Chair of Sensor Technology
WISEglass

WISEglass

ACTLab Activities

WISEglass is our approach to smart eyewear. It is based on WISEnode and embedded into off-the-shelf eyeglasses. The vision behind WISEglass is to embed electronics into regular eyeglasses where the focus is on sensing and processing.

Current Efforts

Currently we are working on a 3D printed prototype which will integrate the hardware to a higher degree. The goal is to make all wires disappear and integrate the sensing and processing hardware in a ubiquitous fashion.

Key features

  • Multi-modal wearable sensor platform.
  • Stream data via Bluetooth Smart or store up to 512MB locally.
  • Battery runtime of 32 hours.

Objectives

  • Integrate sensing and processing electronics into regular eyeglasses.
  • Enable smart eyewear for a wide range of sensing applications.
WISEglass prototype: Baseboard, battery, accelerometer, gyroscope, and magnetometer are mounted on the outside of the eyeglasses’ temple. The pulse sensor is mounted on the inside of a temple. The light sensor is integrated into the bridge.
Passauer Data Science Konferenz 2016 (PASDAS)

Possible applications 

Activity recognition

WISEglass can be used to distinguish different activities of daily life. In a study with 9 participants we evaluated the recognition performance for 20 different activities which were grouped into 9 activity clusters. Using leave-one-person-out cross-validation, we achieved an average recognition rate of 77%. For more details, please see [2, 3].

Screen-use detection

Screen-use and its timing are important factors for circadian phase shift. Especially when exposed to at night, the light from e.g. a computer screen can induce a phase delay and hence hamper falling asleep. Using a Gaussian Mixture Model classifier we obtained 80%accuracy in the work presented in [3].

Click on the picture to watch "WISEglass Screen-use detection"

Heart rate estimation

The pulse sensor built into WISEnode can be used to determine heart rate. In our evaluation study [3] we found the mean root mean square error during stationary activities to be below 9 bpm. In [4] we integrated the heart rate into a the popular Pac-Man game.

Wireless game controller

To demonstrate the wide range of possible applications we modified the popular Pac-Man game such that it can be controlled using WISEglass [4]. The user controls the moving direction of Pac-Man through head gestures (e.g. shaking head to the left for left) which are sensed by the gyroscope. In addition we integrated a heart rate display into the game so the user can see the effect of playing on the heart rate.

Nutrition monitoring

The combination of nutrition monitoring and eyeglasses is an innovating and promising concept. At our lab, we bring this concept into life and prove this is a practical method for the chewing monitoring. By integrating EMG (electromyography) sensor and skull vibration sensor into our eyeglasses, we turn the eyeglasses into "diet eyeglasses", which so far can count chewing numbers online[8], classifying category of daily food intake [5][7]. Higher level of integration and better user experience will be our main focus.

Publication List

About

Project start: February 2015

Available Sensors:

  • 3 axis accelerometer
  • 3 axis gyroscope
  • 3 axis compass
  • RGB light sensor
  • Pulse sensor

Battery runtime: 32 hours

People:
Jakob Kasbauer
Martin Freund
Rui Zhang
Florian Wahl
Prof. Dr. Oliver Amft