Below is a fascinating video from Zdenek Kalal, a PhD student at the University of Surrey in the UK that has developed a novel camera that he calls Predator that is on the forefront of computer vision. The real-time visual tracking system can recognize a moving object in a video and follow the object, with implications for new user interfaces as well as the tracking of moving targets in video surveillance, augmented reality, motion capture and robot navigation.
The video demonstrates the ability to recognize specific cars, people, and animals in video surveillance for better monitoring. For augmented reality, items that are quickly and easily recognized can become icons in an interface to quickly offer more information about their properties as you walk through an area. This is really cutting-edge research that seems to take a quick leap forward, offering a whole world of new possibilities.
You can try Predator yourself at http://goo.gl/Kj95y
