doccs484_intro [Compatibility Mode] - Bilkent University Computer
download 
Şikayet Transkript
cs484_intro [Compatibility Mode] - Bilkent University Computer
Introduction Selim Aksoy Department of Computer Engineering Bilkent University [email protected] What is computer vision? “What does it mean, to see? The plain man's answer (and Aristotle's, too) would be, to know what is where by looking.” -- David Marr, Vision (1982) Automatic understanding of images and video Computing properties of the 3D world from visual data (measurement). Algorithms and representations to allow a machine to recognize objects, people, scenes, and activities (perception and interpretation). CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from Trevor Darrell, UC Berkeley, Alyosha Efros, Carnegie Mellon 2 Why study computer vision? As image sources multiply, so do applications Relieve humans of boring, easy tasks Enhance human abilities: human-computer interaction, visualization Perception for robotics / autonomous agents Organize and give access to visual content Goals of vision research: Give machines the ability to understand scenes. Aid understanding and modeling of human vision. Automate visual operations. Adapted from Trevor Darrell, UC Berkeley CS 484, Spring 2012 ©2012, Selim Aksoy 3 Why study computer vision? Movies, news, sports Personal photo albums Surveillance and security CS 484, Spring 2012 Medical and scientific images ©2012, Selim Aksoy 4 Related disciplines Artificial intelligence Graphics Image processing Computer vision Machine learning Cognitive science Algorithms CS 484, Spring 2012 ©2012, Selim Aksoy 5 Applications Medical image analysis Security Biometrics Surveillance Tracking Target recognition Remote sensing Robotics CS 484, Spring 2012 Industrial inspection, quality control Document analysis Multimedia Assisted living Human-computer interfaces … ©2012, Selim Aksoy 6 Medical image analysis http://www.clarontech.com CS 484, Spring 2012 ©2012, Selim Aksoy 7 Medical image analysis http://www.clarontech.com CS 484, Spring 2012 ©2012, Selim Aksoy 8 Medical image analysis http://www.clarontech.com CS 484, Spring 2012 ©2012, Selim Aksoy 9 Medical image analysis 3D imaging: MRI, CT CS 484, Spring 2012 Image guided surgery Grimson et al., MIT ©2012, Selim Aksoy Adapted from CSE 455, U of Washington 10 Medical image analysis Cancer detection and grading CS 484, Spring 2012 ©2012, Selim Aksoy 11 Medical image analysis Slice of lung CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from Linda Shapiro, U of Washington 12 Medical image analysis CS 484, Spring 2012 ©2012, Selim Aksoy 13 Biometrics Adapted from Anil Jain, Michigan State CS 484, Spring 2012 ©2012, Selim Aksoy 14 Surveillance and tracking CS 484, Spring 2012 University of Central Florida, Computer Vision Lab ©2012, Selim Aksoy 15 Surveillance and tracking Adapted from Octavia Camps, Penn State CS 484, Spring 2012 ©2012, Selim Aksoy 16 Surveillance and tracking Adapted from Martial Hebert, CMU CS 484, Spring 2012 ©2012, Selim Aksoy 17 Surveillance and tracking Generating traffic patterns University of Central Florida, Computer Vision Lab CS 484, Spring 2012 ©2012, Selim Aksoy 18 Surveillance and tracking Tracking in UAV videos Adapted from Martial Hebert, CMU, and Masaharu Kobashi, U of Washington CS 484, Spring 2012 ©2012, Selim Aksoy 19 Smart cars CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from CSE 455, U of Washington 20 Vehicle and pedestrian protection Lane departure warning, collision warning, traffic sign recognition, pedestrian recognition, blind spot warning CS 484, Spring 2012 ©2012, Selim Aksoy http://www.mobileye-vision.com 21 Forest fire monitoring system Early warning of forest fires CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from Enis Cetin, Bilkent University 22 Robotics CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from CSE 455, U of Washington 23 Robotics Adapted from Steven Seitz, U of Washington CS 484, Spring 2012 ©2012, Selim Aksoy 24 Autonomous navigation CS 484, Spring 2012 http://www.darpa.mil/grandchallenge/index.asp http://en.wikipedia.org/wiki/DARPA_Grand_Challenge ©2012, Selim Aksoy 25 Autonomous navigation Michigan State University CS 484, Spring 2012 General Dynamics Robotics Systems http://www.gdrs.com ©2012, Selim Aksoy 26 Face detection and recognition CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from CSE 455, U of Washington 27 Industrial automation Automatic fruit sorting Color Vision Systems http://www.cvs.com.au CS 484, Spring 2012 ©2012, Selim Aksoy 28 Industrial automation Industrial robotics; bin picking http://www.braintech.com CS 484, Spring 2012 ©2012, Selim Aksoy 29 Postal service automation General Dynamics Robotics Systems http://www.gdrs.com CS 484, Spring 2012 ©2012, Selim Aksoy 30 Optical character recognition Digit recognition, AT&T labs License place recognition http://www.research.att.com/~yann Adapted from Steven Seitz, U of Washington CS 484, Spring 2012 ©2012, Selim Aksoy 31 Document analysis Adapted from Shapiro and Stockman CS 484, Spring 2012 ©2012, Selim Aksoy 32 Document analysis CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from Linda Shapiro, U of Washington 33 Sports video analysis Tennis review system CS 484, Spring 2012 ©2012, Selim Aksoy http://www.hawkeyeinnovations.co.uk 34 Scene classification CS 484, Spring 2012 ©2012, Selim Aksoy 35 Object recognition CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from Rob Fergus, MIT 36 Object recognition Lincoln, Microsoft Research Situated search Yeh et al., MIT CS 484, Spring 2012 kooaba Google Goggles Bing Vision ©2012, Selim Aksoy 37 Land cover classification CS 484, Spring 2012 ©2012, Selim Aksoy 38 Land cover classification CS 484, Spring 2012 ©2012, Selim Aksoy 39 Object recognition CS 484, Spring 2012 ©2012, Selim Aksoy 40 Object recognition Recognition of buildings and building groups CS 484, Spring 2012 ©2012, Selim Aksoy 41 Organizing image archives Adapted from Pinar Duygulu, Bilkent University CS 484, Spring 2012 ©2012, Selim Aksoy 42 Photo tourism: exploring photo collections Building 3D scene models from individual photos CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from Steven Seitz, U of Washington 43 Photosynth CS 484, Spring 2012 ©2012, Selim Aksoy 44 Content-based retrieval Online shopping catalog search http://www.like.com CS 484, Spring 2012 ©2012, Selim Aksoy 45 3D scanning and reconstruction Adapted from Linda Shapiro, U of Washington CS 484, Spring 2012 ©2012, Selim Aksoy 46 Earth viewers (3D modeling) CS 484, Spring 2012 ©2012, Selim Aksoy 47 Motion capture CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from Linda Shapiro, U of Washington 48 Visual effects CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from CSE 455, U of Washington 49 Motion capture Microsoft’s XBox Kinect CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from CSE 455, U of Washington 50 Mozaic Adapted from David Forsyth, UC Berkeley CS 484, Spring 2012 ©2012, Selim Aksoy 51 Mozaic Adapted from David Forsyth, UC Berkeley CS 484, Spring 2012 ©2012, Selim Aksoy 52 Critical issues What information should be extracted? How can it be extracted? How should it be represented? How can it be used to aid analysis and understanding? CS 484, Spring 2012 ©2012, Selim Aksoy 53 Perception and grouping Subjective contours CS 484, Spring 2012 ©2012, Selim Aksoy 54 Perception and grouping Adapted from Gonzales and Woods CS 484, Spring 2012 ©2012, Selim Aksoy 55 Perception and grouping Müller-Lyer Illusion Adapted from Alyosha Efros, Carnegie Mellon CS 484, Spring 2012 ©2012, Selim Aksoy 56 CS 484, Spring 2012 ©2012, Selim Aksoy Copyright A.Kitaoka 2003 58 Perception and grouping Occlusion Adapted from Michael Black, Brown University CS 484, Spring 2012 ©2012, Selim Aksoy 59 What the computer gets CS 484, Spring 2012 ©2012, Selim Aksoy 60 Challenges 1: view point variation Michelangelo 1475-1564 Adapted from L. Fei-Fei, R. Fergus, A. Torralba CS 484, Spring 2012 ©2012, Selim Aksoy 61 Challenges 2: illumination Adapted from Fei-Fei Li CS 484, Spring 2012 ©2012, Selim Aksoy 62 Challenges 3: occlusion Magritte, 1957 Adapted from L. Fei-Fei, R. Fergus, A. Torralba CS 484, Spring 2012 ©2012, Selim Aksoy 63 Challenges 4: scale Adapted from L. Fei-Fei, R. Fergus, A. Torralba CS 484, Spring 2012 ©2012, Selim Aksoy 64 Challenges 5: deformation Xu, Beihong 1943 CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from L. Fei-Fei, R. Fergus, A. Torralba 65 Challenges 6: background clutter Adapted from Fei-Fei Li CS 484, Spring 2012 ©2012, Selim Aksoy 66 Challenges 7: intra-class variation CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from L. Fei-Fei, R. Fergus, A. Torralba 67 Recognition How can different cues such as color, texture, shape, motion, etc., can be used for recognition? Which parts of image should be recognized together? How can objects be recognized without focusing on detail? How can objects with many free parameters be recognized? How do we structure very large model bases? CS 484, Spring 2012 ©2012, Selim Aksoy 68 Color Adapted from Martial Hebert, CMU CS 484, Spring 2012 ©2012, Selim Aksoy 69 Texture CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from David Forsyth, UC Berkeley 70 Color, texture, and proximity Adapted from Fei-Fei Li CS 484, Spring 2012 ©2012, Selim Aksoy 71 Segmentation Original Images Color Regions Texture Regions Line Clusters Adapted from Linda Shapiro, U of Washington CS 484, Spring 2012 ©2012, Selim Aksoy 72 Segmentation CS 484, Spring 2012 ©2012, Selim Aksoy Adapted from Jianbo Shi, U Penn 73 Shape Recognized objects Adapted from Enis Cetin, Bilkent University Model database CS 484, Spring 2012 ©2012, Selim Aksoy 74 Motion Adapted from Michael Black, Brown University CS 484, Spring 2012 ©2012, Selim Aksoy 75 Detection Adapted from David Forsyth, UC Berkeley CS 484, Spring 2012 ©2012, Selim Aksoy 76 Detection Adapted from David Forsyth, UC Berkeley CS 484, Spring 2012 ©2012, Selim Aksoy 77 Detection Adapted from Michael Black, Brown University CS 484, Spring 2012 ©2012, Selim Aksoy 78 Recognition Adapted from Michael Black, Brown University CS 484, Spring 2012 ©2012, Selim Aksoy 79 Recognition Adapted from David Forsyth, UC Berkeley CS 484, Spring 2012 ©2012, Selim Aksoy 80 Parts and relations Adapted from Michael Black, Brown University CS 484, Spring 2012 ©2012, Selim Aksoy 81 Parts and relations Adapted from Michael Black, Brown University CS 484, Spring 2012 ©2012, Selim Aksoy 82 Context Adapted from Antonio Torralba, MIT CS 484, Spring 2012 ©2012, Selim Aksoy 83 Context Adapted from Antonio Torralba, MIT CS 484, Spring 2012 ©2012, Selim Aksoy 84 Context Adapted from Derek Hoiem, CMU CS 484, Spring 2012 ©2012, Selim Aksoy 85 Context Adapted from Derek Hoiem, CMU CS 484, Spring 2012 ©2012, Selim Aksoy 86 Stages of computer vision Low-level image image Mid-level image features / attributes Image analysis / image understanding High-level features “making sense”, recognition CS 484, Spring 2012 ©2012, Selim Aksoy 87 Low-level sharpening blurring Adapted from Linda Shapiro, U of Washington CS 484, Spring 2012 ©2012, Selim Aksoy 88 Low-level Canny original image Mid-level edge image ORT data structure edge image CS 484, Spring 2012 circular arcs and line segments ©2012, Selim Aksoy Adapted from Linda Shapiro, U of Washington 89 Mid-level K-means clustering (followed by connected component analysis) regions of homogeneous color original color image data structure Adapted from Linda Shapiro, U of Washington CS 484, Spring 2012 ©2012, Selim Aksoy 90 Low-level to high-level low-level edge image mid-level high-level consistent line clusters Adapted from Linda Shapiro, U of Washington CS 484, Spring 2012 ©2012, Selim Aksoy 91
Benzer belgeler
Introduction - Bilkent University Computer Engineering Department
Adapted from Martial Hebert, CMU, and
Masaharu Kobashi, U of Washington
CS 484, Spring 2010
Introduction - Bilkent University Computer Engineering Department
Adapted from Michael Black, Brown University
CS 484, Spring 2007
Brockers, Roland........................................................ 262
Linear Filtering – Part II - Bilkent University Computer Engineering
Correlation can also be used for matching.
If we want to determine whether an image f
contains a particular object, we let h be that
object (also called a template) and compute the
correlation betw...
Fon Günlük Raporu
AFA- AKPORTFÖY FT AMERIKA YABANCI HISSE SENED
Eylül 2016
I-FONU TANITICI BİLGİLER
A-)Fonun Adı
AFA- FT AMERİKA
Şubat 2015
I-FONU TANITICI BİLGİLER
A-)Fonun Adı
