No abstract

Perceiving and recognizing material properties of surfaces and objects are fundamental aspects of new and emerging use cases such as robotic perception, virtual reality (VR) applications, digital twins, and creating a 3D digital map of an environment. In this paper, we present results from our simulation-based study of reflection-loss-based material identification from eight common building materials. The study focuses on 2.6 GHz, 28 GHz, and 60 GHz radio carrier frequencies. Analysis of simulation results indicates that a combination of incident angle and reflection loss can be used to properly identify the common building materials. We, therefore, propose a novel joint communication and sensing method for material recognition using reflection loss of the radio signal by the scatterers around the propagation path in a wireless communication network. Compared to existing material identification methods, the proposed reflection-loss-based method is capable of identifying materials from a significant distance without requiring any contact with the object and without requiring dedicated sensors from the infrastructure point of view.

No abstract

No abstract

The obstacle of imaging through multimode fibers (MMFs) is encountered due to the fact that the inherent mode dispersion and mode coupling lead the output of the MMF to be scattered and bring about image distortions. As a result, only noise-like speckle patterns can be formed on the distal end of the MMF. We propose a deep learning model exploited for computational imaging through an MMF, which contains an autoencoder (AE) for feature extraction and image reconstruction and self-normalizing neural networks (SNNs) sandwiched and employed for high-order feature representation. It was demonstrated both in simulations and in experiments that the proposed AE-SNN combined deep learning model could reconstruct image information from various binary amplitude-only targets going through a 5-meter-long MMF. Simulations indicate that our model works effectively even in the presence of system noise, and the experimental results prove that the method is valid for image reconstruction through the MMF. Enabled by the spatial variability and the self-normalizing properties, our model can be generalized to solve varieties of other computational imaging problems.