DT2140 Multimodal interfaces

Suggested projects

This list will be completed and is non-exhaustive. You may choose any project topic that interests you more, as long as you have had it approved by one of the teachers of the course.

Supervisors: OE=Olov Engwall, AF=Anders Friberg, RB=Roberto Bresin, JM=Jonas Moll AL=Anders Lundstrom.

Tangible interfaces, Augmented Reality etc.

Visual input and gestures

Audio visual recognition of direction gestures using Kinect skeleton tracking (OE): People in conversation replace directions words (right, left, front, back) with hand gestures. The goal of this project is to replace sentences such as:
"You have to go there and then turn there" into "You have to go right and then turn left."
Requirements: Kinect Camera, Kinect SDK + Kincect gesture recognition toolkit, Microsoft speech recognition, Good programming skills in C# or C++, Ambition.
Difficulty factor: Above Medium, Fun factor: High

Person Identification using Kinect skeletal data (OE): Can we use skeletal data to recognize people? (to log them into their computer accounts, open their email address, or open doors for them? How do we do it? What is the optimal pose to capture? And how difficult is it to fool it?
Requirements: Kinect Camera, Kinect SDK + Kincect gesture recognition toolkit, Microsoft speech recognition, Good programming skills in C# or C++, Ambition.
Difficulty factor: Medium, Fun factor: High

Recognizing emotional state by gestures (AF): Use a web camera or the accelerometers in wiimote as an interface to pd.

Sound and Music

Spoken interaction

Haptic interfaces

---

Course responsible: Olov Engwall, engwall@kth.se, 790 75 65