@article{5be8500fad954846bac17277173dc10d,
title = "DeepBinaryMask: Learning a binary mask for video compressive sensing",
abstract = "In this paper, we propose an encoder-decoder neural network model referred to as DeepBinaryMask for video compressive sensing. In video compressive sensing one frame is acquired using a set of coded masks (sensing matrix) from which a number of video frames, equal to the number of coded masks, is reconstructed. The proposed framework is an end-to-end model where the sensing matrix is trained along with the video reconstruction. The encoder maps a video block to compressive measurements by learning the binary elements of the sensing matrix. The decoder is trained to map the measurements from a video patch back to a video block via several hidden layers of a Multi-Layer Perceptron network. The predicted video blocks are stacked together to recover the unknown video sequence. The reconstruction performance is found to improve when using the trained sensing mask from the network as compared to other mask designs such as random, across a wide variety of compressive sensing reconstruction algorithms. Finally, our analysis and discussion offers insights into understanding the characteristics of the trained mask designs that lead to the improved reconstruction quality.",
keywords = "Binary mask, Compressive sensing, Deep learning, Mask optimization, Video reconstruction",
author = "Michael Iliadis and Leonidas Spinoulas and Katsaggelos, {Aggelos K.}",
note = "Funding Information: The following is the Supplementary material related to this article. MMC Additional reconstruction videos to demonstrate the effectiveness of the learnt masks. MMC Michael Iliadis He received his B.S. degree in Digital Systems from the University of Piraeus, Greece in 2008, the M.S. degree in Computer Science from the University of Bath, UK in 2009 and the Ph.D. degree in Computer Science from Northwestern University, IL, USA in 2016. In 2016–2017, he was a Research Scientist at Sony US Research Center. In 2017, he joined Vidado where he is currently a Machine Learning Researcher. His current research interests include deep learning, sparse modeling and compressive sensing. Leonidas Spinoulas He was born in Korinthos, Greece. He received his Diploma degree in Electrical and Computer Engineering from the National Technical University of Athens, Greece in 2010. In September 2010 he joined Northwestern University, Evanston, IL, USA and the Image and Video Processing Laboratory (IVPL) under the supervision of Prof. Aggelos K. Katsaggelos. He received the M. Sc. Degree in Electrical Engineering and Computer Science in 2012 and the Ph.D. degree from the same department in August 2016. He currently holds a Research Scientist position with the Information Sciences Institute (University of Southern California), Marina del Rey, CA. He was previously a Research Scientist for Ricoh Innovations Corporation, Cupertino, CA, USA. He was the recipient of the best paper awards at EUSIPCO 2013 and SENSORCOMM 2015. His primary research interests include image processing, image restoration, inverse problems, Bayesian methods, compressive sensing and deep learning. Aggelos K. Katsaggelos He received the Diploma degree in electrical and mechanical engineering from the Aristotelian University of Thessaloniki, Greece, in 1979, and the M.S. and Ph.D. degrees in Electrical Engineering from the Georgia Institute of Technology, in 1981 and 1985, respectively. In 1985, he joined the Department of Electrical Engineering and Computer Science at Northwestern University, where he is currently a Professor, holder of the Joseph Cummings Chair. He is a member of the Academic Staff, NorthShore University Health System, an affiliated faculty at the Department of Linguistics and he has an appointment with the Argonne National Laboratory. He was previously the holder of the Ameritech Chair of Information Technology and the AT&T Chair and the co-Founder and Director of the Motorola Center for Seamless Communications. He has published extensively in the areas of multimedia processing and communications (over 250 journal papers, 500 conference papers and 40 book chapters) and he is the holder of 26 international patents. He is the co-author of Rate-Distortion Based Video Compression (Kluwer, 1997), Super-Resolution for Images and Video (Claypool, 2007), Joint Source-Channel Video Transmission (Claypool, 2007), Machine Learning Refined (Cambridge University Press, 2016) and The Essentials of Sparse Modeling and Optimization (Springer, 2017, forthcoming). He has supervised 56 PhD dissertations so far. Among his many professional activities Prof. Katsaggelos was Editor-in-Chief of the IEEE Signal Processing Magazine (1997–2002), a BOG Member of the IEEE Signal Processing Society (1999–2001), a member of the Publication Board of the IEEE Proceedings (2003–2007), and he is currently a member of the Awards Board of the Signal Processing Society. He is a Fellow of the IEEE (1998) and SPIE (2009) and the recipient of the IEEE Third Millennium Medal (2000), the IEEE Signal Processing Society Meritorious Service Award (2001), the IEEE Signal Processing Society Technical Achievement Award (2010), an IEEE Signal Processing Society Best Paper Award (2001), an IEEE ICME Paper Award (2006), an IEEE ICIP Paper Award (2007), an ISPA Paper Award (2009), and a EUSIPCO paper award (2013). He was a Distinguished Lecturer of the IEEE Signal Processing Society (2007–2008). Publisher Copyright: {\textcopyright} 2019 Elsevier Inc.",
year = "2020",
month = jan,
doi = "10.1016/j.dsp.2019.102591",
language = "English (US)",
volume = "96",
journal = "Digital Signal Processing: A Review Journal",
issn = "1051-2004",
publisher = "Elsevier Inc.",
}