Robotic Cameras and Sensor Networks for High Resolution Environment Monitoring Ken Goldberg and Dezhen Song (Paul Wright and Carlo Sequin) Alpha Lab, IEOR.

Slides:



Advertisements
Similar presentations
Just Add Wheels: Leveraging Commodity Laptop Hardware for Robotics Education Jonathan Kelly, Jonathan Binney, Arvind Pereira, Omair Khan and Gaurav S.
Advertisements

Ascendent's Fusion 360 hybrid platform creates a true hybrid surveillance system by utilizing the advantages of Analog, Megapixel, and IP technologies.
Fundamental tools: clustering
Fast Algorithms For Hierarchical Range Histogram Constructions
Yasuhiro Fujiwara (NTT Cyber Space Labs)
On Map-Matching Vehicle Tracking Data
Intelligent Systems Lab. Extrinsic Self Calibration of a Camera and a 3D Laser Range Finder from Natural Scenes Davide Scaramuzza, Ahad Harati, and Roland.
Experiences with Streaming Construction of SAH KD Trees Stefan Popov, Johannes Günther, Hans-Peter Seidel, Philipp Slusallek.
Robert Pless, CS 546: Computational Geometry Lecture #3 Last Time: Convex Hulls Today: Plane Sweep Algorithms, Segment Intersection, + (Element Uniqueness,
A Versatile Depalletizer of Boxes Based on Range Imagery Dimitrios Katsoulas*, Lothar Bergen*, Lambis Tassakos** *University of Freiburg **Inos Automation-software.
Ken Goldberg UC Berkeley The Robot Next Door. Previous Predictions “Household robots will do all chores.” (1930) “Atomic Batteries will be commonplace.”
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
Vision, Video and Virtual Reality Omnidirectional Vision Lecture 6 Omnidirectional Cameras CSC 59866CD Fall 2004 Zhigang Zhu, NAC 8/203A
On-Demand Sharing of a High-Resolution Panorama Video from Networked Robotic Cameras Supported in part by CPSC 643 Dezhen Song Texas A&M University.
1 Frame Selection Algorithms for Collaboratively Tele-Operated Robotic Cameras.
CPSC 643 Aligning Windows of Live Video from an Imprecise Pan-Tilt-Zoom Robotic Camera into a Remote Panoramic Display Dezhen Song Department of Computer.
3D Computer Vision and Video Computing Omnidirectional Vision Topic 11 of Part 3 Omnidirectional Cameras CSC I6716 Spring 2003 Zhigang Zhu, NAC 8/203A.
Ken Goldberg. Director, BCNM Professor, IEOR, EECS, School of Information UC Berkeley.
Themis Palpanas1 VLDB - Aug 2004 Fair Use Agreement This agreement covers the use of all slides on this CD-Rom, please read carefully. You may freely use.
ShareCam: Interface, System Architecture, and Implementation of a Collaboratively Controlled Robotic Webcam Dezhen Song (TAMU) and Ken Goldberg (UC Berkeley)
ART: Augmented Reality Table for Interactive Trading Card Game Albert H.T. Lam, Kevin C. H. Chow, Edward H. H. Yau and Michael R. Lyu Department of Computer.
Vladlen Koltun, UC Berkeley Joint work with Sariel Har-Peled, Dezhen Song and Ken Goldberg Efficient Algorithms for Shared Camera Control.
Mission: to understand what is new about new media from cross-disciplinary and global perspectives that emphasize humanities and the public interest.
Networked robots ken goldberg, uc berkeley
Applications of Voronoi Diagrams to GIS Rodrigo I. Silveira Universitat Politècnica de Catalunya Geometria Computacional FIB - UPC.
1 Motion in 2D image sequences Definitely used in human vision Object detection and tracking Navigation and obstacle avoidance Analysis of actions or.
Geometric Probing with Light Beacons on Multiple Mobile Robots Sarah Bergbreiter CS287 Project Presentation May 1, 2002.
BRASS Analysis of QuasiStatic Scheduling Techniques in a Virtualized Reconfigurable Machine Yury Markovskiy, Eylon Caspi, Randy Huang, Joseph Yeh, Michael.
Chip Planning 1. Introduction Chip Planning:  Deals with large modules with −known areas −fixed/changeable shapes −(possibly fixed locations for some.
SG-VoIP Page 1 / 14 PLANET Pan / Tilt Internet Camera Internet Surveillance Solution.
1 Geometric Intersection Determining if there are intersections between graphical objects Finding all intersecting pairs Brute Force Algorithm Plane Sweep.
Introduction Tracking the corners Camera model and collision detection Keyframes Path Correction Controlling the entire path of a virtual camera In computer.
Efficient Algorithms for Robust Feature Matching Mount, Netanyahu and Le Moigne November 7, 2000 Presented by Doe-Wan Kim.
Professional Solution for Central Management and Visual Alarm Verification Presentation by TeleEye Group Presentation by TeleEye Group TeleEye Central.
3D SLAM for Omni-directional Camera
Localization for Mobile Robot Using Monocular Vision Hyunsik Ahn Jan Tongmyong University.
Lars Arge Presented by Or Ozery. I/O Model Previously defined: N = # of elements in input M = # of elements that fit into memory B = # of elements per.
General ideas to communicate Show one particular Example of localization based on vertical lines. Camera Projections Example of Jacobian to find solution.
Sejong University, DMS Lab. An Efficient True-Motion Estimator Using Candidate Vectors from a Parametric Motion Model Dong-kywn Kim IEEE TRANSACTIONS ON.
Double Integrals Introduction.
Automated Intruder Tracking using Particle Filtering and a Network of Binary Motion Sensors Jeremy Schiff EECS Department University of California, Berkeley.
Image-Based Segmentation of Indoor Corridor Floors for a Mobile Robot
Image-Based Segmentation of Indoor Corridor Floors for a Mobile Robot Yinxiao Li and Stanley T. Birchfield The Holcombe Department of Electrical and Computer.
Exact and Distributed Algorithms for Collaborative Camera Control Dezhen Song * A. Frank van der Stappen † Ken Goldberg * * UC Berkeley, USA † Utrecht.
1 Subdivision. 2 Subdivision for game Why? Large model require many memory for storage Need to dynamically tessellated during game play Make surface modeling.
CSE554Contouring IISlide 1 CSE 554 Lecture 3: Contouring II Fall 2011.
CSE554Contouring IISlide 1 CSE 554 Lecture 5: Contouring (faster) Fall 2013.
Hierarchical Occlusion Map Zhang et al SIGGRAPH 98.
Image-Based Rendering Geometry and light interaction may be difficult and expensive to model –Think of how hard radiosity is –Imagine the complexity of.
1 ShareCam Part II: Approximate and Distributed Algorithms for a Collaboratively Controlled Robotic Webcam Supported in part by the National Science Foundation.
The Message Passing Communication Model David Woodruff IBM Almaden.
1 ShareCam Part I: Interface, System Architecture, and Implementation of a Collaboratively Controlled Robotic Webcam Dezhen Song Ken Goldberg UC Berkeley.
AXIS Panorama PTZ Network Camera Pan, Tilt and Zoom in a live panorama over your network.
Reading 1D Barcodes with Mobile Phones Using Deformable Templates.
Trajectory-Based Ball Detection and Tracking with Aid of Homography in Broadcast Tennis Video Xinguo Yu, Nianjuan Jiang, Ee Luang Ang Present by komod.
VIVOTEK Technology Roadmap Presenter: Steve Ma / Director of Product Marketing.
NETWORK VIDEO SURVEILLANCE. CCTV Closed-Circuit Television (CCTV) is the use of video cameras to transmit signal to a specific place on a designated device.
VIVOTEK 2007 Product Roadmap
IP Speed Dome Solution 2006-Feb-22.
A Forest of Sensors: Using adaptive tracking to classify and monitor activities in a site Eric Grimson AI Lab, Massachusetts Institute of Technology
Omnidirectional Vision
Zhigang Zhu, K. Deepak Rajasekar Allen R. Hanson, Edward M. Riseman
Orthogonal Range Searching and Kd-Trees
Factors that Influence the Geometric Detection Pattern of Vehicle-based Licence Plate Recognition Systems Martin Rademeyer Thinus Booysen, Arno Barnard.
Coding Approaches for End-to-End 3D TV Systems
Eric Grimson, Chris Stauffer,
Omnidirectional Vision
EE4271 VLSI Design, Fall 2016 VLSI Channel Routing.
Aggregate-Max Nearest Neighbor Searching in the Plane
Presentation transcript:

Robotic Cameras and Sensor Networks for High Resolution Environment Monitoring Ken Goldberg and Dezhen Song (Paul Wright and Carlo Sequin) Alpha Lab, IEOR and EECS University of California, Berkeley

Networked Robots

internet tele-robot:

RoboMotes: Gaurav S. Sukhatme, USC

Smart Dust: Kris Pister, UCB (Image: Kenn Brown)

Networked Cameras

Security Applications Banks, Airports, Freeways, Sports Events, Concerts, Hospitals, Schools, Warehouses, Stores, Playgrounds, Casinos, Prisons, etc.

Conventional Security Cameras Immobile or Repetitive Sweep Low resolution

New Video Cameras: Omnidirectional vs. Robotic Fixed lens with mirror 6M Pixel CCD $ 20.0 K 1M Pixel / Steradian Pan, Tilt, Zoom (21x) 0.37M Pixel CCD $ 1.2 K 500M Pixel / Steradian

Where to look?

Sensor Net Detects Activity “Motecams” Other sensors: audio, pressure switches, light beams, IR, etc Generate bounding boxes and motion vectors Transmit to Robot camera Activity localization

Block Motion Estimator Ron Fearing’s Xilinx FPGA board can compute motion vectors in hardware Extract: bounding frames

Viewpoint Selection Problem Given n bounding frames, find optimal frame

Related Work Facilities Location –Megiddo and Supowit [84] –Eppstein [97] –Halperin et al. [02] Rectangle Fitting –Grossi and Italiano [99,00] –Agarwal and Erickson [99] –Mount et al [96] Similarity Measures –Kavraki [98] –Broder et al [98, 00] –Veltkamp and Hagedoorn [00]

Problem Definition Requested frames :  i =[x i, y i, z i ], i=1,…,n

Problem Definition Assumptions –Camera has fixed aspect ratio: 4 x 3 –Candidate frame  = [x, y, z] t –(x, y)  R 2 (continuous set) – z  Z (discrete set) (x, y) 3z 4z

Problem Definition “Satisfaction” for frame i: 0  S i  1 S i = 0 S i = 1  =    i  =  i

Symmetric Difference Intersection-Over-Union Similarity Metrics Nonlinear functions of (x,y)

Intersection over Maximum: Requested frame  i, Area= a i Candidate frame  Area = a Satisfaction Metrics pipi

Intersection over Maximum: s i ( ,  i ) s i = Requested frame  i Candidate frame 

Satisfaction Function – s i (x,y) is a plateau One top plane Four side planes Quadratic surfaces at corners Critical boundaries: 4 horizontal, 4 vertical (for fixed z)

Objective Function Global Satisfaction: for fixed z Find  * = arg max S(  )

S(x,y) is non-differentiable, non-convex, but piecewise linear along axis-parallel lines. Properties of Global Satisfaction

Approximation Algorithm x y d Compute S(x,y) at lattice of sample points:

Approximation Algorithm –Run Time: –O(w h m n / d 2 )  * : Optimal frame : Optimal at lattice : Smallest frame at lattice that encloses  *

Exact Algorithm Virtual corner: Intersection between boundaries –Self intersection: –Frame intersection : y x

Exact Algorithm Claim: An optimal point occurs at a virtual corner. Proof: –Along vertical boundary, S(y) is a 1D piecewise linear function: extrema must occur at boundaries

Exact Algorithm Exact Algorithm: Check all virtual corners  (mn 2 ) virtual corners  (n) time to evaluate S for each  (mn 3 ) total runtime

Improved Exact Algorithm Sweep horizontally: solve at each vertical –Sort critical points along y axis: O(n log n) –1D problem at each vertical boundary O(nm) –O(n) 1D problems –O(n 2 m) total runtime O(n) 1D problems

Examples

Summary Networked robots High res. security cameras Omnidirectional vs. robotic Motion Sensing Network Viewpoint Selection Problem Algorithms

Future Work Dynamic Version with motion prediction Multiple outputs: –p cameras –p views from one camera “Temporal” version: fairness –Integrate s i over time: minimize accumulated dissatisfaction for any frame request Obstacle Avoidance

Related Work Facility Location Problems –Megiddo and Supowit [84] –Eppstein [97] –Halperin et al. [02] Rectangle Fitting, Range Search, Range Sum, and Dominance Sum –Friesen and Chan [93] –Kapelio et al [95] –Mount et al [96] –Grossi and Italiano [99,00] –Agarwal and Erickson [99] –Zhang [02]

Related Work Similarity Measures –Kavraki [98] –Broder et al [98, 00] –Veltkamp and Hagedoorn [00] Frame selection algorithms –Song, Goldberg et al [02, 03, 04], –Har-peled et al. [03]

Problem Definition Assumptions –Camera has fixed aspect ratio: 4 x 3 –Candidate frame c = [x, y, z] t –(x, y)  R 2 (continuous set) – Resolution z  Z Z = 10 means a pixel in the image = 10×10m 2 area Bigger z = larger frame = lower resolution (x, y) 3z 4z

Problem Definition Requests : r i =[x l i, y t i, x r i, y b i, z i ], i=1,…,n ( x l i, y t i ) ( x r i, y b i )

Optimization Problem User i’s satisfaction Total satisfaction

Problem Definition “Satisfaction” for user i: 0  S i  1 S i = 0 S i = 1  = c  r i c = r i

Measure user i’s satisfaction: Coverage-Resolution Ratio Metrics Requested frame r i Area= a i Candidate frame c Area = a pipi

Comparison with Similarity Metrics Symmetric Difference Intersection-Over-Union Nonlinear functions of (x,y), Does not measure resolution difference

Optimization Problem

Requested Frame r i Candidate Frame c (for fixed z) Objective Function Properties

s i (x,y) is a plateau One top plane Four side planes Quadratic surfaces at corners Critical boundaries: 4 horizontal, 4 vertical Objective Function for Fixed Resolution 4z x y 3z 4(z i -z)

Objective Function Total satisfaction: for fixed z Frame selection problem: Find c * = arg max S(c)

S(x,y) is non-differentiable, non-convex, non-concave, but piecewise linear along axis-parallel lines. Objective Function Properties 4z x y 3z 4(z i -z) 3z y sisi (z/z i ) 2 3(z i -z) x sisi 4z (z/z i ) 2 4(z i -z)

Plateau Vertex Definition Intersection between boundaries –Self intersection: –Plateau intersection : y x

Plateau Vertex Optimality Condition Claim 1: An optimal point occurs at a plateau vertex in the objective space for a fixed Resolution. Proof: –Along vertical boundary, S(y) is a 1D piecewise linear function: extrema must occur at x boundaries y S(y)S(y)

Fixed Resolution Exact Algorithm Brute force Exact Algorithm: Check all plateau vertices  (n 2 ) plateau vertices  (n) time to evaluate S for each  (n 3 ) total runtime

Improved Fixed Resolution Algorithm Sweep horizontally: solve at each vertical –Sort critical points along y axis: O(n log n) –1D problem at each vertical boundary O(n) –O(n) 1D problems –O(n 2 m) total runtime for m zoom levels O(n) 1D problems y S(y)S(y) x y

A New Architecture Activity and Video database Activity localization Activities Frame selection Active surveillance Control commands Videos

Software diagram TCP/IP Activity & video database Core (with shared memory segments) RPC module Communication Console/Log Activity server Activity generation Motescam Wireless Camera control Calibration Panoramic image generation Video server Panasonic HCM 280 Camera Visual C++ NesC + Tiny OS Gnu C++ MySQL

Database: indexing video data Activity Index –Timestamp –Speed (Or other sensor data) –Range Query video data using activity –Show video clips of moving objects with speed faster than 1 meter per second in zone 1 in last 10 days –Show video clips of zone 1 when CO 2 concentration exceeded the threshold in Jan (Assuming CO 2 sensor is used in detecting activity) Activity and Video database