Lane Marking Image Pre-processing for Autonomous Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated lane marking systems require large amounts of training data and computing resources due to the variability of road markings and the presence of extraneous data in images, leading to inefficiencies and inaccuracies in identifying lane markings for autonomous vehicles.
Innovation Solution
The system preprocesses images by dividing them into sub-images of straight road sections, normalizing them, and emphasizing road pixels, reducing the need for extensive training data and computing resources while maintaining accuracy through machine learning models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If automated lane marking systems use full images with extraneous data, then comprehensive road information is captured, but computing resources and training data requirements increase significantly
Solution Approach 1:
The patent divides the image processing task into segments by identifying and processing only the relevant road portions containing lane markings. The system segments the image based on road detection, isolates lane marking regions, and processes only those segments rather than entire images, thereby reducing computational complexity while maintaining identification accuracy.
Solution Approach 2:
The patent extracts and removes extraneous data from images by identifying and eliminating background elements, buildings, trees, and other non-road features. This extraction process isolates only the relevant road and lane marking information, reducing the data volume that requires processing while preserving the essential information needed for accurate lane marking identification.
2Measurement precision
If large amounts of training data are used to account for road variability, then model accuracy improves, but processing time and computational cost increase
Solution Approach 1:
The patent performs preliminary actions by pre-processing images to extract and normalize road features before lane marking detection. The system pre-identifies road boundaries, normalizes road orientations, and pre-segments relevant regions, thereby reducing the complexity of the main detection task and enabling faster processing while maintaining high accuracy with reduced training data requirements.
Solution Approach 2:
The patent applies parameter changes by normalizing road representations through transformations such as rotation alignment, scaling adjustments, and perspective corrections. These parameter changes standardize the input data format, reducing variability that would otherwise require extensive training data, thereby improving detection accuracy while reducing processing time.
3Adaptability or versatility
If images include all environmental features, then complete scene context is available, but the proportion of relevant road data decreases
Solution Approach 1:
The patent extracts and removes extraneous environmental features such as buildings, trees, and background elements from images. This extraction process isolates only the road surface and lane marking pixels, increasing the proportion of relevant data while preserving sufficient scene context for accurate lane marking detection through selective feature retention.
Data Source
AI summary
Systems and processes can reduce or divide images of road networks into sub-images that depict straight or substantially straight sections of roads in the road networks. These sub-images or image segments can be normalized by, for example, rotating each of the sub-images such that the depicted roads are horizontal or otherwise share the same angle. By aligning disparate images of roads, it is possible to both reduce the amount of training data used to generate a machine learning model and to increase the accuracy of an automated lane marking or labelling system. Further, the use of normalized images by the machine learning model enables a reduction in computing resources used to perform automated lane marking processes while maintaining or improving accuracy of the lane marking processes.