Dan O’Sullivan

You look at a screen that works as a mirror reflecting your face. If you blink your eyes, a picture of me thumbing my nose at you comes up but you will never know. Just like you will never know if your refrigerator light is really off. This was done as the Thursday project in the 7 projects in 7 days (5 in 5 for me, … er make that 3.5 in 5) festival at ITP. I am hoping to get back this afternoon to finish it but don’t know if I will.

I am looking for holes in the skin color to find the eyes. When I get back today I will segement out just the holes for the eyes.

Here is the code so far:

Read the rest of this entry »

Allows people to congregate in a layer on top of your web browser. Using a webcam attached to your computer the application grabs your face and sends it to other people looking at the same web page. Your face is displayed on other peoples’ browser at the place on the page you are most interested in as expressed by your cursor location. The web page becomes a substrate for gathering. In the future I would like to degrade the resolution of faces of people interested in things further away on the page and change to peer to peer architecture for the actual transmission of the images. This was done as the Thursday project in the 7 projects in 7 days (5 in 5 for me, … er make that 4 in 5) festival at ITP. Read the rest of this entry »

For determining the popularity of different video segments on public displays. It uses a camera and computer vision to notice how many faces are watching the screen. It takes advantage of a shortcoming of the OpenCV processing libraries for the face detection which only detect faces only at very limited angles. It it finds a face you can be assured that they are facing only the screen. Shawn Van Every created a video drop box for people to leave video to be seen on various screens around the floor. We wanted to be able to cull a best of list from the drop box so Shawn VanEvery and I thought face tracking might be interesting. It is currently hardwired to a particular video and only shows the “Attention Quotient” on the screen. If I had more time, I would integrate it with a database of videos and register the attention into that database. This was done as the Tuesday project in the 7 projects in 7 days (5 in 5 for me) festival at ITP.

Tech: I used IP cameras for the video capture. Below is the code:

Read the rest of this entry »

As people stand in front of a mirror, this applications uses face detection technology to find the faces in the video and then display them with just the faces switched. Each person looks normal except they have someone elses eyes, nose and mouth. This far I go before. In this excersize I wanted it to work for a crowd standing in front of the large screen display at IAC, Gehry building. This required that the faces be shared across multiple application so today I did the networking for that. If I had more time I would add an oval alpha mask so the faces blend better.  This was done as a Monday project in the 7 projects in 7 days (5 in 5 for me) festival at ITP.

Tech: I used the OpenCV processing libraries for the face detection. I used IP cameras for the video capture. Below is the code: Read the rest of this entry »

This is a ten foot video screen on the wall a the Liberty Science Center that allow visitors to spray virtual graffiti using light emitting spray cans. Utube Video.

I worked with Tom Igoe, Stephen Lewis, and Joseph O’Connell to develop this. I worked mostly on the video tracking software.

Check it out at: http://comicable.com/

“The Never-Ending Break-Up Make-Up Storytelling Comic Book Generator” (or NEGBUMCSBG as we like to call it ) arose from an interest in storytelling, comics, and the desire to create a shared space that not only allowed participants to create stories but also allowed individuals to locate and connect similar stories, or other similarly minded storytellers. Read the rest of this entry »

The computer revolution has made it easy for people with little to no technical training to use a computer for such everyday tasks as typing a letter, saving files, or recording data. But what about more imaginative purposes such as starting your car, opening a door, or tracking the contents of your refrigerator? “Physical Computing” will not only change the way you use your computer, it will change the way you think about your computer-how you view its capabilities, how you interact with it, and how you put it to work for you. It’s time to bridge the gap between the physical and the virtual-time to use more than just your fingers to interact with your computer. Step outside of the confines of the basic computer and into the broader world of computing. Get it.

Trading Glances allows people to trade glances separated in time. The installation consists of a screen displaying faces streaming by as if the viewer were passing people in the street.

As the viewer watches the other person’s face, the system records their face and precise eye movements. Later their face is added to this stream of faces in the installation and on the project web site. People can go to the site to see who glanced at them and replay exactly how another person’s gaze travels across their face. Ones’ eye movements can betray very private preferences and yet they are usually publicly viewable. This project tries to invade the privacy of the person doing the surveillance.

Eyebeam

This is a chat environment that allows fans to congregate around their favorite part of the Xena television show. This interface differes from movie SpaceTime Chat because the clip is broken down into segments which are depicted by the bars of the bar chart. The height of the bar maps to the number of comments for that segment. Comments are distributed synchnonously to other people logged on concurrently and also stored for future users. The software works for all types of streaming media. Special moderators can log on and edit chat. Chat is automatically censored for profanity. There is also a sniffer which detects the appropriate version of this clip to play for the user’s connection speed. I worked with Sharleen Smith, Yaron Ben-Zvi at Oxygen.

Read the rest of this entry »

Project Description: This was an experiment to bring the video tracking and video recognition that is very popular at ITP into the realm of very small and inexpensive microcontrollers. It is a continuation of a project that made use of a PIC microcontroller and a Quickcam. With the introduction of very cheap CMOS cameras and very fast SX microcontrollers, this tool could have greater speed and resolution. At the same time a group at CMU developed a commercial kit which uses the same components (better engineering).

Technical Notes: I wrote the software in C for a SX Chip and build the circuitry to connect to a CMOS camera from Omnivision.