3D Structure Detection for GNSS Accuracy in Urban Canyons
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Global Navigation Satellite System (GNSS) receivers experience reduced accuracy in urban areas due to signal blocking by buildings and structures, creating a high multi-path radio frequency (RF) environment, limiting their effectiveness in providing accurate navigation information.
Innovation Solution
A computer-implemented method using a processor to generate bird's-eye-view (BEV) camera and height images from radar or lidar data, merging these images with camera data to detect three-dimensional structures and reconfigure the navigation system receiver, allowing for improved signal reception by adjusting frequencies based on detected structures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GNSS receiver operates in open-sky environment, then navigation accuracy is improved (within 1.5 meters), but the system cannot function effectively in urban areas with buildings blocking signals
Solution Approach 1:
The system transitions from traditional 2D map matching to 3D building model-based navigation. By constructing three-dimensional building models with height information and performing 3D geometric intersections between satellite signals and building structures, the system achieves accurate positioning in urban canyons where traditional 2D methods fail.
Solution Approach 2:
The system pre-acquires building geometric information and constructs 3D building models before navigation operations. By preparing building footprint data, height information, and spatial relationships in advance, the system enables rapid and accurate signal path analysis when the vehicle enters urban areas without requiring real-time map updates.
2Measurement precision
If traditional GNSS receiver is used without 3D structure detection, then device complexity is reduced, but measurement precision deteriorates in urban environments with multi-path RF signals
Solution Approach 1:
The system introduces 3D building models as intermediary objects between the GNSS receiver and satellite signals. These models serve as virtual representations of urban structures that enable the receiver to predict and compensate for signal blockages and multi-path effects without requiring complex hardware modifications.
Solution Approach 2:
The system replaces physical signal processing hardware with computational geometry methods. Instead of using complex antenna arrays or signal filtering hardware to handle multi-path effects, the system uses 3D building models and geometric intersection algorithms to predict and correct positioning errors software-based.
3Measurement precision
If static maps or continuous map updates are used to improve navigation, then measurement precision is improved, but device complexity and data requirements increase
Solution Approach 1:
The system extracts only the essential geometric features of buildings (footprint coordinates, height information, spatial relationships) needed for navigation, rather than processing complete map datasets. By extracting and storing only critical building parameters, the system achieves accurate 3D positioning with minimal data requirements and processing complexity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate detection of three-dimensional structures without prior information, enhancing GNSS receiver performance in urban environments by reducing false alarms and improving navigation accuracy without the need for continuous map updates or static maps.
Implementation Method 1
generating a BEV radar image of the proximity of the vehicle, the BEV radar image comprising two-dimensional coordinates of the one or more structures in the proximity based on radar data captured from a radar of the vehicle
Implementation Method 2
generating a BEV lidar image of the proximity of the vehicle, the BEV lidar image comprising two-dimensional coordinates of the one or more structures in the proximity based on lidar data captured from a lidar of the vehicle
Data Source
AI summary
A computer-implemented method for detecting one or more three-dimensional structures in a proximity of a vehicle at runtime includes generating, by a processor, a birds-eye-view (BEV) camera image of the proximity of the vehicle, the BEV camera image comprising two-dimensional coordinates of one or more structures in the proximity. The method further includes generating, by the processor, a BEV height image of the proximity of the vehicle, the BEV height image providing height of the one or more structures in the proximity. The method further includes detecting one or more edges of the three-dimensional structures based on the BEV camera image and the BEV height image. The method further includes generating models of the three-dimensional structures by plane-fitting based on the edges of the one or more three-dimensional structures. The method further includes reconfiguring a navigation system receiver based on the models of the three-dimensional structures.