Computer Vision Lecture 13

Size: px
Start display at page:

Download "Computer Vision Lecture 13"

Transcription

1 N pixel Coure Outline Coputer Viion Lecture 3 Local Feature II Iage Proceing Baic Segentation & Grouping Object Recognition Object Categorization I Sliding Window baed Object Detection Local Feature & Matching Local Feature Detection and Decription Recognition with Local Feature Batian Leibe RWTH Aachen leibe@viion.rwth-aachen.de Object Categorization II Part baed Approache 3D Recontruction Motion and Tracking 3 Recap: Local Feature Matching Outline A N pixel A 2 A 3 A Siilarity eaure d(, ) T A B B. Find a et o ditinctive keypoint 2. Deine a region around each keypoint 3. Extract and noralize the region content 4. Copute a local decriptor ro the noralized region 5. Match local decriptor 4 Recap: Requireent or Local Feature Proble : Detect the ae point independently in both iage Proble 2: For each point correctly recognize the correponding one We need a repeatable detector! We need a reliable and ditinctive decriptor! Slide credit: Darya Frolova, Deni Siakov? 5 Recap: Harri Detector [Harri88] Recap: Harri Detector Repone [Harri88] Copute econd oent atrix (autocorrelation atrix) 2 I x ( D) I xi y ( ) D M( I, D) g( I ) 2 I xi y ( D) I y ( D). Iage derivative I x I y 2. Square o derivative I x 2 I y 2 I x I y 3. Gauian ilter g( I ) 4. Cornerne unction two trong eigenvalue 2 R det[ M(, )] [trace( M(, ] I D I D g( I ) g( I ) [ g( I I )] [ g( I ) g( I )] x y x y x y g(i x2 ) g(i y2 ) g(i x I y ) Eect: A very precie corner detector. 5. Peror non-axiu uppreion R 6 7

2 Recap: Heian Detector [Beaudet78] Recap: Heian Detector Repone [Beaudet78] Heian deterinant I Heian ( I) I xx xy I xy I yy I xx I xy I yy det( Heian( I)) I I xx yy I 2 xy Eect: Repone ainly on corner and trongly textured area. In Matlab: I. I ( I ).^ 2 xx yy xy 8 9 Topic o Thi Lecture Fro Point to Region Local Feature Extraction (cont d) Scale Invariant Region Selection Orientation noralization Aine Invariant Feature Extraction The Harri and Heian operator deine interet point. Precie localization High repeatability Local Decriptor SIFT Application In order to copare thoe point, we need to copute a decriptor over a region. How can we deine uch a region in a cale invariant anner? I.e. how can we detect cale invariant interet region? 0 Naïve Approach: Exhautive Search Naïve Approach: Exhautive Search Multi-cale procedure Copare decriptor while varying the patch ize Multi-cale procedure Copare decriptor while varying the patch ize A Siilarity eaure d ( A, B) B 2 A Siilarity eaure d ( A, B) B 3 2

3 Naïve Approach: Exhautive Search Multi-cale procedure Copare decriptor while varying the patch ize Naïve Approach: Exhautive Search Multi-cale procedure Copare decriptor while varying the patch ize A Siilarity eaure d ( A, B) B 4 A Siilarity eaure d ( A, B) B 5 Naïve Approach: Exhautive Search Autoatic Scale Selection Coparing decriptor while varying the patch ize Coputationally ineicient Ineicient but poible or atching Prohibitive or retrieval in large databae Prohibitive or recognition Solution: Deign a unction on the region, which i cale invariant (the ae or correponding region, even i they are at dierent cale) Exaple: average intenity. For correponding region (even o dierent ize) it will be the ae. For a point in one iage, we can conider it a a unction o region ize (patch width) A Siilarity eaure d( A, B ) B 6 Iage Region ize Slide credit: Kriten Grauan cale = ½ Iage 2 Region ize 7 Autoatic Scale Selection Autoatic Scale Selection Coon approach: Take a local axiu o thi unction. Obervation: region ize or which the axiu i achieved hould be invariant to iage cale. Function repone or increaing cale (cale ignature) Iportant: thi cale invariant region ize i ound in each iage independently! Iage cale = ½ Iage 2 2 = ½ Region ize 2 Slide credit: Kriten Grauan Region ize 8 ( Ii i ( x, ( Ii ( x, i 9 3

4 Autoatic Scale Selection Function repone or increaing cale (cale ignature) Autoatic Scale Selection Function repone or increaing cale (cale ignature) ( Ii i ( x, ( Ii ( x, i 20 ( Ii i ( x, ( Ii ( x, i 2 Autoatic Scale Selection Autoatic Scale Selection Function repone or increaing cale (cale ignature) Function repone or increaing cale (cale ignature) ( Ii i ( x, ( Ii ( x, i 22 ( Ii i ( x, ( Ii ( x, i 23 Autoatic Scale Selection Autoatic Scale Selection Function repone or increaing cale (cale ignature) Noralize: Recale to ixed ize ( Ii i ( x, ( Ii i ( x, )) ( Ii i ( x, ( Ii i ( x, )) 24 Slide credit: Tinne Tuytelaar 25 4

5 What I A Ueul Signature Function? Laplacian-o-Gauian = blob detector Characteritic Scale We deine the characteritic cale a the cale that produce peak o Laplacian repone Characteritic cale 26 T. Lindeberg (998). "Feature detection with autoatic cale election." International Journal o Coputer Viion 30 (2): pp Laplacian-o-Gauian (LoG) Laplacian-o-Gauian (LoG) Interet point: Local axia in cale pace o Laplacian-o- Gauian 5 4 Interet point: Local axia in cale pace o Laplacian-o- Gauian 5 4 L ( ) L ( ) xx yy 3 L ( ) L ( ) xx yy Slide adapted ro Krytian Mikolajczyk Slide adapted ro Krytian Mikolajczyk Laplacian-o-Gauian (LoG) Laplacian-o-Gauian (LoG) Interet point: Local axia in cale pace o Laplacian-o- Gauian 5 4 Interet point: Local axia in cale pace o Laplacian-o- Gauian 5 4 L ( ) L ( ) xx yy 3 L ( ) L ( ) xx yy Lit o (x, y, σ) Slide adapted ro Krytian Mikolajczyk Slide adapted ro Krytian Mikolajczyk 5

6 Reaple Blur Subtract LoG Detector: Worklow LoG Detector: Worklow LoG Detector: Worklow Dierence-o-Gauian (DoG) We can eiciently approxiate the Laplacian with a dierence o Gauian: 2 L Gxx x y Gyy x y (,, ) (,, ) (Laplacian) DoG G( x, y, k) G( x, y, ) (Dierence o Gauian) Advantage? No need to copute 2 nd derivative. Gauian are coputed anyway, e.g. in a Gauian pyraid Key point localization with DoG DoG Eicient Coputation Detect axia o dierence-o-gauian (DoG) in cale pace Coputation in Gauian cale pyraid Then reject point with low contrat (threhold) Eliinate edge repone Sapling with tep 4 =2 Candidate keypoint: lit o (x,y,σ) Original iage 2 4 Slide credit: David Lowe Slide adapted ro Krytian Mikolajczyk 37 6

7 Reult: Lowe DoG Harri-Laplace [Mikolajczyk 0]. Initialization: Multicale Harri corner detection Slide adapted ro Krytian Mikolajczyk Coputing Harri unction Detecting local axia 40 Harri-Laplace [Mikolajczyk 0]. Initialization: Multicale Harri corner detection 2. Scale election baed on Laplacian (ae procedure with Heian Heian-Laplace) Harri point Suary: Scale Invariant Detection Given: Two iage o the ae cene with a large cale dierence between the. Goal: Find the ae interet point independently in each iage. Solution: Search or axia o uitable unction in cale and in pace (over the iage). Two trategie Laplacian-o-Gauian (LoG) Dierence-o-Gauian (DoG) a a at approxiation Slide adapted ro Krytian Mikolajczyk Harri-Laplace point 4 Thee can be ued either on their own, or in cobination with ingle-cale keypoint detector (Harri, Heian). 42 Topic o Thi Lecture Rotation Invariant Decriptor Local Feature Extraction (cont d) Scale Invariant Region Selection Orientation noralization Aine Invariant Feature Extraction Local Decriptor SIFT Find local orientation Doinant direction o gradient or the iage patch Rotate patch according to thi angle Thi put the patche into a canonical orientation. Application 43, Matthew Brown 44 7

8 Orientation Noralization: Coputation Topic o Thi Lecture Copute orientation hitogra Select doinant orientation Noralize: rotate to ixed orientation [Lowe, SIFT, 999] Local Feature Extraction (cont d) Scale Invariant Region Selection Orientation noralization Aine Invariant Feature Extraction Local Decriptor SIFT Application Slide adapted ro David Lowe 0 2 p The Need or Invariance Aine Adaptation Proble: Deterine the characteritic hape o the region. Auption: hape can be decribed by local aine rae. Up to now, we had invariance to Tranlation Scale Rotation Not uicient to atch region under viewpoint change For thi, we need alo aine adaptation Slide credit: Tinne Tuytelaar 47 Solution: iterative approach Ue a circular window to copute econd oent atrix. Copute eigenvector to adapt the circle to an ellipe. Recopute econd oent atrix uing new window and iterate Slide adapted ro Svetlana Lazebnik 48 Iterative Aine Adaptation Aine Noralization/Dekewing rotate recale. Detect keypoint, e.g. ulti-cale Harri 2. Autoatically elect the cale 3. Adapt aine hape baed on econd order oent atrix 4. Reine point location K. Mikolajczyk and C. Schid, Scale and aine invariant interet point detector, 49 IJCV 60():63-86, Slide credit: Tinne Tuytelaar Step Rotate the ellipe ain axi to horizontal Scale the x axi, uch that it or a circle Slide credit: Tinne Tuytelaar 50 8

9 Aine Adaptation Exaple Aine Adaptation Exaple Scale-invariant region (blob) Aine-adapted blob 5 52 Suary: Aine-Inv. Feature Extraction Invariance v. Covariance Extract aine region Noralize region Eliinate rotational abiguity Copare decriptor Invariance: eature(tranor(iage)) = eature(iage) Covariance: eature(tranor(iage)) = tranor(eature(iage)) 53 Covariant detection invariant decription, David Lowe 54 Topic o Thi Lecture Local Decriptor Local Feature Extraction (cont d) Orientation noralization Aine Invariant Feature Extraction Local Decriptor SIFT Application Recognition with Local Feature Matching local eature Finding conitent coniguration Alignent: linear tranoration Aine etiation Hoography etiation 55 We know how to detect point Next quetion: How to decribe the or atching? Slide credit: Kriten Grauan? Point decriptor hould be:. Invariant 2. Ditinctive 56 9

10 Local Decriptor Siplet decriptor: lit o intenitie within a patch. What i thi going to be invariant to? Feature Decriptor Diadvantage o patche a decriptor: Sall hit can aect atching core a lot Solution: hitogra Slide credit: Kriten Grauan p 58 Feature Decriptor: SIFT Scale Invariant Feature Tranor Decriptor coputation: Divide patch into 4x4 ub-patche: 6 cell Copute hitogra o gradient orientation (8 reerence angle) or all pixel inide each ub-patch Reulting decriptor: 4x4x8 = 28 dienion Overview: SIFT Extraordinarily robut atching technique Can handle change in viewpoint up to ~60 deg. out-o-plane rotation Can handle igniicant change in illuination Soetie even day v. night (below) Fat and eicient can run in real tie Lot o code available David G. Lowe. "Ditinctive iage eature ro cale-invariant keypoint. IJCV 60 (2), pp. 9-0, Slide credit: Steve Seitz 60 Working with SIFT Decriptor Local Decriptor: SURF One iage yield: n 2D point giving poition o the patche [n x 2 atrix] n cale paraeter peciying the ize o each patch [n x vector] n orientation paraeter peciying the angle o the patch [n x vector] n 28-dienional decriptor: each one i a hitogra o the gradient orientation within a patch [n x 28 atrix] Fat approxiation o SIFT idea Eicient coputation by 2D box ilter & integral iage 6 tie ater than SIFT Equivalent quality or object identiication GPU ipleentation available Feature 00Hz (detector + decriptor, ig) Slide credit: Steve Seitz 6 62 [Bay, ECCV 06], [Corneli, CVGPU 08] 0

11 You Can Try It At Hoe For ot local eature detector, executable are available online: Topic o Thi Lecture Application o Local Invariant Feature Local Feature Extraction (cont d) Orientation noralization Aine Invariant Feature Extraction Local Decriptor SIFT Application Recognition with Local Feature Matching local eature Finding conitent coniguration Alignent: linear tranoration Aine etiation Hoography etiation Wide baeline tereo Motion tracking Panoraa Mobile robot navigation 3D recontruction Recognition Speciic object Texture Categorie 65 Slide credit: Kriten Grauan 66 Wide-Baeline Stereo Autoatic Moaicing 67 Iage ro T. Tuytelaar ECCV 2006 tutorial 68 [Brown & Lowe, ICCV 03]

12 Panoraa Stitching Recognition o Speciic Object, Scene Schid and Mohr 997 Sivic and Zieran, 2003 iphone verion available 69 [Brown, Szeliki, and Winder, 2005] Slide credit: Kriten Grauan Rothganger et al Lowe Recognition o Categorie Value o Local Feature Contellation odel Bag o word Advantage Critical to ind ditinctive and repeatable local region or ultiview atching. Coplexity reduction via election o ditinctive point. Decribe iage, object, part without requiring egentation; robutne to clutter & occluion. Robutne: iilar decriptor in pite o oderate view change, noie, blur, etc. Weber et al. (2000) Fergu et al. (2003) Curka et al. (2004) Dorko & Schid (2005) Sivic et al. (2005) Lazebnik et al. (2006), How can we ue local eature or uch application? Next week: atching and recognition 7 Slide adapted ro Kriten Grauan 72 Reerence and Further Reading More detail on hoography etiation can be ound in Chapter 4.7 o R. Hartley, A. Zieran Multiple View Geoetry in Coputer Viion 2nd Ed., Cabridge Univ. Pre, 2004 Detail about the DoG detector and the SIFT decriptor can be ound in D. Lowe, Ditinctive iage eature ro cale-invariant keypoint, IJCV 60(2), pp. 9-0, 2004 Try the available local eature detector and decriptor 2

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

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

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

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 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

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

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

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

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

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

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

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

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

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

Image Denoising Based on Non-Local Low-Rank Dictionary Learning

Image Denoising Based on Non-Local Low-Rank Dictionary Learning Advanced cience and Technology Letter Vol.11 (AT 16) pp.85-89 http://dx.doi.org/1.1457/atl.16. Iage Denoiing Baed on Non-Local Low-Rank Dictionary Learning Zhang Bo 1 1 Electronic and Inforation Engineering

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

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

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

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: Finding Features (part 1/2)

Lecture 6: Finding Features (part 1/2) Lecture 6: Finding Features (part 1/2) Professor Fei- Fei Li Stanford Vision Lab Lecture 6 -! 1 What we will learn today? Local invariant features MoHvaHon Requirements, invariances Keypoint localizahon

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

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

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

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

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

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

Determination of the local contrast of interference fringe patterns using continuous wavelet transform

Determination of the local contrast of interference fringe patterns using continuous wavelet transform Determination of the local contrat of interference fringe pattern uing continuou wavelet tranform Jong Kwang Hyok, Kim Chol Su Intitute of Optic, Department of Phyic, Kim Il Sung Univerity, Pyongyang,

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

A First Digit Theorem for Square-Free Integer Powers

A First Digit Theorem for Square-Free Integer Powers Pure Matheatical Science, Vol. 3, 014, no. 3, 19-139 HIKARI Ltd, www.-hikari.co http://dx.doi.org/10.1988/p.014.4615 A Firt Digit Theore or Square-Free Integer Power Werner Hürliann Feldtrae 145, CH-8004

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

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

CHAPTER 8 OBSERVER BASED REDUCED ORDER CONTROLLER DESIGN FOR LARGE SCALE LINEAR DISCRETE-TIME CONTROL SYSTEMS

CHAPTER 8 OBSERVER BASED REDUCED ORDER CONTROLLER DESIGN FOR LARGE SCALE LINEAR DISCRETE-TIME CONTROL SYSTEMS CHAPTER 8 OBSERVER BASED REDUCED ORDER CONTROLLER DESIGN FOR LARGE SCALE LINEAR DISCRETE-TIME CONTROL SYSTEMS 8.1 INTRODUCTION 8.2 REDUCED ORDER MODEL DESIGN FOR LINEAR DISCRETE-TIME CONTROL SYSTEMS 8.3

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

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

The Extended Balanced Truncation Algorithm

The Extended Balanced Truncation Algorithm International Journal of Coputing and Optiization Vol. 3, 2016, no. 1, 71-82 HIKARI Ltd, www.-hikari.co http://dx.doi.org/10.12988/ijco.2016.635 The Extended Balanced Truncation Algorith Cong Huu Nguyen

More information

A method to determine relative stroke detection efficiencies from multiplicity distributions

A method to determine relative stroke detection efficiencies from multiplicity distributions A ethod to deterine relative stroke detection eiciencies ro ultiplicity distributions Schulz W. and Cuins K. 2. Austrian Lightning Detection and Inoration Syste (ALDIS), Kahlenberger Str.2A, 90 Vienna,

More information

The state of the art and beyond

The state of the art and beyond Feature Detectors and Descriptors The state of the art and beyond Local covariant detectors and descriptors have been successful in many applications Registration Stereo vision Motion estimation Matching

More information

Ocean currents II. Wind-water interaction and drag forces Ekman transport, circular and geostrophic flow General ocean flow pattern

Ocean currents II. Wind-water interaction and drag forces Ekman transport, circular and geostrophic flow General ocean flow pattern Ocean current II Wind-water interaction and drag orce Ekan tranport, circular and geotrophic low General ocean low pattern Wind-Water urace interaction Water otion at the urace o the ocean (ixed layer)

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

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

Topic 7 Fuzzy expert systems: Fuzzy inference

Topic 7 Fuzzy expert systems: Fuzzy inference Topic 7 Fuzzy expert yte: Fuzzy inference adani fuzzy inference ugeno fuzzy inference Cae tudy uary Fuzzy inference The ot coonly ued fuzzy inference technique i the o-called adani ethod. In 975, Profeor

More information

Accelerator School Transverse Beam Dynamics-3. V. S. Pandit

Accelerator School Transverse Beam Dynamics-3. V. S. Pandit Accelerator School 8 Tranvere Bea Dnaic-3 V S Pandit Cloed or olution Equation o otion K i a or o Hill equation arge accelerator and tranport line are equipped with an dipole or delection and quadrupole

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

CS Lecture 13. More Maximum Likelihood

CS Lecture 13. More Maximum Likelihood CS 6347 Lecture 13 More Maxiu Likelihood Recap Last tie: Introduction to axiu likelihood estiation MLE for Bayesian networks Optial CPTs correspond to epirical counts Today: MLE for CRFs 2 Maxiu Likelihood

More information

_10_EE394J_2_Spring12_Inertia_Calculation.doc. Procedure for Estimating Grid Inertia H from Frequency Droop Measurements

_10_EE394J_2_Spring12_Inertia_Calculation.doc. Procedure for Estimating Grid Inertia H from Frequency Droop Measurements Procedure or Etiating Grid Inertia ro Frequency Droop Meaureent While the exion or inertia and requency droop are well known, it i prudent to rederive the here. Treating all the grid generator a one large

More information

Social Studies 201 Notes for March 18, 2005

Social Studies 201 Notes for March 18, 2005 1 Social Studie 201 Note for March 18, 2005 Etimation of a mean, mall ample ize Section 8.4, p. 501. When a reearcher ha only a mall ample ize available, the central limit theorem doe not apply to the

More information

Feature Extraction Techniques

Feature Extraction Techniques Feature Extraction Techniques Unsupervised Learning II Feature Extraction Unsupervised ethods can also be used to find features which can be useful for categorization. There are unsupervised ethods that

More information

Lecture 10 Filtering: Applied Concepts

Lecture 10 Filtering: Applied Concepts Lecture Filtering: Applied Concept In the previou two lecture, you have learned about finite-impule-repone (FIR) and infinite-impule-repone (IIR) filter. In thee lecture, we introduced the concept of filtering

More information

NAME (pinyin/italian)... MATRICULATION NUMBER... SIGNATURE

NAME (pinyin/italian)... MATRICULATION NUMBER... SIGNATURE POLITONG SHANGHAI BASIC AUTOMATIC CONTROL June Academic Year / Exam grade NAME (pinyin/italian)... MATRICULATION NUMBER... SIGNATURE Ue only thee page (including the bac) for anwer. Do not ue additional

More information

LEARNING DISCRIMINATIVE BASIS COEFFICIENTS FOR EIGENSPACE MLLR UNSUPERVISED ADAPTATION. Yajie Miao, Florian Metze, Alex Waibel

LEARNING DISCRIMINATIVE BASIS COEFFICIENTS FOR EIGENSPACE MLLR UNSUPERVISED ADAPTATION. Yajie Miao, Florian Metze, Alex Waibel LEARNING DISCRIMINATIVE BASIS COEFFICIENTS FOR EIGENSPACE MLLR UNSUPERVISED ADAPTATION Yajie Miao, Florian Metze, Alex Waibel Language Technologie Intitute, Carnegie Mellon Univerity, Pittburgh, PA, USA

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

Pattern Recognition and Machine Learning. Artificial Neural networks

Pattern Recognition and Machine Learning. Artificial Neural networks Pattern Recognition and Machine Learning Jaes L. Crowley ENSIMAG 3 - MMIS Fall Seester 2016/2017 Lessons 9 11 Jan 2017 Outline Artificial Neural networks Notation...2 Convolutional Neural Networks...3

More information

1.3.3 Statistical (or precision) uncertainty Due to transient variations, spatial variations 100%

1.3.3 Statistical (or precision) uncertainty Due to transient variations, spatial variations 100% 1.1 Why eaure, and why tudy eaureent? 1. Introductory Exaple Exaple: Meauring your weight: The eaureent i not the thing. 1.3 Practical Source o Meaureent Uncertainty Exaple: Meauring T o roo. 1.3.1 Reading

More information

Maximally Stable Local Description for Scale Selection

Maximally Stable Local Description for Scale Selection Maximally Stable Local Description for Scale Selection Gyuri Dorkó and Cordelia Schmid INRIA Rhône-Alpes, 655 Avenue de l Europe, 38334 Montbonnot, France {gyuri.dorko,cordelia.schmid}@inrialpes.fr Abstract.

More information

Conditions for equilibrium (both translational and rotational): 0 and 0

Conditions for equilibrium (both translational and rotational): 0 and 0 Leon : Equilibriu, Newton econd law, Rolling, Angular Moentu (Section 8.3- Lat tie we began dicuing rotational dynaic. We howed that the rotational inertia depend on the hape o the object and the location

More information

Control of industrial robots. Decentralized control

Control of industrial robots. Decentralized control Control of indutrial robot Decentralized control Prof Paolo Rocco (paolorocco@poliiit) Politecnico di Milano Dipartiento di Elettronica, Inforazione e Bioingegneria Introduction Once the deired otion of

More information

Block designs and statistics

Block designs and statistics Bloc designs and statistics Notes for Math 447 May 3, 2011 The ain paraeters of a bloc design are nuber of varieties v, bloc size, nuber of blocs b. A design is built on a set of v eleents. Each eleent

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

15 N 5 N. Chapter 4 Forces and Newton s Laws of Motion. The net force on an object is the vector sum of all forces acting on that object.

15 N 5 N. Chapter 4 Forces and Newton s Laws of Motion. The net force on an object is the vector sum of all forces acting on that object. Chapter 4 orce and ewton Law of Motion Goal for Chapter 4 to undertand what i force to tudy and apply ewton irt Law to tudy and apply the concept of a and acceleration a coponent of ewton Second Law to

More information

A practical approach to real-time application of speaker recognition using wavelets and linear algebra

A practical approach to real-time application of speaker recognition using wavelets and linear algebra A practical approach to real-tie application o speaker recognition using wavelets and linear algebra Duc Son Pha, Michael C. Orr, Brian Lithgow and Robert Mahony Departent o Electrical and Coputer Systes

More information

Intelligent Systems: Reasoning and Recognition. Artificial Neural Networks

Intelligent Systems: Reasoning and Recognition. Artificial Neural Networks Intelligent Systes: Reasoning and Recognition Jaes L. Crowley MOSIG M1 Winter Seester 2018 Lesson 7 1 March 2018 Outline Artificial Neural Networks Notation...2 Introduction...3 Key Equations... 3 Artificial

More information

Physics 20 Lesson 16 Friction

Physics 20 Lesson 16 Friction Phyic 0 Leon 16 riction In the previou leon we learned that a rictional orce i any orce that reit, retard or ipede the otion o an object. In thi leon we will dicu how riction reult ro the contact between

More information

Comparing Means: t-tests for Two Independent Samples

Comparing Means: t-tests for Two Independent Samples Comparing ean: t-tet for Two Independent Sample Independent-eaure Deign t-tet for Two Independent Sample Allow reearcher to evaluate the mean difference between two population uing data from two eparate

More information

PHYSICS 211 MIDTERM II 12 May 2004

PHYSICS 211 MIDTERM II 12 May 2004 PHYSIS IDTER II ay 004 Exa i cloed boo, cloed note. Ue only your forula heet. Write all wor and anwer in exa boolet. The bac of page will not be graded unle you o requet on the front of the page. Show

More information

Chapter 9: Controller design. Controller design. Controller design

Chapter 9: Controller design. Controller design. Controller design Chapter 9. Controller Deign 9.. Introduction 9.2. Eect o negative eedback on the network traner unction 9.2.. Feedback reduce the traner unction rom diturbance to the output 9.2.2. Feedback caue the traner

More information

CHAPTER 4 DESIGN OF STATE FEEDBACK CONTROLLERS AND STATE OBSERVERS USING REDUCED ORDER MODEL

CHAPTER 4 DESIGN OF STATE FEEDBACK CONTROLLERS AND STATE OBSERVERS USING REDUCED ORDER MODEL 98 CHAPTER DESIGN OF STATE FEEDBACK CONTROLLERS AND STATE OBSERVERS USING REDUCED ORDER MODEL INTRODUCTION The deign of ytem uing tate pace model for the deign i called a modern control deign and it i

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

Lecture 2 Phys 798S Spring 2016 Steven Anlage. The heart and soul of superconductivity is the Meissner Effect. This feature uniquely distinguishes

Lecture 2 Phys 798S Spring 2016 Steven Anlage. The heart and soul of superconductivity is the Meissner Effect. This feature uniquely distinguishes ecture Phy 798S Spring 6 Steven Anlage The heart and oul of uperconductivity i the Meiner Effect. Thi feature uniquely ditinguihe uperconductivity fro any other tate of atter. Here we dicu oe iple phenoenological

More information

Scale Efficiency in DEA and DEA-R with Weight Restrictions

Scale Efficiency in DEA and DEA-R with Weight Restrictions Available online at http://ijdea.rbiau.ac.ir Int. J. Data Envelopent Analyi (ISSN 2345-458X) Vol.2, No.2, Year 2014 Article ID IJDEA-00226, 5 page Reearch Article International Journal of Data Envelopent

More information

The Features For Dark Matter And Dark Flow Found.

The Features For Dark Matter And Dark Flow Found. The Feature For Dark Matter And Dark Flow Found. Author: Dan Vier, Alere, the Netherland Date: January 04 Abtract. Fly-By- and GPS-atellite reveal an earth-dark atter-halo i affecting the orbit-velocitie

More information

s s 1 s = m s 2 = 0; Δt = 1.75s; a =? mi hr

s s 1 s = m s 2 = 0; Δt = 1.75s; a =? mi hr Flipping Phyic Lecture Note: Introduction to Acceleration with Priu Brake Slaing Exaple Proble a Δv a Δv v f v i & a t f t i Acceleration: & flip the guy and ultiply! Acceleration, jut like Diplaceent

More information

AP Physics Momentum AP Wrapup

AP Physics Momentum AP Wrapup AP Phyic Moentu AP Wrapup There are two, and only two, equation that you get to play with: p Thi i the equation or oentu. J Ft p Thi i the equation or ipule. The equation heet ue, or oe reaon, the ybol

More information

EE 6882 Visual Search Engine

EE 6882 Visual Search Engine EE 6882 Visual Search Engine Prof. Shih Fu Chang, Feb. 13 th 2012 Lecture #4 Local Feature Matching Bag of Word image representation: coding and pooling (Many slides from A. Efors, W. Freeman, C. Kambhamettu,

More information

2FSK-LFM Compound Signal Parameter Estimation Based on Joint FRFT-ML Method

2FSK-LFM Compound Signal Parameter Estimation Based on Joint FRFT-ML Method International Conerence on et eaureent Coputational ethod (C 5 FS-F Copound Signal Paraeter Etiation Baed on Joint FF- ethod Zhaoyang Qiu Bin ang School o Electronic Engineering Univerity o Electronic

More information

Affine Adaptation of Local Image Features Using the Hessian Matrix

Affine Adaptation of Local Image Features Using the Hessian Matrix 29 Advanced Video and Signal Based Surveillance Affine Adaptation of Local Image Features Using the Hessian Matrix Ruan Lakemond, Clinton Fookes, Sridha Sridharan Image and Video Research Laboratory Queensland

More information

EXPERIMENTAL APPLICATION OF HIGH PRECISION K-SPACE FILTERS AND STOPPING RULES FOR FULLY AUTOMATED PNAH

EXPERIMENTAL APPLICATION OF HIGH PRECISION K-SPACE FILTERS AND STOPPING RULES FOR FULLY AUTOMATED PNAH ICSV Cairn Autralia - July, 00 EXPERIMENTAL APPLICATION OF HIGH PRECISION K-SPACE FILTERS AND STOPPING RULES FOR FULLY AUTOMATED PNAH Abtract Rick Scholte, Ine Lopez, Bert Roozen, Henk Nijeijer Departent

More information

Unit 12 Refrigeration and air standard cycles November 30, 2010

Unit 12 Refrigeration and air standard cycles November 30, 2010 Unit Rerigeration and air tandard cycle Noveber 0, 00 Unit Twelve Rerigeration and Air Standard Cycle Mechanical Engineering 70 Therodynaic Larry Caretto Noveber 0, 00 Outline Two oewhat related topic

More information

Proc. of the IEEE/OES Seventh Working Conference on Current Measurement Technology UNCERTAINTIES IN SEASONDE CURRENT VELOCITIES

Proc. of the IEEE/OES Seventh Working Conference on Current Measurement Technology UNCERTAINTIES IN SEASONDE CURRENT VELOCITIES Proc. of the IEEE/OES Seventh Working Conference on Current Measureent Technology UNCERTAINTIES IN SEASONDE CURRENT VELOCITIES Belinda Lipa Codar Ocean Sensors 15 La Sandra Way, Portola Valley, CA 98 blipa@pogo.co

More information

Conservation of Energy

Conservation of Energy Add Iportant Conervation of Energy Page: 340 Note/Cue Here NGSS Standard: HS-PS3- Conervation of Energy MA Curriculu Fraework (006):.,.,.3 AP Phyic Learning Objective: 3.E.., 3.E.., 3.E..3, 3.E..4, 4.C..,

More information

into a discrete time function. Recall that the table of Laplace/z-transforms is constructed by (i) selecting to get

into a discrete time function. Recall that the table of Laplace/z-transforms is constructed by (i) selecting to get Lecture 25 Introduction to Some Matlab c2d Code in Relation to Sampled Sytem here are many way to convert a continuou time function, { h( t) ; t [0, )} into a dicrete time function { h ( k) ; k {0,,, }}

More information

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science.

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science. Proeor William Ho Dept o Electrical Engineering &Computer Science http://inide.mine.edu/~who/ Uncertaint Uncertaint Let a that we have computed a reult (uch a poe o an object), rom image data How do we

More information

Mobile Communications TCS 455

Mobile Communications TCS 455 Mobile Counication TCS 455 Dr. Prapun Sukopong prapun@iit.tu.ac.th Lecture 24 1 Office Hour: BKD 3601-7 Tueday 14:00-16:00 Thurday 9:30-11:30 Announceent Read Chapter 9: 9.1 9.5 Section 1.2 fro [Bahai,

More information

Kernel based Object Tracking using Color Histogram Technique

Kernel based Object Tracking using Color Histogram Technique Kernel based Object Tracking using Color Histogra Technique 1 Prajna Pariita Dash, 2 Dipti patra, 3 Sudhansu Kuar Mishra, 4 Jagannath Sethi, 1,2 Dept of Electrical engineering, NIT, Rourkela, India 3 Departent

More information

The Root Locus Method

The Root Locus Method The Root Locu Method MEM 355 Performance Enhancement of Dynamical Sytem Harry G. Kwatny Department of Mechanical Engineering & Mechanic Drexel Univerity Outline The root locu method wa introduced by Evan

More information

24P 2, where W (measuring tape weight per meter) = 0.32 N m

24P 2, where W (measuring tape weight per meter) = 0.32 N m Ue of a 1W Laer to Verify the Speed of Light David M Verillion PHYS 375 North Carolina Agricultural and Technical State Univerity February 3, 2018 Abtract The lab wa et up to verify the accepted value

More information

Learning Multiplicative Interactions

Learning Multiplicative Interactions CSC2535 2011 Lecture 6a Learning Multiplicative Interaction Geoffrey Hinton Two different meaning of multiplicative If we take two denity model and multiply together their probability ditribution at each

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

Nanotechnology and high-precision optical displacement sensor design for optomechatronical systems

Nanotechnology and high-precision optical displacement sensor design for optomechatronical systems Nanotechnology and high-preciion optical diplaceent enor deign for optoechatronical yte A. Rotai* a, b, c, R. Yadipour a and K. Abbaian a, Z. D. Koozehkanani a, A. Ghanbari b, c, d and F. J. Sharifi e

More information

Nonmonotonic Networks. a. IRST, I Povo (Trento) Italy, b. Univ. of Trento, Physics Dept., I Povo (Trento) Italy

Nonmonotonic Networks. a. IRST, I Povo (Trento) Italy, b. Univ. of Trento, Physics Dept., I Povo (Trento) Italy Storage Capacity and Dynaics of Nononotonic Networks Bruno Crespi a and Ignazio Lazzizzera b a. IRST, I-38050 Povo (Trento) Italy, b. Univ. of Trento, Physics Dept., I-38050 Povo (Trento) Italy INFN Gruppo

More information

5.5. Collisions in Two Dimensions: Glancing Collisions. Components of momentum. Mini Investigation

5.5. Collisions in Two Dimensions: Glancing Collisions. Components of momentum. Mini Investigation Colliion in Two Dienion: Glancing Colliion So ar, you have read aout colliion in one dienion. In thi ection, you will exaine colliion in two dienion. In Figure, the player i lining up the hot o that the

More information

ME 375 FINAL EXAM Wednesday, May 6, 2009

ME 375 FINAL EXAM Wednesday, May 6, 2009 ME 375 FINAL EXAM Wedneday, May 6, 9 Diviion Meckl :3 / Adam :3 (circle one) Name_ Intruction () Thi i a cloed book examination, but you are allowed three ingle-ided 8.5 crib heet. A calculator i NOT allowed.

More information

EE 4443/5329. LAB 3: Control of Industrial Systems. Simulation and Hardware Control (PID Design) The Inverted Pendulum. (ECP Systems-Model: 505)

EE 4443/5329. LAB 3: Control of Industrial Systems. Simulation and Hardware Control (PID Design) The Inverted Pendulum. (ECP Systems-Model: 505) EE 4443/5329 LAB 3: Control of Indutrial Sytem Simulation and Hardware Control (PID Deign) The Inverted Pendulum (ECP Sytem-Model: 505) Compiled by: Nitin Swamy Email: nwamy@lakehore.uta.edu Email: okuljaca@lakehore.uta.edu

More information

SMALL-SIGNAL STABILITY ASSESSMENT OF THE EUROPEAN POWER SYSTEM BASED ON ADVANCED NEURAL NETWORK METHOD

SMALL-SIGNAL STABILITY ASSESSMENT OF THE EUROPEAN POWER SYSTEM BASED ON ADVANCED NEURAL NETWORK METHOD SMALL-SIGNAL STABILITY ASSESSMENT OF THE EUROPEAN POWER SYSTEM BASED ON ADVANCED NEURAL NETWORK METHOD S.P. Teeuwen, I. Erlich U. Bachmann Univerity of Duiburg, Germany Department of Electrical Power Sytem

More information

On the Use of High-Order Moment Matching to Approximate the Generalized-K Distribution by a Gamma Distribution

On the Use of High-Order Moment Matching to Approximate the Generalized-K Distribution by a Gamma Distribution On the Ue of High-Order Moent Matching to Approxiate the Generalized- Ditribution by a Gaa Ditribution Saad Al-Ahadi Departent of Syte & Coputer Engineering Carleton Univerity Ottawa Canada aahadi@ce.carleton.ca

More information

Social Studies 201 Notes for November 14, 2003

Social Studies 201 Notes for November 14, 2003 1 Social Studie 201 Note for November 14, 2003 Etimation of a mean, mall ample ize Section 8.4, p. 501. When a reearcher ha only a mall ample ize available, the central limit theorem doe not apply to the

More information

State Space: Observer Design Lecture 11

State Space: Observer Design Lecture 11 State Space: Oberver Deign Lecture Advanced Control Sytem Dr Eyad Radwan Dr Eyad Radwan/ACS/ State Space-L Controller deign relie upon acce to the tate variable for feedback through adjutable gain. Thi

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