Recognising Panoramas M. Brown and D. Lowe, University of British Columbia.

Slides:



Advertisements
Similar presentations
Distinctive Image Features from Scale-Invariant Keypoints
Advertisements

Computer Vision : CISC 4/689
Feature points extraction Many slides are courtesy of Darya Frolova, Denis Simakov A low level building block in many applications: Structure from motion.
Object Recognition from Local Scale-Invariant Features David G. Lowe Presented by Ashley L. Kapron.
Presented by Xinyu Chang
Summary of Friday A homography transforms one 3d plane to another 3d plane, under perspective projections. Those planes can be camera imaging planes or.
Outline Feature Extraction and Matching (for Larger Motion)
Object Recognition using Invariant Local Features Applications l Mobile robots, driver assistance l Cell phone location or object recognition l Panoramas,
Distinctive Image Features from Scale- Invariant Keypoints Mohammad-Amin Ahantab Technische Universität München, Germany.
Photo Stitching Panoramas from Multiple Images Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 02/28/12.
Image alignment Image from
Matching with Invariant Features
Object Recognition with Invariant Features n Definition: Identify objects or scenes and determine their pose and model parameters n Applications l Industrial.
Fast High-Dimensional Feature Matching for Object Recognition David Lowe Computer Science Department University of British Columbia.
Robust and large-scale alignment Image from
1 Interest Operators Find “interesting” pieces of the image –e.g. corners, salient regions –Focus attention of algorithms –Speed up computation Many possible.
Object Recognition with Invariant Features n Definition: Identify objects or scenes and determine their pose and model parameters n Applications l Industrial.
Recognising Panoramas
1 Interest Operator Lectures lecture topics –Interest points 1 (Linda) interest points, descriptors, Harris corners, correlation matching –Interest points.
Automatic Panoramic Image Stitching using Local Features Matthew Brown and David Lowe, University of British Columbia.
Feature matching and tracking Class 5 Read Section 4.1 of course notes Read Shi and Tomasi’s paper on.
Distinctive Image Feature from Scale-Invariant KeyPoints
Feature tracking Class 5 Read Section 4.1 of course notes Read Shi and Tomasi’s paper on good features.
Computer Vision A Hand-Held “Scanner” for Large-Format Images COMP 256 Adrian Ilie Steps Towards.
Image Stitching and Panoramas
Automatic Image Stitching using Invariant Features Matthew Brown and David Lowe, University of British Columbia.
Automatic Matching of Multi-View Images
NIPS 2003 Tutorial Real-time Object Recognition using Invariant Local Image Features David Lowe Computer Science Department University of British Columbia.
Automatic Image Alignment via Motion Estimation
Panorama Stitching and Augmented Reality. Local feature matching with large datasets n Examples: l Identify all panoramas and objects in an image set.
Distinctive Image Features from Scale-Invariant Keypoints David G. Lowe – IJCV 2004 Brien Flewelling CPSC 643 Presentation 1.
Sebastian Thrun CS223B Computer Vision, Winter Stanford CS223B Computer Vision, Winter 2005 Lecture 3 Advanced Features Sebastian Thrun, Stanford.
Summary of Previous Lecture A homography transforms one 3d plane to another 3d plane, under perspective projections. Those planes can be camera imaging.
Feature Matching and RANSAC : Computational Photography Alexei Efros, CMU, Fall 2005 with a lot of slides stolen from Steve Seitz and Rick Szeliski.
Overview Introduction to local features
Image Stitching Tamara Berg CSE 590 Computational Photography Many slides from Alyosha Efros & Derek Hoiem.
Advanced Computer Vision Feature-based Alignment Lecturer: Lu Yi & Prof. Fuh CSIE NTU.
Recognition and Matching based on local invariant features Cordelia Schmid INRIA, Grenoble David Lowe Univ. of British Columbia.
Object Tracking/Recognition using Invariant Local Features Applications l Mobile robots, driver assistance l Cell phone location or object recognition.
Image Stitching Shangliang Jiang Kate Harrison. What is image stitching?
Overview Harris interest points Comparing interest points (SSD, ZNCC, SIFT) Scale & affine invariant interest points Evaluation and comparison of different.
Local invariant features Cordelia Schmid INRIA, Grenoble.
Image stitching Digital Visual Effects Yung-Yu Chuang with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac.
Example: line fitting. n=2 Model fitting Measure distances.
Evaluation of interest points and descriptors. Introduction Quantitative evaluation of interest point detectors –points / regions at the same relative.
CVPR 2003 Tutorial Recognition and Matching Based on Local Invariant Features David Lowe Computer Science Department University of British Columbia.
Lecture 7: Features Part 2 CS4670/5670: Computer Vision Noah Snavely.
Overview Introduction to local features Harris interest points + SSD, ZNCC, SIFT Scale & affine invariant interest point detectors Evaluation and comparison.
Local features: detection and description
Automatic Image Alignment : Computational Photography Alexei Efros, CMU, Fall 2011 with a lot of slides stolen from Steve Seitz and Rick Szeliski.
776 Computer Vision Jan-Michael Frahm Spring 2012.
Automatic Image Alignment with a lot of slides stolen from Steve Seitz and Rick Szeliski © Mike Nese CS194: Image Manipulation & Computational Photography.
Summary of Monday A homography transforms one 3d plane to another 3d plane, under perspective projections. Those planes can be camera imaging planes or.
Recognizing specific objects Matching with SIFT Original suggestion Lowe, 1999,2004.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching.
Invariant Local Features Image content is transformed into local feature coordinates that are invariant to translation, rotation, scale, and other imaging.
776 Computer Vision Jan-Michael Frahm Spring 2012.
SIFT Scale-Invariant Feature Transform David Lowe
Presented by David Lee 3/20/2006
Local features: detection and description May 11th, 2017
RANSAC and mosaic wrap-up
Features Readings All is Vanity, by C. Allan Gilbert,
SIFT Demo Heather Dunlop March 20, 2006.
Image Mosaicing Shiran Stan-Meleh
CSE 455 – Guest Lectures 3 lectures Contact Interest points 1
Feature Matching and RANSAC
Noah Snavely.
Computational Photography
Automatic Panoramic Image Stitching using Invariant Features
Recognition and Matching based on local invariant features
Presentation transcript:

Recognising Panoramas M. Brown and D. Lowe, University of British Columbia

Introduction Are you getting the whole picture? –Compact Camera FOV = 50 x 35°

Introduction Are you getting the whole picture? –Compact Camera FOV = 50 x 35° –Human FOV = 200 x 135°

Introduction Are you getting the whole picture? –Compact Camera FOV = 50 x 35° –Human FOV = 200 x 135° –Panoramic Mosaic = 360 x 180°

Why Recognising Panoramas?

1D Rotations () –Ordering matching images

Why Recognising Panoramas? 1D Rotations () –Ordering matching images

Why Recognising Panoramas? 1D Rotations () –Ordering matching images

Why Recognising Panoramas? 2D Rotations (, ) –Ordering matching images 1D Rotations () –Ordering matching images

Why Recognising Panoramas? 1D Rotations () –Ordering matching images 2D Rotations (, ) –Ordering matching images

Why Recognising Panoramas? 1D Rotations () –Ordering matching images 2D Rotations (, ) –Ordering matching images

Why Recognising Panoramas?

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching –SIFT Features –Nearest Neighbour Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching –SIFT Features –Nearest Neighbour Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Invariant Features Schmid & Mohr 1997, Lowe 1999, Baumberg 2000, Tuytelaars & Van Gool 2000, Mikolajczyk & Schmid 2001, Brown & Lowe 2002, Matas et. al. 2002, Schaffalitzky & Zisserman 2002

SIFT Features Invariant Features –Establish invariant frame Maxima/minima of scale-space DOG x, y, s Maximum of distribution of local gradients –Form descriptor vector Histogram of smoothed local gradients 128 dimensions SIFT features are… –Geometrically invariant to similarity transforms, some robustness to affine change –Photometrically invariant to affine changes in intensity

Overview Feature Matching –SIFT Features –Nearest Neighbour Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Nearest Neighbour Matching Find k-NN for each feature –k number of overlapping images (we use k = 4) Use k-d tree –k-d tree recursively bi-partitions data at mean in the dimension of maximum variance –Approximate nearest neighbours found in O(nlogn)

Overview Feature Matching –SIFT Features –Nearest Neighbour Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching –RANSAC for Homography –Probabilistic model for verification Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching –RANSAC for Homography –Probabilistic model for verification Bundle Adjustment Multi-band Blending Results Conclusions

RANSAC for Homography

Overview Feature Matching Image Matching –RANSAC for Homography –Probabilistic model for verification Bundle Adjustment Multi-band Blending Results Conclusions

Probabilistic model for verification

Compare probability that this set of RANSAC inliers/outliers was generated by a correct/false image match –n i = #inliers, n f = #features –p 1 = p(inlier | match), p 0 = p(inlier | ~match) –p min = acceptance probability Choosing values for p 1, p 0 and p min

Finding the panoramas

Overview Feature Matching Image Matching –RANSAC for Homography –Probabilistic model for verification Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching Bundle Adjustment –Error function Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching Bundle Adjustment –Error function Multi-band Blending Results Conclusions

Error function Sum of squared projection errors –n = #images –I(i) = set of image matches to image i –F(i, j) = set of feature matches between images i,j –r ij k = residual of k th feature match between images i,j Robust error function

Parameterise each camera by rotation and focal length This gives pairwise homographies Homography for Rotation

Bundle Adjustment New images initialised with rotation, focal length of best matching image

Bundle Adjustment New images initialised with rotation, focal length of best matching image

Overview Feature Matching Image Matching Bundle Adjustment –Error function Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Multi-band Blending Burt & Adelson 1983 –Blend frequency bands over range

Low frequency ( > 2 pixels) High frequency ( < 2 pixels) 2-band Blending

Linear Blending

2-band Blending

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Results

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Overview Feature Matching Image Matching Bundle Adjustment Multi-band Blending Results Conclusions

Fully automatic panoramas –A recognition problem… Invariant feature based method –SIFT features, RANSAC, Bundle Adjustment, Multi- band Blending –O(nlogn) Future Work –Advanced camera modelling radial distortion, camera motion, scene motion, vignetting, exposure, high dynamic range, flash … –Full 3D case – recognising 3D objects/scenes in unordered datasets

Questions?

Analytical computation of derivatives

Levenberg-Marquardt Iteration step of form