A team of researchers from Microsoft Research were able to modify an ordinary camera to capture depth.
Microsoft Research has discovered a method that makes use of the ordinary 2D smartphone camera, or a webcam to capture detailed hand movements or facial expressions, making it a Kinect-like device.
The team of researchers were successful in making actual working depth sensors from a modified Android smartphone as well as a regular Microsoft webcam. Both the devices were successfully able to track a user’s hands and face. This technology would allow users to modify gadgets to respond to gestures.
The cameras pick up infrared light which, combined with algorithms, show depth. The demo video shows high accuracy and users can even pinch hands mid-air to zoom on screen. The variation of normal light in a room don't affect the infrared.
Another team of researchers have develop their own RGB-depth camera out of off-the-shelf parts. The technology could help figure out a way to meld it with software to capture 3D models of people and objects that deform, shift and move in real-time. No information is available when or if this kit will come to market.
Microsoft researchers under Project Adam are giving Microsoft's voice assistant Cortana the ability to identify objects. The team claims that the project is 50 times faster and twice as precise as Google's 16,000 computer neural network-powered image recognition system. The technology was showed off by Microsoft Research's executive vice president of technology and research, Harry Shum at the company's Faculty Summit. The technology could help build new tools for visually challenged users.
Source: Microsoft Research
Follow Us
Silky Malhotra
Silky Malhotra loves learning about new technology, gadgets, and more. When she isn’t writing, she is usually found reading, watching Netflix, gardening, travelling, or trying out new cuisines. View Full Profile
