Deep learning enables real-time imaging around corners

Science Daily  January 16, 2020
A team of researchers in the US (Stanford University, Princeton University, Southern Methodist University, Rice University) developed an imaging system which uses a commercially available camera sensor and a powerful laser source that is similar to the one found in a laser pointer. The laser beam bounces off a visible wall onto the hidden object and then back onto the wall, creating a speckle pattern that encodes the shape of the hidden object. It can distinguish submillimeter details of a hidden object from 1 meter away. The system can be combined with other imaging systems that produce low-resolution room-sized reconstructions. By accurately characterizing the noise, they synthesized data to train the algorithm to solve the reconstruction problem using deep learning without having to capture costly experimental training data. The researchers tested the new technique by reconstructing images of 1-centimeter-tall letters and numbers hidden behind a corner .With further development, the system might let self-driving cars ‘look’ around parked cars or busy intersections, it could also be installed on satellites and spacecraft for tasks such as capturing images inside a cave on an asteroid…read more. Open Access TECHNICAL ARTICLE

Busy intersection (stock image). Credit: © Gudellaphoto / Adobe Stock

Posted in Imaging technology.

Leave a Reply