2011-7-28P. 1/30 Heping Song, Tong Liu, Xiaomu Luo and Guoli Wang Feedback based Sparse Recovery for Motion Tracking in RF Sensor Networks IEEE Inter.

Slides:



Advertisements
Similar presentations
Tutorial on Exploiting Rich Information in WSNs: A Case for Low Power Radar Anish Arora The Samraksh Company samraksh.com Anish Arora The Samraksh Company.
Advertisements

Multi-Label Prediction via Compressed Sensing By Daniel Hsu, Sham M. Kakade, John Langford, Tong Zhang (NIPS 2009) Presented by: Lingbo Li ECE, Duke University.
Patch-based Image Deconvolution via Joint Modeling of Sparse Priors Chao Jia and Brian L. Evans The University of Texas at Austin 12 Sep
Silvina Rybnikov Supervisors: Prof. Ilan Shimshoni and Prof. Ehud Rivlin HomePage:
Ilias Theodorakopoulos PhD Candidate
Compressed sensing Carlos Becker, Guillaume Lemaître & Peter Rennert
Richard Baraniuk Rice University Progress in Analog-to- Information Conversion.
Abstract Introduction Implementation Algorithm References and Acknowledgments Results We use 10 NI USRP-2920 units with full duplex daughterboards to simultaneously.
Entropy-constrained overcomplete-based coding of natural images André F. de Araujo, Maryam Daneshi, Ryan Peng Stanford University.
Recognition of Traffic Lights in Live Video Streams on Mobile Devices
Project Progress Presentation Coffee delivery mission Dec, 10, 2007 NSH 3211 Hyun Soo Park, Iacopo Gentilini 1.
Tracking Objects with Dynamics Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 04/21/15 some slides from Amin Sadeghi, Lana Lazebnik,
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
1 Robust Video Stabilization Based on Particle Filter Tracking of Projected Camera Motion (IEEE 2009) Junlan Yang University of Illinois,Chicago.
MULTI-TARGET TRACKING THROUGH OPPORTUNISTIC CAMERA CONTROL IN A RESOURCE CONSTRAINED MULTIMODAL SENSOR NETWORK Jayanth Nayak, Luis Gonzalez-Argueta, Bi.
Video Processing EN292 Class Project By Anat Kaspi.
Background Estimation with Gaussian Distribution for Image Segmentation, a fast approach Gianluca Bailo, Massimo Bariani, Paivi Ijas, Marco Raggio IEEE.
Dynamic Face Recognition Committee Machine Presented by Sunny Tang.
Image Denoising with K-SVD Priyam Chatterjee EE 264 – Image Processing & Reconstruction Instructor : Prof. Peyman Milanfar Spring 2007.
Tracking using the Kalman Filter. Point Tracking Estimate the location of a given point along a sequence of images. (x 0,y 0 ) (x n,y n )
Optical Flow
1 Integration of Background Modeling and Object Tracking Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung IEEE ICME, 2006.
A Smart Sensor to Detect the Falls of the Elderly.
MULTIPLE MOVING OBJECTS TRACKING FOR VIDEO SURVEILLANCE SYSTEMS.
Presented by Pat Chan Pik Wah 28/04/2005 Qualifying Examination
6.829 Computer Networks1 Compressed Sensing for Loss-Tolerant Audio Transport Clay, Elena, Hui.
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
Eagle Vision 24/7 security system Day - Night - Dark.
FINAL PRESENTATION ANAT KLEMPNER SPRING 2012 SUPERVISED BY: MALISA MARIJAN YONINA ELDAR A Compressed Sensing Based UWB Communication System 1.
MACHINE VISION GROUP Multimodal sensing-based camera applications Miguel Bordallo 1, Jari Hannuksela 1, Olli Silvén 1 and Markku Vehviläinen 2 1 University.
Tutorial: multicamera and distributed video surveillance Third ACM/IEEE International Conference on Distributed Smart Cameras.
SensEye: A Multi-Tier Camera Sensor Network by Purushottam Kulkarni, Deepak Ganesan, Prashant Shenoy, and Qifeng Lu Presenters: Yen-Chia Chen and Ivan.
Compressive Sampling: A Brief Overview
TP15 - Tracking Computer Vision, FCUP, 2013 Miguel Coimbra Slides by Prof. Kristen Grauman.
Compressed Sensing Based UWB System Peng Zhang Wireless Networking System Lab WiNSys.
Brian Renzenbrink Jeff Robble Object Tracking Using the Extended Kalman Particle Filter.
A General Framework for Tracking Multiple People from a Moving Camera
Cs: compressed sensing
Introduction to Compressive Sensing
Video Tracking Using Learned Hierarchical Features
An Information Fusion Approach for Multiview Feature Tracking Esra Ataer-Cansizoglu and Margrit Betke ) Image and.
SCALE Speech Communication with Adaptive LEarning Computational Methods for Structured Sparse Component Analysis of Convolutive Speech Mixtures Volkan.
Kevin Cherry Robert Firth Manohar Karki. Accurate detection of moving objects within scenes with dynamic background, in scenarios where the camera is.
Lei Li Computer Science Department Carnegie Mellon University Pre Proposal Time Series Learning completed work 11/27/2015.
PARALLEL FREQUENCY RADAR VIA COMPRESSIVE SENSING
An Introduction to Kalman Filtering by Arthur Pece
Image Decomposition, Inpainting, and Impulse Noise Removal by Sparse & Redundant Representations Michael Elad The Computer Science Department The Technion.
A Weighted Average of Sparse Representations is Better than the Sparsest One Alone Michael Elad and Irad Yavneh SIAM Conference on Imaging Science ’08.
A Prototype System for 3D Dynamic Face Data Collection by Synchronized Cameras Yuxiao Hu Hao Tang.
CHARACTERIZATION PRESENTATION ANAT KLEMPNER SPRING 2012 SUPERVISED BY: MALISA MARIJAN YONINA ELDAR A Compressed Sensing Based UWB Communication System.
Final Year Project. Project Title Kalman Tracking For Image Processing Applications.
Tracking with dynamics
Target Tracking In a Scene By Saurabh Mahajan Supervisor Dr. R. Srivastava B.E. Project.
Outline Introduction Network model Two-phase algorithm Simulation
CS654: Digital Image Analysis Lecture 11: Image Transforms.
Optimal Relay Placement for Indoor Sensor Networks Cuiyao Xue †, Yanmin Zhu †, Lei Ni †, Minglu Li †, Bo Li ‡ † Shanghai Jiao Tong University ‡ HK University.
Jianchao Yang, John Wright, Thomas Huang, Yi Ma CVPR 2008 Image Super-Resolution as Sparse Representation of Raw Image Patches.
Zhaoxia Fu, Yan Han Measurement Volume 45, Issue 4, May 2012, Pages 650–655 Reporter: Jing-Siang, Chen.
Date of download: 7/7/2016 Copyright © 2016 SPIE. All rights reserved. Evaluation of the orthogonal matching pursuit (OMP) cost over the target space in.
Jeremy Watt and Aggelos Katsaggelos Northwestern University
Computing and Compressive Sensing in Wireless Sensor Networks
Peng Zhang Cognitive Radio Institute
Digital Image Processing Introduction
הפקולטה להנדסת חשמל - המעבדה לבקרה ורובוטיקה גילוי תנועה ועקיבה אחר מספר מטרות מתמרנות הטכניון - מכון טכנולוגי לישראל TECHNION.
SIMPLE ONLINE AND REALTIME TRACKING WITH A DEEP ASSOCIATION METRIC
Aishwarya sreenivasan 15 December 2006.
Orthogonal Matching Pursuit (OMP)
LAB MEETING Speaker : Cheolsun Kim
Presentation transcript:

P. 1/30 Heping Song, Tong Liu, Xiaomu Luo and Guoli Wang Feedback based Sparse Recovery for Motion Tracking in RF Sensor Networks IEEE Inter. Conf. on Networking, Architecture, and Storage (NAS 2011) July 28-30, 2011, Dalian, China

P. 2/30 Outline Experiments 3 Discussions Sparse Recovery Introduction Motivation Linear Model

P. 3/30 An image is a grid of pixels Matrix = a grid of pixels color by number

P. 4/30 Tomography Tomo- means “a slice/section/part” in Greek W ikipedia

P. 5/30 Magic Square

P. 6/30 RF Sensor Networks

P. 7/30 The Network Layout

P. 8/30 Radio Tomography Imaging x1x1 x4x4 x7x7 x2x2 x5x5 x8x8 x3x3 x6x6 x9x9 y6y6 y5y5 y2y2 y3y3 y1y1 y4y4 y x Inverse problem Weighte d Sum

P. 9/30 Linear Model

P. 10/30 Elliptical Weight Model

P. 11/30  Video cameras. Don’t work in dark, through smoke or walls. Privacy concerns.  Thermal imagers. Limited by walls. High cost.  Motion detectors. Also limited by walls. High false alarms.  Ultra wideband (UWB) radar. High cost.  Received signal strength (RSS) in WSN Device-free Localization (DFL)

P. 12/30  Track image max x / Kalman filter  The sparse nature of location finding  Directly track the location of moving targets Motivation

P. 13/30 Sparse Recovery

P. 14/30 Greedy Sparse Recovery Support DetectionSignal Estimation A, y x

P. 15/30 Support Detection Strategy  Select atoms of measurement matrix A to generate y  Determine active atoms in sparse representation of x

P. 16/30 Orthogonal Matching Pursuit (OMP)

P. 17/30 Demo - OMP(1)

P. 18/30 Demo - OMP(2)

P. 19/30 Demo - OMP(3)

P. 20/30 Demo - OMP(4)

P. 21/30 Compressed Measurements  Weight matrix --overcomplete dictionary  Feedback information

P. 22/30 Heuristic Selection via Feedback Info.

P. 23/30 Feedback Structure Predicted support The locations of the previous frame Recovered support Sparse recovery Next frame

P. 24/30 Experiments-1 resolution 6x6

P. 25/30 Experiments-2 resolution 13x13

P. 26/30 Experiments-3 resolution 27x27

P. 27/30 Experiments-4 compressed meas.

P. 28/30 Experiments-5 compressed meas.

P. 29/30 Experiments-6 compressed meas.

P. 30/30 Discussions Thank You!