Fused Pavement Marker Detection for Autonomous Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving systems struggle to accurately detect and track lane boundaries marked by raised pavement markers, particularly in environments without painted lane markings, leading to operational inefficiencies and potential safety issues.
Innovation Solution
An in-vehicle lane boundary detection system that combines a camera and image processing module with a lidar detector and lidar processing module to detect and track lane boundaries using both non-reflective and reflective raised pavement markers, fusing image-based and lidar-based probability models to enhance detection accuracy and range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a camera-based image processing system is used to detect raised pavement markers, then detection capability for non-reflective markers is improved, but detection range and reliability are limited
Solution Approach 1:
The patent combines camera-based image processing and lidar-based detection into a unified lane boundary detection system. The camera detects both reflective and non-reflective raised pavement markers, while lidar provides additional detection capability and range. The systems fuse their probability models to achieve improved detection reliability and extended detection range.
2Length of stationary object
If lidar detection is used to detect reflective raised pavement markers, then detection range is improved, but ability to detect non-reflective markers is lost
Solution Approach 1:
The camera-based image processing system serves multiple functions: detecting both reflective and non-reflective raised pavement markers, providing probability model formulation, and working in conjunction with lidar. This multi-functional approach ensures comprehensive marker detection capability while maintaining extended detection range through lidar.
3Device complexity
If a single detection system is used, then device complexity is reduced, but detection accuracy and reliability deteriorate
Solution Approach 1:
The detection system is segmented into distinct functional modules: camera-based image processing module for detecting raised pavement markers, lidar-based detection module for extended range detection, and a fusing module that combines their probability models. This segmentation allows each module to specialize in specific detection tasks while maintaining overall system accuracy through coordinated operation.
4Speed
If image-based processing is used alone, then processing speed is maintained, but detection reliability in environments without painted markings deteriorates
Solution Approach 1:
The fusing module acts as an intermediary that combines the probability models from image-based processing and lidar detection. This intermediary integration allows the system to leverage the speed advantage of image processing while achieving the reliability enhancement provided by lidar, particularly in environments without painted lane markings.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system provides accurate and reliable detection of lane boundaries, improving the performance of autonomous driving systems and lane departure warning systems by leveraging the strengths of both camera and lidar technologies, even in environments without painted markings.
Implementation Method 1
a lidar detector and an associated lidar processing module for detecting reflective raised pavement markers
Data Source
AI summary
An in-vehicle system for estimating a lane boundary based on raised pavement markers that mark the boundary. The in-vehicle system includes a camera for obtaining image data regarding reflective raised pavement markers and non-reflective raised pavement markers, an image processor for processing frames of image data captured by the camera, a lidar detector for obtaining lidar data regarding reflective raised pavement markers, and a lidar processor for processing frames of lidar data captured by the lidar detector. The image processor generates a first probabilistic model for the lane boundary and the lidar processor generates a second probabilistic model for the lane boundary. The in-vehicle system fuses the first probabilistic model and the second probabilistic model to generate a fused probabilistic model and estimates the lane boundary based on the fused probabilistic model.