Proactive Sensing for Improving Hand Pose Estimation
summary
Proactive sensing continually repositions a camera to raise hand-pose confidence by choosing rotations that reduce occlusion. A low-cost rig built from Leap Motion mounted on a Lego EV3 with IMU swings left/right or holds still while an approximate KD-tree nearest-neighbor policy predicts actions and updates an online user tree. A 17-subject study shows statistically significant higher confidence than static or random sensing, with per-user online updates improving performance.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 0:18Scenario
- 1:09HumanComputer Interaction
- 2:00Gestural Interaction
- 3:18Prototype
- 4:46Learning System
- 5:59Sensitivity Types
- 6:44Experiment
- 7:27Results
- 8:01Conclusion
related talks
14mBack-Hand-Pose: 3D Hand Pose Estimation for a Wrist-worn Camera via Dorsum Deformation Network
07mFingerTrak: Continuous 3D Hand Pose Tracking by Deep Learning Hand Silhouettes Captured by ...
05mTouchPose: Hand Pose Prediction, Depth Estimation, and Touch Classification from Capacitive Images
21mSketchingWithHands: 3D Sketching Handheld Products with First-Person Hand Posture
08mSo Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
13mUltraPoser: Pushing the Limits of IMU-based Full-Body Pose Estimation with Ultrasound Sensing on ...
20mToward Realistic Hands Gesture Interface: Keeping it Simple for Developers and Machines
19mBackHand: Sensing Hand Gestures via Back of the Hand