Onboard LIDAR Transit Positioning with 3D-to-2D Reference Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for determining the location of vehicles along pathways using 3D LIDAR images are computationally intensive, exceeding the power capacity of standard subway trains, and require significant installation and maintenance costs for wayside equipment.
Innovation Solution
Converting 3D LIDAR images to 2D images, which are then compared to reference 2D images, allowing the location determination to be performed on the vehicle itself without the need for wayside equipment, using techniques like keypoints and descriptors to enhance matching efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If 3D LIDAR images are processed to determine vehicle location, then location accuracy is improved, but power consumption exceeds the capacity of standard subway trains
Solution Approach 1:
The patent extracts only the essential features needed for location determination from the full 3D LIDAR data. By converting 3D images to 2D images and using keypoints and descriptors, the system processes only the most relevant information, dramatically reducing computational load and power consumption while maintaining location accuracy.
Solution Approach 2:
The patent creates simplified 2D representations (copies) of the original 3D LIDAR images. These 2D images serve as efficient proxies that retain the essential spatial information needed for location determination but require far less computational resources to process.
2Measurement precision
If conventional location determination methods are used, then location data can be obtained, but significant installation and maintenance costs are incurred for wayside equipment
Solution Approach 1:
The patent enables the vehicle to determine its own location using only onboard LIDAR sensors and processing equipment. The vehicle independently captures 3D images, converts them to 2D images, extracts keypoints and descriptors, and matches them against reference data without requiring any external wayside equipment for installation or maintenance.
Solution Approach 2:
The patent replaces the mechanical/physical wayside equipment infrastructure with an optical-computational system based on LIDAR sensing and image processing. This substitution eliminates the need for physical installation and maintenance of wayside devices while achieving the same location determination function.
3Measurement precision
If 3D LIDAR images are directly compared to reference images, then accurate location determination is achieved, but computational complexity becomes excessive
Solution Approach 1:
The patent segments the complex 3D image comparison task into distinct stages: (1) conversion of 3D images to 2D images, (2) extraction of keypoints from 2D images, (3) generation of descriptors for keypoints, and (4) matching of descriptors against reference data. This segmentation reduces computational complexity at each stage while preserving location determination accuracy.
Solution Approach 2:
The patent transforms the problem from 3D image space to 2D image space, and then to a feature space defined by keypoints and descriptors. This dimensional reduction and transformation simplifies the comparison operation while maintaining the essential spatial relationships needed for accurate location determination.
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
This approach reduces power consumption and eliminates the need for costly wayside equipment, enabling accurate vehicle location determination on standard subway trains with reduced operational costs and increased efficiency.
Implementation Method 1
The vehicle may employ Light Detection and Ranging (LIDAR) technology to generate the 3D image of the pathway
Data Source
AI summary
Transit location systems and methods using LIDAR are provided. In some embodiments, a computer-implemented method comprises receiving a 3D image captured from a vehicle on a pathway; transforming the 3D image into a first 2D image; and determining a location of the vehicle along the pathway, comprising: comparing the first 2D image to a plurality of second 2D images each captured at a respective known location along the pathway, selecting one or more of the second 2D images based on the comparing, and determining the location of the vehicle along the pathway based on the known location where the selected one or more of the second 2D images was captured. The 3D image may be captured by capturing LIDAR data with a LIDAR unit mounted on the vehicle.