LuxAct: Enhance Everyday Objects for Visual Sensing with Interaction-Powered Illumination
summary
LuxAct encodes object ID and sensor data into sequences of RGB blinks that are powered by interaction-powered piezoelectric generators (striking and plucking) and decoded by POV cameras on AR headsets. The system uses ternary encoding with four interaction bits — theoretically 3^4 but reduced to 21 circular-unique sequences — and a parallel red/blue LED sensor readout where resistive changes shift color. Decoding uses a color-ratio sensor decoding method (reference bit subtraction) to cancel ambient light; prototypes (hinge, zipper bag, paper-towel weight) work but blinking is visible and fabrication/noise limit scale.
AI-written summary · about
chapters (7)
- 0:00Introduction and motivation
- 1:30LuxAct system overview
- 3:14Interaction-powered illumination
- 6:24LED tracking algorithm
- 8:09Sensing with color ratio
- 10:40Limitations and future work
- 11:24Q&A session
related talks
19mAdventures with blinking lights
18mSelf-Powered Gesture Recognition with Ambient Light
16mRVEdge-Vision: A Fully Open,Ultra-Efficient On-Device AI Platform for Smart Eyewear
19mAirCode: Unobtrusive Physical Tags for Digital Fabrication
20mMake an Amazing World pt.2
17mExploiting Digital Micro-Mirror Devices for Ambient Light Communication
22mI/O Braid: Scalable Touch-Sensitive Lighted Cords Using Spiraling, Repeating Sensing Textiles ...
17mI can stop adding more LEDs anytime I want, I just choose not to
