Automatic 3D modelling of Architecture Anthony Dick 1 Phil Torr 2 Roberto Cipolla 1 1 Department of Engineering 2 Microsoft Research, University of Cambridge.

Slides:



Advertisements
Similar presentations
Epipolar Geometry.
Advertisements

3D reconstruction.
Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
Modeling 3D Deformable and Articulated Shapes Yu Chen, Tae-Kyun Kim, Roberto Cipolla Department of Engineering University of Cambridge.
More single view geometry Describes the images of planes, lines,conics and quadrics under perspective projection and their forward and backward properties.
Structure and Motion from Line Segments in Multiple Images Camillo J. Taylor, David J. Kriegman Presented by David Lariviere.
3D Computer Vision and Video Computing 3D Vision Topic 4 of Part II Visual Motion CSc I6716 Fall 2011 Cover Image/video credits: Rick Szeliski, MSR Zhigang.
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
Exchanging Faces in Images SIGGRAPH ’04 Blanz V., Scherbaum K., Vetter T., Seidel HP. Speaker: Alvin Date: 21 July 2004.
Workshop on Earth Observation for Urban Planning and Management, 20 th November 2006, HK 1 Zhilin Li & Kourosh Khoshelham Dept of Land Surveying & Geo-Informatics.
Last Time Pinhole camera model, projection
Plenoptic Stitching: A Scalable Method for Reconstructing 3D Interactive Walkthroughs Daniel G. Aliaga Ingrid Carlbom
Epipolar Geometry and the Fundamental Matrix F
Multi-view stereo Many slides adapted from S. Seitz.
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2005 with a lot of slides stolen from Steve Seitz and.
3D reconstruction of cameras and structure x i = PX i x’ i = P’X i.
reconstruction process, RANSAC, primitive shapes, alpha-shapes
CS664 Lecture #19: Layers, RANSAC, panoramas, epipolar geometry Some material taken from:  David Lowe, UBC  Jiri Matas, CMP Prague
3D Computer Vision and Video Computing 3D Vision Lecture 15 Stereo Vision (II) CSC 59866CD Fall 2004 Zhigang Zhu, NAC 8/203A
Automatic Photo Popup Derek Hoiem Alexei A. Efros Martial Hebert Carnegie Mellon University.
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
May 2004Stereo1 Introduction to Computer Vision CS / ECE 181B Tuesday, May 11, 2004  Multiple view geometry and stereo  Handout #6 available (check with.
Motion from normal flow. Optical flow difficulties The aperture problemDepth discontinuities.
CSCE 641 Computer Graphics: Image-based Modeling (Cont.) Jinxiang Chai.
55:148 Digital Image Processing Chapter 11 3D Vision, Geometry Topics: Basics of projective geometry Points and hyperplanes in projective space Homography.
Statistical Color Models (SCM) Kyungnam Kim. Contents Introduction Trivariate Gaussian model Chromaticity models –Fixed planar chromaticity models –Zhu.
3-D Scene u u’u’ Study the mathematical relations between corresponding image points. “Corresponding” means originated from the same 3D point. Objective.
Automatic Camera Calibration
A Practical System for Modelling Body Shapes from Single View Measurements Yu Chen 1, Duncan Robertson 2, Roberto Cipolla 1 Department of Engineering,
Lecture 11 Stereo Reconstruction I Lecture 11 Stereo Reconstruction I Mata kuliah: T Computer Vision Tahun: 2010.
CSE 473/573 Computer Vision and Image Processing (CVIP) Ifeoma Nwogu Lecture 35 – Review for midterm.
Multimodal Interaction Dr. Mike Spann
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
The Brightness Constraint
Exploitation of 3D Video Technologies Takashi Matsuyama Graduate School of Informatics, Kyoto University 12 th International Conference on Informatics.
IMAGE MOSAICING Summer School on Document Image Processing
Periodic Motion Detection via Approximate Sequence Alignment Ivan Laptev*, Serge Belongie**, Patrick Perez* *IRISA/INRIA, Rennes, France **Univ. of California,
Dynamic 3D Scene Analysis from a Moving Vehicle Young Ki Baik (CV Lab.) (Wed)
I 3D: Interactive Planar Reconstruction of Objects and Scenes Adarsh KowdleYao-Jen Chang Tsuhan Chen School of Electrical and Computer Engineering Cornell.
CSCE 643 Computer Vision: Structure from Motion
Correspondence-Free Determination of the Affine Fundamental Matrix (Tue) Young Ki Baik, Computer Vision Lab.
Forward-Scan Sonar Tomographic Reconstruction PHD Filter Multiple Target Tracking Bayesian Multiple Target Tracking in Forward Scan Sonar.
1 Formation et Analyse d’Images Session 7 Daniela Hall 25 November 2004.
Plenoptic Modeling: An Image-Based Rendering System Leonard McMillan & Gary Bishop SIGGRAPH 1995 presented by Dave Edwards 10/12/2000.
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
© 2005 Martin Bujňák, Martin Bujňák Supervisor : RNDr.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
3D Imaging Motion.
1 Camera calibration based on arbitrary parallelograms 授課教授:連震杰 學生:鄭光位.
Raquel A. Romano 1 Scientific Computing Seminar May 12, 2004 Projective Geometry for Computer Vision Projective Geometry for Computer Vision Raquel A.
Image-Based Segmentation of Indoor Corridor Floors for a Mobile Robot Yinxiao Li and Stanley T. Birchfield The Holcombe Department of Electrical and Computer.
Looking at people and Image-based Localisation Roberto Cipolla Department of Engineering Research team
 Marc Levoy Using Plane + Parallax to Calibrate Dense Camera Arrays Vaibhav Vaish, Bennett Wilburn, Neel Joshi, Marc Levoy Computer Science Department.
Final Review Course web page: vision.cis.udel.edu/~cv May 21, 2003  Lecture 37.
55:148 Digital Image Processing Chapter 11 3D Vision, Geometry Topics: Basics of projective geometry Points and hyperplanes in projective space Homography.
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
Image-Based Rendering Geometry and light interaction may be difficult and expensive to model –Think of how hard radiosity is –Imagine the complexity of.
Model Refinement from Planar Parallax Anthony DickRoberto Cipolla Department of Engineering University of Cambridge.
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
Lec 26: Fundamental Matrix CS4670 / 5670: Computer Vision Kavita Bala.
11/25/03 3D Model Acquisition by Tracking 2D Wireframes Presenter: Jing Han Shiau M. Brown, T. Drummond and R. Cipolla Department of Engineering University.
3D Single Image Scene Reconstruction For Video Surveillance Systems
Motion Segmentation with Missing Data using PowerFactorization & GPCA
Approximate Models for Fast and Accurate Epipolar Geometry Estimation
Estimation of 3D Bounding Box for Image Object
The Brightness Constraint
3D Photography: Epipolar geometry
The Brightness Constraint
A Bayesian Estimation of Building Shape using MCMC
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Presentation transcript:

Automatic 3D modelling of Architecture Anthony Dick 1 Phil Torr 2 Roberto Cipolla 1 1 Department of Engineering 2 Microsoft Research, University of Cambridge Cambridge

Automatic 3D modelling of architecture - BMVC'00 2 The goal Generate 3D models of architectural scenes from several images automatically –Including accurate geometry, texture Interactively built using Photobuilder! Available at +

Automatic 3D modelling of architecture - BMVC'00 3 Our approach Previous structure from motion algorithms use only image data We integrate image data with prior knowledge of architecture –The scene will be piecewise planar –Walls are likely to intersect at right angles –Walls are likely to be perpendicular to a common ground plane –Walls are likely contain doors and windows which have a highly constrained shape

Automatic 3D modelling of architecture - BMVC'00 4 Model representation Scene is modelled as a collection of “wall” planes Each wall plane has a plane equation and a boundary Each wall plane may contain offset layers such as doors, windows b c Front view a ar d (x,y) Overhead view Each offset layer is one of a collection of parameterised shapes

Automatic 3D modelling of architecture - BMVC'00 5 Model estimation Structure estimation has 2 parts: –How many walls are in the scene and what are their parameters? –How many offset layers does each wall contain, what shape are they, and what are their parameters? [ECCV2000] Model selection between different shapes

Automatic 3D modelling of architecture - BMVC'00 6 Previous work Manually defined homography Initialise offset layer estimates using dense correspondence Fit 4 different shape models to each region –Use Bayesian model selection criterion to select best shape model Initial After model fitting + selection

Automatic 3D modelling of architecture - BMVC'00 7 What’s new Extension to scenes with multiple wall planes Automatic segmentation of walls

Automatic 3D modelling of architecture - BMVC'00 8 Initialisation Feature-based structure from motion –Track points –Estimate pairwise epipolar geometry –Camera self-calibration [Mendonca CVPR99]

Automatic 3D modelling of architecture - BMVC'00 9 Plane segmentation Recursive RANSAC plane extraction Assume all planes perpendicular to common ground plane Project onto ground plane Derive plane boundaries perpendicular and parallel to ground plane Reconstruction projected onto ground plane

Automatic 3D modelling of architecture - BMVC'00 10 Optimising the planar model Gradient descent search –Cost function: SSE of model projected into each image Parameters to vary: –Ground plane orientation –Boundary and intersection points of each plane Before fitting After fitting

Automatic 3D modelling of architecture - BMVC'00 11 Evaluating the cost function Search requires many evaluations of cost function This is expensive Green’s Theorem: Sum vector field A around region boundary Cache results for best efficiency R1 R2 Cost of R2, L(R2) = L(R1) – L(e1) – L(e2) + L(e3) + L(e4) e1 e2 e3 e4 e1 e2

Automatic 3D modelling of architecture - BMVC'00 12 Results Courtyard corner

Automatic 3D modelling of architecture - BMVC'00 13 The “castle” sequence Images from

Automatic 3D modelling of architecture - BMVC'00 14 Future work Use of lines to initialise offset layers –Join nearby lines into rectangles –Use knowledge of window height/width ratios More extensive and structured set of shapes –Rather than simply testing each possibility –Possible use of architectural shape grammars And in conclusion… –General framework of combining prior knowledge and image data is a useful one –Challenge is to formulate prior knowledge usefully

Automatic 3D modelling of architecture - BMVC'00 15 The Bayesian framework constan t model priorevidence likelihood prior Bayes Rule: Evidence: Model parameters  Wall planes: plane boundary, plane equations Offset layers: Height, width, x, y position

Automatic 3D modelling of architecture - BMVC'00 16 Having optimised for main walls, want to fit doors, windows etc. This is the same problem tackled earlier, but initialisation is now more difficult –Each plane covers less of the image –There may be some fitting errors Manually set number of primitives on each plane –Assumes evenly spaced, vertically centred –Fits each model from this initialisation Planar parallax