Instance-level recognition: Local invariant features. Cordelia Schmid INRIA, Grenoble
|
|
- Madlyn Rosa Todd
- 5 years ago
- Views:
Transcription
1 nstance-level recognition: ocal invariant features Cordelia Schmid NRA Grenoble
2 Overview ntroduction to local features Harris interest points + SSD ZNCC SFT Scale & affine invariant interest point detectors Evaluation and comparison of different detectors Region descriptors and their performance
3 ocal features local descriptor Several / man local descriptors per image Robust to occlusion/clutter + no object segmentation required Photometric : distinctive nvariant : to image transformations + illumination changes
4 ocal features: interest points
5 ocal features: Contours/segments
6 ocal features: segmentation
7 Application: Matching Find corresponding locations in the image
8 llustration Matching nterest points etracted with Harris detector ~ 500 points
9 llustration Matching Matching nterest points matched based on cross-correlation 188 pairs
10 llustration Global constraints Matching Global constraint - Robust estimation of the fundamental matri 99 inliers 89 outliers
11 Application: Panorama stitching mages courtes of A. Zisserman.
12 Application: nstance-level recognition Search for particular objects and scenes in large databases
13 nstance-level recognition: Approach mage content is transformed into local features invariant to geometric and photometric transformations Matching local invariant descriptors ocal Features e.g. SFT K. Grauman B. eibe Slide credit: David owe 13
14 Difficulties Finding the object despite possibl large changes in scale viewpoint lighting and partial occlusion requires invariant description Scale Viewpoint ighting Occlusion
15 Difficulties Ver large images collection need for efficient indeing Flickr has billion photographs more than 1 million added dail Facebook has 15 billion images ~7 million added dail arge personal collections Video collections i.e. YouTube
16 Applications Take a picture of a product or advertisement find relevant information on the web [Piee Milpi]
17 Applications Cop detection for images and videos Quer video Search in 00h of video
18 Applications Son Aibo Robotics Recognize docking station Place recognition oop closure in SAM K. Grauman B. eibe Slide credit: David owe 18
19 ocal features - histor ine segments [owe 87 Aache 90] nterest points & cross correlation [Z. Zhang et al. 95] Rotation invariance with differential invariants [Schmid&Mohr 96] Scale & affine invariant detectors [indeberg 98 owe 99 Tutelaars&VanGool 00 Mikolajczk&Schmid 0 Matas et al. 0] Dense detectors and descriptors [eung&malik 99 Fei-Fei& Perona 05 azebnik et al. 06] Contour and region segmentation descriptors [Shotton et al. 05 Opelt et al. 06 Ferrari et al. 06 eordeanu et al. 07]
20 ocal features 1 Etraction of local features Contours/segments nterest points & regions Regions b segmentation Dense features points on a regular grid Description of local features Dependant on the feature tpe Contours/segments angles length ratios nterest points grelevels gradient histograms Regions segmentation teture + color distributions
21 ine matching Etraction de contours Zero crossing of aplacian ocal maima of gradients Chain contour points hsteresis Etraction of line segments Description of segments Mi-point length orientation angle between pairs etc.
22 Eperimental results line segments images
23 Eperimental results line segments 48 / 1 line segments etracted
24 Eperimental results line segments 89 matched line segments - 100% correct
25 Eperimental results line segments 3D reconstruction
26 Problems of line segments Often onl partial etraction ine segments broken into parts Missing parts nformation not ver discriminative 1D information Similar for man segments Potential solutions Pairs and triplets of segments nterest points
27 Overview ntroduction to local features Harris interest points + SSD ZNCC SFT Scale & affine invariant interest point detectors Evaluation and comparison of different detectors Region descriptors and their performance
28 Harris detector [Harris & Stephens 88] Based on the idea of auto-correlation mportant difference in all directions => interest point
29 Harris detector Auto-correlation function for a point and a shift A = k k k + k + k k W W
30 Harris detector Auto-correlation function for a point and a shift A = k k k + k + k k W W { A small in all directions large in one directions large in all directions uniform region contour interest point
31 Harris detector
32 Harris detector Discret shifts are avoided based on the auto-correlation matri + = + + with first order approimation = W k k k k k k + = + + k k k k k k k k A k k k W k k k + + =
33 Harris detector = W k k W k k k k W k k k k W k k k k k k k k k k Auto-correlation matri the sum can be smoothed with a Gaussian = G
34 Harris detector Auto-correlation matri A G = captures the structure of the local neighborhood measure based on eigenvalues of this matri strong eigenvalues 1 strong eigenvalue 0 eigenvalue => interest point => contour => uniform region
35 nterpreting the eigenvalues Classification of image points using eigenvalues of autocorrelation matri: λ Edge λ >> λ 1 Corner λ 1 and λ are large λ 1 ~ λ ; \ λ 1 and λ are small; Flat region Edge λ 1 >> λ λ 1
36 R Corner response function = det A A α: constant 0.04 to 0.06 α trace = λ1λ α λ1 + Edge R < 0 Corner R > 0 λ Flat region R small Edge R < 0
37 Harris detector Cornerness function f = det A k trace A = 1λ k λ λ + λ 1 Reduces the effect of a strong contour nterest point detection Treshold absolut relatif number of corners ocal maima f > thresh 8 neighbourhood f f
38 Harris Detector: Steps
39 Compute corner response R Harris Detector: Steps
40 Harris Detector: Steps Find points with large corner response: R>threshold
41 Harris Detector: Steps Take onl the points of local maima of R
42 Harris Detector: Steps
43 Harris detector: Summar of steps 1. Compute Gaussian derivatives at each piel. Compute second moment matri A in a Gaussian window around each piel 3. Compute corner response function R 4. Threshold R 5. Find local maima of response function non-maimum suppression
44 Harris - invariance to transformations Geometric transformations translation rotation similitude rotation + scale change affine valide for local planar objects Photometric transformations Affine intensit changes a + b
45 Harris Detector: nvariance Properties Rotation Ellipse rotates but its shape i.e. eigenvalues remains the same Corner response R is invariant to image rotation
46 Harris Detector: nvariance Properties Affine intensit change Onl derivatives are used => invariance to intensit shift + b ntensit scale: a R threshold R image coordinate image coordinate Partiall invariant to affine intensit change dependent on tpe of threshold
47 Harris Detector: nvariance Properties Scaling Corner All points will be classified as edges Not invariant to scaling
48 Comparison of patches - SSD Comparison of the intensities in the neighborhood of two interest points 1 1 image 1 image SSD : sum of square difference N N + i + j + i + N i= N j= N 1 j Small difference values similar patches
49 Comparison of patches j i j i N N i N N j N = = + SSD : nvariance to photometric transformations? ntensit changes + b => Normalizing with the mean of each patch ntensit changes a + b m j i m j i N N i N N j N = = + => Normalizing with the mean of each patch = = N N i N N j N m j i m j i σ σ => Normalizing with the mean and standard deviation of each patch
50 Cross-correlation ZNCC = = N N i N N j N m j i m j i σ σ zero normalized SSD ZNCC: zero normalized cross correlation = = σ σ m j i m j i N N i N N j N ZNCC values between -1 and 1 1 when identical patches in practice threshold around 0.5
51 ocal descriptors Grevalue derivatives Differential invariants [Koenderink 87] SFT descriptor [owe 99]
52 Grevalue derivatives: mage gradient The gradient of an image: The gradient points in the direction of most rapid increase in intensit The gradient direction is given b how does this relate to the direction of the edge? The edge strength is given b the gradient magnitude
53 Differentiation and convolution Recall for D function f: f = lim ε 0 f + ε ε f ε We could approimate this as f f n+1 f n Convolution with the filter -1 1
54 Finite difference filters Other approimations of derivative filters eist:
55 Effects of noise Consider a single row or column of the image Plotting intensit as a function of position gives a signal Where is the edge?
56 Solution: smooth first f g f * g d d f g To find edges look for peaks in d f g d
57 Derivative theorem of convolution Differentiation is convolution and convolution is associative: d d f g = d f g d This saves us one operation: f d d g f d d g
58 ocal descriptors σ σ σ G G Grevalue derivatives Convolution with Gaussian derivatives ep 1 σ πσ σ G + = = d d G G σ σ = M * * * * σ σ σ σ G G G G v
59 ocal descriptors * G G G σ σ σ Notation for grevalue derivatives [Koenderink 87] = = M M * * * * G G G G σ σ σ σ v nvariance?
60 ocal descriptors rotation invariance nvariance to image rotation : differential invariants [Koen87] gradient magnitude K K K K aplacian
61 aplacian of Gaussian OG OG = G σ + G σ
62 SFT descriptor [owe 99] Approach 8 orientations of the gradient 44 spatial grid Dimension 18 soft-assignment to spatial bins normalization of the descriptor to norm one comparison with Euclidean distance image patch gradient 3D histogram
63 ocal descriptors - rotation invariance Estimation of the dominant orientation etract gradient orientation histogram over gradient orientation peak in this histogram 0 π Rotate patch in dominant direction
64 ocal descriptors illumination change Robustness to illumination changes in case of an affine transformation = a + b 1
65 ocal descriptors illumination change Robustness to illumination changes in case of an affine transformation = a + b 1 Normalization of derivatives with gradient magnitude + +
66 ocal descriptors illumination change Robustness to illumination changes in case of an affine transformation = a + b 1 Normalization of derivatives with gradient magnitude + + Normalization of the image patch with mean and variance
67 nvariance to scale changes Scale change between two images Scale factor s can be eliminated Support region for calculation!! n case of a convolution with Gaussian derivatives defined b ep 1 σ πσ σ G + = = d d G G σ σ σ
68 Overview ntroduction to local features Harris interest points + SSD ZNCC SFT Scale & affine invariant interest point detectors Evaluation and comparison of different detectors Region descriptors and their performance
69 Scale invariance - motivation Description regions have to be adapted to scale changes nterest points have to be repeatable for scale changes
70 Harris detector + scale changes Repeatabilit rate R ε = { a i b i dist H ai b ma a b i i i < ε}
71 Scale adaptation Scale change between two images = = s s 1 1 Scale adapted derivative calculation
72 Scale adaptation = = s s Scale change between two images σ σ s G s G n n i i n i i K K = Scale adapted derivative calculation sσ n s
73 Scale adaptation σ i where are the derivatives with Gaussian convolution ~ σ σ σ σ σ G
74 Scale adaptation σ i where are the derivatives with Gaussian convolution ~ σ σ σ σ σ G ~ σ σ σ σ σ s s s s s G s Scale adapted auto-correlation matri
75 Harris detector adaptation to scale R ε { a b dist H a b < ε} = i i i i
76 Multi-scale matching algorithm s = 1 s = 3 s = 5
77 Multi-scale matching algorithm s = 1 8 matches
78 Multi-scale matching algorithm Robust estimation of a global affine transformation s = 1 3 matches
79 Multi-scale matching algorithm s = 1 3 matches s = 3 4 matches
80 Multi-scale matching algorithm s = 1 3 matches s = 3 4 matches highest number of matches correct scale s = 5 16 matches
81 Matching results Scale change of 5.7
82 Matching results 100% correct matches 13 matches
83 Scale selection We want to find the characteristic scale of the blob b convolving it with aplacians at several scales and looking for the maimum response However aplacian response decas as scale increases: original signal radius=8 increasing σ Wh does this happen?
84 Scale normalization The response of a derivative of Gaussian filter to a perfect step edge decreases as σ increases 1 σ π
85 Scale normalization The response of a derivative of Gaussian filter to a perfect step edge decreases as σ increases To keep response the same scale-invariant must multipl Gaussian derivative b σ aplacian is the second Gaussian derivative so it must be aplacian is the second Gaussian derivative so it must be multiplied b σ
86 Effect of scale normalization Original signal Unnormalized aplacian response Scale-normalized aplacian response maimum
87 Blob detection in D aplacian of Gaussian: Circularl smmetric operator for blob detection in D g = g + g
88 Blob detection in D aplacian of Gaussian: Circularl smmetric operator for blob detection in D Scale-normalized: g g g = σ + norm
89 Scale selection The D aplacian is given b / σ + σ + e up to scale For a binar circle of radius r the aplacian achieves a maimum at σ = r / r aplacian response image r / scale σ
90 Characteristic scale We define the characteristic scale as the scale that produces peak of aplacian response characteristic scale T. indeberg Feature detection with automatic scale selection. nternational Journal of Computer Vision 30 : pp
91 Scale selection For a point compute a value gradient aplacian etc. at several scales Normalization of the values with the scale factor e.g. aplacian s + Select scale s at the maimum characteristic scale s + scale Ep. results show that the aplacian gives best results
92 Scale selection Scale invariance of the characteristic scale s norm. ap. scale
93 Scale selection Scale invariance of the characteristic scale s norm. ap. norm. ap. scale scale Relation between characteristic scales s s 1 = s
94 Scale-invariant detectors Harris-aplace Mikolajczk & Schmid 01 aplacian detector indeberg 98 Difference of Gaussian owe 99 Harris-aplace aplacian
95 Harris-aplace multi-scale Harris points selection of points at maimum of aplacian invariant points + associated regions [Mikolajczk & Schmid 01]
96 Matching results 13 / 190 detected interest points
97 Matching results 58 points are initiall matched
98 Matching results 3 points are matched after verification all correct
99 OG detector Convolve image with scalenormalized aplacian at several scales OG = s G σ + G σ Detection of maima and minima of aplacian in scale space
100 Hessian detector Hessian matri H = Determinant of Hessian matri DET = Penalizes/eliminates long structures with small derivative in a single direction
101 Efficient implementation Difference of Gaussian DOG approimates the aplacian DOG = G kσ G σ Error due to the approimation
102 DOG detector Fast computation scale space processed one octave at a time David G. owe. "Distinctive image features from scale-invariant kepoints. JCV 60.
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
More informationInstance-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
More informationInstance-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
More informationInstance-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
More informationKeypoint 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
More informationFeature 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
More informationOverview. 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
More informationFeature 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
More informationEdges 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
More informationCEE598 - 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:
More informationOverview. 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
More informationRecap: 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
More informationPerception 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
More informationCorners, 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?
More information6.869 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
More informationLecture 05 Point Feature Detection and Matching
nstitute of nformatics nstitute of Neuroinformatics Lecture 05 Point Feature Detection and Matching Davide Scaramuzza 1 Lab Eercise 3 - Toda afternoon Room ETH HG E 1.1 from 13:15 to 15:00 Wor description:
More informationLecture 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:
More informationDetectors 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:
More informationBlob 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
More informationSIFT 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
More informationImage 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/).
More informationInterest 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
More informationLecture 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
More informationCS5670: 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
More informationAdvances 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;
More informationCSE 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
More informationBlobs & 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
More informationOverview. 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
More informationINTEREST 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
More informationVlad 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
More information* 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
More informationLecture 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
More informationImage 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
More informationProperties 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
More informationFeature 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
More informationFeature 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
More informationExtract 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=
More informationSURF 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
More informationLoG 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
More informationInvariant 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
More informationScale & 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
More informationAchieving 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
More informationCS 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
More informationCS4670: 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
More informationOptical flow. Subhransu Maji. CMPSCI 670: Computer Vision. October 20, 2016
Optical flow Subhransu Maji CMPSC 670: Computer Vision October 20, 2016 Visual motion Man slides adapted from S. Seitz, R. Szeliski, M. Pollefes CMPSC 670 2 Motion and perceptual organization Sometimes,
More informationLecture 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
More informationMotion estimation. Digital Visual Effects Yung-Yu Chuang. with slides by Michael Black and P. Anandan
Motion estimation Digital Visual Effects Yung-Yu Chuang with slides b Michael Black and P. Anandan Motion estimation Parametric motion image alignment Tracking Optical flow Parametric motion direct method
More informationSIFT: 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
More informationLocal 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
More informationCorner 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
More informationLecture 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
More informationSIFT: 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
More informationMaximally 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.
More informationWavelet-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
More informationHarris 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
More informationAdvanced 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
More informationImage 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
More informationScale & 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
More informationEdge Detection. Image Processing - Computer Vision
Image Processing - Lesson 10 Edge Detection Image Processing - Computer Vision Low Level Edge detection masks Gradient Detectors Compass Detectors Second Derivative - Laplace detectors Edge Linking Image
More informationScale-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
More informationLecture 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
More informationFace 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
More informationEdge 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
More informationGlobal 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
More informationThe 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
More informationLecture 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
More informationOrientation 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
More informationMultiscale Autoconvolution Histograms for Affine Invariant Pattern Recognition
Multiscale Autoconvolution Histograms for Affine Invariant Pattern Recognition Esa Rahtu Mikko Salo Janne Heikkilä Department of Electrical and Information Engineering P.O. Box 4500, 90014 University of
More informationMachine 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
More informationarxiv: 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]
More informationMachine 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
More informationCamera calibration. Outline. Pinhole camera. Camera projection models. Nonlinear least square methods A camera calibration tool
Outline Camera calibration Camera projection models Camera calibration i Nonlinear least square methods A camera calibration tool Applications Digital Visual Effects Yung-Yu Chuang with slides b Richard
More informationTaking derivative by convolution
Taking derivative by convolution Partial derivatives with convolution For 2D function f(x,y), the partial derivative is: For discrete data, we can approximate using finite differences: To implement above
More informationCovariance Tracking Algorithm on Bilateral Filtering under Lie Group Structure Yinghong Xie 1,2,a Chengdong Wu 1,b
Applied Mechanics and Materials Online: 014-0-06 ISSN: 166-748, Vols. 519-50, pp 684-688 doi:10.408/www.scientific.net/amm.519-50.684 014 Trans Tech Publications, Switzerland Covariance Tracking Algorithm
More informationEE 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,
More informationSIFT, 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.
More informationInterest Point Detection. Lecture-4
nterest Point Detection Lectre-4 Contents Harris Corner Detector Sm o Sqares Dierences (SSD Corrleation Talor Series Eigen Vectors and Eigen Vales nariance and co-ariance What is an interest point Epressie
More informationINF Introduction to classifiction Anne Solberg Based on Chapter 2 ( ) in Duda and Hart: Pattern Classification
INF 4300 151014 Introduction to classifiction Anne Solberg anne@ifiuiono Based on Chapter 1-6 in Duda and Hart: Pattern Classification 151014 INF 4300 1 Introduction to classification One of the most challenging
More informationAn Improved Harris-Affine Invariant Interest Point Detector
An Improved Harris-Affine Invariant Interest Point Detector KARINA PEREZ-DANIE, ENRIQUE ESCAMIA, MARIKO NAKANO, HECTOR PEREZ-MEANA Mechanical and Electrical Engineering School Instituto Politecnico Nacional
More informationFeature 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
More informationFeature 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
More informationComputer Vision I. Announcements
Announcements Motion II No class Wednesda (Happ Thanksgiving) HW4 will be due Frida 1/8 Comment on Non-maximal supression CSE5A Lecture 15 Shi-Tomasi Corner Detector Filter image with a Gaussian. Compute
More informationImage Filtering. Slides, adapted from. Steve Seitz and Rick Szeliski, U.Washington
Image Filtering Slides, adapted from Steve Seitz and Rick Szeliski, U.Washington The power of blur All is Vanity by Charles Allen Gillbert (1873-1929) Harmon LD & JuleszB (1973) The recognition of faces.
More informationDistinguish 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
More informationEdge Detection PSY 5018H: Math Models Hum Behavior, Prof. Paul Schrater, Spring 2005
Edge Detection PSY 5018H: Math Models Hum Behavior, Prof. Paul Schrater, Spring 2005 Gradients and edges Points of sharp change in an image are interesting: change in reflectance change in object change
More informationGiven 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
More informationObject Recognition Using Local Characterisation and Zernike Moments
Object Recognition Using Local Characterisation and Zernike Moments A. Choksuriwong, H. Laurent, C. Rosenberger, and C. Maaoui Laboratoire Vision et Robotique - UPRES EA 2078, ENSI de Bourges - Université
More informationFiltering and Edge Detection
Filtering and Edge Detection Local Neighborhoods Hard to tell anything from a single pixel Example: you see a reddish pixel. Is this the object s color? Illumination? Noise? The next step in order of complexity
More informationDeformation and Viewpoint Invariant Color Histograms
1 Deformation and Viewpoint Invariant Histograms Justin Domke and Yiannis Aloimonos Computer Vision Laboratory, Department of Computer Science University of Maryland College Park, MD 274, USA domke@cs.umd.edu,
More informationBoosting color saliency in image feature detection
Boosting color saliency in image feature detection Joost Van de Weijer, Theo Gevers, Andrew Bagdanov To cite this version: Joost Van de Weijer, Theo Gevers, Andrew Bagdanov. Boosting color saliency in
More informationCITS 4402 Computer Vision
CITS 4402 Computer Vision A/Prof Ajmal Mian Adj/A/Prof Mehdi Ravanbakhsh Lecture 06 Object Recognition Objectives To understand the concept of image based object recognition To learn how to match images
More informationEdge Detection. Computer Vision P. Schrater Spring 2003
Edge Detection Computer Vision P. Schrater Spring 2003 Simplest Model: (Canny) Edge(x) = a U(x) + n(x) U(x)? x=0 Convolve image with U and find points with high magnitude. Choose value by comparing with
More informationAffine 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
More informationEECS150 - 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)
More informationGaussian derivatives
Gaussian derivatives UCU Winter School 2017 James Pritts Czech Tecnical University January 16, 2017 1 Images taken from Noah Snavely s and Robert Collins s course notes Definition An image (grayscale)
More informationFace Detection and Recognition
Face Detection and Recognition Face Recognition Problem Reading: Chapter 18.10 and, optionally, Face Recognition using Eigenfaces by M. Turk and A. Pentland Queryimage face query database Face Verification
More informationLaplacian Filters. Sobel Filters. Laplacian Filters. Laplacian Filters. Laplacian Filters. Laplacian Filters
Sobel Filters Note that smoothing the image before applying a Sobel filter typically gives better results. Even thresholding the Sobel filtered image cannot usually create precise, i.e., -pixel wide, edges.
More informationINF Anne Solberg One of the most challenging topics in image analysis is recognizing a specific object in an image.
INF 4300 700 Introduction to classifiction Anne Solberg anne@ifiuiono Based on Chapter -6 6inDuda and Hart: attern Classification 303 INF 4300 Introduction to classification One of the most challenging
More informationA 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
More information