Blog Archive: 2010

Nudging the world toward better pictures and video

on Comments (2)

An excellent article on FXPAL’s NudgeCam application recently appeared in MIT’s Technology Review. NudgeCam encapsulates standard video capture heuristics, such as how to frame a face and good brightness characteristics, in order to provide guidance to users as they are taking video, using image analysis techniques such as face recognition,  as to how to adjust the camera to improve the video capture.

For its size, FXPAL has surprising breadth and variety of expertise. The NudgeCam work resulted from a collaboration between Scott Carter, whose expertise is in mobile and ubiquitous computing,  and John Doherty, our multimedia specialist, who knows all the standard video capture heuristics and many more. John Adcock brought image analysis techniques to the team, and 2009 FXPAL summer intern Stacy Branham contributed her human-computer interaction expertise.

A different application, also developed at FXPAL, supports rephotography in an industrial setting. Rephotography is the art of taking a photograph from the same location and angle as a previous photograph. Continue Reading

Revisualizing a past FXPAL researcher

on Comments (1)
Traces of Gold, by Chris Culy

Traces of Gold, by Chris Culy

Chris Culy, who worked on discourse parsing at FXPAL a number of years ago, is now in Italy working as a Senior Researcher and the Language Technologies Technical Officer at the Institute for Specialised Communication and Multilingualism. He oversees language-related software development and leads a research project on linguistic data visualization. But the real excitement is that he has a solo art show, Revisualizing the visual, opening today.  His work combines his  interest in photography with his  interest in how information is structured and perceived. The software he has written to support his work transforms colors into shapes or uses color information to create rambling colorful paths based on the image. To create effective artworks, Chris carefully chooses the original photograph and tunes the algorithms to it. Don’t miss the video that shows some of this process in action!