Kinect & 3D. Tamara Berg Advanced Mul7media



Similar documents
Announcements. Active stereo with structured light. Project structured light patterns onto the object

How does the Kinect work? John MacCormick

Towards Internet-scale Multi-view Stereo

3 Image-Based Photo Hulls. 2 Image-Based Visual Hulls. 3.1 Approach. 3.2 Photo-Consistency. Figure 1. View-dependent geometry.

Interactive Dense 3D Modeling of Indoor Environments

Colorado School of Mines Computer Vision Professor William Hoff

On Benchmarking Camera Calibration and Multi-View Stereo for High Resolution Imagery

Feature Tracking and Optical Flow

3D/4D acquisition. 3D acquisition taxonomy Computer Vision. Computer Vision. 3D acquisition methods. passive. active.

A unified framework for content-aware view selection and planning through view importance

State of the Art and Challenges in Crowd Sourced Modeling

Incremental Surface Extraction from Sparse Structure-from-Motion Point Clouds

Introduction to Computer Graphics

3D Scanner using Line Laser. 1. Introduction. 2. Theory

Terrain Traversability Analysis using Organized Point Cloud, Superpixel Surface Normals-based segmentation and PCA-based Classification

Color Segmentation Based Depth Image Filtering

Space Perception and Binocular Vision

Introduction Epipolar Geometry Calibration Methods Further Readings. Stereo Camera Calibration

Polarized 3D. Achuta Kadambi, MIT Media Lab. Joint work with Vahe Taamazyan, Boxin Shi, and Ramesh Raskar. MIT Media Lab 2

Using Photorealistic RenderMan for High-Quality Direct Volume Rendering

Binocular Vision and The Perception of Depth

Introduction. C 2009 John Wiley & Sons, Ltd

1. INTRODUCTION Graphics 2

AJR Automa+c Jamming Recogni+on

3D Face Modeling. Vuong Le. IFP group, Beckman Institute University of Illinois ECE417 Spring 2013

THE PERFORMANCE EVALUATION OF MULTI-IMAGE 3D RECONSTRUCTION SOFTWARE WITH DIFFERENT SENSORS

CS635 Spring Department of Computer Science Purdue University

Window-based, discontinuity preserving stereo

Surface Reconstruction from Multi-View Stereo

Kapitel 12. 3D Television Based on a Stereoscopic View Synthesis Approach

Three-Dimensional Data Recovery Using Image-Based Modeling

PCL - SURFACE RECONSTRUCTION

Dense Matching Methods for 3D Scene Reconstruction from Wide Baseline Images

6 Space Perception and Binocular Vision

Blender 3D Animation

Workshop Report 08w5070 Multi-View and Geometry Processing for 3D Cinematography

CS 534: Computer Vision 3D Model-based recognition

A Short Introduction to Computer Graphics

Data Sheet. definiti 3D Stereo Theaters + definiti 3D Stereo Projection for Full Dome. S7a1801

Epipolar Geometry. Readings: See Sections 10.1 and 15.6 of Forsyth and Ponce. Right Image. Left Image. e(p ) Epipolar Lines. e(q ) q R.

Deriving Camera and Point Location From a Series of Photos Using Numerical Optimization

Improvements in Real-Time Correlation-Based Stereo Vision

DESIGN & DEVELOPMENT OF AUTONOMOUS SYSTEM TO BUILD 3D MODEL FOR UNDERWATER OBJECTS USING STEREO VISION TECHNIQUE

What Makes a Great Picture?

Files Used in this Tutorial

Immersive Medien und 3D-Video

High-Resolution Depth for Binocular Image-Based Modelling

Part-Based Recognition

Computer Graphics AACHEN AACHEN AACHEN AACHEN. Public Perception of CG. Computer Graphics Research. Methodological Approaches

Building Rome on a Cloudless Day

Modelling 3D Avatar for Virtual Try on

A Framework for Modeling 3D Scenes using Pose-free Equations

Spatio-Temporally Coherent 3D Animation Reconstruction from Multi-view RGB-D Images using Landmark Sampling

Current status of image matching for Earth observation

Lecture 12: Cameras and Geometry. CAP 5415 Fall 2010

BUILDING TELEPRESENCE SYSTEMS: Translating Science Fiction Ideas into Reality

Tracking Densely Moving Markers

ACCURACY ASSESSMENT OF BUILDING POINT CLOUDS AUTOMATICALLY GENERATED FROM IPHONE IMAGES

The acquisition of appearance properties of real objects: state of the art, challenges, perspectives

Point Cloud Simulation & Applications Maurice Fallon

Digital 3D Animation

A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms

Limitations of Human Vision. What is computer vision? What is computer vision (cont d)?

Simple and efficient online algorithms for real world applications

Motion Capture Sistemi a marker passivi

Interactive Segmentation, Tracking, and Kinematic Modeling of Unknown 3D Articulated Objects

Towards Linear-time Incremental Structure from Motion

Turning Mobile Phones into 3D Scanners

Keeping Pace with Big Data

How To Use 3D On A Computer Or Tv

A NEW SUPER RESOLUTION TECHNIQUE FOR RANGE DATA. Valeria Garro, Pietro Zanuttigh, Guido M. Cortelazzo. University of Padova, Italy

Consolidated Visualization of Enormous 3D Scan Point Clouds with Scanopy

Towards optimal non-rigid surface tracking

DETECTION OF PLANAR PATCHES IN HANDHELD IMAGE SEQUENCES

MeshLab and Arc3D: Photo-Reconstruction and Processing of 3D meshes

Limits and Possibilities of Markerless Human Motion Estimation

3-D Scene Data Recovery using Omnidirectional Multibaseline Stereo

Photo Uncrop. 1 Introduction. Qi Shan, Brian Curless, Yasutaka Furukawa, Carlos Hernandez, and Steven M. Seitz

ENGN D Photography / Winter 2012 / SYLLABUS

Spatial location in 360 of reference points over an object by using stereo vision

Vision based Vehicle Tracking using a high angle camera

The Visual Internet of Things System Based on Depth Camera

Online Model Reconstruction for Interactive Virtual Environments

Projection Center Calibration for a Co-located Projector Camera System

Dynamic composition of tracking primitives for interactive vision-guided navigation

Character Animation from 2D Pictures and 3D Motion Data ALEXANDER HORNUNG, ELLEN DEKKERS, and LEIF KOBBELT RWTH-Aachen University

How To Use A Webmail On A Pc Or Macodeo.Com

Assessment. Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall

Image-Based Motion Compensation for Structured Light Scanning of Dynamic Surfaces. Sören König and Stefan Gumhold

Computer Graphics and Image Processing Introduction

ROBUST VEHICLE TRACKING IN VIDEO IMAGES BEING TAKEN FROM A HELICOPTER

3D Model based Object Class Detection in An Arbitrary View

Introduction to Computer Graphics. Reading: Angel ch.1 or Hill Ch1.

Finding people in repeated shots of the same scene

Lighting Estimation in Indoor Environments from Low-Quality Images

LOCAL SURFACE PATCH BASED TIME ATTENDANCE SYSTEM USING FACE.

Filters for Black & White Photography

Edge tracking for motion segmentation and depth ordering

Visualization system and applications at BIFI

Real-Time Stereo Reconstruction in Robotically Assisted Minimally Invasive Surgery

Transcription:

Kinect & 3D Tamara Berg Advanced Mul7media

Recovering 3D from Images How can we automa7cally compute 3D geometry from images? What cues in the image provide 3D informa7on? Slide credit: S. Narasimhan

Visual Cues for 3D Shading Merle Norman Cosme-cs, Los Angeles Slide credit: S. Narasimhan

Visual Cues for 3D Shading Texture The Visual Cliff, by William Vandivert, 1960 Slide credit: S. Narasimhan

Visual Cues for 3D Shading Texture Focus From The Art of Photography, Canon Slide credit: S. Narasimhan

Visual Cues for 3D Shading Texture Focus Mo7on Slide credit: S. Narasimhan

Why do we have two eyes? Cyclope vs. Odysseus Slide credit: S. Narasimhan

Stereo Reconstruc7on The Stereo Problem Shape from two (or more) images Biological mo7va7on Slide credit: S. Narasimhan

Mul7- view stereo Slide credit: S. Seitz & S Lazebnik

What is stereo vision? Generic problem formula7on: given several images of the same object or scene, compute a representa7on of its 3D shape Slide credit: S. Seitz & S Lazebnik

What is stereo vision? Generic problem formula7on: given several images of the same object or scene, compute a representa7on of its 3D shape Images of the same object or scene Arbitrary number of images (from two to thousands) Arbitrary camera posi7ons (camera network or video sequence) Calibra7on may be ini7ally unknown Representa7on of 3D shape Depth maps Meshes Point clouds Patch clouds Volumetric models Layered models Slide credit: S. Seitz & S Lazebnik

Binocular Stereo Slide credit: S. Narasimhan

Binocular Stereo Basic Principle: Triangula7on Gives reconstruc7on as intersec7on of two rays Requires calibra7on point correspondence Slide credit: S. Narasimhan

Stereo Corresondence

Stereo Correspondence Determine Pixel Correspondence Pairs of points that correspond to same scene point Epipolar Constraint Reduces correspondence problem to 1D search along conjugate epipolar lines Java demo: h_p://www.ai.sri.com/~luong/research/meta3dviewer/epipolargeo.html Slide credit: S. Narasimhan

Basic Stereo Algorithm For each epipolar line For each pixel in the leb image compare with every pixel on same epipolar line in right image pick pixel with minimum match cost Improvement: match windows This should look familar... Correla7on, Sum of Squared Difference (SSD), etc. Slide credit: S. Narasimhan

Size of Matching window W = 3 W = 20 Effect of window size Smaller window Good/bad? Larger window Good/bad? Be_er results with adap1ve window T. Kanade and M. Okutomi, A Stereo Matching Algorithm with an Adap1ve Window: Theory and Experiment,, Proc. Interna7onal Conference on Robo7cs and Automa7on, 1991. D. Scharstein and R. Szeliski. Stereo matching with nonlinear diffusion. Interna7onal Journal of Computer Vision, 28(2):155-174, July 1998 Slide credit: S. Narasimhan

Stereo Results Data from University of Tsukuba Scene Ground truth Slide credit: S. Narasimhan

Results with Window Search Window- based matching (best window size) Ground truth Slide credit: S. Narasimhan

From feature matching to dense stereo 1. Extract features 2. Get a sparse set of ini7al matches 3. Itera7vely expand matches to nearby loca7ons 4. Use visibility constraints to filter out false matches 5. Perform surface reconstruc7on Yasutaka Furukawa and Jean Ponce, Accurate, Dense, and Robust Mul-- View Stereopsis, CVPR 2007. Slide credit: S. Seitz & S Lazebnik

Stereo from community photo collec7ons For photos taken from the Internet, we need structure from mo1on techniques to reconstruct both camera posi7ons and 3D points Slide credit: S. Seitz & S Lazebnik

Stereo from community photo collec7ons M. Goesele, N. Snavely, B. Curless, H. Hoppe, S. Seitz, Mul7- View Stereo for Community Photo Collec7ons, ICCV 2007 h_p://grail.cs.washington.edu/projects/mvscpc/ Slide credit: S. Seitz & S Lazebnik

What about the kinect?

Basic Stereo Algorithm What s the hard part? Slide credit: S. Narasimhan

Active stereo with structured light Let s make correspondence easy!! L. Zhang, B. Curless, and S. M. Seitz. Rapid Shape Acquisi7on Using Color Structured Light and Mul7- pass Dynamic Programming. 3DPVT 2002 Slide credit: S. Seitz

Active stereo with structured light Project structured light patterns onto the object Simplifies the correspondence problem Allows us to use only one camera Instead of 2 cameras, use camera + projector camera projector L. Zhang, B. Curless, and S. M. Seitz. Rapid Shape Acquisi7on Using Color Structured Light and Mul7- pass Dynamic Programming. 3DPVT 2002 Slide credit: S. Seitz

Active stereo with structured light Project structured light patterns onto the object Simplifies the correspondence problem Allows us to use only one camera camera projector L. Zhang, B. Curless, and S. M. Seitz. Rapid Shape Acquisi7on Using Color Structured Light and Mul7- pass Dynamic Programming. 3DPVT 2002 Slide credit: S. Seitz

Active stereo with structured light L. Zhang, B. Curless, and S. M. Seitz. Rapid Shape Acquisi7on Using Color Structured Light and Mul7- pass Dynamic Programming. 3DPVT 2002 Slide credit: S. Seitz

Kinect in ac7on

Depth Maps

What about people?

Recovering skeletons

How?

Training Data - Capture a large database of mo7on capture (mocap) of human ac7ons. - Retarget mocap to meshes spanning the range of body shapes and sizes - Render depth and body part images

Classify based on depth features

Test Results

Kinect in ac7on

Kool Apps Kinect for recogni7on Kinectbot