Mike Karlesky

Biomechanics of Expressivity: Final Presentation

by Mike Karlesky on May 10, 2013

Final Biomechanics of Expressivity Presentation Ultimately, I tend to think that using a bare biomechanical model of the kinetics and kinematics of human gesture to produce an “expressivity vector” is a successful failure. The result does not quite mesh with human expectations of gesture. We clearly possess filters and thresholds and feature extraction models in […] more…

Biomechanics of Expressivity Presentation

by Mike Karlesky on April 15, 2013

My Presentation [PDF] more…

Biomechanics of Expressivity: Visualization Work

by Mike Karlesky on April 8, 2013

As I’ve noted previously, meaningfully visualizing my expressivity vectors has certain challenges. The dimensionality of the data is difficult to visualize from a single vantage point. A good sense of motion seems to be key even though it is somewhat abstracted from the full range of motion of an upper body. And, of course, as […] more…

In the 2012 U.S. presidential election, the NYU Movement Lab performed extensive analysis of the movements and body language the candidates used in debates and appearances. The most comprehensive and computational of these efforts was their Gesture Cloud. more…

Biomechanics of Expressivity: Final Design

by Mike Karlesky on April 1, 2013

Design Interaction space & hardware In working through the nitty gritty of extracting the biomechanics of expressivity from Kinect data, I realized that I had lost sight of a primary design goal — processing the gestural activity of two people with one another rather than a single individual interacting with a gesture sensing technology. So […] more…

(Original article and video) Not human biomechanics but still interesting… Vertebrate physiologist Tomasz Owerkowicz straps masks onto crocodiles and alligators to measure air intake and oxygen use to understand the piston-like nature of their diaphragms. In the process, he and his colleagues hope to also understand how dinosaurs breathed. more…

Biomechanics of Expressivity: Minimum Viable Product

by Mike Karlesky on March 25, 2013

The accompanying image is a screenshot of my minimum viable product. The upper body skeleton is produced with data from the Microsoft Kinect’s seated mode. The gray “stripe” is a simple vector drawn in 3D space to visually depict the result of expressivity calculations. Both graphical depictions are easier to grok when they’re in motion. […] more…

Look at that athletic performance asymptote… more…

The Pain of Electricity (AC versus DC)

by Mike Karlesky on March 12, 2013

For those of you in our class zapping yourselves… Mehdi Sadaghdar posts entertaining electrical-engineering-y demonstration videos. In this one he explores the sensation and pain of direct and alternating current passed through the body. Beware, while the video is fun to watch, parts of it might make you cringe. There’s an interesting segment at about 2:50 […] more…

Biomechanics of Expressivity: Concept Development

by Mike Karlesky on March 11, 2013

My goal is to create a measure of human expressivity calculated from the kinetics and kinematics of the human body. Ideally, this measure will take the form of a single “expression vector” whose instantaneous magnitude and direction map to the total force and resolution of direction of a person’s gesturing. The raw data for the […] more…