I am building systems that can understand what they see. In this day and age, the necessary hardware is easily accessible since a digital camera and a computer can now be purchased for well under € 100. It is the software that is the real challenge.Continue reading “Understanding events”
A major assumption in modern computer vision is that you have to track points on surfaces in order to see in 3D. You can use 2 images from 2 static cameras (“stereo”), or 2 images from 1 moving camera (“motion”). Continue reading “Solving correspondence”
I am right-eyed. A phenomenon also called “master eye” or “ocular dominance”.
So my left eye is the lazy one. And I don’t think it was properly treated when I was growing up. What I remember is that I saw double while reading: two images floating on top of each other. I could not fuse the two images into one “percept” of the book in front of me. I could accomplish that fusion easily for normal objects that were further away than the words on a page at arm’s length.Continue reading “Upgrading vision system OVS-0”
Here is an interview that journalist Jim Jansen of the newspaper Het Parool had with me. He wanted to know how scientists spend their Summer holiday. It is in Dutch though, but I added a translation in English. Continue reading “Interview with newspaper “Het Parool””
Although sometimes credited to the Renaissance artists and engineers, the camera obscura, or pinhole camera was already used by the Chinese in the 4th century BC and the Arabs in the 10th century AD. If you have never seen one in action, you are missing out. The images have a vibrant dreamlike quality, especially when objects in the scene are moving.
I don’t drive. I tried to get my driver’s license several times, but I failed. The main reason is quite ironic. My control of the car was up to standards, but all the examiners stated that I lacked the perceptual abilities to safely navigate traffic. At that moment, I had spend almost half of my life studying visual perception. That knowledge apparently does not transfer to my visual skills at all.
Being skilled in the art of drawing a convincing scene in linear perspective is no guarantee anymore for a successful career. For roughly four centuries this was a pretty good tool to have in your kit as a visual artist – from the moment that Filippo Brunelleschi gave his demonstration of a perspective rendering of the Baptistery in Florence in 1425, right up until Joseph Nicéphore Niépce took the first photograph of a view from a window in Saint-Loup-de-Varennes in 1826.
The three guys in the painting above are all depictions of King Charles I, painted from different viewpoints by Anthonis van Dyck in 1636. In the middle we see a frontal view (“en face”), on the left a side view (“en profile”), and the most intriguing is the one on the right: the three-quarter view (“en trois quarts”). So here is the question that has bugged me for some time. Why is it called three-quarter, or 3/4? Three quarters of what?
One of my friends is a true soccer fan and he has probably watched every single game of the 2010 FIFA World Cup. I only watch the occasional game, like yesterday when the Dutch team played Cameroon (2-1). And I have to admit I sometimes get distracted from the game itself and start studying the way it is filmed. Its truly amazing that we can now watch it from so many viewing angles, with slow-motion replays of crucial events.