Keep the Phone in Your Pocket: Enabling Smartphone Operation with an IMU Ring for Visually ...
summary
A ring with a 9-axis IMU mounted on the index finger and wired to an Arduino senses subtle one-handed taps and swipes; data is filtered with Madgwick and fed to a multi-level SVM that classifies 15 gestures from 4,500 samples collected from 20 visually impaired participants, yielding 95.5% accuracy (leave-one-out CV). The prototype reduces registration time versus phone-based methods, scores higher on privacy and fun, and shows practical limits (unintentional registration), prompting plans for a physical button and onboard Bluetooth/battery.
AI-written summary · about
chapters (16)
- 0:00Start
- 0:20Background
- 0:51Related Works
- 1:11Keep the phone in Your Pocket
- 1:54COMMANDS AND GESTURES DESIG
- 2:07Command Design Step 1: Query scenarios
- 2:26Gesture Design • Define Design Space
- 2:43Mapping
- 2:58GESTURE RECOGNITION
- 3:22Registration Recognition Triple tap of finger pulp
- 4:0515 Classification Result
- 4:20USABILITY EVALUATION
- 4:40Learnability
- 4:50Efficiency
- 5:37Limitations
- 5:57Conclusion
related talks
14m"Wearable Sensory Substitution Device
16mGesturePod: Enabling On-device Gesture-based Interaction for White Cane Users
20mNew User Interface - Part 1
21mExploring Accessible Smartwatch Interactions for People with Upper Body Motor Impairments
40m"Learn to Touch Type" Glove
20mHybrid-Brailler: Combining Physical and Gestural Interaction for Mobile Braille Input and Editing
10mTeethTap: Recognizing Discrete Teeth Gestures using Motion and Acoustic Sensing on an Earpiece
23mRealPen: Providing Realism in Handwriting Tasks on Touch Surfaces using Auditory-Tactile Feedback