3D Image Registration Using Feature Distance Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical imaging systems face challenges in accurately displaying the size of objects within a three-dimensional scene due to fixed pixel size and varying distances from the collection optic, leading to inconsistent object sizing and complexity in registering and reconstructing multiple images during procedures like lithotripsy.
Innovation Solution
A method involving capturing multiple images at different times and positions, generating feature distance maps, and using these maps along with positional camera changes to create a three-dimensional surface approximation, leveraging illumination data and endoscopic device motion to enhance registration and reconstruction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple images are captured and registered to reconstruct three-dimensional scene, then measurement precision of object size is improved, but device complexity and computational requirements increase
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing feature distance maps for each image frame before registration. These feature distance maps contain pre-processed depth information that simplifies the subsequent three-dimensional reconstruction process, reducing computational complexity during real-time operation while maintaining measurement precision.
Solution Approach 2:
The patent segments the image processing task into distinct components: feature detection, feature distance map generation, camera pose estimation, and three-dimensional reconstruction. By dividing the complex registration process into manageable segments, the system reduces overall computational complexity while achieving accurate object size measurement through coordinated processing of each segment.
2Measurement precision
If feature distance maps are generated for all pixels, then measurement precision is improved, but computational processing requirements increase
Solution Approach 1:
The patent applies local quality by generating feature distance maps only for pixels containing relevant anatomical features rather than all pixels in the image. This selective approach concentrates computational resources on regions with diagnostic value, improving depth measurement precision for critical structures while reducing overall computational processing requirements.
3Manufacturing precision
If camera position changes are tracked precisely, then three-dimensional reconstruction accuracy is improved, but device complexity increases
Solution Approach 1:
The patent introduces feature distance maps as an intermediary that mediates between camera position data and three-dimensional reconstruction. These maps translate complex camera pose information into simplified depth representations, improving reconstruction accuracy while reducing the complexity of the tracking system by decoupling position measurement from final reconstruction calculations.
Data Source
AI summary
Systems and methods related to combing multiple images are disclosed. An example method of combining multiple images of a body structure includes capturing a first input image with a digital camera positioned at a first location at a first time point, representing the first image with a first plurality of pixels, capturing a second input image with the digital camera positioned at a second location at a second time point, representing the second image with a second plurality of pixels, generating a first feature distance map of the first input image, generating a second feature distance map of the second input image, calculating the positional change of the digital camera between the first time point and the second time point and utilizing the first feature distance map, the second feature distance map and the positional change of the digital camera to generate a three-dimensional surface approximation the body structure.