BEV Lane Line Recognition With Sliding-Window Curve Fitting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing lane line detection methods based on row classification suffer from overfitting due to structural similarities, leading to low detection accuracy in driverless or assisted driving scenarios.
Innovation Solution
A lane line recognition method that includes distortion correction, perspective transformation to obtain a bird's eye view image, and use of sliding windows to fit curves for accurate lane line detection, enhancing detection accuracy by minimizing overfitting and improving lane line identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If row classification method is used for lane line detection, then detection speed is fast and real-time performance is achieved, but detection accuracy deteriorates due to overfitting from structural similarities
Solution Approach 1:
The patent divides the lane line detection task into multiple stages: initial row classification for fast detection, followed by curve fitting (polynomial or spline) for precise lane line reconstruction. This segmentation allows the system to benefit from both the speed of row classification and the accuracy of curve-based methods, resolving the contradiction between detection speed and accuracy.
2Measurement precision
If curve fitting is applied to improve lane line detection accuracy, then detection precision is improved, but computational complexity and processing time increase
Solution Approach 1:
The patent performs preliminary row classification to identify candidate regions and initial lane line positions before applying computationally intensive curve fitting. This preliminary action reduces the search space and minimizes the computational burden of subsequent curve fitting operations, allowing high accuracy to be achieved without excessive computational complexity.
Data Source
AI summary
A lane line recognition method applied to an electronic device is provided. In the method, the electronic device converts a first foreground image into a bird's-eye view (BEV) image and determines the initial positions of the left lane line and the right lane line of the BEV image and fits a first curve and a second curve after a first sliding window slid each time and fits a third curve and a fourth curve after a second sliding window slid each time. The electronic device recognizes the left lane line according to the second curve and the right lane line according to the fourth curve. The method improves accuracy for recognizing lane lines of a road when a vehicle is moving on the road.