advertisement

Hero6 28 06

75 %
25 %
advertisement
Information about Hero6 28 06
Entertainment

Published on January 14, 2008

Author: Sigismondo

Source: authorstream.com

advertisement

Sequential Adaptive Sensor Management:  Sequential Adaptive Sensor Management Alfred O. Hero III† Dept. of Electrical Engineering and Computer Science, The University of Michigan Slide2:  Progress (since June 05) Theory of information gain (IG) scheduling Result: IG bounds risk (Kreucher CDC05). Implication: IG is a universal surrogate Classification reduction for RL Result: Generalization error bounds (Blatt, Thesis-06). Implication: Minimum # samples and model/measurement complexity Adaptive energy allocation and waveform selection Result: LARS reduction of optimal adaptive waveform selection policy (Rangarajan:ICASSP06) Implication: linear-complexity solution to exponential-complexity problem IRIS: sensor management for STW Result: IRIS adaptive illuminator placement strategy w/ confidence maps Implication: Information-directed path planning for STW (Marble:06) Sequential Sensor Resource Allocation Progress Highlighted Today:  Progress Highlighted Today Adaptive energy allocation and waveform selection [Rangarajan&Raich&Hero] Iterative Redeployment of Illumination and Sensing (IRIS) for STW [Marble&Raich&Hero] Progress 1: Adaptive Waveforms:  Progress 1: Adaptive Waveforms Sequentially illuminate a medium and measure backscatter using an array of sensors. Applications to mine detection, ultrasonic medical imaging, foliage penetrating radar, nondestructive testing, communications, and active audio. GOAL: Optimally design a sequence of waveforms using an array of transducers To image a scatter medium (Estimation). To track targets (Tracking) To discover strong scatterers (Detection). Progress 1a: Energy allocation for D&E:  Progress 1a: Energy allocation for D&E Let past observations be 1. Adaptive Energy Management under average energy constraint 2. Active Waveform Design R. Rangarajan, R. Raich and A. O. Hero, "Optimal experimental design for an inverse scattering problem," ICASSP-2005. Energy allocation question: Given transmission of certain waveforms , how much can we gain through optimal energy allocation between various time steps (Rangarajan:2005)? Gains more than 5dB!!!!:  Gains more than 5dB!!!! RESULT : We prove through optimal energy designs, we can achieve at least 5dB gain (compared to one-step strategy) for estimation problems (imaging). How much can we gain for target detection?? Results for target detection:  Results for target detection Two-step energy design procedure ~ 2dB gain or 20% decrease in average error for same SNR. How much improvement can be achieved asymptotically with time? (Work in progress) Progress 1b: Active waveform selection:  Progress 1b: Active waveform selection M possible waveforms Can only send p out M, p < M+1 Design criterion: Optimal solution: subset selection, is intractable Simplification via rule ensembles:  Simplification via rule ensembles We approximate the decision statistic at receiver (detector, estimator, classifier) by a weighted sum of non-linear functions (rule ensembles (Friedman:2005)) of subsets of q measurements at time t Special case (GAM) for estimating state variable s Reduced GAM waveform selection criterion Friedman, J. H. and Popescu, B. E. "Predictive Learning via Rule Ensembles." (Feb. 2005) Solution via convex relaxation:  Solution via convex relaxation Convex relaxation (Tibshirani:1994) of waveform design criterion (Rangarajan:2006) Tibshirani, R. "Regression selection and shrinkage via the lasso" Technical Report (June. 1994). R. Raghuram, R. Raich and A.O. Hero, "Single-stage waveform selection for adaptive resource constrained state estimation," IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing, Toulouse France, 2006. Summary comparisons:  Summary comparisons HMM diffusion with bi-level variance Diffusion measured in Gaussian additive noise with one of possible subsets of n=5 waveforms Numerical results:  Numerical results Future Directions Sensor network localization/tracking problem. Combine optimal energy allocation with waveform selection. (Work in progress) Slide13:  Elements of IRIS strategy Initial illumination with physical antenna array Antenna array is deployed at an initial location and illuminates the region of interest. Sparse reconstruction image reconstruction (Ting:2006) is performed Form Confidence Map of Image Confidence map (Raich:2005) is computed using initial image and side information Select a region of low confidence from confidence map Simulate external energy/resolution field induced by virtual transmitter Place virtual transmitter in low confidence region and apply FEM, MoM, PO to estimate electric field distribution outside the building Compute induced energy or gradient field (wrt perturbation of virtual transmitter location) Re-illuminate with physical antenna array at maximum of simulated field Progress 2: Iterative Redeployment of Illumination and Sensing (IRIS) M. Ting, R. Raich and A.O. Hero, "Sparse image reconstruction using a sparse prior," ICIP 2006 R. Raich and A.O. Hero, "Sparse image reconstruction for partially unknown blur functions," ICIP 2006 Slide14:  Wall Initial Sensor Position/Configuration Point Scatterer Transmitter Table Chair Sink Weapons Cache IRIS Illustration: Sensor Illumination Slide15:  Wall Sink Weapons Cache IRIS Illustration: Confidence Map Low confidence region Iterative image reconstruction (Fessler&Hero:TIP95) Sparsity constrained deconvolution (Nowak&etal:TSP03) Image confidence maps (Raich&Hero:ICASSP06) Slide16:  Wall Sink Weapons Cache IRIS Illustration: Virtual back-illumination Slide17:  IRIS Illustration: Predict Energy/Resolution MAP Wall Sink Weapons Cache Slide18:  Sparse image reconstruction and confidence mapping MAP-EM Formulation Separates deconvolution from denoising: EM-MAP iterations for image x and confidence map Properties Iterates monotonically increase likelihood Deconvolution (E) only involves adjoint of forward operator Fast implementation with wavenumber migration approx for H Ting,M, Hero,A.O., “Sparse Image Reconstruction Using a Sparse Prior,” ICIP 2006. Slide19:  Sparse Reconstruction Example Slide20:  Accessible Region Simulated Scene Accessible Region Inaccessible Region Inaccessible Region IRIS illustration for STW External Wall – Permittivity: 10 Thickness: 0.2m Length: 10m Slide21:  Sparse iterative Reconstruction (10 iterations) (Marble&Raich&Hero:06) Standard Wavenumber Migration 1m Aperture 1m Aperture IRIS for STW – Iteration 1: Sparse reconstruction Slide22:  Sparse Prior w = 0.25 a = 0.5 Confidence Map shows pixels that have high confidence of being “empty space”. Quantitative map: IRIS for STW – Iteration 1: Confidence Mapping Ambiguous pixels Slide23:  Energy Mapping IRIS for STW – Iteration 1: Insert virtual transmitter and simulate field KL Mapping Slide24:  KL Divergence – Information Gain Virtual Transmitters Electric Field From Transmitter k. Observation Location Div Map= Div(E1,E3)+ Div(E1,E2) Reference Field Horizontal Perturbation Field Vertical Perturbation Field Spectral Information Gain KL Divergence is a measure of Discrimination Error Probability Slide25:  IRIS for STW – Iteration 2: Insert virtual transmitter and simulate field Slide26:  IRIS for STW – Iteration 3: Insert virtual transmitter and simulate field Energy Mapping Cross Range [m] Slide27:  10m Aperture 1m Aperture 1m 1m 1m 1 2 3 4 IRIS for STW – Comparisons to fixed aperture Personnel on A. Hero’s sub-Project (2005-2006):  Personnel on A. Hero’s sub-Project (2005-2006) Raviv Raich, post-doctoral researcher BS Tel Aviv University PhD Georgia Tech, May 2004 Neal Patwari, post-doctoral researcher BS Virginia tech PhD, Univ of Michigan, Sept. 2005 Doron Blatt, 4th year doctoral student BS Univ. Tel Aviv PhD Univ of Michigan, May 2006 Raghuram Rangarajan, 5th year doctoral student BS IIT Madras Dept. Fellowship/MURI GSRA Jay Marble, 5th year doctoral student BS UIUC MURI GSRA Presently employed at NVRL Pubs Since June 2005:  Pubs Since June 2005 Theses of students funded on MURI "Performance Evaluation and Optimization for Inference Systems: Model Uncertainty, Distributed Implementation, and Active Sensing," PhD Thesis, The University of Michigan, May 2006. Journal “Adaptive Multi-modality Sensor Scheduling for Detection and Tracking of Smart Targets”, C. Kreucher, D. Blatt, A. Hero, and K. Kastella, Digital Signal Processing,vol. 15, no. 4, July 2005. "Multitarget Tracking using the Joint Multitarget Probability Density," C. Kreucher, K. Kastella, and A. Hero, IEEE Transactions on Aerospace and Electronic Systems, 39(4):1396-1414, October 2005 (GD Medal winner 2005) . "Convergent incremental optimization transfer algorithms: application to tomography", S. Ahn, J.A. Fessler, D. Blatt, and A. Hero, IEEE Trans. on Medical Imaging, vol. 25, no. 3, pp.283-296, March 2006 Pubs Since June 2005:  Pubs Since June 2005 Conference "Sequential Design of Experiments for a Rayleigh Inverse Scattering Problem," R. Rangarajan, R. Raich, and A.O. Hero, Proc. Of IEEE Workshop on Statistical Signal Processing (SSP), Bordeaux, July 2005. "APOCS: a convergent source localization algorithm for sensor networks," D. Blatt and A.O. Hero, IEEE Workshop on Statistical Signal Processing (SSP), Bordeaux, July 2006 "Incremental optimization transfer algorithms: application to transmission tomography", S. Ahn, J.A. Fessler, D. Blatt, and A. Hero, IEEE Conf on Medical Imaging, Oct. 2005. "A Comparison of Task Driven and Information Driven Sensor Management for Target Tracking," C. Kreucher, A. Hero, and K. Kastella, 44th IEEE Conference on Decision and Control (CDC) Special Session on Information Theoretic Methods for Target Tracking, December 12-15 (Invited) "Single-stage waveform selection for adaptive resource constrained state estimation," R. Raghuram, R. Raich and A.O. Hero, IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing, Toulouse France, June 2006. "Optimal sensor scheduling via classification reduction of policy search (CROPS)," D. Blatt and A.O. Hero, 2006 Workshop on POMDP's, Classification and Regression (Intl Conf on Automated Planning and Scheduling (ICAPS)), Cumbria UK, June 2006. (Invited) Synergistic Activities and Awards since June 2005:  Synergistic Activities and Awards since June 2005 Sensip Nov 2005, A. Hero plenary speaker Member of ARO MURI (John Sidles PI) awarded in 2005 for MRFM sensing and image reconstruction Member of AFOSR MURI (Randy Moses PI) awarded in 2006 for multi-platform radar sensing Member of ISP team (Harry Schmit PI) General Dynamics, Inc K. Kastella: collaboration with A. Hero in sensor management, July 2002- C. Kreucher: former doctoral student of A. Hero, continued collaboration M. Moreland Melbourne: collaborator in area of sensor management Ben Shapo: MS student collaborator in area of sensor management Mike Davis: MS student collaborator in area of satellite MIMO ARL NRC ARLTAB: A Hero is member of NAS oversight/review committee ARLTAB SEDD: A. Hero participated in yearly review Night Vision Lab: Jay Marble spent two weeks of Aug 2005 with Steve Bishop EIC of Foundations and Applications of Sensor Management (Springer - 2006) Contributor, IEEE Proceeedings Special Issue on Large Scale Complex Systems, Editor S. Haykin. Synergistic Activities (ctd):  Synergistic Activities (ctd) In Aug 2005 Jay Marble was at Night Vision Lab (working with Steve Bishop) : Indirectly support the Autonomous Mine Detection System (AMDS) Identify new data sets for algorithm validation: “Check Test 1” (April 2005) Apply multi-stage reinforcement learning algorithms to Army problems. Further develop demonstration software for illustrating algorithm performance. A. Hero visited AFRL Rome (B. Bonneau) in Nov. and gave invited presentation at Sensip on sensor management and at the “Old Crows Conference” at AFRL. Collaboration with Eric Michielsson on IRIS started in fall 2005 – led to several proposals to DARPA, ARO. In May 2005 UM Student Jay Marble was at Georgia Tech (working with Waymond Scott) Transitions:  Transitions Transition of SM methods to control of sensor swarms (GD) – resulted in GD sensor net demo. Marble visited NVRL for 1 month in summer 2005 to demo UM mine detection software June 2006 Marble is now full-time employee at Night Vision Research Laboratory

Add a comment

Related presentations

Related pages

Big Hero 6 (2014) | Fandango - Movie Tickets - Movie Times ...

Big Hero 6 movie info - movie times, trailers, reviews, tickets, actors and more on Fandango.
Read more

Guitar Hero: Warriors of Rock - Wikipedia, the free ...

Guitar Hero: Warriors of Rock (initially referred to as Guitar Hero 6 or Guitar Hero VI) is a music rhythm game and the sixth main entry in the Guitar Hero ...
Read more

Big Hero 6 (2014) - Rotten Tomatoes: Movies | TV Shows ...

Agreeably entertaining and brilliantly animated, Big Hero 6 is briskly-paced, action-packed, and often touching.
Read more

Kodak Hero 6.1 Test | Multifunktionsgerät

7 Testberichte über Kodak Hero 6.1: ... 28.01.2013 . Die Installation unter Windows 7 ... Von Astrid, 06.12.2011 .
Read more

Big Hero 6 Official Trailer #1 (2014) - Disney Animation ...

Big Hero 6 Official Trailer #1 (2014) ... 28 Hiro & Baymax from Big Hero 6 meet guests at Disney's Hollywood Studios - Duration: 2:53.
Read more

Big Hero 6 Review - IGN Video - Video Games, Wikis, Cheats ...

Big Hero 6 Review ... 06 MIN ... → 28 OCT 2014 Marvel and Disney come together in this animated movie about a ragtag ...
Read more

Disney Big Hero 6 ⚽️ (@DisneysBigHero6) | Twitter

Disney Big Hero 6 ⚽️ ‏ @ ... 28 PM - 30 Aug 2015 · Details. 20 retweets 55 likes. Reply. ... 06 PM - 20 Aug 2015 · Details. 136 retweets 221 likes.
Read more

My Hero! 6 - Read My Hero! Chapter 6 Online - Page 28

My Hero! - Read My Hero! 6 Online Reader Tips:Click on the My Hero!manga image or use left-right keyboard arrow keys to go to the next page.
Read more

Big Hero 6 - Trailer #2 - IGN Video - Video Games, Wikis ...

... 06 MIN ... Big Hero 6 2 - Kingdom Hearts 3 Adds Big Hero 6 World - IGN News ... 28 MIN ; Sword Art Online: Lost Song Review ...
Read more

Big Hero 6, Vol. 1: Amazon.de: Haruki Ueno: Fremdsprachige ...

Big Hero 6, Vol. 1: Amazon.de: Haruki Ueno: Fremdsprachige Bücher ... EUR 15,06: EUR 15,80: Taschenbuch "Bitte wiederholen" EUR 11,32. EUR 7,96: EUR 15,41:
Read more