Perception III: Filtering, Edges, and Point-features

Size: px
Start display at page:

Download "Perception III: Filtering, Edges, and Point-features"

Transcription

1 Perception : Filtering, Edges, and Point-features Davide Scaramuzza Universit of Zurich Margarita Chli, Paul Furgale, Marco Hutter, Roland Siegwart 1

2 Toda s outline mage filtering Smoothing Edge detection Point-feature etraction Harris corners SFT features ntroduction

3 mage filtering The word filter comes from signal processing, where filtering refers to the process of accepting or rejecting certain frequenc components Low-pass filtering: retains lowfrequenc components (smoothing) High-pass filtering: retains high-frequenc components (edge detection)

4 Smoothing - Motivation: noise reduction Common tpes of noise Salt and pepper noise: random occurrences of black and white piels mpulse noise: random occurrences of white piels Gaussian noise: variations in intensit drawn from a Gaussian normal distribution

5 Gaussian noise This image shows the noise values added to the raw intensities of an image using σ = 16 Add Gaussian independent and identicall disributed (white) noise: N(μ, σ) out = in + N(μ, σ) How can we reduce the noise?

6 Moving average Let s replace each piel with an average of all the values in its neighborhood Assumptions: Epect piels to be like their neighbors Epect noise processes to be independent from piel to piel

7 Moving average Let s replace each piel with an average of all the values in its neighborhood Moving Average in 1D

8 Weighted Moving Average Can add weights to our moving average Weights: [1, 1, 1, 1, 1] / 5

9 Weighted Moving Average Can add weights to our moving average Non-uniform weights: [1, 4, 6, 4, 1] / 16

10 Moving Average n D F(, ) G(, )

11 Moving Average in D F(, ) G(, )

12 Moving Average n D F(, ) G(, )

13 Moving Average n D F(, ) G(, )

14 Moving Average n D F(, ) G(, )

15 Moving Average n D F(, ) G(, )

16 Correlation The averaging window size is (k + 1) (k + 1): This is called cross-correlation, denoted b: Filtering an image: replace each piel with a linear combination of its neighbors. H The filter kernel or mask H[u, v] specifies the weights of the linear combination. F

17 Averaging filter What values belong in the kernel H for the moving average eample? = ? bo filter

18 Smoothing b averaging Bo filter (black = 0) original filtered

19 Gaussian filter What if we want nearest neighboring piels to have the most influence on the output? This kernel is an approimation of a Gaussian function:

20 Smoothing with a Gaussian Compare with moving average

21 Sample Matlab code >> hsize = 10; >> sigma = 5; >> h = fspecial( gaussian hsize, sigma); >> mesh(h); >> imagesc(h); >> im = imread( panda.jpg ); >> outim = imfilter(im, h); >> imshow(outim); im outim

22 Separable filters A filter is separable when it can be written as the product of two 1D vectors. This reduces the costs of convolution the image the filtered image can be obtained as a cascade of the two 1D convolution operators! Eample: constant averaging filter Eample : Gaussian filter Consider an m m image and an n n separable filter D convolution number of multiplications per piel = n 1D Correlation no. multiplications per piel = n H separable filters H

23 Boundar issues What about near the edge? the filter window falls off the edge of the image need to pad the image borders methods: zero padding (black) wrap around cop edge reflect across edge

24 Convolution Flip the filter in both dimensions (bottom to top, right to left) Then appl cross-correlation G = H F H Notation for convolution operator 180 deg turn F

25 Properties of convolution Linear & shift invariant Commutative: f h = h f Associative (f g) h = f (g h) dentit: unit impulse e = [, 0, 0, 1, 0, 0, ]. f e = f Differentiation: h f = h f

26 Edge Detection Ultimate goal of edge detection: an idealized line drawing. Edge contours in the image correspond to important scene contours.

27 Edge = intensit discontinuit in one direction Edges correspond to sharp changes of intensit How to detect an edge?

28 Edge = intensit discontinuit in one direction Edges correspond to sharp changes of intensit How to detect an edge? Change is measured b 1 st order derivative in 1D Big intensit change magnitude of derivative is large Or nd order derivative is zero.

29 1D Edge Detection Effect of Noise Consider a single row or column of the image () d d () Where is the edge? image noise cannot be ignored

30 Solution: smooth first () () G s( ) ( ) G ( ) d s( ) s( ) d Where is the edge? Edges occur at maima/minima of s()

31 Derivative Theorem of Convolution d d ) s( ) G ( ) ( ) G ( ) ( This saves us one operation: () G d ( ) G ( ) d s( ) G ( ) ( ) Edges occur at maima/minima of s()

32 Zero-crossings Locations of Maima/minima in s() are equivalent to zero-crossings in s () () G d ( ) d G ( ) : Laplacian of Gaussian operator s ( ) G ( ) ( ) Edges occur at zero-crossings of s ( )

33 D Edge Detection Find gradient of smoothed image in both directions Discard piels with (i.e. edge strength), below a certain below a certain threshold Non-maima suppression: identif local maima of detected edges G G G G G S S S

34 D Edge detection: Eample : original image (Lena image)

35 D Edge detection: Eample S G G G S : Edge strength

36 D Edge detection: Eample Thresholding S

37 D Edge detection: Eample Thinning: non-maimal suppression edge image

38 Partial derivatives of an image (, ) (, )

39 Popular 1 st -Derivative Filters Sample Matlab code >> im = imread( lion.jpg ) >> M = fspecial( sobel ); >> outim = imfilter(double(im), M); >> imagesc(outim); >> colormap gra;

40 Derivative of Gaussian filter ( g) h ( g h)

41 Derivative of Gaussian filters -direction -direction

42 D edge detection filters Laplacian of Gaussian Gaussian derivative of Gaussian is the Laplacian operator: h = h h +

43 Summar on filters Smoothing Values positive Sum to 1 constant regions same as input Amount of smoothing proportional to mask size Remove high-frequenc components; low-pass filter Derivatives Opposite signs used to get high response in regions of high contrast Sum to 0 no response in constant regions High absolute value at points of high contrast

44 Point Features This panorama was generated using AUTOSTTCH (freeware) Build our own:

45 Point Features Harris corners SFT features and more recent algorithms from the state of the art

46 Applications Point features are widel used in: Robot navigation Object recognition 3D reconstruction Visual odometr ndeing and database retrieval Google mages mage stitching: see eample

47 Applications Point features are widel used in: Robot navigation Object recognition 3D reconstruction Visual odometr ndeing and database retrieval Google mages mage stitching: see eample

48 How to build a panorama? We need to match (align) images

49 How to build a panorama? Detect feature points in both images

50 How to build a panorama? Detect feature points in both images Find corresponding pairs

51 How to build a panorama? Detect feature points in both images Find corresponding pairs Use these pairs to align images

52 Matching with Features Problem 1: Detect the same points independentl in both images, if the are in the field of view no chance to match! We need a repeatable feature detector

53 Matching with Features Problem : For each point, identif its correct correspondence in the other image(s)? We need a reliable and distinctive feature descriptor

54 Template matching Find locations in an image that are similar to a template f we look at filters as templates, we can use correlation to detect these locations Detected template Correlation map

55 Similarit measures Sum of Squared Differences (SSD) Sum of Absolute Differences (SAD) (used in optical mice) k k u k k v v u F v u H SSD ), ( ), ( k k u k k v v u F v u H SAD ), ( ), (

56 Similarit measures For slight invariance to intensit changes, the Zero-mean Normalized Cross Correlation (ZNCC) is widel used k k u k k v F k k u k k v H k k u k k v F H v u F v u H v u F v u H ZNCC ), ( ), ( ), ( ), ( 1 ), ( 1 ), ( N v u F N v u H k k u k k v F k k u k k v H

57 Correlation as an inner product Considering the filter H and the portion of the image F as vectors their correlation is: H, F H F cos H F Can ou think of a similar interpretation for the SSD? n ZNCC we consider the unit vectors of H and F, hence we measure their similarit based on the angle. Alternativel, ZNCC maimizes cosθ cos H, H F F k ukvk ukvk k k k H ( u, v) F ( u, v) k H ( u, v) F( u, v) H H k ukvk F F

58 Harris Corner Detector C.Harris and M.Stephens. A Combined Corner and Edge Detector. 1988

59 What is a distinctive feature? mage pairs with etracted patches below Notice how some patches can be localized or matched with higher accurac than others Ke propert: in the region around a corner, image gradient has two or more dominant directions Corners are repeatable and distinctive

60 dentifing Corners How do we identif corners? Shifting a window in an direction should give a large change in intensit in at least directions flat region: no intensit change edge : no change along the edge direction corner : significant change in at least directions

61 How do we implement this? Two image patches of size P one centered at and one centered at The Sum of Squared Differences between them is: Let and. Approimating with a 1 st order Talor epansion: This produces the approimation ), ( P SSD, ), ( ), ( ), ( ), ( ), ( ), ( ), ( ), ( ), ( ), ( P SSD, ) ), ( ), ( ), (

62 How do we implement this? This can be written in a matri form as P SSD, ) ), ( ), ( ), ( M SSD ), ( SSD ), (, P M

63 How do we implement this? This can be written in a matri form as P SSD, ) ), ( ), ( ), ( M SSD ), ( SSD ), ( Alternative wa to write this matri, P M

64 How do we implement this? This can be written in a matri form as P SSD, ) ), ( ), ( ), ( M SSD ), ( ] [, P M SSD ), ( Alternative was to write this matri nd moment matri

65 What does this matri reveal? First, consider an ais-aligned corner: This means dominant gradient directions align with or ais f either λ 1 or λ is close to 0, then this is not a corner: What if we have a corner that is not aligned with the image aes? M M M Corner Edge Flat region

66 General Case 0 R Since M is smmetric, it can alwas be decomposed into R M const We can visualize M as an ellipse with ais lengths determined b the eigenvalues and the two aes orientations determined b R (i.e., the eigenvectors of M) The two eigenvectors identif the directions of largest and smallest changes of SSD direction of the largest change of SSD ( ma ) -1/ ( min) -1/ direction of the smallest change of SSD

67 nterpreting the eigenvalues Classification of image points using eigenvalues of M A corner can then be identified b checking whether the minimum of the two eigenvalues of M is larger than a certain user-defined threshold R = min(, ) > threshold R is called cornerness function The corner detector using this criterion is called «Shi-Tomasi» detector Edge >> 1 Corner 1 and are large, R = min(, ) > threshold J. Shi and C. Tomasi (June 1994). "Good Features to Track,". EEE Conference on Computer Vision and Pattern Recognition SSD increases in all directions 1 and are small; SSD is almost constant in all directions Flat region Edge 1 >> 1

68 nterpreting the eigenvalues Computation of λ 1 and λ is epensive Harris & Stephens suggested using a different cornerness function: R 1 k( 1 ) det( M) k trace ( M) k is constant in the range (0.04 to 0.15) Edge >> 1 Corner 1 and are large, R = min(, ) > threshold 1 and are small; SSD is almost constant in all directions SSD increases in all directions Flat Edge region 1 >> 1

69 Harris Detector: Workflow

70 Harris Detector: Workflow Compute corner response C

71 Harris Detector: Workflow Find points with large corner response: C > threshold

72 Harris Detector: Workflow Take onl the points of local maima of thresholded C

73 Harris Detector: Workflow

74 Harris detector: properties Repeatabilit: How does the Harris detector behave to common image transformations? Will we be able to re-detect the same image patches (Harris corners) when the image ehibits changes in Rotation, View-point, Zoom, llumination? dentif properties of detector & adapt accordingl

75 Harris Detector: Some Properties Rotation invariance mage 1 mage Ellipse rotates but its shape (i.e. eigenvalues) remains the same Corner response C is invariant to image rotation

76 Harris Detector: Some Properties But: non-invariant to image scale! mage 1 mage All points will be classified as edges Corner!

77 Harris Detector: Some Properties Qualit of Harris detector for different scale changes Repeatabilit= # correspondences detected # correspondences present Scaling the image b ~0% of correspondences get detected

78 Summar on Harris properties Harris detector: probabl the most widel used and known corner detector The detection is invariant to Rotation Linear intensit changes note: to make the matching invariant to these we need a suitable descriptor and matching criterion (e.g. SSD on patches is not rotation- or affine- invariant) The detection is NOT invariant to Scale changes Geometric affine changes: an image transformation which distorts the neighborhood of the corner, can distort its cornerness response

79 Scale nvariant Detection Consider regions (e.g. discs) of different sizes around a point Aim: corresponding regions look the same in image space, when the appropriate scale-change is applied Choose corresponding regions (discs) independentl in each image

80 Scale nvariant Detection Approach: design a function to appl on the region (disc), which is scale invariant (i.e. remains constant for corresponding regions, even if the are at different scales) eample: average image intensit over corresponding regions (at different scales) should remain constant Average intensit value enclosed in each disc, as a function of the disc-radius: mage 1 scale = 1/ mage region size region size

81 Scale nvariant Detection dentif the local maimum in each response these occur at corresponding region sizes The corresponding scale-invariant region size is found in each image independentl! mage 1 scale = 1/ mage region size s 1 s region size

82 Scale nvariant Detection A good function for scale detection has one clear, sharp peak bad bad Good! region size region size region size Sharp, local intensit changes in an image, are good regions to monitor for identifing relative scale in usual images. look for blobs or corners

83 Scale nvariant Detection Functions for determining scale: convolve image with kernel to identif sharp intensit discontinuities f Kernel mage Laplacian of Gaussian kernel: G(, LoG G(, ) ) ) Approimation: Difference of Gaussians (DoG) kernel SFT detector [Lowe et.al., JCV04] DoG Gk (, ) G (, ) G(, Note: These kernels are invariant to scale and rotation

84 LoG for Scale invariant detection Response of LoG for corresponding regions Harris-Laplacian multi-scale detector

85 Scale nvariant Detectors Eperimental evaluation of detectors w.r.t. scale change Repeatabilit= # correspondences detected # correspondences present

86 SFT features SFT: Scale nvariant Feature Transform an approach for detecting and describing regions of interest in an image (developed b D. Lowe in 004) SFT features are reasonabl invariant to changes in: rotation, scaling, small changes in viewpoint, illumination Ver powerful in capturing + describing distinctive structure, but also computationall demanding Main SFT stages: 1. Etract kepoints + scale. Assign kepoint orientation 3. Generate kepoint descriptor

87 Subsample SFT detector (kepoint location + scale) 1. Scale-space pramid: subsample and blur original image. Difference of Gaussians (DoG) pramid: subtract successive smoothed images Blur 3. Kepoints: local etrema in the DoG pramid DoG:

88 SFT: assign kepoint orientation Define orientation of kepoint to achieve rotation invariance Sample intensities around the kepoint Compute a histogram of orientations of intensit gradients Peaks in histogram: dominant orientations Kepoint orientation = histogram peak f there are multiple candidate peaks, construct a different kepoint for each such orientation 0

89 SFT descriptor Descriptor : identit card of kepoint Simplest descriptor: matri of intensit values around a kepoint (image patch) deall, a descriptor should be highl distinctive tolerant/invariant to common image transformations SFT descriptor: 18-element vector Describe all gradient orientations relative to the kepoint orientation Divide kepoint neighborhood in 4 4 regions & compute orientation histograms along 8 directions SFT descriptor: concatenation of all (=18) values Descriptor Matching: L -distance between these descriptor vectors

90 SFT kepoints Final SFT kepoints with detected orientation & scale

91 Feature stabilit to view point change

92 SFT for Planar recognition Planar surfaces can be reliabl recognized at a rotation of 60 awa from the camera Onl 3 points are needed for recognition But objects need to have enough teture Recognition under occlusion

93 Code and Demos SFT feature detector Demo: for Matlab, Win, and Linu (freeware) Make our own panorama with AUTOSTTCH (freeware):

94 More recent features from SOTA suitable for Robotics applications

95 FAST detector [Rosten et al., PAM 010] FAST: Features from Accelerated Segment Test Studies intensit of piels on circle around candidate piel C C is a FAST corner if a set of N contiguous piels on circle are: all brighter than intensit_of(c)+theshold, or all darker than intensit_of(c)+theshold C Tpical FAST mask: test for 1 contiguous piels in a 16-piel circle Ver fast detector - in the order of 100 Mega-piel/second Based on slide b S. Leutenegger

96 BREF descriptor [Calonder et. al, ECCV 010] Binar Robust ndependent Elementar Features Goal: high speed (in description and matching) Binar descriptor formation: Smooth image for each detected kepoint (e.g. FAST), sample all intensit pairs ( 1, ) (tpicall 56 pairs) according to pattern around the kepoint for each pair p if 1 < then set bit p of descriptor to 1 else set bit p of descriptor to 0 Not scale/rotation invariant (etensions eist ) Allows ver fast Hamming Distance matching: count the number of bits that are different in the descriptors matched Pattern for intensit pair samples generated randoml Based on slide b S. Leutenegger

97 BRSK descriptor Detector based on FAST Binar descriptor, formed b pairwise intensit comparisons (like BREF) Pattern defines intensit comparisons in the kepoint neighborhood Red circles: size of the smoothing kernel applied Blue circles: smoothed piel value used Compare short- and long-distance pairs for orientation assignment and descriptor formation Detection and descriptor speed: 10 times faster than SURF (and even faster than SFT) Slower than BREF, but scale- and rotation- invariant BRSK sampling pattern Based on slide b S. Leutenegger

98 BRSK in action Open-source code for FAST, BREF, BRSK and man more, available at the OpenCV librar

Lecture 05 Point Feature Detection and Matching

Lecture 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 information

Keypoint extraction: Corners Harris Corners Pkwy, Charlotte, NC

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

More information

Instance-level recognition: Local invariant features. Cordelia Schmid INRIA, Grenoble

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 information

Instance-level l recognition. Cordelia Schmid INRIA

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

More information

CEE598 - Visual Sensing for Civil Infrastructure Eng. & Mgmt.

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:

More information

Vlad Estivill-Castro (2016) Robots for People --- A project for intelligent integrated systems

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

More information

Instance-level recognition: Local invariant features. Cordelia Schmid INRIA, Grenoble

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 information

Lecture 04 Image Filtering

Lecture 04 Image Filtering Institute of Informatics Institute of Neuroinformatics Lecture 04 Image Filtering Davide Scaramuzza 1 Lab Exercise 2 - Today afternoon Room ETH HG E 1.1 from 13:15 to 15:00 Work description: your first

More information

6.869 Advances in Computer Vision. Prof. Bill Freeman March 1, 2005

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

More information

Instance-level recognition: Local invariant features. Cordelia Schmid INRIA, Grenoble

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

More information

Instance-level l recognition. Cordelia Schmid & Josef Sivic INRIA

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

More information

Edges and Scale. Image Features. Detecting edges. Origin of Edges. Solution: smooth first. Effects of noise

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

More information

Feature extraction: Corners and blobs

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

More information

Feature extraction: Corners and blobs

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

More information

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 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 information

Lecture 8: Interest Point Detection. Saad J Bedros

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:

More information

Lecture 8: Interest Point Detection. Saad J Bedros

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

More information

Recap: edge detection. Source: D. Lowe, L. Fei-Fei

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

More information

Advances in Computer Vision. Prof. Bill Freeman. Image and shape descriptors. Readings: Mikolajczyk and Schmid; Belongie et al.

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;

More information

Computer Vision Lecture 3

Computer Vision Lecture 3 Computer Vision Lecture 3 Linear Filters 03.11.2015 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Demo Haribo Classification Code available on the class website...

More information

INTEREST POINTS AT DIFFERENT SCALES

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

More information

Motion 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 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 information

Optical flow. Subhransu Maji. CMPSCI 670: Computer Vision. October 20, 2016

Optical 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 information

Detectors part II Descriptors

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:

More information

Image Analysis. Feature extraction: corners and blobs

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/).

More information

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 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 information

Corner detection: the basic idea

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

More information

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 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 information

Lecture Outline. Basics of Spatial Filtering Smoothing Spatial Filters. Sharpening Spatial Filters

Lecture Outline. Basics of Spatial Filtering Smoothing Spatial Filters. Sharpening Spatial Filters 1 Lecture Outline Basics o Spatial Filtering Smoothing Spatial Filters Averaging ilters Order-Statistics ilters Sharpening Spatial Filters Laplacian ilters High-boost ilters Gradient Masks Combining Spatial

More information

Lecture 12. Local Feature Detection. Matching with Invariant Features. Why extract features? Why extract features? Why extract features?

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

More information

* h + = Lec 05: Interesting Points Detection. Image Analysis & Retrieval. Outline. Image Filtering. Recap of Lec 04 Image Filtering Edge Features

* 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 information

CS5670: Computer Vision

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

More information

CS4670: Computer Vision Kavita Bala. Lecture 7: Harris Corner Detec=on

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

More information

Computer Vision & Digital Image Processing

Computer Vision & Digital Image Processing Computer Vision & Digital Image Processing Image Segmentation Dr. D. J. Jackson Lecture 6- Image segmentation Segmentation divides an image into its constituent parts or objects Level of subdivision depends

More information

Edge Detection. Image Processing - Computer Vision

Edge 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 information

CSE 473/573 Computer Vision and Image Processing (CVIP)

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

More information

SURF Features. Jacky Baltes Dept. of Computer Science University of Manitoba WWW:

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

More information

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. 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 information

Invariant local features. Invariant Local Features. Classes of transformations. (Good) invariant local features. Case study: panorama stitching

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

More information

Blob Detection CSC 767

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

More information

LoG Blob Finding and Scale. Scale Selection. Blobs (and scale selection) Achieving scale covariance. Blob detection in 2D. Blob detection in 2D

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

More information

Feature detectors and descriptors. Fei-Fei Li

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

More information

Feature detectors and descriptors. Fei-Fei Li

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

More information

Blobs & Scale Invariance

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

More information

Achieving scale covariance

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

More information

Extract useful building blocks: blobs. the same image like for the corners

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=

More information

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 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 information

Image Processing 1 (IP1) Bildverarbeitung 1

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

More information

Advanced Features. Advanced Features: Topics. Jana Kosecka. Slides from: S. Thurn, D. Lowe, Forsyth and Ponce. Advanced features and feature matching

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

More information

Properties of detectors Edge detectors Harris DoG Properties of descriptors SIFT HOG Shape context

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

More information

Local Features (contd.)

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

More information

SIFT: Scale Invariant Feature Transform

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

More information

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 (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 information

Harris Corner Detector

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

More information

Image matching. by Diva Sian. by swashford

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

More information

Outline. Convolution. Filtering

Outline. Convolution. Filtering Filtering Outline Convolution Filtering Logistics HW1 HW2 - out tomorrow Recall: what is a digital (grayscale) image? Matrix of integer values Images as height fields Let s think of image as zero-padded

More information

Machine vision, spring 2018 Summary 4

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

More information

Machine vision. Summary # 4. The mask for Laplacian is given

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

More information

Filtering and Edge Detection

Filtering 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 information

INF Introduction to classifiction Anne Solberg

INF Introduction to classifiction Anne Solberg INF 4300 8.09.17 Introduction to classifiction Anne Solberg anne@ifi.uio.no Introduction to classification Based on handout from Pattern Recognition b Theodoridis, available after the lecture INF 4300

More information

Roadmap. Introduction to image analysis (computer vision) Theory of edge detection. Applications

Roadmap. Introduction to image analysis (computer vision) Theory of edge detection. Applications Edge Detection Roadmap Introduction to image analysis (computer vision) Its connection with psychology and neuroscience Why is image analysis difficult? Theory of edge detection Gradient operator Advanced

More information

Templates, Image Pyramids, and Filter Banks

Templates, Image Pyramids, and Filter Banks Templates, Image Pyramids, and Filter Banks 09/9/ Computer Vision James Hays, Brown Slides: Hoiem and others Review. Match the spatial domain image to the Fourier magnitude image 2 3 4 5 B A C D E Slide:

More information

Edge Detection. Introduction to Computer Vision. Useful Mathematics Funcs. The bad news

Edge Detection. Introduction to Computer Vision. Useful Mathematics Funcs. The bad news Edge Detection Introduction to Computer Vision CS / ECE 8B Thursday, April, 004 Edge detection (HO #5) Edge detection is a local area operator that seeks to find significant, meaningful changes in image

More information

INF Introduction to classifiction Anne Solberg Based on Chapter 2 ( ) in Duda and Hart: Pattern Classification

INF 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 information

Taking derivative by convolution

Taking 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 information

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. 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 information

Lecture 7: Finding Features (part 2/2)

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

More information

Edge 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 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 information

CITS 4402 Computer Vision

CITS 4402 Computer Vision CITS 4402 Computer Vision Prof Ajmal Mian Adj/A/Prof Mehdi Ravanbakhsh, CEO at Mapizy (www.mapizy.com) and InFarm (www.infarm.io) Lecture 04 Greyscale Image Analysis Lecture 03 Summary Images as 2-D signals

More information

Computational Photography

Computational Photography Computational Photography Si Lu Spring 208 http://web.cecs.pdx.edu/~lusi/cs50/cs50_computati onal_photography.htm 04/0/208 Last Time o Digital Camera History of Camera Controlling Camera o Photography

More information

Enhancement Using Local Histogram

Enhancement Using Local Histogram Enhancement Using Local Histogram Used to enhance details over small portions o the image. Deine a square or rectangular neighborhood hose center moves rom piel to piel. Compute local histogram based on

More information

Wavelet-based Salient Points with Scale Information for Classification

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

More information

Image Filtering. Slides, adapted from. Steve Seitz and Rick Szeliski, U.Washington

Image 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 information

Scale & Affine Invariant Interest Point Detectors

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

More information

SIFT: SCALE INVARIANT FEATURE TRANSFORM BY DAVID LOWE

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

More information

Interest Point Detection. Lecture-4

Interest 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 information

INF Anne Solberg One of the most challenging topics in image analysis is recognizing a specific object in an image.

INF 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 information

Lecture 7: Finding Features (part 2/2)

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

More information

Lecture 6: Edge Detection. CAP 5415: Computer Vision Fall 2008

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

More information

Feature Extraction and Image Processing

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

More information

Laplacian Filters. Sobel Filters. Laplacian Filters. Laplacian Filters. Laplacian Filters. Laplacian Filters

Laplacian 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 information

Mathematics 309 Conic sections and their applicationsn. Chapter 2. Quadric figures. ai,j x i x j + b i x i + c =0. 1. Coordinate changes

Mathematics 309 Conic sections and their applicationsn. Chapter 2. Quadric figures. ai,j x i x j + b i x i + c =0. 1. Coordinate changes Mathematics 309 Conic sections and their applicationsn Chapter 2. Quadric figures In this chapter want to outline quickl how to decide what figure associated in 2D and 3D to quadratic equations look like.

More information

Orientation Map Based Palmprint Recognition

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

More information

Computer Vision Lecture 3

Computer Vision Lecture 3 Demo Haribo Classification Computer Vision Lecture 3 Linear Filters 23..24 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Code available on the class website...

More information

CONTINUOUS SPATIAL DATA ANALYSIS

CONTINUOUS SPATIAL DATA ANALYSIS CONTINUOUS SPATIAL DATA ANALSIS 1. Overview of Spatial Stochastic Processes The ke difference between continuous spatial data and point patterns is that there is now assumed to be a meaningful value, s

More information

TRACKING and DETECTION in COMPUTER VISION Filtering and edge detection

TRACKING and DETECTION in COMPUTER VISION Filtering and edge detection Technischen Universität München Winter Semester 0/0 TRACKING and DETECTION in COMPUTER VISION Filtering and edge detection Slobodan Ilić Overview Image formation Convolution Non-liner filtering: Median

More information

EECS150 - Digital Design Lecture 15 SIFT2 + FSM. Recap and Outline

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)

More information

Polynomial and Rational Functions

Polynomial and Rational Functions Polnomial and Rational Functions Figure -mm film, once the standard for capturing photographic images, has been made largel obsolete b digital photograph. (credit film : modification of work b Horia Varlan;

More information

Reading. 3. Image processing. Pixel movement. Image processing Y R I G Q

Reading. 3. Image processing. Pixel movement. Image processing Y R I G Q Reading Jain, Kasturi, Schunck, Machine Vision. McGraw-Hill, 1995. Sections 4.-4.4, 4.5(intro), 4.5.5, 4.5.6, 5.1-5.4. 3. Image processing 1 Image processing An image processing operation typically defines

More information

Edge Detection. Computer Vision P. Schrater Spring 2003

Edge 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 information

Lecture 3: Linear Filters

Lecture 3: Linear Filters Lecture 3: Linear Filters Professor Fei Fei Li Stanford Vision Lab 1 What we will learn today? Images as functions Linear systems (filters) Convolution and correlation Discrete Fourier Transform (DFT)

More information

Functions of Several Variables

Functions of Several Variables Chapter 1 Functions of Several Variables 1.1 Introduction A real valued function of n variables is a function f : R, where the domain is a subset of R n. So: for each ( 1,,..., n ) in, the value of f is

More information

Scale-space image processing

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

More information

Colorado School of Mines Image and Multidimensional Signal Processing

Colorado School of Mines Image and Multidimensional Signal Processing Image and Multidimensional Signal Processing Professor William Hoff Department of Electrical Engineering and Computer Science Spatial Filtering Main idea Spatial filtering Define a neighborhood of a pixel

More information

Camera calibration. Outline. Pinhole camera. Camera projection models. Nonlinear least square methods A camera calibration tool

Camera 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 information

Multimedia Databases. Previous Lecture. 4.1 Multiresolution Analysis. 4 Shape-based Features. 4.1 Multiresolution Analysis

Multimedia Databases. Previous Lecture. 4.1 Multiresolution Analysis. 4 Shape-based Features. 4.1 Multiresolution Analysis Previous Lecture Multimedia Databases Texture-Based Image Retrieval Low Level Features Tamura Measure, Random Field Model High-Level Features Fourier-Transform, Wavelets Wolf-Tilo Balke Silviu Homoceanu

More information

Lecture 3: Linear Filters

Lecture 3: Linear Filters Lecture 3: Linear Filters Professor Fei Fei Li Stanford Vision Lab 1 What we will learn today? Images as functions Linear systems (filters) Convolution and correlation Discrete Fourier Transform (DFT)

More information

Scale & Affine Invariant Interest Point Detectors

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

More information

Edge Detection. CS 650: Computer Vision

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

More information