Traffic Sign Plausibility Checking via Server Map Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomously driving vehicles face challenges in accurately recognizing traffic signs, especially when they are concealed by other road users or adverse weather conditions, leading to potential inaccuracies in vehicle control and safety risks in road traffic.
Innovation Solution
A method and device for plausibility checking of traffic signs using a server, which involves reading information and position signals from a vehicle's optical sensor, comparing them to stored map data, and providing confirmation or alternative signals to ensure accurate recognition and control, even in uncertain conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traffic signs are recognized using only vehicle-mounted optical sensors, then the system structure remains simple, but recognition reliability deteriorates when signs are concealed by road users or bad weather
Solution Approach 1:
A server acts as an intermediary between multiple vehicles and the traffic sign recognition system. The server receives recognition results from multiple vehicles, performs plausibility checks by comparing results from different sources, and provides corrected traffic sign information back to vehicles. This mediator approach enhances recognition reliability without requiring each vehicle to have complex independent recognition systems.
Solution Approach 2:
The system merges recognition results from multiple vehicles into a single plausibility-checked result. By combining data from multiple optical sensors across different vehicles and performing collective plausibility verification, the system achieves higher reliability than individual vehicle systems could achieve alone.
2Measurement precision
If plausibility checking with server is implemented, then traffic sign recognition accuracy is improved, but communication data volume and processing time increase
Solution Approach 1:
The plausibility check performs only the necessary comparison operations with pre-stored map data rather than exhaustive verification. The server compares recognition results against expected traffic signs at known locations, performing partial checks only where needed to verify plausibility, thus reducing processing time while maintaining accuracy.
Solution Approach 2:
Traffic sign positions and types are pre-stored in map data on the server before plausibility checking occurs. This preliminary preparation allows the server to quickly compare real-time recognition results against expected values without performing complex real-time analysis, significantly reducing checking time.
3Reliability
If multiple vehicles contribute recognition data to the server, then recognition robustness is enhanced, but communication load and data processing requirements increase
Solution Approach 1:
The system extracts only the essential recognition results (traffic sign type and position) from each vehicle's optical sensor data for transmission to the server, rather than transmitting complete raw image data or extensive metadata. This extraction approach enables multiple vehicles to contribute to robust recognition while keeping communication load and server processing requirements manageable.
Data Source
AI summary
A method is described for checking the plausibility of a recognition of a traffic sign for an autonomously driving vehicle. The method includes a step of reading in, in which an information signal and a position signal are read in via an interface to a vehicle device of the vehicle, the information signal representing a piece of information concerning a traffic sign in road traffic that is recognized using an optical sensor of the vehicle, and the position signal representing an instantaneous position of the vehicle. In addition, the method includes a step of comparing, in which the recognized traffic sign is compared to a sign that is noted on a stored map at the instantaneous position of the vehicle, using the information signal and the position signal. Lastly, the method includes a step of providing a confirmation signal at an interface to the vehicle device when the step of comparing results in a match of the recognized traffic sign with the sign that is noted at the relevant position of the vehicle.