Parallel Road Sign Fusion for Accurate Traffic Sign Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing traffic sign detection systems struggle to accurately identify and filter out irrelevant signs, particularly in scenarios involving parallel roads, leading to false positives.
Innovation Solution
A method and apparatus that utilize image and map data to detect traffic signs on parallel roads, determining their relevance to the vehicle's current path and providing valid or invalid indications based on association with the path.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traffic sign detection systems detect all signs in the field of view, then the detection coverage is improved, but false positives increase due to irrelevant signs on parallel roads
Solution Approach 1:
The patent introduces map data as an intermediary to mediate between detected traffic signs and the vehicle's current path. The system cross-references detected signs with map information about parallel roads and the vehicle's actual trajectory to determine relevance, filtering out signs that belong to parallel roads without eliminating detection coverage
Solution Approach 2:
The patent segments the detection process into two independent stages: first detecting all traffic signs in the field of view without filtering, then separately determining relevance to the current path using map data. This segmentation allows the system to maintain comprehensive detection coverage while systematically eliminating false positives through path association analysis
2Object-generated harmful factors
If the system filters out traffic signs on parallel roads, then false positives are reduced, but detection coverage may be compromised
Solution Approach 1:
The patent performs preliminary detection of all traffic signs before applying the filtering criterion of path association. By detecting all signs first and then using map data to determine which signs are relevant to the current path, the system ensures no relevant signs are missed while effectively filtering false positives
Data Source
AI summary
Aspects presented herein may enable a UE to obtain information related to parallel roads to rule out inapplicable/irrelevant traffic signs. In one aspect, a UE detects at least one traffic sign is present on a set of parallel roads based on a set of images and map data. The UE identifies whether the at least one traffic sign is associated with a current path traveled by a vehicle based on the detection that the at least one traffic sign is present on the parallel roads. The UE outputs a first indication that the at least one traffic sign is valid based on the at least one traffic sign being associated with the current path traveled by the vehicle, or a second indication that the at least one traffic sign is invalid based on the at least one traffic sign not being associated with the current path traveled by the vehicle.