Ellipses Ring Marker for High-speed Finger Tracking
summary
A finger-ring marker with four ellipses (10 mm radius, 3D-printed nylon) enables pose estimation by fitting perspective-projected ellipses and runs on a high-frame-rate pipeline using an 500-fps camera and IR illumination. The recognition algorithm keeps processing below 2 ms per frame (thinning and LM optimization both under 1 ms), supports dynamic projection mapping to a palm with end-to-end latency ≈3 ms, and shows a systematic tilt bias (true 50° estimated ≈60°) to be corrected.
AI-written summary · about
chapters (7)
- 0:00Introduction and motivation
- 1:22Marker design background
- 2:38Ellipses Ring Marker concept
- 3:29High-speed recognition algorithm
- 6:28Performance evaluation results
- 7:35Dynamic projection demo
- 8:49Conclusion and future work
related talks
11mEfficient Finger Model and Accurate Tracking for Hover-and-Touch, Mid-air and Microgesture Intera...
14mDeepFisheye: Near-Surface Multi-Finger Tracking Technology Using Fisheye Camera
07mFingerTrak: Continuous 3D Hand Pose Tracking by Deep Learning Hand Silhouettes Captured by ...
14mBack-Hand-Pose: 3D Hand Pose Estimation for a Wrist-worn Camera via Dorsum Deformation Network
18mCamTrackPoint: Camera-Based Pointing Stick Using Transmitted Light through Finger
14mOddEyeCam: A Sensing Technique for Body-Centric Peephole Interaction using WFoV RGB and NFoV ...
17mEchoFlex: Hand Gesture Recognition using Ultrasound Imaging
20mToward Realistic Hands Gesture Interface: Keeping it Simple for Developers and Machines