Rearward White Line Inference Using Forward Lane Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in accurately inferring the rearward white line for lane change assistance due to limitations in GNSS availability in tunnels and buildings, and accumulated errors in yaw rate integration, which affect the accuracy of determining the host vehicle's azimuth.
Innovation Solution
A rearward white line inference device and method that includes a white line detection unit, an azimuth-relative-to-white-line generation unit, a relative azimuth inference unit, a target detection unit, a moving distance inference unit, a host vehicle trajectory inference unit, and a white line position inference unit, which collectively infer the rearward white line by combining data from GNSS, yaw rate sensors, and forward white line detection to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GNSS is used to obtain host vehicle azimuth for inferring rearward white line, then positioning accuracy is improved, but GNSS becomes unavailable in tunnels and buildings
Solution Approach 1:
The system switches between different azimuth measurement methods (GNSS, yaw rate integration, white line detection) based on availability conditions. When GNSS is unavailable, the system changes to alternative parameters and methods to maintain azimuth measurement capability.
Solution Approach 2:
The patent introduces intermediate solutions (yaw rate sensors, forward white line detection) that act as mediators when the primary GNSS system is unavailable, allowing continuous azimuth measurement through alternative pathways.
2Reliability
If yaw rate integration is used to obtain host vehicle azimuth, then availability is improved, but accumulated error increases when changing lane
Solution Approach 1:
The system uses feedback from forward white line detection to correct and reset accumulated errors in yaw rate integration. By continuously comparing inferred azimuth with azimuth derived from white line detection, the system identifies and corrects drift errors.
Solution Approach 2:
The system performs preliminary white line detection and azimuth calculation before relying on yaw rate integration for extended periods, establishing an accurate reference point that prevents accumulated error from developing.
3Device complexity
If only forward white line detection is equipped, then device complexity is reduced, but rearward white line cannot be directly detected
Solution Approach 1:
Instead of directly detecting the rearward white line with a rearward-facing sensor, the system inverts the approach by detecting the forward white line and using geometric relationships and vehicle trajectory to infer the rearward white line position.
Solution Approach 2:
The system creates a virtual copy of the forward white line detection capability by using the detected forward white line characteristics, combined with vehicle motion data, to generate information about the rearward white line without physical rearward detection hardware.
Data Source
AI summary
An object is to provide a rearward white line inference device, a target recognition device, and a method capable of inferring a rearward white line with high accuracy. A rearward white line inference device includes: a white line detection unit that detects a white line ahead of a host vehicle; an azimuth-relative-to-white-line generation unit that obtains an azimuth of the host vehicle relative to the white line every predetermined time interval based on a detection result of the white line detection unit; and a relative azimuth inference unit that infers a relative azimuth from the azimuth of the host vehicle at a certain point based on the azimuth of the host vehicle obtained by the azimuth-relative-to-white-line generation unit.