Toward Ultralightweight Remote Sensing With Harmonic Lenses and Convolutional Neural Networks

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing 2018-09, Vol.11 (9), p.3338-3348
• Main Authors: Nikonorov, Artem V., Petrov, Maksim V., Bibikov, Sergei A., Yakimov, Pavel Y., Kutikova, Viktoriya V., Yuzifovich, Yuriy V., Morozov, Andrey A., Skidanov, Roman V., Kazanskiy, Nikolay L.
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Cameras; Color correction; Colour; deconvolution; deep learning; Detection; Diffractive optics; Harmonic analysis; harmonic lens; Image color analysis; Image quality; Image reconstruction; Imaging techniques; Lenses; Machine learning; Neural networks; Onboard equipment; Optical diffraction; Optical imaging; Optics; point spread function (PSF) estimation; Remote sensing; Remote sensing systems; Restoration; Satellites; Solar energy; Solar power; Solar powered aircraft; Spaceborne remote sensing; Unmanned aerial vehicles
• ISSN: 1939-1404; 2151-1535
• DOI: 10.1109/JSTARS.2018.2856538

In this paper, we describe our advances in manufacturing a 256-layer 7-μm thick harmonic lens with 150 and 300 mm focal distances combined with color correction, deconvolution, and a feedforwarding deep learning neural network capable of producing images approaching photographic visual quality. While reconstruction of images taken with diffractive optics was presented in previous works, this paper is the first to use deep neural networks during the restoration step. The level of imaging quality we achieved with our imaging system can facilitate the emergence of ultralightweight remote sensing cameras for nano- and pico-satellites, and for aerial remote sensing systems onboard small UAVs and solar-powered airplanes.