Ego Lane Search Using Lane Marking Type Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional lane detection systems struggle to accurately identify and select the ego lane in scenarios with multiple lane markings, especially in construction sites where markings are confusing or missing, leading to false detections and reduced system availability.
Innovation Solution
A device and method that classify lane candidates based on the type and orientation of lane markings, using a predetermined hierarchy to search for the ego lane, and apply criteria such as width, distance, and geometry to select the appropriate lane for the vehicle to drive on, even in complex road conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional lane detection systems shut down during construction sites with yellow lane markings, then false detections are avoided, but system availability is restricted
Solution Approach 1:
The patent segments lane markings by color type (white vs. yellow) and creates separate lane candidate lists for each type. The system processes white lane markings and yellow lane markings independently, allowing simultaneous evaluation of both types without interference, thus maintaining system operation during construction sites while avoiding false detections through proper segmentation of detection results
Solution Approach 2:
The patent changes the parameter of lane candidate classification by introducing color-based categorization (white lane candidates vs. yellow lane candidates). This parameter change enables the system to distinguish between normal road conditions and construction site conditions, allowing continuous operation with adjusted detection parameters rather than system shutdown
2Adaptability or versatility
If multiple lane markings with the same color are detected, then comprehensive lane coverage is achieved, but correct ego lane selection becomes difficult
Solution Approach 1:
The patent segments multiple lane markings of the same color into organized lists (white lane candidate list, yellow lane candidate list) with defined search orders. This segmentation transforms the complex problem of selecting among multiple same-color markings into a structured search process through the lane candidate list, reducing selection complexity while maintaining comprehensive coverage
Solution Approach 2:
The patent performs preliminary classification of lane markings into white and yellow categories before ego lane selection, and pre-organizes them into ordered candidate lists. This preliminary action establishes a clear search hierarchy, making the subsequent ego lane selection process simpler and more deterministic rather than dealing with unorganized multiple candidates
3Reliability
If lane markings are missing or detected incorrectly, then system robustness is tested, but correct lane selection becomes challenging
Solution Approach 1:
The patent creates redundant lane candidate lists for both white and yellow lane markings, preparing multiple potential ego lane options in advance. This beforehand cushioning ensures that if some lane markings are missing or incorrectly detected, alternative candidates remain available, maintaining detection robustness and precision through pre-prepared backup options
Data Source
Figure 1~2
Figure 3A~3B
Figure 3C~3D
AI summary
A device for searching for a lane on which a vehicle can drive, wherein the device is configured to receive an image captured by a camera, the image showing an area in front of the vehicle, detect lane markings in the image, determine for each of the lane markings if the respective lane marking is of a first type indicating a road condition of a first type or a second type indicating a road condition of a second type, create lane candidates from the lane markings, divide the lane candidates into classes of lane candidates depending on the type of the lane markings of the lane candidates, and search the classes of lane candidates for a lane on which the vehicle can drive.