LiDAR Road Marking Detection Using Intensity Gradient Edges
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing semantic segmentation algorithms for autonomous driving rely on computationally expensive neural networks to process camera images for extracting semantic labels from LiDAR data, and existing techniques for detecting road markings from LiDAR point clouds struggle to distinguish road markings due to reliance on calibrated intensity values, which are insufficient as high intensity points can be present on other surfaces like buildings and curbs.
Innovation Solution
A method that processes LiDAR datasets by determining gradient edge points and identifying road marking edges based on intensity gradients, using uncalibrated intensity values to identify road markings, which can be used to generate maps and facilitate autonomous driving operations without requiring extensive training or calibration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If neural networks are used for semantic segmentation of LiDAR data, then semantic labeling accuracy is improved, but computational cost and processing time increase significantly
Solution Approach 1:
The patent replaces the mechanical/computational system of neural networks with a gradient-based detection algorithm. Instead of using complex neural network computations to identify road markings, the system uses intensity gradient calculations and geometric constraints to detect road marking edges, achieving comparable accuracy with significantly reduced computational cost and processing time.
Solution Approach 2:
The patent extracts and utilizes only the intensity gradient information from LiDAR data, separating this useful signal from the complex processing required by neural networks. By focusing specifically on intensity gradients and geometric relationships, the system achieves efficient road marking detection without the overhead of full neural network processing.
2Measurement precision
If calibrated intensity values are used to detect road markings, then detection accuracy is improved, but system complexity and calibration requirements increase
Solution Approach 1:
The patent enables the system to detect road markings using uncalibrated intensity values by relying on relative intensity gradients rather than absolute calibrated values. The algorithm automatically adapts to different sensors and environments by detecting intensity changes and patterns, eliminating the need for manual calibration procedures while maintaining detection accuracy.
Solution Approach 2:
The patent changes the detection parameter from absolute calibrated intensity values to relative intensity gradients. This parameter transformation allows the system to work with uncalibrated sensors by focusing on intensity differences and patterns rather than absolute values, thereby reducing calibration complexity while preserving detection capability.
Data Source
AI summary
Systems, methods, and autonomous vehicles for detecting road marking points from LiDAR data may obtain a LiDAR dataset generated by a LiDAR system; process, for each laser emitter of the LiDAR system, a point cloud associated with that laser emitter by: determining, for each point in the point cloud, based on a gradient of intensity at that point, whether that point corresponds to a gradient edge point; and determining, based on intensities of points in an interior segment of points between at least one candidate pair of gradient edge points and intensities of points in exterior segments of points outside the at least one candidate pair of gradient edge points, whether that candidate pair of gradient edge points corresponds to a road marking edge; and aggregate, from the processing of the plurality of point clouds, candidate pairs of gradient edge points determined to correspond to road marking edges.