Sensor Positioning via Synthetic Vision Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current positioning devices lack precision in determining the relative position and spatial orientation of a moveable platform relative to an object, especially under conditions where GNSS signals are disrupted or unreliable, and there is a need for automated systems using cameras and GPUs.
Innovation Solution
The method involves using synthetic model datasets and trained synthetic models for computer vision object detection to determine the relative coordinate position and spatial orientation of a moveable platform by capturing images of objects with sensors, identifying the object, and generating model outputs based on the platform's position and orientation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GNSS positioning methods are used to determine position and navigation, then metropolitan-area position determination is supported, but measurement precision and accuracy are insufficient for applications requiring precise altitude information
Solution Approach 1:
The patent introduces an intermediary computer vision system that uses synthetic model datasets and trained synthetic models to determine relative position and spatial orientation. This intermediary system bridges the gap between GNSS providing absolute geographic coordinates and the need for precise relative positioning, especially when GNSS signals are disrupted or insufficient for high-precision altitude measurements.
Solution Approach 2:
The patent replaces the reliance on GNSS radio signal reception with a computer vision-based optical system. By using cameras to capture images and comparing them against synthetic model datasets, the system substitutes the electromagnetic signal-based positioning with an image-processing-based approach that achieves higher measurement precision for relative position and spatial orientation.
2Measurement precision
If traditional GNSS receivers are used for position determination, then absolute geographic coordinate position can be obtained, but accuracy is insufficient for applications reliant on precise altitude information
Solution Approach 1:
The patent makes the positioning system multi-functional by integrating both GNSS capabilities for absolute positioning and computer vision capabilities for relative positioning. The system can switch between or combine these methods depending on the application requirements, providing both absolute geographic coordinates and precise relative position/spatial orientation data including altitude information.
Solution Approach 2:
The patent segments the positioning function into two independent components: GNSS for determining absolute geographic coordinates and computer vision for determining relative position and spatial orientation. This segmentation allows each component to optimize for its specific function while working together to provide comprehensive positioning data with high altitude measurement accuracy.
3Measurement precision
If automated positioning devices using cameras and GPUs are implemented, then precise relative position determination is achieved, but device complexity and computational requirements increase
Solution Approach 1:
The patent applies preliminary action by pre-generating synthetic model datasets that represent various objects from multiple viewpoints and conditions. These datasets are used to train synthetic models in advance, so that during actual operation, the system only needs to capture images and compare them against the pre-trained models, significantly reducing real-time computational complexity while maintaining high measurement precision.
Solution Approach 2:
The patent uses copying by creating synthetic model datasets that are digital representations of physical objects. Instead of requiring complex real-time 3D reconstruction from images, the system compares captured images against pre-created synthetic copies of objects, simplifying the computational process while achieving precise relative position and spatial orientation determination.
Data Source
AI summary
A method and system to determine the position of a moveable platform relative to an object is disclosed. The method can include storing one or more synthetic models each trained by one of the one or more synthetic model datasets corresponding to one or more objects in a database; capturing an image of the object by one or more sensors associated with the moveable platform; identifying the object by comparing the captured image of the object to the one or more synthetic model datasets; generating a first model output using a first synthetic model of the one or more synthetic models, the first model output including a first relative coordinate position and a first spatial orientation of the moveable platform; and generating a platform coordinate output and a platform spatial orientation output of the moveable platform at the first position based on the first model output.