Silhouette Tracking with Mask Library for Attitude Determination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Visual attitude determination systems face challenges in accurately determining the attitude of objects with ambiguous shapes or occlusions, such as aircraft with detachable fuel tanks or satellites with articulating solar panels, due to mismatches in silhouette images, which can significantly reduce the accuracy of attitude scoring.
Innovation Solution
The use of mask library images that include structures not physically part of the object, such as refueling booms or external fuel tanks, to identify and remove ambiguous areas from the comparison process, improving the certainty of attitude determination by comparing pixel matches between the object image and the library image, either through binary or full intensity comparisons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a silhouette library is created for objects with variable configurations (e.g., aircraft with detachable fuel tanks), then the system must create multiple libraries for every possible configuration, but this increases device complexity and may not recognize unique configurations
Solution Approach 1:
The patent segments the silhouette comparison process into two distinct stages: first comparing the main object silhouette, then separately comparing mask silhouettes for ambiguous areas. This segmentation allows the system to handle variable configurations without requiring separate libraries for each possible arrangement, as the mask library contains all possible ambiguous structures that can be selectively applied during comparison.
Solution Approach 2:
The patent introduces mask images as an intermediary element between the object image and the silhouette library. These masks represent ambiguous or variable structures (like fuel tanks or solar panels) and are used to selectively mask out regions during comparison. This intermediary approach allows the system to accommodate multiple configurations without expanding the core silhouette library.
2Measurement precision
If pixel-to-pixel matching is performed between object image and library image, then measurement precision is improved, but areas with occlusions or ambiguous structures reduce the overall Fit score significantly
Solution Approach 1:
The patent extracts ambiguous or occluding areas from the overall silhouette comparison by using mask images. These masks identify specific regions (such as exhaust plumes, propellers, or detachable structures) that should be excluded from the Fit score calculation. By taking out these problematic areas separately, the system maintains high measurement precision for the remaining stable structures without being penalized by unavoidable occlusions.
Solution Approach 2:
The patent performs preliminary identification and masking of ambiguous areas before the final attitude determination. By pre-defining mask libraries that represent various ambiguous structures and their possible locations, the system prepares in advance for potential occlusions, allowing the main comparison process to focus on reliable features while predetermined mask regions are automatically excluded from scoring.
Data Source
AI summary
A method and system for increasing the certainty of a silhouette matching process, where the process is being used for attitude determination of an object of interest, for example an aircraft. The method involves using one or more mask images that include structure or features that may or may not always be associated with the object of interest, and overlaying the mask image(s) onto a library image of the aircraft. Each pixel of the library image is compared against corresponding pixels of the mask image(s) to determine which pixels represent ambiguous areas of the library image. Those pixels are eliminated from consideration in determining a Fit score, where the Fit score represents a percentage value indicative of a certainty of the matching process in identifying the attitude of the aircraft. The method and system is applicable to a wide ranging variety of object detection applications.