Surgical Reference Array Tracking Using Multi-Frame Template Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing camera tracking systems for computer-assisted navigation during surgery are prone to intermittent pauses and reduced tracking accuracy due to objects being moved outside the tracking area or obstructed from camera view, necessitating improved tracking accuracy and reliability.
Innovation Solution
A camera tracking system that generates an array template by determining and averaging coordinates of physical objects in video frames, using a processor to track the pose of a reference array over time, and adjusts tracking based on defined accuracy rules, ensuring continuous and accurate navigation even when objects are obstructed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing navigation systems track objects using camera systems, then real-time pose feedback is provided to the surgeon, but tracking accuracy deteriorates when objects are moved outside tracking area or obstructed from camera view
Solution Approach 1:
The system performs preliminary actions by generating an array template from multiple video frames before tracking begins. This template serves as a reference that allows the system to continue tracking even when objects temporarily leave the tracking area or become obstructed, as the template contains pre-established coordinate information that can be used during such interruptions.
Solution Approach 2:
The array template acts as an intermediary between the camera tracking system and the reference array. When direct visual tracking is blocked or objects move outside the tracking area, the template provides intermediate coordinate data that maintains the tracking relationship, allowing the system to bridge gaps in direct observation and continue providing pose feedback.
2Reliability
If camera tracking systems use fixed tracking area boundaries, then the system structure remains simple, but tracking reliability decreases when objects move outside the tracking area
Solution Approach 1:
The system performs preliminary actions by generating an array template from multiple video frames before tracking begins. This template serves as a reference that allows the system to continue tracking even when objects temporarily leave the tracking area or become obstructed, as the template contains pre-established coordinate information that can be used during such interruptions.
Solution Approach 2:
The system transitions from purely spatial tracking within a fixed camera field of view to temporal tracking by incorporating the time dimension. The array template captures spatial coordinates across multiple time points, allowing the system to reconstruct object positions even when they temporarily leave the current viewing area, effectively adding a temporal buffer to the spatial tracking.
3Measurement precision
If the system uses multiple video frames to generate array template, then tracking accuracy improves through coordinate averaging, but processing time increases
Solution Approach 1:
The system performs preliminary actions by generating an array template from multiple video frames before tracking begins. This template serves as a reference that allows the system to continue tracking even when objects temporarily leave the tracking area or become obstructed, as the template contains pre-established coordinate information that can be used during such interruptions.
Solution Approach 2:
The system uses a defined number of video frames (excessive action) to generate the array template, which provides sufficient accuracy for tracking purposes. By processing a specific number of frames rather than continuously processing all available data in real-time, the system achieves high measurement precision during template generation while accepting a one-time processing delay that does not affect ongoing tracking performance.
Data Source
AI summary
A camera tracking system for computer assisted navigation during surgery. The camera tracking system includes a processor operative to receive streams of video frames from tracking cameras which image a plurality of physical objects arranged as a reference array. For each of the physical objects imaged in a sequence of the video frames, that processor determines a set of coordinates for the physical object over the sequence of the video frames. For each of the physical objects, the processor generates an arithmetic combination of the set of coordinates for the physical object. The processor generates an array template identifying coordinates of the physical objects based on the arithmetic combinations of the sets of coordinates for the physical objects, and tracks pose of the physical objects of the reference array over time based on comparison of the array template to the reference array imaged in the streams of video frames.


