Direct Object Recognition Without Line-of-Sight Using Optical Coherence
This addresses the challenge of non-line-of-sight recognition for applications like surveillance or robotics, but it is incremental as it builds on existing NLOS methods with a simpler deep learning approach.
The paper tackled the problem of recognizing objects without a direct line-of-sight by using optical coherence and speckle patterns, achieving robust performance with a deep neural network approach as verified through simulations and experiments.
Visual object recognition under situations in which the direct line-of-sight is blocked, such as when it is occluded around the corner, is of practical importance in a wide range of applications. With coherent illumination, the light scattered from diffusive walls forms speckle patterns that contain information of the hidden object. It is possible to realize non-line-of-sight (NLOS) recognition with these speckle patterns. We introduce a novel approach based on speckle pattern recognition with deep neural network, which is simpler and more robust than other NLOS recognition methods. Simulations and experiments are performed to verify the feasibility and performance of this approach.