Learning in the dark: 3D integral imaging object recognition in very low illumination conditions using convolutional neural networks
Authors:
- 14 September 2018
- journal article
- research article
- Published by Optica Publishing Group in OSA Continuum
- Vol. 1 (2) , 373-383
Abstract
We propose a framework for three-dimensional (3D) object recognition and classification in very low illumination environments using convolutional neural networks (CNNs). 3D images are reconstructed using 3D integral imaging (InIm) with conventional visible spectrum image sensors. After imaging the low light scene using 3D InIm, the 3D reconstructed image has a higher signal-to-noise ratio than a single 2D image, which is a result of 3D InIm being optimal in the maximum likelihood sense for read-noise dominant images. Once 3D reconstruction has been performed, the 3D image is denoised and regions of interest are extracted to detect 3D objects in a scene. The extracted regions are then inputted into a CNN, which was trained under low illumination conditions using 3D InIm reconstructed images, to perform object recognition. To the best of our knowledge, this is the first report of utilizing 3D InIm and convolutional neural networks for 3D training and 3D object classification under very low illumination conditions.Keywords
Funding Information
- Communications-Electronics Research, Development and Engineering Center (CERDEC) (W909MY-12-D-0008)
This publication has 16 references indexed in Scilit:
- Observations of in situ deep-sea marine bioluminescence with a high-speed, high-resolution sCMOS cameraDeep Sea Research Part I: Oceanographic Research Papers, 2016
- 3D touchable holographic light-field displayApplied Optics, 2016
- Free-depths reconstruction with synthetic impulse response in integral imagingOptics Express, 2015
- An Augmented Lagrangian Method for Total Variation Video RestorationIEEE Transactions on Image Processing, 2011
- Three dimensional visualization by photon counting computational Integral ImagingOptics Express, 2008
- Detecting Pedestrians Using Patterns of Motion and AppearanceInternational Journal of Computer Vision, 2005
- Analysis of resolution limitation of integral photographyJournal of the Optical Society of America A, 1998
- Real-time pickup method for a three-dimensional image based on integral photographyApplied Optics, 1997
- Face recognition: a convolutional neural-network approachIEEE Transactions on Neural Networks, 1997
- Épreuves réversibles donnant la sensation du reliefJournal de Physique Théorique et Appliquée, 1908