Eye-Trace: Segmentation of Volumetric Microscopy Images with Eyegaze
summary
System records continuous gaze-input skeleton tracing while users “fly” through 3D electron-microscopy stacks using a gamepad for pan/zoom and a chin rest for stability, with a low-cost EyeTribe/Eyes Right tracker. A 20-participant study (one discarded) traces 12 fibers at 10–40 frames/sec; tracing accuracy for large fibers stays within boundaries, for medium/small fibers error exceeds boundaries, but overall accuracy is about ≈ the fiber radius and supports speeds up to 40 sections/s. Mouse is more accurate; gaze is faster; repetition yields little improvement except modest learning on small fibers.
AI-written summary · about
chapters (15)
- 0:00Introduction
- 2:15Manual Annotation
- 3:04Manual Annotation in Neuroscience
- 3:54Manual Annotation Function
- 4:17Eyegaze Interaction
- 5:38Open Source
- 6:59User Experiment
- 7:46Data Preparation
- 8:30Experiment
- 9:50Main Experiment
- 10:38Repetition Experiment
- 11:18Size Accuracy Experiment
- 12:42Repetition Experiments
- 12:55Task Difficulty
- 13:45Conclusion
related talks
19mEyeScout: Active Eye Tracking for Position and Movement Independent Gaze Interaction with Large ...
19mGazeProjector: Accurate Gaze Estimation and Seamless Gaze Interaction Across ...
09mUsing Gaze Behavior and Head Orientation for Implicit Identification in Virtual Reality
10mHAGI: Head-Assisted Gaze Imputation for Mobile Eye Trackers
48mEye Tracking (a Deep Learning Approach)
40mThe eye of the Python, an eye tracking system. From zero to...
11mEfficient Finger Model and Accurate Tracking for Hover-and-Touch, Mid-air and Microgesture Intera...
10mEllipses Ring Marker for High-speed Finger Tracking