Can this 3D camera device help the visually-challenged?

A group of scientists from Massachusetts Institute of Technology (MIT) - including a few Indian-origin researchers - have developed a wearable device consisting of a 3D camera that could be a virtual 'guide dog' to help visually-impaired people.

The researchers also developed a low-power chip to process the 3D camera data. The chip only consumes one-thousandth of the power a conventional computer processor executing the same algorithms would require.

Using this chip, the researchers built a prototype of a complete navigation system for the visually-impaired. The system is about the size of a binoculars case and is worn around the neck.

The user carries a mechanical Braille interface developed at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), which conveys information about the distance to the nearest obstacle in the direction the user is moving.

"There was some prior work on this type of system, but the problem was that the systems were too bulky, because they require tonnes of different processing," said first author Dongsuk Jeon, from MIT's Microsystems Research Laboratories (MTL)..

"We wanted to miniaturise this system and realised that it is critical to make a very tiny chip that saves power but still provides enough computational power," said Jeon, now at Seoul National University in South Korea.

The output of any 3D camera can be converted into a 3D representation called a 'point cloud', which depicts the spatial locations of individual points on the surfaces of objects.

The researchers, including Professor Anantha Chandrakasan and graduate student Priyanka Raina, modified the standard algorithm to trace the point cloud in order to drastically reduce the chip's power consumption.