Descargar vídeo Duración: 0:35
an early test using the Horn Schunk method for optical flow tracking. What's that? you want to see me toss around photos and scale them using just my hands like in Minority Report?? please... btw this is max msp with jitter and cv.jit (I'm summing 7 points directly below the cube to come up with an average motion vector)
demo of /cameraFlow. simple app showing optical flow tracking
A home-made system for tracking actors (humanoids) in a video sequence. Uses a number of algorithms, including pattern matching, motion detection and a bit of AI. As you can see it's still not 100% reliable. Sometimes a car or a bus gets classified as human by mistake. This is partially due to low ...
A demonstration of a tracking algorithm which uses optical flow information to disambiguate between visually-similar objects. A two-stage dynamic model is used which allows tracking with only a small number of particles in the particle filter (25).
This is one of the many experiments I'm doing as part of my Master's thesis in Computer Engineering. I'm working on an unsupervised bayesian motion detector based on features clustering and coherent motion likelihood, as suggested by Brostow/Cipolla. The features I'm tracking here are the ...
Installation produced by participiants of the course "Interaktive Mediainstallationen" at Hochschule Furtwangen University (2008). Footage taken at "Tag der Medien" on July 1st 2008.