Subspace Video Representations. CS 510 Lecture #22 April 14 th, 2014
|
|
- Suzan Morris
- 5 years ago
- Views:
Transcription
1 Subspace Video Representations CS 510 Lecture #22 April 14 th, 2014
2 Standard BoW : Video Edition Research in video analysis is still new BoW is currently the most common method for comparing videos STIPs for interest points For still images, fixed grids are now common HoF or Hof+HoG feature descriptors K-Means clustering to create codebook TF-IDF or histogram correlation to determine similarity 2
3 Video Matching : CSU Edition We (CSU) do research on video matching Lui et al F&G 08, CVPR 10, F&G 11 O Hara et al F&G 11, IVC 12, AVSS 12, CVPR 12, WACV 13 Marrinan et al CVPR 14 We also do other video-related work Motion segmentation : Mo et al ECCV 12 Video stabilization : Dutta et al WACV 14 Face video challenge : Beveridge et al BTAS 13 3
4 CSU video BoW We never use BoW to match videos Assumes temporal segmentation Short, pre-attended videos Too slow Many feature descriptors Many label look-ups Too selective (ignores data) Most pixels not part of any STIP feature Only edge/flow information contributes Complex training process Our approach is non-standard Not in OpenCV or Szeliski s text but promising 4
5 CSU s Approach to Video Analysis Goal : Describe videos in natural language (english) 1. Video è Tracklets A mini-video that tracks one moving object A bounding box for each frame Size & location of box varies across frames 2. Tracklet è Label Streams One label per frame per stream Streams: Appearance, Action, Trajectory Generate nouns, verbs, relations 3. Label Stream è Event Description In sentences (with nouns, verbs & relations) Less well developed than #1 and #2 above 5
6 Example Video Play video 6
7 Action Labeling There are many parts to this process And most need further development Today, we focus on action labeling How do we label a tracklet segment as Walking? Running? Digging? Picking up? 7
8 Action Labeling Framework Start with short training videos of actions 1.5 seconds of a person digging 1.5 seconds of a person walking 1.5 seconds of Possibly many examples per verb Now, given a new video : Divide it into tracklets For every 1.5 second window of each tracklet Measure it s similarity to training actions Return label of best fit (most similar training action) 8
9 Action Labeling as Video Matching Every window is a short, small video So is every training sample Labeling reduces to Measuring similarity between videos Selecting the most similar video If similarity score too low, no match Training samples extracted automatically The more training samples, the better How do we label them? Wigness, et al WACV 14 9
10 Measuring Video Similarity Goal: measure the similarity between two videos: Videos are small and short Videos focus on one actor Use all available information Step 1 : resample Resample test video to match height & width of training video Sliding window removes need for temporal resampling Result: two video cubes of the same size 10
11 Video as Subspace A video is a sequence of image frames Each frame is a point in image space Dimensionality : h w A video can be modeled by the image subspace spanned by its frames Note: h w >> t (# of frames) The subspace basis is computed using PCA Dimensionality = # of non-zero eigenvalues Eigenvectors define a basis for the subspace 11
12 Video as Subspace (II) Represent video as matrix X Every column is a vectorized frame Compute PCA XX T = RλR T Eigenvectors R are the subspace basis Remove eigenvectors with zero eigenvalues 12
13 Video as Subspace : Why? Why represent a video as a subspace? It contains every frame of the video It contains every linear combination of frames In effect, it interpolates between frames Motion interpolation Illumination interpolation But only linear interpolation Compact # of basis # of frames 13
14 Comparing Subspaces To compare videos, we compare their subspaces If two subspaces intersect The videos contain the same frame, or A combination of frames from video 1 equals a combination of frames from video 2 But this hardly ever happens (never) How do we compare non-intersecting subspaces? 14
15 Visualizing Subspace Comparison Imagine 2 1D subspaces in 3D i.e. two vectors in three space Call one A, the other B The vectors are normalized (basis vectors) If they are same, the subspaces intersect Otherwise, the smaller the angle between them, the more similar the subspaces So AB measures similarity 15
16 Visualizing (II) Now imagine 2 2D subspaces in 4D Each subspace is a plane In 4D, they may not intersect In fact, assume they don t Call one subspace A and the other B There exists an angle between any vector in A and any vector in B There exists a pair of vectors for which this angle is smallest Call these vectors the principal vector Call this angle the 1 st principal angle Among all vectors perpendicular to the principal vectors, there is a pair with the second smallest angle Call this the 2 nd principal angle 16
17 Visualizing (III) In other words, the 1 st principal angle is: argmin a A,b B, a =1, b =1 And if a 1, b 1 are the 1 st principal vectors, the 2 nd principal angle is: argmin a b ( ) a 2 A,b 2 B,a 1 a 2 =0,b 1 b 2 =0, a 2 =1, b 2 =1 a 2 b 2 ( ) The pattern repeats for higher dimensional subspaces 17
18 Computing Principal Angles There are in infinite number of vectors in every subspace, but We can compute the principal angles as: SVD( A T B) = RλR T Where A and B are sets of orthogonal basis vectors The principal angles are the eigenvalues The principal vectors are the eigenvectors 18
19 CSU Version #1 Compare tracklets by Using PCA to compute the subspace basis set of tracklet #1 Use PCA again to compute the subspace of tracklet #2 Use PCA to compute principal angle between the subspaces The smallest principal angle wins 19
20 Could you use this for PA3? Perhaps Substitute STIP cube for tracklet Use basis vectors as descriptor Principal angle becomes similarity measure Inverse becomes distance Cluster using pairwise distances Hint: use agglomerative clustering K-Means doesn t work well ( mean is difficult) Use in bag of words 20
Approximate Nearest Neighbors. CS 510 Lecture #24 April 18 th, 2014
Approximate Nearest Neighbors CS 510 Lecture #24 April 18 th, 2014 How is the assignment going? 2 hcp://breckon.eu/toby/demos/videovolumes/ Review: Video as Data Cube Mathematically, the cube can be viewed
More informationCSE 481C Imitation Learning in Humanoid Robots Motion capture, inverse kinematics, and dimensionality reduction
1 CSE 481C Imitation Learning in Humanoid Robots Motion capture, inverse kinematics, and dimensionality reduction Robotic Imitation of Human Actions 2 The inverse kinematics problem Joint angles Human-robot
More informationCS4670: Computer Vision
CS4670: Computer Vision Noah Snavely Lecture 6: Feature matching and alignment Szeliski: Chapter 6.1 Reading Last time: Corners and blobs Scale-space blob detector: Example Feature descriptors We know
More informationLocal Descriptors. CS 510 Lecture #21 April 6 rd 2015
Local Descriptors CS 510 Lecture #21 April 6 rd 2015 A Bit of Context, Transition David G. Lowe, "Three- dimensional object recogni5on from single two- dimensional images," Ar#ficial Intelligence, 31, 3
More informationRecognition: Face Recognition. Linda Shapiro EE/CSE 576
Recognition: Face Recognition Linda Shapiro EE/CSE 576 1 Face recognition: once you ve detected and cropped a face, try to recognize it Detection Recognition Sally 2 Face recognition: overview Typical
More informationPA2 Introduction to Tracking. Connected Components. Moving Object Detection. Pixel Grouping. After Pixel Grouping 2/19/17. Any questions?
/19/17 PA Introduction to Tracking Any questions? Yes, its due Monday. CS 510 Lecture 1 February 15, 017 Moving Object Detection Assuming a still camera Two algorithms: Mixture of Gaussians (Stauffer Grimson)
More informationDimension Reduction CS534
Dimension Reduction CS534 Why dimension reduction? High dimensionality large number of features E.g., documents represented by thousands of words, millions of bigrams Images represented by thousands of
More informationAnnouncements. Recognition I. Gradient Space (p,q) What is the reflectance map?
Announcements I HW 3 due 12 noon, tomorrow. HW 4 to be posted soon recognition Lecture plan recognition for next two lectures, then video and motion. Introduction to Computer Vision CSE 152 Lecture 17
More informationImage Processing. Image Features
Image Processing Image Features Preliminaries 2 What are Image Features? Anything. What they are used for? Some statements about image fragments (patches) recognition Search for similar patches matching
More informationLecture 8 Object Descriptors
Lecture 8 Object Descriptors Azadeh Fakhrzadeh Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University 2 Reading instructions Chapter 11.1 11.4 in G-W Azadeh Fakhrzadeh
More informationvector space retrieval many slides courtesy James Amherst
vector space retrieval many slides courtesy James Allan@umass Amherst 1 what is a retrieval model? Model is an idealization or abstraction of an actual process Mathematical models are used to study the
More informationWhat do we mean by recognition?
Announcements Recognition Project 3 due today Project 4 out today (help session + photos end-of-class) The Margaret Thatcher Illusion, by Peter Thompson Readings Szeliski, Chapter 14 1 Recognition What
More informationClustering K-means. Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, Carlos Guestrin
Clustering K-means Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, 2014 Carlos Guestrin 2005-2014 1 Clustering images Set of Images [Goldberger et al.] Carlos Guestrin 2005-2014
More informationTwo-view geometry Computer Vision Spring 2018, Lecture 10
Two-view geometry http://www.cs.cmu.edu/~16385/ 16-385 Computer Vision Spring 2018, Lecture 10 Course announcements Homework 2 is due on February 23 rd. - Any questions about the homework? - How many of
More informationMSA220 - Statistical Learning for Big Data
MSA220 - Statistical Learning for Big Data Lecture 13 Rebecka Jörnsten Mathematical Sciences University of Gothenburg and Chalmers University of Technology Clustering Explorative analysis - finding groups
More informationCSE 40171: Artificial Intelligence. Learning from Data: Unsupervised Learning
CSE 40171: Artificial Intelligence Learning from Data: Unsupervised Learning 32 Homework #6 has been released. It is due at 11:59PM on 11/7. 33 CSE Seminar: 11/1 Amy Reibman Purdue University 3:30pm DBART
More informationDeep Learning For Video Classification. Presented by Natalie Carlebach & Gil Sharon
Deep Learning For Video Classification Presented by Natalie Carlebach & Gil Sharon Overview Of Presentation Motivation Challenges of video classification Common datasets 4 different methods presented in
More informationFeature Descriptors. CS 510 Lecture #21 April 29 th, 2013
Feature Descriptors CS 510 Lecture #21 April 29 th, 2013 Programming Assignment #4 Due two weeks from today Any questions? How is it going? Where are we? We have two umbrella schemes for object recognition
More informationLocal Patch Descriptors
Local Patch Descriptors Slides courtesy of Steve Seitz and Larry Zitnick CSE 803 1 How do we describe an image patch? How do we describe an image patch? Patches with similar content should have similar
More information( ) =cov X Y = W PRINCIPAL COMPONENT ANALYSIS. Eigenvectors of the covariance matrix are the principal components
Review Lecture 14 ! PRINCIPAL COMPONENT ANALYSIS Eigenvectors of the covariance matrix are the principal components 1. =cov X Top K principal components are the eigenvectors with K largest eigenvalues
More informationHarder case. Image matching. Even harder case. Harder still? by Diva Sian. by swashford
Image matching Harder case by Diva Sian by Diva Sian by scgbt by swashford Even harder case Harder still? How the Afghan Girl was Identified by Her Iris Patterns Read the story NASA Mars Rover images Answer
More informationDimensionality Reduction, including by Feature Selection.
Dimensionality Reduction, including by Feature Selection www.cs.wisc.edu/~dpage/cs760 Goals for the lecture you should understand the following concepts filtering-based feature selection information gain
More information3D Models and Matching
3D Models and Matching representations for 3D object models particular matching techniques alignment-based systems appearance-based systems GC model of a screwdriver 1 3D Models Many different representations
More informationEVENT DETECTION AND HUMAN BEHAVIOR RECOGNITION. Ing. Lorenzo Seidenari
EVENT DETECTION AND HUMAN BEHAVIOR RECOGNITION Ing. Lorenzo Seidenari e-mail: seidenari@dsi.unifi.it What is an Event? Dictionary.com definition: something that occurs in a certain place during a particular
More informationVerification: is that a lamp? What do we mean by recognition? Recognition. Recognition
Recognition Recognition The Margaret Thatcher Illusion, by Peter Thompson The Margaret Thatcher Illusion, by Peter Thompson Readings C. Bishop, Neural Networks for Pattern Recognition, Oxford University
More informationNAME: Sample Final Exam (based on previous CSE 455 exams by Profs. Seitz and Shapiro)
Computer Vision Prof. Rajesh Rao TA: Jiun-Hung Chen CSE 455 Winter 2009 Sample Final Exam (based on previous CSE 455 exams by Profs. Seitz and Shapiro) Write your name at the top of every page. Directions
More informationFeature Detection and Matching
and Matching CS4243 Computer Vision and Pattern Recognition Leow Wee Kheng Department of Computer Science School of Computing National University of Singapore Leow Wee Kheng (CS4243) Camera Models 1 /
More informationUsing Spin Images for Efficient Object Recognition in Cluttered 3D Scenes
Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes TDT 03 - Advanced Topics in Computer Graphics Presentation by Ruben H. Fagerli Paper to be summarized Using Spin Images for Efficient
More informationComputer Vision. Exercise Session 10 Image Categorization
Computer Vision Exercise Session 10 Image Categorization Object Categorization Task Description Given a small number of training images of a category, recognize a-priori unknown instances of that category
More informationFinding 2D Shapes and the Hough Transform
CS 4495 Computer Vision Finding 2D Shapes and the Aaron Bobick School of Interactive Computing Administrivia Today: Modeling Lines and Finding them CS4495: Problem set 1 is still posted. Please read the
More informationXPM 2D Transformations Week 2, Lecture 3
CS 430/585 Computer Graphics I XPM 2D Transformations Week 2, Lecture 3 David Breen, William Regli and Maxim Peysakhov Geometric and Intelligent Computing Laboratory Department of Computer Science Drexel
More informationFinal Exam Study Guide
Final Exam Study Guide Exam Window: 28th April, 12:00am EST to 30th April, 11:59pm EST Description As indicated in class the goal of the exam is to encourage you to review the material from the course.
More informationXPM 2D Transformations Week 2, Lecture 3
CS 430/585 Computer Graphics I XPM 2D Transformations Week 2, Lecture 3 David Breen, William Regli and Maxim Peysakhov Geometric and Intelligent Computing Laboratory Department of Computer Science Drexel
More informationLarge scale object/scene recognition
Large scale object/scene recognition Image dataset: > 1 million images query Image search system ranked image list Each image described by approximately 2000 descriptors 2 10 9 descriptors to index! Database
More informationEECS150 - Digital Design Lecture 14 FIFO 2 and SIFT. Recap and Outline
EECS150 - Digital Design Lecture 14 FIFO 2 and SIFT Oct. 15, 2013 Prof. Ronald Fearing Electrical Engineering and Computer Sciences University of California, Berkeley (slides courtesy of Prof. John Wawrzynek)
More informationSingle-view 3D Reconstruction
Single-view 3D Reconstruction 10/12/17 Computational Photography Derek Hoiem, University of Illinois Some slides from Alyosha Efros, Steve Seitz Notes about Project 4 (Image-based Lighting) You can work
More informationRevision Problems for Examination 2 in Algebra 1
Centre for Mathematical Sciences Mathematics, Faculty of Science Revision Problems for Examination in Algebra. Let l be the line that passes through the point (5, 4, 4) and is at right angles to the plane
More informationGeometric camera models and calibration
Geometric camera models and calibration http://graphics.cs.cmu.edu/courses/15-463 15-463, 15-663, 15-862 Computational Photography Fall 2018, Lecture 13 Course announcements Homework 3 is out. - Due October
More informationCS6670: Computer Vision
CS6670: Computer Vision Noah Snavely Lecture 7: Image Alignment and Panoramas What s inside your fridge? http://www.cs.washington.edu/education/courses/cse590ss/01wi/ Projection matrix intrinsics projection
More informationColumn and row space of a matrix
Column and row space of a matrix Recall that we can consider matrices as concatenation of rows or columns. c c 2 c 3 A = r r 2 r 3 a a 2 a 3 a 2 a 22 a 23 a 3 a 32 a 33 The space spanned by columns of
More informationNeural Networks for Machine Learning. Lecture 15a From Principal Components Analysis to Autoencoders
Neural Networks for Machine Learning Lecture 15a From Principal Components Analysis to Autoencoders Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed Principal Components
More informationModelling and Visualization of High Dimensional Data. Sample Examination Paper
Duration not specified UNIVERSITY OF MANCHESTER SCHOOL OF COMPUTER SCIENCE Modelling and Visualization of High Dimensional Data Sample Examination Paper Examination date not specified Time: Examination
More informationSUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS
SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS Cognitive Robotics Original: David G. Lowe, 004 Summary: Coen van Leeuwen, s1460919 Abstract: This article presents a method to extract
More informationThe SIFT (Scale Invariant Feature
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor developed by David Lowe University of British Columbia Initial paper ICCV 1999 Newer journal paper IJCV 2004 Review: Matt Brown s Canonical
More informationFeature Tracking and Optical Flow
Feature Tracking and Optical Flow Prof. D. Stricker Doz. G. Bleser Many slides adapted from James Hays, Derek Hoeim, Lana Lazebnik, Silvio Saverse, who 1 in turn adapted slides from Steve Seitz, Rick Szeliski,
More informationCS6670: Computer Vision
CS6670: Computer Vision Noah Snavely Lecture 16: Bag-of-words models Object Bag of words Announcements Project 3: Eigenfaces due Wednesday, November 11 at 11:59pm solo project Final project presentations:
More informationLocal Image Features
Local Image Features Computer Vision CS 143, Brown Read Szeliski 4.1 James Hays Acknowledgment: Many slides from Derek Hoiem and Grauman&Leibe 2008 AAAI Tutorial This section: correspondence and alignment
More informationNeural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing
Neural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing feature 3 PC 3 Beate Sick Many slides are taken form Hinton s great lecture on NN: https://www.coursera.org/course/neuralnets
More informationLecture 3 Sections 2.2, 4.4. Mon, Aug 31, 2009
Model s Lecture 3 Sections 2.2, 4.4 World s Eye s Clip s s s Window s Hampden-Sydney College Mon, Aug 31, 2009 Outline Model s World s Eye s Clip s s s Window s 1 2 3 Model s World s Eye s Clip s s s Window
More informationSpectral Classification
Spectral Classification Spectral Classification Supervised versus Unsupervised Classification n Unsupervised Classes are determined by the computer. Also referred to as clustering n Supervised Classes
More informationLecture 8: Fitting. Tuesday, Sept 25
Lecture 8: Fitting Tuesday, Sept 25 Announcements, schedule Grad student extensions Due end of term Data sets, suggestions Reminder: Midterm Tuesday 10/9 Problem set 2 out Thursday, due 10/11 Outline Review
More informationSegmentation Computer Vision Spring 2018, Lecture 27
Segmentation http://www.cs.cmu.edu/~16385/ 16-385 Computer Vision Spring 218, Lecture 27 Course announcements Homework 7 is due on Sunday 6 th. - Any questions about homework 7? - How many of you have
More informationString distance for automatic image classification
String distance for automatic image classification Nguyen Hong Thinh*, Le Vu Ha*, Barat Cecile** and Ducottet Christophe** *University of Engineering and Technology, Vietnam National University of HaNoi,
More informationCSE 494: Information Retrieval, Mining and Integration on the Internet
CSE 494: Information Retrieval, Mining and Integration on the Internet Midterm. 18 th Oct 2011 (Instructor: Subbarao Kambhampati) In-class Duration: Duration of the class 1hr 15min (75min) Total points:
More informationAssignment 6: Ray Tracing
Assignment 6: Ray Tracing Programming Lab Due: Monday, April 20 (midnight) 1 Introduction Throughout this semester you have written code that manipulated shapes and cameras to prepare a scene for rendering.
More informationCSC321: Neural Networks. Lecture 13: Learning without a teacher: Autoencoders and Principal Components Analysis. Geoffrey Hinton
CSC321: Neural Networks Lecture 13: Learning without a teacher: Autoencoders and Principal Components Analysis Geoffrey Hinton Three problems with backpropagation Where does the supervision come from?
More informationLast week. Multi-Frame Structure from Motion: Multi-View Stereo. Unknown camera viewpoints
Last week Multi-Frame Structure from Motion: Multi-View Stereo Unknown camera viewpoints Last week PCA Today Recognition Today Recognition Recognition problems What is it? Object detection Who is it? Recognizing
More informationHarder case. Image matching. Even harder case. Harder still? by Diva Sian. by swashford
Image matching Harder case by Diva Sian by Diva Sian by scgbt by swashford Even harder case Harder still? How the Afghan Girl was Identified by Her Iris Patterns Read the story NASA Mars Rover images Answer
More informationImage Analysis, Classification and Change Detection in Remote Sensing
Image Analysis, Classification and Change Detection in Remote Sensing WITH ALGORITHMS FOR ENVI/IDL Morton J. Canty Taylor &. Francis Taylor & Francis Group Boca Raton London New York CRC is an imprint
More informationCS231A Midterm Review. Friday 5/6/2016
CS231A Midterm Review Friday 5/6/2016 Outline General Logistics Camera Models Non-perspective cameras Calibration Single View Metrology Epipolar Geometry Structure from Motion Active Stereo and Volumetric
More informationClustering and Dimensionality Reduction
Clustering and Dimensionality Reduction Some material on these is slides borrowed from Andrew Moore's excellent machine learning tutorials located at: Data Mining Automatically extracting meaning from
More informationFeature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking
Feature descriptors Alain Pagani Prof. Didier Stricker Computer Vision: Object and People Tracking 1 Overview Previous lectures: Feature extraction Today: Gradiant/edge Points (Kanade-Tomasi + Harris)
More informationAction recognition in videos
Action recognition in videos Cordelia Schmid INRIA Grenoble Joint work with V. Ferrari, A. Gaidon, Z. Harchaoui, A. Klaeser, A. Prest, H. Wang Action recognition - goal Short actions, i.e. drinking, sit
More informationCSE 258 Lecture 5. Web Mining and Recommender Systems. Dimensionality Reduction
CSE 258 Lecture 5 Web Mining and Recommender Systems Dimensionality Reduction This week How can we build low dimensional representations of high dimensional data? e.g. how might we (compactly!) represent
More informationCommon Core Vocabulary and Representations
Vocabulary Description Representation 2-Column Table A two-column table shows the relationship between two values. 5 Group Columns 5 group columns represent 5 more or 5 less. a ten represented as a 5-group
More informationCS201 Computer Vision Camera Geometry
CS201 Computer Vision Camera Geometry John Magee 25 November, 2014 Slides Courtesy of: Diane H. Theriault (deht@bu.edu) Question of the Day: How can we represent the relationships between cameras and the
More informationBoardworks Ltd KS3 Mathematics. S1 Lines and Angles
1 KS3 Mathematics S1 Lines and Angles 2 Contents S1 Lines and angles S1.1 Labelling lines and angles S1.2 Parallel and perpendicular lines S1.3 Calculating angles S1.4 Angles in polygons 3 Lines In Mathematics,
More informationRay tracing. Computer Graphics COMP 770 (236) Spring Instructor: Brandon Lloyd 3/19/07 1
Ray tracing Computer Graphics COMP 770 (236) Spring 2007 Instructor: Brandon Lloyd 3/19/07 1 From last time Hidden surface removal Painter s algorithm Clipping algorithms Area subdivision BSP trees Z-Buffer
More informationRecap Randomized Algorithms Comparing SLS Algorithms. Local Search. CPSC 322 CSPs 5. Textbook 4.8. Local Search CPSC 322 CSPs 5, Slide 1
Local Search CPSC 322 CSPs 5 Textbook 4.8 Local Search CPSC 322 CSPs 5, Slide 1 Lecture Overview 1 Recap 2 Randomized Algorithms 3 Comparing SLS Algorithms Local Search CPSC 322 CSPs 5, Slide 2 Stochastic
More informationTracking Computer Vision Spring 2018, Lecture 24
Tracking http://www.cs.cmu.edu/~16385/ 16-385 Computer Vision Spring 2018, Lecture 24 Course announcements Homework 6 has been posted and is due on April 20 th. - Any questions about the homework? - How
More informationCS 231A CA Session: Problem Set 4 Review. Kevin Chen May 13, 2016
CS 231A CA Session: Problem Set 4 Review Kevin Chen May 13, 2016 PS4 Outline Problem 1: Viewpoint estimation Problem 2: Segmentation Meanshift segmentation Normalized cut Problem 1: Viewpoint Estimation
More informationComputer Vision II Lecture 14
Computer Vision II Lecture 14 Articulated Tracking I 08.07.2014 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Outline of This Lecture Single-Object Tracking Bayesian
More informationHistograms of Sparse Codes for Object Detection
Histograms of Sparse Codes for Object Detection Xiaofeng Ren (Amazon), Deva Ramanan (UC Irvine) Presented by Hossein Azizpour What does the paper do? (learning) a new representation local histograms of
More informationImage Stitching. Slides from Rick Szeliski, Steve Seitz, Derek Hoiem, Ira Kemelmacher, Ali Farhadi
Image Stitching Slides from Rick Szeliski, Steve Seitz, Derek Hoiem, Ira Kemelmacher, Ali Farhadi Combine two or more overlapping images to make one larger image Add example Slide credit: Vaibhav Vaish
More informationImage matching. Announcements. Harder case. Even harder case. Project 1 Out today Help session at the end of class. by Diva Sian.
Announcements Project 1 Out today Help session at the end of class Image matching by Diva Sian by swashford Harder case Even harder case How the Afghan Girl was Identified by Her Iris Patterns Read the
More informationOptical flow and tracking
EECS 442 Computer vision Optical flow and tracking Intro Optical flow and feature tracking Lucas-Kanade algorithm Motion segmentation Segments of this lectures are courtesy of Profs S. Lazebnik S. Seitz,
More informationN-Views (1) Homographies and Projection
CS 4495 Computer Vision N-Views (1) Homographies and Projection Aaron Bobick School of Interactive Computing Administrivia PS 2: Get SDD and Normalized Correlation working for a given windows size say
More informationWikipedia - Mysid
Wikipedia - Mysid Erik Brynjolfsson, MIT Filtering Edges Corners Feature points Also called interest points, key points, etc. Often described as local features. Szeliski 4.1 Slides from Rick Szeliski,
More informationInterlude: Solving systems of Equations
Interlude: Solving systems of Equations Solving Ax = b What happens to x under Ax? The singular value decomposition Rotation matrices Singular matrices Condition number Null space Solving Ax = 0 under
More informationImage classification Computer Vision Spring 2018, Lecture 18
Image classification http://www.cs.cmu.edu/~16385/ 16-385 Computer Vision Spring 2018, Lecture 18 Course announcements Homework 5 has been posted and is due on April 6 th. - Dropbox link because course
More informationLarge-Scale Face Manifold Learning
Large-Scale Face Manifold Learning Sanjiv Kumar Google Research New York, NY * Joint work with A. Talwalkar, H. Rowley and M. Mohri 1 Face Manifold Learning 50 x 50 pixel faces R 2500 50 x 50 pixel random
More informationSHOT-BASED OBJECT RETRIEVAL FROM VIDEO WITH COMPRESSED FISHER VECTORS. Luca Bertinetto, Attilio Fiandrotti, Enrico Magli
SHOT-BASED OBJECT RETRIEVAL FROM VIDEO WITH COMPRESSED FISHER VECTORS Luca Bertinetto, Attilio Fiandrotti, Enrico Magli Dipartimento di Elettronica e Telecomunicazioni, Politecnico di Torino (Italy) ABSTRACT
More informationLarge Scale 3D Reconstruction by Structure from Motion
Large Scale 3D Reconstruction by Structure from Motion Devin Guillory Ziang Xie CS 331B 7 October 2013 Overview Rome wasn t built in a day Overview of SfM Building Rome in a Day Building Rome on a Cloudless
More informationImage Features. Work on project 1. All is Vanity, by C. Allan Gilbert,
Image Features Work on project 1 All is Vanity, by C. Allan Gilbert, 1873-1929 Feature extrac*on: Corners and blobs c Mo*va*on: Automa*c panoramas Credit: Ma9 Brown Why extract features? Mo*va*on: panorama
More informationCSE 255 Lecture 5. Data Mining and Predictive Analytics. Dimensionality Reduction
CSE 255 Lecture 5 Data Mining and Predictive Analytics Dimensionality Reduction Course outline Week 4: I ll cover homework 1, and get started on Recommender Systems Week 5: I ll cover homework 2 (at the
More informationFace detection and recognition. Detection Recognition Sally
Face detection and recognition Detection Recognition Sally Face detection & recognition Viola & Jones detector Available in open CV Face recognition Eigenfaces for face recognition Metric learning identification
More informationFeature descriptors and matching
Feature descriptors and matching Detections at multiple scales Invariance of MOPS Intensity Scale Rotation Color and Lighting Out-of-plane rotation Out-of-plane rotation Better representation than color:
More informationThree-Dimensional Viewing Hearn & Baker Chapter 7
Three-Dimensional Viewing Hearn & Baker Chapter 7 Overview 3D viewing involves some tasks that are not present in 2D viewing: Projection, Visibility checks, Lighting effects, etc. Overview First, set up
More informationLocal Feature Detectors
Local Feature Detectors Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr Slides adapted from Cordelia Schmid and David Lowe, CVPR 2003 Tutorial, Matthew Brown,
More informationDimension reduction : PCA and Clustering
Dimension reduction : PCA and Clustering By Hanne Jarmer Slides by Christopher Workman Center for Biological Sequence Analysis DTU The DNA Array Analysis Pipeline Array design Probe design Question Experimental
More informationMining of Massive Datasets Jure Leskovec, Anand Rajaraman, Jeff Ullman Stanford University Infinite data. Filtering data streams
/9/7 Note to other teachers and users of these slides: We would be delighted if you found this our material useful in giving your own lectures. Feel free to use these slides verbatim, or to modify them
More informationDigital Geometry Processing
Digital Geometry Processing Spring 2011 physical model acquired point cloud reconstructed model 2 Digital Michelangelo Project Range Scanning Systems Passive: Stereo Matching Find and match features in
More informationBiometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong)
Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong) References: [1] http://homepages.inf.ed.ac.uk/rbf/hipr2/index.htm [2] http://www.cs.wisc.edu/~dyer/cs540/notes/vision.html
More informationDense 3D Reconstruction. Christiano Gava
Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Today: dense 3D reconstruction The matching problem
More informationRecognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213)
Recognition of Animal Skin Texture Attributes in the Wild Amey Dharwadker (aap2174) Kai Zhang (kz2213) Motivation Patterns and textures are have an important role in object description and understanding
More informationCS 229 Midterm Review
CS 229 Midterm Review Course Staff Fall 2018 11/2/2018 Outline Today: SVMs Kernels Tree Ensembles EM Algorithm / Mixture Models [ Focus on building intuition, less so on solving specific problems. Ask
More informationDense 3D Reconstruction. Christiano Gava
Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Wide baseline matching (SIFT) Today: dense 3D reconstruction
More informationEFFICIENT REPRESENTATION OF LIGHTING PATTERNS FOR IMAGE-BASED RELIGHTING
EFFICIENT REPRESENTATION OF LIGHTING PATTERNS FOR IMAGE-BASED RELIGHTING Hyunjung Shim Tsuhan Chen {hjs,tsuhan}@andrew.cmu.edu Department of Electrical and Computer Engineering Carnegie Mellon University
More informationRobotics Programming Laboratory
Chair of Software Engineering Robotics Programming Laboratory Bertrand Meyer Jiwon Shin Lecture 8: Robot Perception Perception http://pascallin.ecs.soton.ac.uk/challenges/voc/databases.html#caltech car
More informationIPL at ImageCLEF 2017 Concept Detection Task
IPL at ImageCLEF 2017 Concept Detection Task Leonidas Valavanis and Spyridon Stathopoulos Information Processing Laboratory, Department of Informatics, Athens University of Economics and Business, 76 Patission
More information