3D Road Mesh and Graph Generation from Drivable Surface Polygons
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The generation of road graphs is computationally complex, laborious, and inaccurate due to the need for manual annotation using vehicle sensor information.
Innovation Solution
A system and method that generates three-dimensional meshes of roads using connection and separation graphs based on drivable surface polygons, which are automatically generated from sensor data, to create accurate road graphs for electronic maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual annotation is used to generate road graphs from vehicle sensor information, then the accuracy of road graph generation is improved, but the computational complexity and labor required increase significantly
Solution Approach 1:
The system enables automated generation of road graphs by having the computational system perform tasks that would otherwise require manual annotation. The processor automatically processes sensor data, generates drivable surface polygons, creates connection and separation graphs, and constructs 3D meshes without human intervention, thereby maintaining accuracy while reducing manual labor and computational overhead.
Solution Approach 2:
The invention transforms the input data parameters from raw sensor information into structured drivable surface polygons with defined geometric properties. By changing the parameter representation from unstructured sensor data to structured polygonal forms with connection and separation relationships, the system achieves accurate road graph generation with reduced computational complexity.
2Measurement precision
If manual annotation is used to generate road graphs, then the accuracy is improved, but the time and labor required increase
Solution Approach 1:
The system performs automated processing where the processor independently completes the entire road graph generation pipeline including sensor data processing, polygon generation, graph construction, and 3D mesh creation without requiring manual annotation time, thereby achieving high accuracy while dramatically reducing the time required.
Solution Approach 2:
The system performs preliminary processing of sensor data into drivable surface polygons before generating the final road graph. By pre-processing and structuring the data in advance into connection and separation graphs, the system reduces the time required for final road graph generation while maintaining accuracy.
3Ease of manufacture
If traditional methods are used to generate road graphs, then the process is established, but the productivity and efficiency decrease
Solution Approach 1:
The automated system performs all road graph generation tasks independently without manual intervention, transforming an established but labor-intensive process into an efficient automated pipeline that maintains process reliability while dramatically improving productivity and output speed.
Solution Approach 2:
The invention replaces manual mechanical annotation processes with automated computational processing. The processor executes algorithms to generate drivable surface polygons, construct graphs, and create 3D meshes, substituting human manual work with automated computational mechanisms thereby improving efficiency while maintaining established process integrity.
Data Source
AI summary
Systems and methods for generating three-dimensional meshes that represent road surfaces of a road network are disclosed herein. In one example, a system includes a processor and a memory having instructions that, when executed by the processor, cause the processor to generate a three-dimensional mesh representing road surfaces of a road network using a connection graph, a separation graph, and drivable surface polygons representing drivable surfaces of the road and generate a road graph for an electronic map based on the three-dimensional mesh, wherein the road graph is a digital representation of a topology of a road network.