Horizontal Road Marking Recognition via Cell Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for recognizing horizontal road markings are inefficient, requiring significant computational effort and time, especially in dynamic driving scenarios where quick and accurate lane recognition is crucial for vehicle automation.
Innovation Solution
A method that captures road images and divides the central region into vertically superimposed cells with predefined lines aligned around a horizontal direction, calculates probability values and displacement values for each line, and uses a convolutional neural network to rapidly identify and determine the course of horizontal road markings, reducing computational effort and enhancing processing speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a complete image evaluation is performed to recognize horizontal road markings, then recognition accuracy is improved, but computational effort and processing time increase significantly
Solution Approach 1:
The image is divided into multiple vertically superimposed cells, with the central region containing potential horizontal road markings being evaluated in detail while peripheral regions are processed differently or skipped, reducing overall computational load while maintaining recognition accuracy for relevant markings
Solution Approach 2:
The central region of the image where horizontal road markings are most likely to appear is extracted and evaluated separately with higher computational resources, while peripheral regions receive minimal or no processing, achieving a balance between accuracy and processing time
2Reliability
If multiple predefined lines with various alignments are evaluated for each cell to accurately identify road markings, then recognition reliability is improved, but computational complexity increases
Solution Approach 1:
Different processing strategies are applied to different regions: the central region receives full evaluation with multiple predefined lines and角度 variations, while peripheral regions use simplified processing or are skipped entirely, optimizing the balance between reliability and computational complexity
Data Source
AI summary
A method for recognizing horizontal road markings and determining the course thereof. The method includes the steps of capturing an image of a road, and dividing a central region of the image into a plurality of vertically superimposed cells and assigning to each cell predefined lines that are variously aligned around a horizontal direction. In a further step, at least one probability value for the presence of a road marking and displacement values of the line to the road marking are calculated for each line of each cell. The probability values and the displacement values are subsequently entered into a calculation function, and at least one line is output. The course of the horizontal road marking is determined from the at least one line and the displacement values.