Traffic Light Clustering for Reliable Vehicle-Based Position Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to reliably record relevant traffic light information, such as position and phase sequences, for automatic vehicle functions, especially when approaching a traffic light system.
Innovation Solution
A method involving detection devices on vehicles to retrieve and process traffic light objects, cluster them based on spatial position, and derive absolute positions using GPS or coordinate systems, filtering and refining data to create a precise virtual image of the traffic light system for vehicle functions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traffic light information is recorded by detection devices on vehicles, then the availability of traffic light data is improved, but the reliability of recorded traffic light information deteriorates due to inconsistent detection results from multiple vehicles
Solution Approach 1:
The patent merges traffic light detection data from multiple vehicles into a single coordinated system. Detection devices on multiple vehicles capture traffic light information, which is then combined and processed centrally to produce reliable, consistent traffic light data that overcomes the limitations of individual vehicle detections.
Solution Approach 2:
The system implements feedback mechanisms where detected traffic light information from multiple vehicles is continuously monitored, validated, and corrected. Inconsistent detections are identified and resolved through comparison across multiple data sources, ensuring that only reliable traffic light information is used for automatic vehicle functions.
2Measurement precision
If traffic light objects are clustered based on spatial position, then the precision of traffic light position determination is improved, but the complexity of data processing increases
Solution Approach 1:
The patent segments the complex task of traffic light position determination into manageable steps: first clustering traffic light objects based on spatial proximity, then determining positions within each cluster, and finally coordinating results across clusters. This segmentation reduces processing complexity while maintaining high precision through systematic analysis of grouped data.
Solution Approach 2:
The system transitions from two-dimensional image data to three-dimensional spatial coordination by incorporating depth information and vehicle position data. This dimensional expansion enables more accurate traffic light positioning by considering spatial relationships in multiple dimensions rather than relying solely on planar image coordinates.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for processing data about a traffic light system controlling a roadway segment, consisting of at least one traffic light, is described. Traffic light objects representing traffic light information about the traffic light system are retrieved. At least one cluster within the traffic light objects is identified, with each identified cluster representing a corresponding traffic light of the system. The traffic light objects are then assigned to this cluster. The spatial position of the traffic light is derived based on the assigned traffic light objects. Furthermore, a device and a computer program for processing the traffic light system data are described.