LIDAR Feature Mapping With Edge Extraction for Fast 3D Map Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating three-dimensional high-precision maps face challenges in ensuring accuracy and efficiency due to labor-intensive data processing, environmental vulnerabilities, and the difficulty in updating feature data in response to changes in the environment, such as road construction or obstacles.
Innovation Solution
A feature data generation system that utilizes a laser scanner with LIDAR technology to extract edge patterns, assign terrestrial reference frame positions, and generate feature data, incorporating self-position estimation and anomaly detection to ensure accurate and efficient updating of feature databases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a laser scanner using LIDAR technology is used to acquire position data of all measurement points surrounding the vehicle, then measurement precision is improved, but processing time and labor increase enormously
Solution Approach 1:
The patent extracts only the necessary feature data from the enormous amount of position data acquired by the laser scanner. By identifying and extracting only the relevant measurement points that constitute features (road edges, lanes, guard rails, road signs, crosswalks), the system avoids processing all position data, thereby reducing processing time and labor while maintaining high measurement precision for the extracted features.
Solution Approach 2:
The patent segments the enormous dataset into manageable components by categorizing measurement points into different feature types (road edges, lanes, guard rails, road signs, crosswalks). This segmentation allows for targeted processing of specific feature categories rather than processing all position data uniformly, significantly reducing the time and computational resources required.
2Device complexity
If feature data is acquired using a monocular camera, then device complexity is reduced, but measurement precision deteriorates due to insufficient ranging accuracy
Solution Approach 1:
The patent replaces the optical measurement system (monocular camera) with a LIDAR-based measurement system. LIDAR technology uses laser light to directly measure distance through time-of-flight calculations, providing accurate ranging data without the complexity of multiple cameras or sophisticated image processing algorithms. This substitution maintains device simplicity while dramatically improving measurement precision.
3Measurement precision
If compound-eye cameras are used to acquire feature data, then measurement precision is improved through triangulation, but device complexity and cost increase
Solution Approach 1:
The patent replaces the complex optical triangulation system (compound-eye cameras requiring calibration and positioning) with a LIDAR-based direct measurement system. LIDAR provides accurate ranging through direct time-of-flight measurement of laser light, eliminating the need for multiple cameras, calibration procedures, and complex triangulation calculations, thereby reducing device complexity while maintaining high measurement precision.
Solution Approach 2:
The patent introduces LIDAR technology as an intermediary measurement tool between the vehicle and the environment. Instead of using complex camera systems that require mutual calibration and positioning, the LIDAR system independently provides accurate distance measurements to all surrounding objects, simplifying the overall measurement system while maintaining high precision.
4Measurement precision
If compound-eye cameras perform repeated triangulation calculation during vehicle movement, then measurement precision is improved, but processing time increases enormously
Solution Approach 1:
The patent replaces the computationally intensive repeated triangulation calculations required by compound-eye cameras with direct time-of-flight measurements from LIDAR. Each measurement point's distance is calculated independently and immediately based on the time for laser light to travel to and from the target, eliminating the need for repeated complex mathematical calculations while maintaining high measurement precision.
5Device complexity
If a monocular camera is used to grasp surrounding situation, then device complexity is reduced, but feature data accuracy deteriorates
Solution Approach 1:
The patent replaces the simple but inaccurate monocular camera system with a LIDAR-based measurement system. LIDAR provides direct, accurate distance measurements to surrounding features through time-of-flight calculation, enabling high-precision feature data acquisition (road edges, lanes, guard rails, road signs, crosswalks) without the complexity of multiple cameras or sophisticated image processing.
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 secures the accuracy of three-dimensional high-precision maps by reducing unnecessary data, correcting for environmental changes, and ensuring timely updates, thereby enhancing the reliability of autonomous driving systems.
Implementation Method 1
a laser scanner using LIDAR technology to extract edge patterns
Implementation Method 2
The use of the LIDAR technology makes it possible to acquire position data of an accurate distance to a measurement point using laser light
Data Source
AI summary
In a feature data generation system, an edge pattern indicating a boundary of a target feature existing around a vehicle is extracted from position data of a large number of measurement points surrounding the vehicle measured using a LIDAR technology, on the basis of image data of surroundings of the vehicle obtained by imaging so as to reduce the amount of information, positions in a terrestrial reference frame are assigned to the extracted edge pattern, and a shape characteristic vector and a feature characteristic vector to be used for generating or updating a feature in a feature database, are generated from the edge pattern to which the positions in the terrestrial reference frame are assigned.