Feature detectors and descriptors. Fei-Fei Li
|
|
|
- Erica Marshall
- 5 years ago
- Views:
Transcription
1 Feature detectors and descriptors Fei-Fei Li
2 Feature Detection e.g. DoG detected points (~300) coordinates, neighbourhoods Feature Description e.g. SIFT local descriptors (invariant) vectors database of local descriptors Matching / Indexing / Recognition e.g. Mahalanobis distance + Voting algorithm [Mikolajczyk & Schmid 01]
3 Some of the challenges Geometry Rotation Similarity (rotation + uniform scale) Affine (scale dependent on direction) valid for: orthographic camera, locally planar object Photometry Affine intensity change (I a I + b)
4 Detector Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) Kadir & Brady, 01 Matas, 02 Descriptor SIFT, PCA-SIFT Intensity Rotation Scale Affine others others
5 Detector Descriptor Intensity Rotation Scale Affine Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) SIFT, PCA-SIFT Kadir & Brady, 01 Matas, 02 others others
6 An introductory example: Harris corner detector C.Harris, M.Stephens. A Combined Corner and Edge Detector. 1988
7 Harris Detector: Basic Idea flat region: no change in all directions edge : no change along the edge direction corner : significant change in all directions
8 Harris Detector: Mathematics Change of intensity for the shift [u,v]: xy, [ ] 2 Euv (, ) = wxy (, ) I( x+ u, y + v) I( x, y) Window function Shifted intensity Intensity Window function w(x,y) = or 1 in window, 0 outside Gaussian
9 Harris Detector: Mathematics For small shifts [u,v] we have a bilinear approximation: u Euv (, ) [ uv, ] M v where M is a 2 2 matrix computed from image derivatives: M 2 I x II x y = w( x, y) 2 xy, I xiy Iy
10 Harris Detector: Mathematics Intensity change in shifting window: eigenvalue analysis u Euv (, ) [ uv, ] M v λ 1, λ 2 eigenvalues of M Ellipse E(u,v) = const direction of the fastest change (λ max ) -1/2 (λ min )-1/2 direction of the slowest change
11 Harris Detector: Mathematics Classification of image points using eigenvalues of M: λ 2 Edge λ 2 >> λ 1 Corner λ 1 and λ 2 are large, λ 1 ~ λ 2 ; E increases in all directions λ 1 and λ 2 are small; E is almost constant in all directions Flat region Edge λ 1 >> λ 2 λ 1
12 Harris Detector: Mathematics Measure of corner response: R = det M k M ( trace ) 2 det M trace M = λ λ 1 2 = λ + λ 1 2 (k empirical constant, k = )
13 Harris Detector: Mathematics R depends only on eigenvalues of M λ 2 Edge R < 0 Corner R is large for a corner R is negative with large magnitude for an edge R > 0 R is small for a flat region Flat R small Edge R < 0 λ 1
14 Harris Detector The Algorithm: Find points with large corner response function R (R > threshold) Take the points of local maxima of R
15 Harris Detector: Workflow
16 Harris Detector: Workflow Compute corner response R
17 Harris Detector: Workflow Find points with large corner response: R>threshold
18 Harris Detector: Workflow Take only the points of local maxima of R
19 Harris Detector: Workflow
20 Harris Detector: Summary Average intensity change in direction [u,v] can be expressed as a bilinear form: u Euv (, ) [ uv, ] M v Describe a point in terms of eigenvalues of M: measure of corner response ( ) 2 R = λ λ k λ + λ A good (corner) point should have a large intensity change in all directions, i.e. R should be large positive
21 Harris Detector: Some Rotation invariance Properties Ellipse rotates but its shape (i.e. eigenvalues) remains the same Corner response R is invariant to image rotation
22 Harris Detector: Some Properties Partial invariance to affine intensity change Only derivatives are used => invariance to intensity shift I I + b Intensity scale: I a I R R threshold x (image coordinate) x (image coordinate)
23 Harris Detector: Some Properties But: non-invariant to image scale! All points will be classified as edges Corner!
24 Harris Detector: Some Properties Quality of Harris detector for different scale changes Repeatability rate: # correspondences # possible correspondences C.Schmid et.al. Evaluation of Interest Point Detectors. IJCV 2000
25 Detector Descriptor Intensity Rotation Scale Affine Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) Kadir & Brady, 01 Matas, 02 SIFT, PCA- SIFT Yes Yes No No others others
26 Detector Descriptor Intensity Rotation Scale Affine Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) Kadir & Brady, 01 Matas, 02 SIFT, PCA- SIFT Yes Yes No No others others
![Interest point detectors Harris-Laplace [Mikolajczyk & Schmid 01] Adds scale invariance to Harris points Set s i = λs d Detect at several scales](/docs-images/81/82779406/images/27-0.jpg "by varying s d Only take local maxima (8-neighbourhood) of scale adapted Harris points Further restrict to scales at which Laplacian is local")
27 Interest point detectors Harris-Laplace [Mikolajczyk & Schmid 01] Adds scale invariance to Harris points Set s i = λs d Detect at several scales by varying s d Only take local maxima (8-neighbourhood) of scale adapted Harris points Further restrict to scales at which Laplacian is local maximum
![Interest point detectors Harris-Laplace [Mikolajczyk & Schmid 01] Selected scale determines size of support region](/docs-images/81/82779406/images/28-0.jpg "Laplacian justified experimentally compared to gradient squared & DoG [Lindeberg 98] gives thorough analysis of")
28 Interest point detectors Harris-Laplace [Mikolajczyk & Schmid 01] Selected scale determines size of support region Laplacian justified experimentally compared to gradient squared & DoG [Lindeberg 98] gives thorough analysis of scale-space
29 Interest point detectors Harris-Affine [Mikolajczyk & Schmid 02] Adds invariance to affine image transformations Initial locations and isotropic scale found by Harris-Laplace Affine invariant neighbourhood evolved iteratively using the moment matrix μ: ) )), ( ))(, ( (( ) ( ),, ( T D D I D I L L g Σ Σ Σ = Σ Σ x x x μ ) 2 exp( 2 1 ) ( 1 x x Σ Σ = Σ T g π ) ( ) ( ), ( x x I g L Σ = Σ
30 Interest point detectors Harris-Affine [Mikolajczyk & Schmid 02] For affinely related points: x = L Ax R If μ ( x L, I, L, Σ D, L Σ ) = M L Σ I, L = tm 1 L Σ D, L = dm 1 L and μ ( xr, I, R, ΣD, R Σ ) = M R Σ I, R = tm 1 R Σ D, R = dm 1 R Then by normalising: 2 x L M 1/ x We get: x L Rx R L L and x R M x 1/ 2 R so the normalised regions are related by a pure rotation See also [Lindeberg & Garding 97] and [Baumberg 00] R
![Interest point detectors Harris-Affine [Mikolajczyk & Schmid 02] Algorithm iteratively adapts shape of](/docs-images/81/82779406/images/31-0.jpg "support region spatial location x (k) integration scale σ I (based on Laplacian) derivation scale σ D =")
31 Interest point detectors Harris-Affine [Mikolajczyk & Schmid 02] Algorithm iteratively adapts shape of support region spatial location x (k) integration scale σ I (based on Laplacian) derivation scale σ D = sσ I
32 Detector Descriptor Intensity Rotation Scale Affine Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) Kadir & Brady, 01 Matas, 02 SIFT, PCA- SIFT Yes Yes No No Yes Yes Yes Yes others others
33 Detector Descriptor Intensity Rotation Scale Affine Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) Kadir & Brady, 01 Matas, 02 SIFT, PCA- SIFT Yes Yes No No Yes Yes Yes Yes others others
34 T.Tuytelaars, L.V.Gool. Wide Baseline Stereo Matching Based on Local, Affinely Invariant Regions. BMVC Affine Invariant Detection Take a local intensity extremum as initial point Go along every ray starting from this point and stop when extremum of function f is reached f It () I points along the ray We will obtain approximately corresponding regions f () t = t 1 t o 0 I () t I dt 0
35 Affine Invariant Detection The regions found may not exactly correspond, so we approximate them with ellipses Geometric Moments: mpq p q = x y f( x, y) dxdy Fact: moments m pq uniquely 2 determine the function f Taking f to be the characteristic function of a region (1 inside, 0 outside), moments of orders up to 2 allow to approximate the region by an ellipse This ellipse will have the same moments of orders up to 2 as the original region
36 Affine Invariant Detection Covariance matrix of region points defines an ellipse: q = Ap T p Σ = 1 1 p 1 T q Σ = 1 2 q 1 Σ = 1 T pp region 1 Σ = 2 T qq region 2 ( p = [x, y] T is relative to the center of mass) Σ = AΣ 2 1 A T Ellipses, computed for corresponding regions, also correspond!
37 T.Tuytelaars, L.V.Gool. Wide Baseline Stereo Matching Based on Local, Affinely Invariant Regions. BMVC Affine Invariant Detection Algorithm summary (detection of affine invariant region): Start from a local intensity extremum point Go in every direction until the point of extremum of some function f Curve connecting the points is the region boundary Compute geometric moments of orders up to 2 for this region Replace the region with ellipse
38 Detector Descriptor Intensity Rotation Scale Affine Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) Kadir & Brady, 01 Matas, 02 SIFT, PCA-SIFT Yes Yes No No Yes Yes Yes Yes Yes Yes No (Yes 04?) Yes others others
39 Detector Descriptor Intensity Rotation Scale Affine Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) Kadir & Brady, 01 Matas, 02 SIFT, PCA-SIFT Yes Yes No No Yes Yes Yes Yes Yes Yes No (Yes 04?) Yes others others
![Interest point detectors Difference of Gaussians [Lowe 99] Difference of Gaussians in scale-space detects blob -like features Can](/docs-images/81/82779406/images/40-0.jpg "be computed efficiently with image pyramid Approximates Laplacian for correct scale factor Invariant to rotation and scale")
40 Interest point detectors Difference of Gaussians [Lowe 99] Difference of Gaussians in scale-space detects blob -like features Can be computed efficiently with image pyramid Approximates Laplacian for correct scale factor Invariant to rotation and scale changes
41 Res ample Blur Subtra ct Key point localization Detect maxima and minima of difference-of-gaussian in scale space (Lowe, 1999) Fit a quadratic to surrounding values for sub-pixel and sub-scale interpolation (Brown & Lowe, 2002) Taylor expansion around point: Offset of extremum (use finite differences for derivatives):
42 Select canonical orientation Create histogram of local gradient directions computed at selected scale Assign canonical orientation at peak of smoothed histogram Each key specifies stable 2D coordinates (x, y, scale, orientation) 0 2π
43 Example of keypoint detection Threshold on value at DOG peak and on ratio of principle curvatures (Harris approach) (a) 233x189 image (b) 832 DOG extrema (c) 729 left after peak value threshold (d) 536 left after testing ratio of principle curvatures
44 Creating features stable to viewpoint change Edelman, Intrator & Poggio (97) showed that complex cell outputs are better for 3D recognition than simple correlation
45 SIFT vector formation Thresholded image gradients are sampled over 16x16 array of locations in scale space Create array of orientation histograms 8 orientations x 4x4 histogram array = 128 dimensions
46 Feature stability to noise Match features after random change in image scale & orientation, with differing levels of image noise Find nearest neighbor in database of 30,000 features
47 Feature stability to affine change Match features after random change in image scale & orientation, with 2% image noise, and affine distortion Find nearest neighbor in database of 30,000 features
48 Detector Descriptor Intensity Rotation Scale Affine Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) Kadir & Brady, 01 Matas, 02 SIFT, PCA-SIFT Yes Yes No No Yes Yes Yes Yes Yes Yes No (Yes 04?) Yes Yes Yes Yes Yes others others
49 Detector Descriptor Intensity Rotation Scale Affine Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) Kadir & Brady, 01 Matas, 02 SIFT, PCA-SIFT Yes Yes No No Yes Yes Yes Yes Yes Yes No (Yes 04?) Yes Yes Yes Yes Yes others others
50 Other interest point detectors Scale Saliency [Kadir & Brady 01, 03]
51 Other interest point detectors Scale Saliency [Kadir & Brady 01, 03] Uses entropy measure of local pdf of intensities: Takes local maxima in scale Weights with change of distribution with scale: To get saliency measure: = D d D d s d p s d p s H d ).,, ( ) log,, ( ), ( 2 x x x = D d D d s d p s s s W d ).,, ( ), ( x x ), ( ), ( ), ( x x x s W s H s Y D D D =
52 Other interest point detectors Scale Saliency [Kadir & Brady 01, 03] H D (s,x) W D (s,x) Just using H D (s,x) Using Y D (s,x) = H D W D Most salient parts detected
53 Other interest point detectors maximum stable extremal regions [matas et al. 02] Sweep threshold of intensity from black to white Locate regions based on stability of region with respect to change of threshold
54 Detector Descriptor Intensity Rotation Scale Affine Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) Kadir & Brady, 01 SIFT, PCA-SIFT Yes Yes No No Yes Yes Yes Yes Yes Yes No (Yes 04?) Yes Yes Yes Yes Yes Yes Yes Yes? Matas, 02 Yes Yes Yes? others others
55 Detector Descriptor Intensity Rotation Scale Affine Harris corner Mikolajczyk & Schmid 01, 02 Tuytelaars, 00 Lowe 99 (DoG) Kadir & Brady, 01 SIFT, PCA-SIFT Yes Yes No No Yes Yes Yes Yes Yes Yes No (Yes 04?) Yes Yes Yes Yes Yes Yes Yes Yes? Matas, 02 Yes Yes Yes? others others
56 Affine-invariant texture recognition Texture recognition under viewpoint changes and non-rigid transformations Use of affine-invariant regions invariance to viewpoint changes spatial selection => more compact representation, reduction of redundancy in texton dictionary [A sparse texture representation using affine-invariant regions, S. Lazebnik, C. Schmid and J. Ponce, CVPR 2003]
57 Overview of the approach
58 Region extraction Harris detector Laplace detector
59 Descriptors Spin images
60 Spatial selection clustering each pixel clustering selected pixels
61 Signature and EMD Hierarchical clustering => Signature : S = { ( m 1, w 1 ),, ( m k, w k ) } Earth movers distance D( S, S ) = [ i,j f ij d( m i, m j )] / [ i,j f ij ] robust distance, optimizes the flow between distributions can match signatures of different size not sensitive to the number of clusters
62 Database with viewpoint changes 20 samples of 10 different textures
63 Results Spin images Gabor-like filters
Feature detectors and descriptors. Fei-Fei Li
Feature detectors and descriptors Fei-Fei Li Feature Detection e.g. DoG detected points (~300) coordinates, neighbourhoods Feature Description e.g. SIFT local descriptors (invariant) vectors database of
Advances in Computer Vision. Prof. Bill Freeman. Image and shape descriptors. Readings: Mikolajczyk and Schmid; Belongie et al.
6.869 Advances in Computer Vision Prof. Bill Freeman March 3, 2005 Image and shape descriptors Affine invariant features Comparison of feature descriptors Shape context Readings: Mikolajczyk and Schmid;
Feature extraction: Corners and blobs
Feature extraction: Corners and blobs Review: Linear filtering and edge detection Name two different kinds of image noise Name a non-linear smoothing filter What advantages does median filtering have over
Local Features (contd.)
Motivation Local Features (contd.) Readings: Mikolajczyk and Schmid; F&P Ch 10 Feature points are used also or: Image alignment (homography, undamental matrix) 3D reconstruction Motion tracking Object
Corners, Blobs & Descriptors. With slides from S. Lazebnik & S. Seitz, D. Lowe, A. Efros
Corners, Blobs & Descriptors With slides from S. Lazebnik & S. Seitz, D. Lowe, A. Efros Motivation: Build a Panorama M. Brown and D. G. Lowe. Recognising Panoramas. ICCV 2003 How do we build panorama?
Lecture 12. Local Feature Detection. Matching with Invariant Features. Why extract features? Why extract features? Why extract features?
Lecture 1 Why extract eatures? Motivation: panorama stitching We have two images how do we combine them? Local Feature Detection Guest lecturer: Alex Berg Reading: Harris and Stephens David Lowe IJCV We
Edges and Scale. Image Features. Detecting edges. Origin of Edges. Solution: smooth first. Effects of noise
Edges and Scale Image Features From Sandlot Science Slides revised from S. Seitz, R. Szeliski, S. Lazebnik, etc. Origin of Edges surface normal discontinuity depth discontinuity surface color discontinuity
Detectors part II Descriptors
EECS 442 Computer vision Detectors part II Descriptors Blob detectors Invariance Descriptors Some slides of this lectures are courtesy of prof F. Li, prof S. Lazebnik, and various other lecturers Goal:
INTEREST POINTS AT DIFFERENT SCALES
INTEREST POINTS AT DIFFERENT SCALES Thank you for the slides. They come mostly from the following sources. Dan Huttenlocher Cornell U David Lowe U. of British Columbia Martial Hebert CMU Intuitively, junctions
Invariant local features. Invariant Local Features. Classes of transformations. (Good) invariant local features. Case study: panorama stitching
Invariant local eatures Invariant Local Features Tuesday, February 6 Subset o local eature types designed to be invariant to Scale Translation Rotation Aine transormations Illumination 1) Detect distinctive
Recap: edge detection. Source: D. Lowe, L. Fei-Fei
Recap: edge detection Source: D. Lowe, L. Fei-Fei Canny edge detector 1. Filter image with x, y derivatives of Gaussian 2. Find magnitude and orientation of gradient 3. Non-maximum suppression: Thin multi-pixel
Image Analysis. Feature extraction: corners and blobs
Image Analysis Feature extraction: corners and blobs Christophoros Nikou cnikou@cs.uoi.gr Images taken from: Computer Vision course by Svetlana Lazebnik, University of North Carolina at Chapel Hill (http://www.cs.unc.edu/~lazebnik/spring10/).
Lecture 8: Interest Point Detection. Saad J Bedros
#1 Lecture 8: Interest Point Detection Saad J Bedros sbedros@umn.edu Review of Edge Detectors #2 Today s Lecture Interest Points Detection What do we mean with Interest Point Detection in an Image Goal:
Blobs & Scale Invariance
Blobs & Scale Invariance Prof. Didier Stricker Doz. Gabriele Bleser Computer Vision: Object and People Tracking With slides from Bebis, S. Lazebnik & S. Seitz, D. Lowe, A. Efros 1 Apertizer: some videos
Overview. Introduction to local features. Harris interest points + SSD, ZNCC, SIFT. Evaluation and comparison of different detectors
Overview Introduction to local features Harris interest points + SSD, ZNCC, SIFT Scale & affine invariant interest point detectors Evaluation and comparison of different detectors Region descriptors and
SIFT keypoint detection. D. Lowe, Distinctive image features from scale-invariant keypoints, IJCV 60 (2), pp , 2004.
SIFT keypoint detection D. Lowe, Distinctive image features from scale-invariant keypoints, IJCV 60 (), pp. 91-110, 004. Keypoint detection with scale selection We want to extract keypoints with characteristic
Corner detection: the basic idea
Corner detection: the basic idea At a corner, shifting a window in any direction should give a large change in intensity flat region: no change in all directions edge : no change along the edge direction
Lecture 6: Finding Features (part 1/2)
Lecture 6: Finding Features (part 1/2) Professor Fei- Fei Li Stanford Vision Lab Lecture 6 -! 1 What we will learn today? Local invariant features MoHvaHon Requirements, invariances Keypoint localizahon
LoG Blob Finding and Scale. Scale Selection. Blobs (and scale selection) Achieving scale covariance. Blob detection in 2D. Blob detection in 2D
Achieving scale covariance Blobs (and scale selection) Goal: independently detect corresponding regions in scaled versions of the same image Need scale selection mechanism for finding characteristic region
Lecture 8: Interest Point Detection. Saad J Bedros
#1 Lecture 8: Interest Point Detection Saad J Bedros sbedros@umn.edu Last Lecture : Edge Detection Preprocessing of image is desired to eliminate or at least minimize noise effects There is always tradeoff
Blob Detection CSC 767
Blob Detection CSC 767 Blob detection Slides: S. Lazebnik Feature detection with scale selection We want to extract features with characteristic scale that is covariant with the image transformation Blob
Achieving scale covariance
Achieving scale covariance Goal: independently detect corresponding regions in scaled versions of the same image Need scale selection mechanism for finding characteristic region size that is covariant
Extract useful building blocks: blobs. the same image like for the corners
Extract useful building blocks: blobs the same image like for the corners Here were the corners... Blob detection in 2D Laplacian of Gaussian: Circularly symmetric operator for blob detection in 2D 2 g=
Overview. Harris interest points. Comparing interest points (SSD, ZNCC, SIFT) Scale & affine invariant interest points
Overview Harris interest points Comparing interest points (SSD, ZNCC, SIFT) Scale & affine invariant interest points Evaluation and comparison of different detectors Region descriptors and their performance
Scale & Affine Invariant Interest Point Detectors
Scale & Affine Invariant Interest Point Detectors Krystian Mikolajczyk and Cordelia Schmid Presented by Hunter Brown & Gaurav Pandey, February 19, 2009 Roadmap: Motivation Scale Invariant Detector Affine
SIFT: Scale Invariant Feature Transform
1 SIFT: Scale Invariant Feature Transform With slides from Sebastian Thrun Stanford CS223B Computer Vision, Winter 2006 3 Pattern Recognition Want to find in here SIFT Invariances: Scaling Rotation Illumination
Overview. Introduction to local features. Harris interest points + SSD, ZNCC, SIFT. Evaluation and comparison of different detectors
Overview Introduction to local features Harris interest points + SSD, ZNCC, SIFT Scale & affine invariant interest point detectors Evaluation and comparison of different detectors Region descriptors and
CSE 473/573 Computer Vision and Image Processing (CVIP)
CSE 473/573 Computer Vision and Image Processing (CVIP) Ifeoma Nwogu inwogu@buffalo.edu Lecture 11 Local Features 1 Schedule Last class We started local features Today More on local features Readings for
Properties of detectors Edge detectors Harris DoG Properties of descriptors SIFT HOG Shape context
Lecture 10 Detectors and descriptors Properties of detectors Edge detectors Harris DoG Properties of descriptors SIFT HOG Shape context Silvio Savarese Lecture 10-16-Feb-15 From the 3D to 2D & vice versa
Maximally Stable Local Description for Scale Selection
Maximally Stable Local Description for Scale Selection Gyuri Dorkó and Cordelia Schmid INRIA Rhône-Alpes, 655 Avenue de l Europe, 38334 Montbonnot, France {gyuri.dorko,cordelia.schmid}@inrialpes.fr Abstract.
CS5670: Computer Vision
CS5670: Computer Vision Noah Snavely Lecture 5: Feature descriptors and matching Szeliski: 4.1 Reading Announcements Project 1 Artifacts due tomorrow, Friday 2/17, at 11:59pm Project 2 will be released
EE 6882 Visual Search Engine
EE 6882 Visual Search Engine Prof. Shih Fu Chang, Feb. 13 th 2012 Lecture #4 Local Feature Matching Bag of Word image representation: coding and pooling (Many slides from A. Efors, W. Freeman, C. Kambhamettu,
Scale-space image processing
Scale-space image processing Corresponding image features can appear at different scales Like shift-invariance, scale-invariance of image processing algorithms is often desirable. Scale-space representation
Scale & Affine Invariant Interest Point Detectors
Scale & Affine Invariant Interest Point Detectors KRYSTIAN MIKOLAJCZYK AND CORDELIA SCHMID [2004] Shreyas Saxena Gurkirit Singh 23/11/2012 Introduction We are interested in finding interest points. What
Keypoint extraction: Corners Harris Corners Pkwy, Charlotte, NC
Kepoint etraction: Corners 9300 Harris Corners Pkw Charlotte NC Wh etract kepoints? Motivation: panorama stitching We have two images how do we combine them? Wh etract kepoints? Motivation: panorama stitching
Lecture 7: Finding Features (part 2/2)
Lecture 7: Finding Features (part 2/2) Professor Fei- Fei Li Stanford Vision Lab Lecture 7 -! 1 What we will learn today? Local invariant features MoHvaHon Requirements, invariances Keypoint localizahon
CS4670: Computer Vision Kavita Bala. Lecture 7: Harris Corner Detec=on
CS4670: Computer Vision Kavita Bala Lecture 7: Harris Corner Detec=on Announcements HW 1 will be out soon Sign up for demo slots for PA 1 Remember that both partners have to be there We will ask you to
CS 3710: Visual Recognition Describing Images with Features. Adriana Kovashka Department of Computer Science January 8, 2015
CS 3710: Visual Recognition Describing Images with Features Adriana Kovashka Department of Computer Science January 8, 2015 Plan for Today Presentation assignments + schedule changes Image filtering Feature
SIFT: SCALE INVARIANT FEATURE TRANSFORM BY DAVID LOWE
SIFT: SCALE INVARIANT FEATURE TRANSFORM BY DAVID LOWE Overview Motivation of Work Overview of Algorithm Scale Space and Difference of Gaussian Keypoint Localization Orientation Assignment Descriptor Building
The state of the art and beyond
Feature Detectors and Descriptors The state of the art and beyond Local covariant detectors and descriptors have been successful in many applications Registration Stereo vision Motion estimation Matching
Vlad Estivill-Castro (2016) Robots for People --- A project for intelligent integrated systems
1 Vlad Estivill-Castro (2016) Robots for People --- A project for intelligent integrated systems V. Estivill-Castro 2 Perception Concepts Vision Chapter 4 (textbook) Sections 4.3 to 4.5 What is the course
Wavelet-based Salient Points with Scale Information for Classification
Wavelet-based Salient Points with Scale Information for Classification Alexandra Teynor and Hans Burkhardt Department of Computer Science, Albert-Ludwigs-Universität Freiburg, Germany {teynor, Hans.Burkhardt}@informatik.uni-freiburg.de
SURF Features. Jacky Baltes Dept. of Computer Science University of Manitoba WWW:
SURF Features Jacky Baltes Dept. of Computer Science University of Manitoba Email: jacky@cs.umanitoba.ca WWW: http://www.cs.umanitoba.ca/~jacky Salient Spatial Features Trying to find interest points Points
Harris Corner Detector
Multimedia Computing: Algorithms, Systems, and Applications: Feature Extraction By Dr. Yu Cao Department of Computer Science The University of Massachusetts Lowell Lowell, MA 01854, USA Part of the slides
Affine Adaptation of Local Image Features Using the Hessian Matrix
29 Advanced Video and Signal Based Surveillance Affine Adaptation of Local Image Features Using the Hessian Matrix Ruan Lakemond, Clinton Fookes, Sridha Sridharan Image and Video Research Laboratory Queensland
SURVEY OF APPEARANCE-BASED METHODS FOR OBJECT RECOGNITION
SURVEY OF APPEARANCE-BASED METHODS FOR OBJECT RECOGNITION Peter M. Roth and Martin Winter Inst. for Computer Graphics and Vision Graz University of Technology, Austria Technical Report ICG TR 01/08 Graz,
Lecture 7: Finding Features (part 2/2)
Lecture 7: Finding Features (part 2/2) Dr. Juan Carlos Niebles Stanford AI Lab Professor Fei- Fei Li Stanford Vision Lab 1 What we will learn today? Local invariant features MoPvaPon Requirements, invariances
Advanced Features. Advanced Features: Topics. Jana Kosecka. Slides from: S. Thurn, D. Lowe, Forsyth and Ponce. Advanced features and feature matching
Advanced Features Jana Kosecka Slides from: S. Thurn, D. Lowe, Forsyth and Ponce Advanced Features: Topics Advanced features and feature matching Template matching SIFT features Haar features 2 1 Features
Given a feature in I 1, how to find the best match in I 2?
Feature Matching 1 Feature matching Given a feature in I 1, how to find the best match in I 2? 1. Define distance function that compares two descriptors 2. Test all the features in I 2, find the one with
CEE598 - Visual Sensing for Civil Infrastructure Eng. & Mgmt.
CEE598 - Visual Sensing for Civil nfrastructure Eng. & Mgmt. Session 9- mage Detectors, Part Mani Golparvar-Fard Department of Civil and Environmental Engineering 3129D, Newmark Civil Engineering Lab e-mail:
SIFT, GLOH, SURF descriptors. Dipartimento di Sistemi e Informatica
SIFT, GLOH, SURF descriptors Dipartimento di Sistemi e Informatica Invariant local descriptor: Useful for Object RecogniAon and Tracking. Robot LocalizaAon and Mapping. Image RegistraAon and SAtching.
Feature extraction: Corners and blobs
Featre etraction: Corners and blobs Wh etract featres? Motiation: panorama stitching We hae two images how do we combine them? Wh etract featres? Motiation: panorama stitching We hae two images how do
Hilbert-Huang Transform-based Local Regions Descriptors
Hilbert-Huang Transform-based Local Regions Descriptors Dongfeng Han, Wenhui Li, Wu Guo Computer Science and Technology, Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of
6.869 Advances in Computer Vision. Prof. Bill Freeman March 1, 2005
6.869 Advances in Computer Vision Prof. Bill Freeman March 1 2005 1 2 Local Features Matching points across images important for: object identification instance recognition object class recognition pose
arxiv: v1 [cs.cv] 10 Feb 2016
![arxiv: v1 [cs.cv] 10 Feb 2016](/thumbs/76/73522588.jpg "arxiv: v1 [cs.cv] 10 Feb 2016")
GABOR WAVELETS IN IMAGE PROCESSING David Bařina Doctoral Degree Programme (2), FIT BUT E-mail: xbarin2@stud.fit.vutbr.cz Supervised by: Pavel Zemčík E-mail: zemcik@fit.vutbr.cz arxiv:162.338v1 [cs.cv]
Instance-level recognition: Local invariant features. Cordelia Schmid INRIA, Grenoble
nstance-level recognition: ocal invariant features Cordelia Schmid NRA Grenoble Overview ntroduction to local features Harris interest points + SSD ZNCC SFT Scale & affine invariant interest point detectors
Instance-level recognition: Local invariant features. Cordelia Schmid INRIA, Grenoble
nstance-level recognition: ocal invariant features Cordelia Schmid NRA Grenoble Overview ntroduction to local features Harris interest t points + SSD ZNCC SFT Scale & affine invariant interest point detectors
Image matching. by Diva Sian. by swashford
Image matching by Diva Sian by swashford Harder case by Diva Sian by scgbt Invariant local features Find features that are invariant to transformations geometric invariance: translation, rotation, scale
Interest Operators. All lectures are from posted research papers. Harris Corner Detector: the first and most basic interest operator
Interest Operators All lectures are from posted research papers. Harris Corner Detector: the first and most basic interest operator SIFT interest point detector and region descriptor Kadir Entrop Detector
Instance-level recognition: Local invariant features. Cordelia Schmid INRIA, Grenoble
nstance-level recognition: ocal invariant features Cordelia Schmid NRA Grenoble Overview ntroduction to local features Harris interest points + SSD ZNCC SFT Scale & affine invariant interest point detectors
Feature Extraction and Image Processing
Feature Extraction and Image Processing Second edition Mark S. Nixon Alberto S. Aguado :*авш JBK IIP AMSTERDAM BOSTON HEIDELBERG LONDON NEW YORK OXFORD PARIS SAN DIEGO SAN FRANCISCO SINGAPORE SYDNEY TOKYO
Rapid Object Recognition from Discriminative Regions of Interest
Rapid Object Recognition from Discriminative Regions of Interest Gerald Fritz, Christin Seifert, Lucas Paletta JOANNEUM RESEARCH Institute of Digital Image Processing Wastiangasse 6, A-81 Graz, Austria
Instance-level l recognition. Cordelia Schmid INRIA
nstance-level l recognition Cordelia Schmid NRA nstance-level recognition Particular objects and scenes large databases Application Search photos on the web for particular places Find these landmars...in
The Kadir Operator Saliency, Scale and Image Description. Timor Kadir and Michael Brady University of Oxford
The Kadir Operator Saliency, Scale and Image Description Timor Kadir and Michael Brady University of Oxford 1 The issues salient standing out from the rest, noticeable, conspicous, prominent scale find
Feature detection.
Feature detection Kim Steenstrup Pedersen kimstp@itu.dk The IT University of Copenhagen Feature detection, The IT University of Copenhagen p.1/20 What is a feature? Features can be thought of as symbolic
Robert Collins CSE598G Mean-Shift Blob Tracking through Scale Space
Mean-Shift Blob Tracking through Scale Space Robert Collins, CVPR 03 Abstract Mean-shift tracking Choosing scale of kernel is an issue Scale-space feature selection provides inspiration Perform mean-shift
Instance-level l recognition. Cordelia Schmid & Josef Sivic INRIA
nstance-level l recognition Cordelia Schmid & Josef Sivic NRA nstance-level recognition Particular objects and scenes large databases Application Search photos on the web for particular places Find these
* h + = Lec 05: Interesting Points Detection. Image Analysis & Retrieval. Outline. Image Filtering. Recap of Lec 04 Image Filtering Edge Features
age Analsis & Retrieval Outline CS/EE 5590 Special Topics (Class ds: 44873, 44874) Fall 06, M/W 4-5:5p@Bloch 00 Lec 05: nteresting Points Detection Recap of Lec 04 age Filtering Edge Features Hoework Harris
A New Shape Adaptation Scheme to Affine Invariant Detector
KSII ANSACIONS ON INENE AND INFOMAION SYSEMS VO. 4, NO. 6, December 2010 1253 Copyright c 2010 KSII A New Shape Adaptation Scheme to Affine Invariant Detector Congxin iu, Jie Yang, Yue Zhou and Deying
Visual Object Recognition
Visual Object Recognition Lecture 2: Image Formation Per-Erik Forssén, docent Computer Vision Laboratory Department of Electrical Engineering Linköping University Lecture 2: Image Formation Pin-hole, and
Representing regions in 2 ways:
Representing regions in 2 ways: Based on their external characteristics (its boundary): Shape characteristics Based on their internal characteristics (its region): Both Regional properties: color, texture,
Image Processing 1 (IP1) Bildverarbeitung 1
MIN-Fakultät Fachbereich Informatik Arbeitsbereich SAV/BV KOGS Image Processing 1 IP1 Bildverarbeitung 1 Lecture : Object Recognition Winter Semester 015/16 Slides: Prof. Bernd Neumann Slightly revised
Feature Vector Similarity Based on Local Structure
Feature Vector Similarity Based on Local Structure Evgeniya Balmachnova, Luc Florack, and Bart ter Haar Romeny Eindhoven University of Technology, P.O. Box 53, 5600 MB Eindhoven, The Netherlands {E.Balmachnova,L.M.J.Florack,B.M.terHaarRomeny}@tue.nl
Human Action Recognition under Log-Euclidean Riemannian Metric
Human Action Recognition under Log-Euclidean Riemannian Metric Chunfeng Yuan, Weiming Hu, Xi Li, Stephen Maybank 2, Guan Luo, National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing,
SCALE-SPACE - Theory and Applications
SCALE-SPACE - Theory and Applications Scale is embedded in the task: do you want only coins or TREASURE? SCALE-SPACE Theory and Applications - Scale-space theory is a framework of multiscale image/signal
Feature Tracking. 2/27/12 ECEn 631
Corner Extraction Feature Tracking Mostly for multi-frame applications Object Tracking Motion detection Image matching Image mosaicing 3D modeling Object recognition Homography estimation... Global Features
EECS150 - Digital Design Lecture 15 SIFT2 + FSM. Recap and Outline
EECS150 - Digital Design Lecture 15 SIFT2 + FSM Oct. 15, 2013 Prof. Ronald Fearing Electrical Engineering and Computer Sciences University of California, Berkeley (slides courtesy of Prof. John Wawrzynek)
Machine vision. Summary # 4. The mask for Laplacian is given
1 Machine vision Summary # 4 The mask for Laplacian is given L = 0 1 0 1 4 1 (6) 0 1 0 Another Laplacian mask that gives more importance to the center element is L = 1 1 1 1 8 1 (7) 1 1 1 Note that the
Rotational Invariants for Wide-baseline Stereo
Rotational Invariants for Wide-baseline Stereo Jiří Matas, Petr Bílek, Ondřej Chum Centre for Machine Perception Czech Technical University, Department of Cybernetics Karlovo namesti 13, Prague, Czech
Lecture 6: Edge Detection. CAP 5415: Computer Vision Fall 2008
Lecture 6: Edge Detection CAP 5415: Computer Vision Fall 2008 Announcements PS 2 is available Please read it by Thursday During Thursday lecture, I will be going over it in some detail Monday - Computer
Edge Detection. CS 650: Computer Vision
CS 650: Computer Vision Edges and Gradients Edge: local indication of an object transition Edge detection: local operators that find edges (usually involves convolution) Local intensity transitions are
Space-time Zernike Moments and Pyramid Kernel Descriptors for Action Classification
Space-time Zernike Moments and Pyramid Kernel Descriptors for Action Classification Luca Costantini 2, Lorenzo Seidenari 1, Giuseppe Serra 1, Licia Capodiferro 2, and Alberto Del Bimbo 1 1 Media Integration
On the Completeness of Coding with Image Features
FÖRSTNER ET AL.: COMPLETENESS OF CODING WITH FEATURES 1 On the Completeness of Coding with Image Features Wolfgang Förstner http://www.ipb.uni-bonn.de/foerstner/ Timo Dickscheid http://www.ipb.uni-bonn.de/timodickscheid/
Machine vision, spring 2018 Summary 4
Machine vision Summary # 4 The mask for Laplacian is given L = 4 (6) Another Laplacian mask that gives more importance to the center element is given by L = 8 (7) Note that the sum of the elements in the
Is the Scale Invariant Feature Transform (SIFT) really Scale Invariant?
Is the Scale Invariant Feature Transform (SIFT) really Scale Invariant? Course prepared by: Jean-Michel Morel, Guoshen Yu and Ives Rey Otero October 24, 2010 Abstract This note is devoted to a mathematical
Lec 12 Review of Part I: (Hand-crafted) Features and Classifiers in Image Classification
Image Analysis & Retrieval Spring 2017: Image Analysis Lec 12 Review of Part I: (Hand-crafted) Features and Classifiers in Image Classification Zhu Li Dept of CSEE, UMKC Office: FH560E, Email: lizhu@umkc.edu,
Face detection and recognition. Detection Recognition Sally
Face detection and recognition Detection Recognition Sally Face detection & recognition Viola & Jones detector Available in open CV Face recognition Eigenfaces for face recognition Metric learning identification
Global Scene Representations. Tilke Judd
Global Scene Representations Tilke Judd Papers Oliva and Torralba [2001] Fei Fei and Perona [2005] Labzebnik, Schmid and Ponce [2006] Commonalities Goal: Recognize natural scene categories Extract features
KAZE Features. 1 Introduction. Pablo Fernández Alcantarilla 1, Adrien Bartoli 1, and Andrew J. Davison 2
KAZE Features Pablo Fernández Alcantarilla 1, Adrien Bartoli 1, and Andrew J. Davison 2 1 ISIT-UMR 6284 CNRS, Université d Auvergne, Clermont Ferrand, France {pablo.alcantarilla,adrien.bartoli}@gmail.com
Perception III: Filtering, Edges, and Point-features
Perception : Filtering, Edges, and Point-features Davide Scaramuzza Universit of Zurich Margarita Chli, Paul Furgale, Marco Hutter, Roland Siegwart 1 Toda s outline mage filtering Smoothing Edge detection
On the consistency of the SIFT Method
1 INTRODUCTION 1 On the consistency of the SIFT Method Jean-Michel Morel Guoshen Yu August 11, 2008 Abstract This note is devoted to the mathematical arguments proving that Lowe s Scale-Invariant Feature
Orientation Map Based Palmprint Recognition
Orientation Map Based Palmprint Recognition (BM) 45 Orientation Map Based Palmprint Recognition B. H. Shekar, N. Harivinod bhshekar@gmail.com, harivinodn@gmail.com India, Mangalore University, Department
Coding Images with Local Features
Int J Comput Vis (2011) 94:154 174 DOI 10.1007/s11263-010-0340-z Coding Images with Local Features Timo Dickscheid Falko Schindler Wolfgang Förstner Received: 21 September 2009 / Accepted: 8 April 2010
Affine Differential Invariants for Invariant Feature Point Detection
Affine Differential Invariants for Invariant Feature Point Detection Stanley L. Tuznik Department of Applied Mathematics and Statistics Stony Brook University Stony Brook, NY 11794 stanley.tuznik@stonybrook.edu
Lesson 04. KAZE, Non-linear diffusion filtering, ORB, MSER. Ing. Marek Hrúz, Ph.D.
Lesson 04 KAZE, Non-linear diffusion filtering, ORB, MSER Ing. Marek Hrúz, Ph.D. Katedra Kybernetiky Fakulta aplikovaných věd Západočeská univerzita v Plzni Lesson 04 KAZE ORB: an efficient alternative
Region Moments: Fast invariant descriptors for detecting small image structures
Region Moments: Fast invariant descriptors for detecting small image structures Gianfranco Doretto Yi Yao Visualization and Computer Vision Lab, GE Global Research, Niskayuna, NY 39 doretto@research.ge.com
Distinguish between different types of scenes. Matching human perception Understanding the environment
Scene Recognition Adriana Kovashka UTCS, PhD student Problem Statement Distinguish between different types of scenes Applications Matching human perception Understanding the environment Indexing of images
Riemannian Metric Learning for Symmetric Positive Definite Matrices
CMSC 88J: Linear Subspaces and Manifolds for Computer Vision and Machine Learning Riemannian Metric Learning for Symmetric Positive Definite Matrices Raviteja Vemulapalli Guide: Professor David W. Jacobs
Interest Point Detection with Wavelet Maxima Lines
Interest Point Detection with Wavelet Maxima Lines Christophe Damerval, Sylvain Meignen To cite this version: Christophe Damerval, Sylvain Meignen. Interest Point Detection with Wavelet Maxima Lines. 7.