Title | : | Innovations in Camera-based Respiratory-Assessment Technology - A Journey from Ad-hoc Engineering to Exact Science |
Speaker | : | A.P. Prathosh (Xerox Research Center India (XRCI)) |
Details | : | Wed, 30 Nov, 2016 11:00 AM @ BSB 361 |
Abstract: | : | This talk describes about the recent advances made on camera-based respiratory-assessment technology. The need for such methods is established by citing a couple of industrially relevant problems. Initially, an ad-hoc engineering solution is proposed which is further generalized using mathematical formalism.Specifically, the problem of estimating the respiration pattern and rate using a consumer-grade 2D camera is considered. The problem is formulated as that of blind-deconvolution of a noisy single-input multiple-output (SIMO) system with periodic excitation. It is then solved using a novel method involving sub-space projection and selective ensemble aggregation of pixel time-series. The validity of the proposed method is demonstrated through theoretical results and experiments on real-life data. Further, the applicability of the method to a broader class of problems is described. The talk concludes by reporting other related approaches developed to solve such class of problems in non-contact human-body vital assessment.
Brief Biography: Prathosh is a data scientist in Philips healthcare India, working on developing computer vision algorithms for healthcare applications. Prior to joining Philips, he was a research scientist in Xerox research center India (XRCI) between September 2014 to November 2016. At XRCI, he was leading the group focusing on non-contact human-body vital measurement, using novel methods in imaging, statistical signal processing and machine learning techniques. He obtained his B.E. in ECE from SJCE, Mysore in July 2011. In August 2011, he moved to the department of EE, Indian Institute of Science (IISc), Bangalore, to pursue integrated PhD. He obtained both masters and PhD degrees in the area of temporal analysis of signals and applied machine learning in less than four years from the completion of B.E. He has published research articles in reputed journals such as IEEE TASLP, IEEE TSP, JASA and IEEE SPL and in leading conferences such as IEEE ICASSP, Interspeech, IEEE EMBC and IEEE BIBE. He is a co-inventor in 12 U.S. patent applications.He was a recipient of the KVPY fellowship given by the DST, Govt. of India during 2008-2011, MHRD fellowship from 2008-2013 and TCS research fellowship during 2013-2014 and patent awards given by Xerox. He is a member of IEEE and reviewer for IEEE signal processing journals and conferences. He is also a serious student of Sanskrit, Indian logic and Philosophy since 16 years. |