Smart Glass for Object Recognition

Abstract

The goal of the project is to experimentally demonstrate a smart glass that can recognize objects. The glass does not consume energy and has no computer chips. It uses the physics of wave dynamics to perform analog artificial neural computing inside a nanostructured material. This smart glass can be as small as a few millimeters and last forever unless mechanically destroyed. The demonstration of a working prototype serves as the foundation to explore exciting possibilities in using wave dynamics for analog computing. The prototype will build on the concept of optical waves passing through a nanophotonic medium can perform artificial neural computing. Complex information is encoded in the wavefront of the input light. The medium transforms the wavefront to realize sophisticated computing tasks such as image recognition. At the output, the optical energy is concentrated in well-defined locations, which, for example, can be interpreted as the identity of the object in the image.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 29, 2021
Accession Number
AD1157088

Entities

People

  • Zongfu Yu

Organizations

  • University of Wisconsin–Madison

Tags

Communities of Interest

  • Advanced Electronics
  • Air Platforms
  • Energy and Power Technologies
  • Sensors

DTIC Thesaurus Topics

  • Acoustic Resonators
  • Air Force
  • Air Force Research Laboratories
  • Artificial Intelligence Software
  • Cameras
  • Computer Vision
  • Computers
  • Computing Devices
  • Detection
  • Fabrication
  • Image Recognition
  • Information Systems
  • Manufacturing
  • Materials
  • Neural Networks
  • Object Recognition
  • Recurrent Neural Networks

Fields of Study

  • Physics

Readers

  • Computer Vision.
  • Optical Physics and Photonics.
  • Quantum Dot Semiconductor Device Photonics and Graphene Optoelectronic Materials and THz Physics.

Technology Areas

  • AI & ML
  • Microelectronics