a polygon. The approach further involves cutting the polygon at one or more cut locations to form a plurality of sub-clusters of the plurality of linear feature detections. The approach further involves extracting respective centerlines for the plurality of sub-clusters and connecting the respective centerlines at the one or more cut locations to generate a network graph of the one or more linear features.