Always seeing the world with fresh eyes can make it hard to find your way around. Giving computers the ability to recognise objects as they scan a new environment will let them navigate much more quickly and understand what they are seeing.
Renato Salas-Moreno at Imperial College London and colleagues have added object recognition to a computer vision technique called simultaneous location and mapping (SLAM). A SLAM-enabled computer has a camera to orient itself in new surroundings as it maps them.
SLAM builds up a picture of the world out of points and lines and contours. In an office, say, chairs and desks would emerge from the room like hills and valleys in a landscape. "The world is meaningless since every point in the map is the same," says Salas-Moreno. "It doesn't know if it is looking at a television or the wall."
Anand and Ravi's blog for a Times of India Group column, now a spin-off which you can follow along as it merrily meanders through myriads of matters. Now, new and improved with a new focus on Education in general, and Math/Science Education in particular. Themes: Science/Technology, Economics, Mathematics and Innovation. Also featuring discussions with some of the world's leading thinkers on science, technology, economics, and innovation.
Thursday, July 4, 2013
Remembering objects lets computers learn like a child
Via InfoWorld: