Vehicle Localization Using Stationary Objects and Multi-Camera Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle localization systems rely heavily on satellite navigation data, which can be inaccurate, and struggle to compute additional positioning attributes like elevation and orientation, while object-based localization systems face challenges with frequently changing objects, increasing complexity and cost.
Innovation Solution
Utilize multiple imaging sensors to detect stationary objects in a vehicle's environment, computing relative positioning based on their orientation to these objects, and combining this with geolocation data to achieve high-accuracy absolute positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If satellite navigation data is used for vehicle localization, then the system can provide positioning data, but the accuracy is insufficient and additional positioning attributes cannot be computed
Solution Approach 1:
The patent combines satellite navigation data with imagery data from multiple imaging sensors to achieve both high accuracy localization and computation of additional positioning attributes. The system merges data from GPS satellites with visual data from cameras to derive not only position but also orientation and elevation information that satellite navigation alone cannot provide.
Solution Approach 2:
The patent introduces stationary objects with known geolocations as intermediaries between the vehicle and the final positioning calculation. By detecting these stationary objects in imagery data and using their known positions, the system can compute relative positioning and derive additional attributes like orientation and elevation without relying solely on satellite navigation limitations.
2Adaptability or versatility
If object-based localization systems use frequently changing objects, then the system can adapt to dynamic environments, but the complexity and cost increase
Solution Approach 1:
The patent applies different qualities to different objects in the localization system. Stationary objects with known geolocations are used as stable reference points for accurate positioning, while other objects in the environment can be dynamically detected and used for additional context. This allows the system to maintain high accuracy through stable references while still adapting to dynamic environments through flexible object detection.
Solution Approach 2:
The patent performs preliminary identification and classification of stationary objects with known geolocations before using them for localization. By pre-establishing a database of stationary objects and their positions, the system reduces real-time computational complexity while maintaining adaptability to dynamic environments through the flexible use of detected objects.
Data Source
AI summary
A method of self-localizing with respect to surrounding objects, comprising obtaining an approximated geolocation of the vehicle, retrieving mapping data comprising a geolocation of one or more stationary objects located in an area surrounding the approximated geolocation, receiving imagery data of a surrounding environment of the vehicle captured by a plurality of distinct imaging sensors deployed in the vehicle, applying one or more trained machine learning models to identify one or more of the stationary objects in the imagery data, computing a relative positioning of the vehicle with respect to one or more of the stationary objects based on an orientation of each of the plurality of imaging sensors with respect to the stationary object(s), computing an absolute positioning of the vehicle based on the relative positioning and the geolocation of the stationary object(s), and outputting the vehicle's absolute positioning.