Satellite Position Association via Pseudo-Projection Diagrams
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating three-dimensional coordinates of subjects in satellite images, such as the line-of-sight intersection method, face challenges with accuracy due to uncertainties in sensor posture information and three-dimensional data resolution, especially when imaging specifications like wavelength and exposure time vary.
Innovation Solution
A position association system that generates a projection diagram from three-dimensional data and creates a pseudo-projection diagram through image-to-image translation using deep learning models like pix2pix, allowing for accurate association of points between the satellite image and three-dimensional shape without relying on exact imaging specifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If the line-of-sight intersection method is used to estimate three-dimensional coordinates, then the estimation process is straightforward, but the accuracy deteriorates due to uncertainties in sensor posture information and three-dimensional data resolution
Solution Approach 1:
The patent introduces a pseudo-projection diagram as an intermediary between the satellite image and the three-dimensional data. This pseudo-projection diagram, generated through image-to-image translation, serves as a mediator that bridges the gap between the two data sources, enabling accurate point association without requiring precise sensor posture information or high-resolution three-dimensional data
Solution Approach 2:
The patent creates a pseudo-projection diagram that is a synthetic copy or representation of what the projection diagram would look like based on the actual satellite image. This copy is generated using deep learning models (pix2pix) and serves as a substitute for the actual projection diagram, allowing for accurate point matching without needing exact imaging specifications
2Measurement precision
If exact imaging specifications (wavelength, exposure time) are required for accurate coordinate estimation, then the accuracy improves, but the system complexity and data requirements increase
Solution Approach 1:
The patent changes the approach from using exact imaging parameters (wavelength, exposure time, sensor posture) to using a learned transformation model. Instead of relying on precise parameter matching, the system uses image-to-image translation that is invariant to these parameter variations, thereby achieving accuracy without requiring exact imaging specifications
3Ease of operation
If traditional point matching methods are used between projection diagram and satellite image, then the process is simple, but the accuracy deteriorates when imaging specifications vary
Solution Approach 1:
The patent creates a pseudo-projection diagram that accurately represents the satellite image content in the projection diagram coordinate system. This copy is generated through deep learning and maintains geometric accuracy even when imaging specifications vary, enabling precise point association
Solution Approach 2:
The patent transforms the matching approach from direct parameter-based matching to a learned geometric transformation. The system learns the mapping relationship between the pseudo-projection diagram and the projection diagram, making the matching process robust to variations in imaging parameters
Data Source
AI summary
The projection diagram generation means 71 generates a projection diagram, which is a diagram obtained by projecting a three-dimensional shape of an object onto a two-dimensional plane along direction of a line of sight of a sensor of an artificial satellite. The pseudo-projection diagram generation means 72 generates a pseudo-projection diagram that represents the projection diagram in a pseudo way, based on a satellite image. The association means 73 associates points in the projection diagram with points in the pseudo-projection diagram. The mapping derivation means 74 derives a mapping that associates the point in the pseudo-projection diagram with points in the three-dimensional shape represented by the three-dimensional data, based on a result of association between the points in the projection diagram and the points in the pseudo-projection diagram.