Aerial Image and Radar Fusion for Precise Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face limitations in accurately determining their location due to the use of vehicle cameras with horizontal or almost horizontal optical axes, which restricts the precision of location determination.
Innovation Solution
Utilizing aerial images and radar sensed environment information to enhance location determination by fusing spatial relationships and bird's eye based location information, leveraging machine learning processes for object detection and mapping, and integrating this with vehicle location estimates from GPS and other sensors to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If horizontal or almost horizontal vehicle cameras are used for location determination, then the device complexity is reduced, but the measurement precision of location determination deteriorates
Solution Approach 1:
The patent combines vehicle camera images with aerial images to determine location. The vehicle camera captures images of the environment, and aerial images providing bird's eye view location information are integrated with these images through image fusion techniques, allowing accurate location determination while maintaining simple horizontal camera configuration
Solution Approach 2:
The patent uses aerial images as an intermediary to bridge the gap between simple horizontal camera setup and accurate location determination. The aerial images serve as a mediator that provides additional spatial context and location information that complements the vehicle camera data
2Measurement precision
If aerial images with normal optical axis are used to provide bird's eye location information, then the measurement precision of location determination is improved, but the device complexity increases
Solution Approach 1:
The patent makes the vehicle camera system multi-functional by using it for both traditional driving perception and location determination. The same vehicle camera images are used for both navigating the vehicle and determining its location by comparing with aerial images, eliminating the need for separate specialized sensors
Solution Approach 2:
The patent uses a portion of the aerial image data and vehicle camera data that is sufficient for location determination without processing the entire datasets. By selectively using relevant features and information from the images, the system achieves accurate location determination while reducing computational complexity
Data Source
AI summary
A method for driving related applications based on aerial images. The method includes (i) determining, by a processor, based on aerial map segment information and sensed environmental information, a driving control action in association the vehicle within at least the environment of the location estimate of the vehicle; (ii) determining, based on the sensed environmental information and according to the aerial map segment information, whether to perform the driving related operation within at least the environment of the location estimate of the vehicle; and (iii) responsive to determining the performance of the driving related operation, outputting information regarding the driving related operation to a control system of the vehicle.