For my final project I am going to work with scene detection on pre-recorded video. I intend to explore not just cut or shot detection, but scene detection (or at the very least an approximation of it). More simply, I also intend to explore commercial detection techniques, in order to mark and remove commercials from recordings of television broadcasts.
My goal is to generate a list of timestamps for the in/out markers of scenes (or commercial breaks), which can then be used for a variety of purposes
For my midterm I’m playing continuing with the idea of self-censoring vis-a-vis voyeurism. Right now my code is working (Barely) allowing you to grab a freeze frame of your face (or another object) and then have that re-mapped to your face.
Conceal your identity. Always put on your ‘best face’…
some of the next steps: store multiple freeze-frames and be able to toggle through them, to have different visages throughout your day.
better tracking of the face. right now using the Skin class, but it could be better.
grab images from external sources (flickr anyone?)
better masking of the image so that it isn’t just a rectangle.
Siemens is set to launch an augmented reality (AR) football game for mobile phones ahead of this year’s World Cup in Germany.
“Kick Real” allows players to take virtual penalty kicks by aiming a mobile camera phone at their foot while kicking an imaginary ball.
My friend Theo Watson did a lot of computer vision work while he was studying at Parson’s design and technology program. this is a project called virtual daisies: as a person walks across a field of daisies, they die beneath their feet and regenerate moments later…
Theodore Watson 2006
IT Conversations: Richard Marks – User Interfaces in Interactive Entertainment
This is an interesting recording from the game developer’s conference, where the developer of Sony’s EyeToy talks about the benefits and challenges of video sensing in interactive entertainment.