Intrinsic Feature Pose Measurement for Imaging Motion Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional motion tracking and correction technologies for imaging, such as SPECT, rely on external markers that are cumbersome and can cause subject discomfort or dislodgement, and often struggle with detecting relevant features from images, leading to inaccurate pose measurements.
Innovation Solution
The system employs intrinsic feature pose calculation methods that extract and track natural features from optical 2D stereo images, determining 3D locations and fitting them to a rigid body transformation to calculate pose changes over time, eliminating the need for external markers and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If external markers are used for motion tracking, then pose measurement accuracy is improved, but device complexity and subject discomfort increase
Solution Approach 1:
The patent extracts and removes external markers from the motion tracking system, instead using intrinsic features naturally present in the subject (such as anatomical landmarks or distinctive visual features) to perform pose estimation. This eliminates the need for additional hardware components and simplifies the overall system while maintaining measurement accuracy.
Solution Approach 2:
The system uses the subject's own inherent features (intrinsic features) for pose tracking rather than requiring external markers. The subject's natural anatomy or visual characteristics serve the dual purpose of both the imaging target and the motion tracking reference, eliminating the need for separate tracking markers and reducing handling complexity.
2Measurement precision
If external markers are used for motion tracking, then pose measurement accuracy is improved, but subject comfort and reliability deteriorate
Solution Approach 1:
The patent removes external markers from the system and relies solely on intrinsic features of the subject for pose estimation. This eliminates the reliability issues associated with markers becoming dislodged, falling off, or causing discomfort to the subject during the imaging scan.
Solution Approach 2:
By using the subject's own inherent features (such as anatomical landmarks, ear canals, eyes, or distinctive visual patterns) for tracking, the system ensures continuous and reliable pose measurement without the risk of marker loss or subject discomfort. The subject's natural features remain constant and cannot be dislodged during the scan.
3Device complexity
If intrinsic features are used for pose measurement, then device complexity is reduced, but measurement precision deteriorates
Solution Approach 1:
The patent segments the pose estimation process into distinct computational steps: extracting intrinsic features from images, tracking their positions across multiple frames, calculating transformations, and determining final pose. This segmentation allows each step to be optimized independently, maintaining high measurement precision while using only intrinsic features without external markers.
Solution Approach 2:
The system transitions from 2D image coordinates of intrinsic features to 3D pose estimation by leveraging temporal information and geometric relationships across multiple frames. By adding the temporal dimension and using computational geometry, the system achieves accurate 3D pose measurement using only intrinsic features, compensating for the absence of external markers through sophisticated image processing and tracking algorithms.
Data Source
AI summary
Systems and methods for generating motion corrected tomographic images are provided. A method includes obtaining first images of a region of interest (ROI) to be imaged and associated with a first time, where the first images are associated with different positions and orientations with respect to the ROI. The method also includes defining an active region in the each of the first images and selecting intrinsic features in each of the first images based on the active region. Second, identifying a portion of the intrinsic features temporally and spatially matching intrinsic features in corresponding ones of second images of the ROI associated with a second time prior to the first time and computing three-dimensional (3D) coordinates for the portion of the intrinsic features. Finally, the method includes computing a relative pose for the first images based on the 3D coordinates.