Clustering Crowdsourced Videos by Line-of-Sight FOCUS: Clustering Crowdsourced Videos by Line-of-Sight Puneet Jain, Justin Manweiler, Arup Acharya, and.

Slides:



Advertisements
Similar presentations
TWO STEP EQUATIONS 1. SOLVE FOR X 2. DO THE ADDITION STEP FIRST
Advertisements

University of Karlsruhe September 30th, 2004 Masayuki Fujita
Kapitel S3 Astronomie Autor: Bennett et al. Raumzeit und Gravitation Kapitel S3 Raumzeit und Gravitation © Pearson Studium 2010 Folie: 1.
Christopher O. Tiemann Michael B. Porter Science Applications International Corporation John A. Hildebrand Scripps Institution of Oceanography Automated.
Copyright © 2003 Pearson Education, Inc. Slide 1 Computer Systems Organization & Architecture Chapters 8-12 John D. Carpinelli.
Chapter 1 The Study of Body Function Image PowerPoint
11 Application of CSF4 in Avian Flu Grid: Meta-scheduler CSF4. Lab of Grid Computing and Network Security Jilin University, Changchun, China Hongliang.
Towards Automating the Configuration of a Distributed Storage System Lauro B. Costa Matei Ripeanu {lauroc, NetSysLab University of British.
FACTORING ax2 + bx + c Think “unfoil” Work down, Show all steps.
Year 6 mental test 5 second questions
Year 6 mental test 10 second questions
Overview of Lecture Partitioning Evaluating the Null Hypothesis ANOVA
Multistage Sampling Module 3 Session 9.
Dr. Marc Valliant, VP & CTO
GeoStamping - A field Information collection mobile application 1 By: Subrata N. Das, Saurabh Gangwar, Ashok K. Joshi RRSC –Central, Nagpur Conference.
Sport Court® Dealer Website Options All website options include Google & Bing Webmasters, Google Analytics setup and are coded W3C Compliant as well as.
- A Powerful Computing Technology Department of Computer Science Wayne State University 1.
Solve Multi-step Equations
Computer Literacy BASICS
Our Digital World Second Edition
Wheres Waldo: Matching People in Images of Crowds Rahul GargDeva RamananSteven M. Seitz Noah Snavely Problem Definition University of Washington University.
Real-Time Projector Tracking on Complex Geometry Using Ordinary Imagery Tyler Johnson and Henry Fuchs University of North Carolina – Chapel Hill ProCams.
Fact-finding Techniques Transparencies
1 Photometric Stereo Reconstruction Dr. Maria E. Angelopoulou.
Developing a Mobile-Optimized Web Instrument for the Consumer Expenditure Diary Survey Nhien To Brandon Kopp Jean Fox Erica Yu Federal CASIC Workshops.
Academic Advisor: Dr. Yuval Elovici Technical Advisor: Dr. Rami Puzis Team Members: Yakir Dahan Royi Freifeld Vitali Sepetnitsky 2.
EU funded FP7: Oct 11 – Sep 14 Co-evolution of Future AR Mobile Platforms Paul Chippendale, Bruno Kessler Foundation FBK, Italy.
ABC Technology Project
1 1 Mechanical Design and Production Dept, Faculty of Engineering, Zagazig University, Egypt. Mechanical Design and Production Dept, Faculty of Engineering,
Taming User-Generated Content in Mobile Networks via Drop Zones Ionut Trestian Supranamaya Ranjan Aleksandar Kuzmanovic Antonio Nucci Northwestern University.
11 Changing Demographics (US Census Dept, 2005). 22.
Computer vision: models, learning and inference
Solving Equations How to Solve Them
Protecting Location Privacy: Optimal Strategy against Localization Attacks Reza Shokri, George Theodorakopoulos, Carmela Troncoso, Jean-Pierre Hubaux,
1 Developing a Predictive Model for Internet Video Quality-of-Experience Athula Balachandran, Vyas Sekar, Aditya Akella, Srinivasan Seshan, Ion Stoica,
Factor P 16 8(8-5ab) 4(d² + 4) 3rs(2r – s) 15cd(1 + 2cd) 8(4a² + 3b²)
Basel-ICU-Journal Challenge18/20/ Basel-ICU-Journal Challenge8/20/2014.
CONTROL VISION Set-up. Step 1 Step 2 Step 3 Step 5 Step 4.
April 2003 ONLINE SERVICE DELIVERY Presentation. 2 What is Online Service Delivery? Vision The current vision of the Online Service Delivery program is.
HJ-Hadoop An Optimized MapReduce Runtime for Multi-core Systems Yunming Zhang Advised by: Prof. Alan Cox and Vivek Sarkar Rice University 1.
25 seconds left…...
1 Using one or more of your senses to gather information.
Subtraction: Adding UP
©Brooks/Cole, 2001 Chapter 12 Derived Types-- Enumerated, Structure and Union.
Improved Census Transforms for Resource-Optimized Stereo Vision
PSSA Preparation.
Xiao Zhang and Wenliang Du Dept. of Electrical Engineering & Computer Science Syracuse University.
AirTrack: Locating Non-WiFi Interferers using Commodity WiFi Hardware Ashish Patro, Shravan Rayanchu, Suman Banerjee University of Wisconsin-Madison Sep.
University of Minnesota Optimizing MapReduce Provisioning in the Cloud Michael Cardosa, Aameek Singh†, Himabindu Pucha†, Abhishek Chandra
Chapter 13 The Data Warehouse
Sheldon Brown, UCSD, Site Director Milton Halem, UMBC Director Yelena Yesha, UMBC Site Director Tom Conte, Georgia Tech Site Director Fundamental Research.
The fundamental matrix F
For Internal Use Only. © CT T IN EM. All rights reserved. 3D Reconstruction Using Aerial Images A Dense Structure from Motion pipeline Ramakrishna Vedantam.
ARIS The Augmented Rea l ity Studio. Outline  Background  Problem definition  Proposed solution  System design  Functionalities  Comparison with.
A Study of Approaches for Object Recognition
OverLay: Practical Mobile Augmented Reality
Satellites in Our Pockets: An Object Positioning System using Smartphones Justin Manweiler, Puneet Jain, Romit Roy Choudhury TsungYun
Video Eyewear for Augmented Reality Presenter: Manjul Sharma Supervisor: Paul Calder.
CSCE 5013 Computer Vision Fall 2011 Prof. John Gauch
U.S. Department of the Interior U.S. Geological Survey Web Presence, Data Sharing, Real- time Analysis and Crowdsourcing GFSAD30 Sixth Workshop – July.
Video Based Palmprint Recognition Chhaya Methani and Anoop M. Namboodiri Center for Visual Information Technology International Institute of Information.
Video Eyewear for Augmented Reality Presenter: Manjul Sharma Supervisor: Paul Calder.
Acquiring 3D models of objects via a robotic stereo head David Virasinghe Department of Computer Science University of Adelaide Supervisors: Mike Brooks.
IIIT HYDERABAD Image-based walkthroughs from partial and incremental scene reconstructions Kumar Srijan Syed Ahsan Ishtiaque C. V. Jawahar Center for Visual.
Augmented Reality Authorized By: Miss.Trupti Pardeshi. NDMVP, Comp Dept. Augmented Reality 1/ 23.
Visual Odometry David Nister, CVPR 2004
Visual Odometry for Ground Vehicle Applications David Nistér, Oleg Naroditsky, and James Bergen Sarnoff Corporation CN5300 Princeton, New Jersey
Map for Easy Paths GIANLUCA BARDARO
Sensor Fusion Localization and Navigation for Visually Impaired People
Presentation transcript:

Clustering Crowdsourced Videos by Line-of-Sight FOCUS: Clustering Crowdsourced Videos by Line-of-Sight Puneet Jain, Justin Manweiler, Arup Acharya, and Kirk Beaty

Clustered by shared subject

CHALLENGES

CAN IMAGE PROCESSING SOLVE THIS PROBLEM?

Camera 2 Camera 4 Camera 3 Camera 1 5 LOGICAL similarity does not imply VISUAL similarity

6 VISUAL similarity does not imply LOGICAL similarity

CAN SMARTPHONE SENSING SOLVE THIS PROBLEM?

Sensors are noisy, hard to distinguish subjects… Why not triangulate?

GPS-COMPASS Line-of-Sight

INSIGHT

Don’t need to visually identify actual SUBJECT, can use background as PROXY hard to identify easy to identify Simplifying Insight 1

same basic structure persists Simplifying Insight 2 Don’t need to directly match videos, can compare all to a predefined visual MODEL

Simplifying Insight 3 Light-of-sight (triangulation) is almost enough, just not via sensing (alone)

FOCUS Fast Optical Clustering of live User Streams Sensing Cloud Vision

Hadoop/HDFS Failover, elasticity Image processing Computer vision Video Streams (Android, iOS, etc.) Clustered Videos FOCUS Cloud Video Analytics Video Extraction Watching Live home: 2 away: 1 Users Select & Watch Organized Streams Change Angle Change Focus

Clustered Videos FOCUS Cloud Video Analytics Video Extraction Watching Live home: 2 away: 1 Users Select & Watch Organized Streams Change Angle Change Focus pre-defined reference “model” Hadoop/HDFS Failover, elasticity Image processing Computer vision

17 Model construction technique based on Photo Tourism: Exploring image collections in 3D Snavely et al., SIGGRAPH 2006 z multi-view reconstruction z keypoint extraction estimates camera POSE and content in field-of-view Multi-view Stereo Reconstruction

Visualizing Camera Pose

~ 1 second at 90 th % ~ 18 seconds at 90 th % 19 z multi-view reconstruction z keypoint extraction z frame-by-frame video to model alignment z sensory inputs Given a pre-defined 3D, align incoming video frames to the model Also known as camera pose estimation

z multi-view reconstruction z keypoint extraction z integration of sensory inputs Gyroscope, provides “diff” from vision initial position Gyroscope, provides “diff” from vision initial position t - 1t - 2 Filesize ≈ 1/Blur Sampled Frame Gyroscope

21 Field-of-view Using POSE + model POINT CLOUD, FOCUS geometrically identifies the set of model points in background of view z multi-view reconstruction z keypoint extraction z pairwise model image analysis

Similarity between image 1 & 2 = 18 Similarity between image 1 & 3 = Finding the similarity across videos as size of point cloud set intersection Finding the similarity across videos as size of point cloud set intersection z multi-view reconstruction z keypoint extraction z pairwise model image analysis

Clustering “similar” videos Similarity Score Application of Modularity Maximization high modularity implies: high correlation among the members of a cluster minor correlation with the members of other clusters

RESULTS

Collegiate Football Stadium Stadium 33K seats 56K maximum attendance Model: 190K points 412 images (2896 x 1944 resolution) Android App on Samsung Galaxy Nexus, S3 325 videos captured seconds each 25

26 Line-of-Sight Accuracy (visual)

Line-of-Sight Accuracy GPS/Compass LOS estimation is <260 meters for the same percentage 27 In >80% of the cases, Line-of-sight estimation is off by < 40 meters

FOCUS Performance 75% true positives Trigger GPS/Compass failover techniques 28

Natural Questions What if 3D model is not available? – Online model generation from first few uploads Stadiums look very different on a game day? – Rigid structures in the background persists Where it won’t work? – Natural or dynamic environment are hard

Conclusion Computer vision and image processing are often computation hungry, restricting real-time deployment Mobile Sensing is a powerful metadata, can often reduce computation burden Computer vision + Mobile Sensing + Geometry, along with right set of BigData tools, can enable many real-time applications FOCUS, displays one such fusion, a ripe area for further research

Thank You