Introduction - Bilkent University Computer Engineering Department

Yorumlar

Transkript

Introduction - Bilkent University Computer Engineering Department
Introduction
Selim Aksoy
Department of Computer Engineering
Bilkent University
[email protected]
What is computer vision?
Analysis of digital images by a computer.
Stockman and Shapiro: making useful decisions about real
physical objects and scenes based on sensed images.
Trucco and Verri: computing properties of the 3D world
from one or more digital images.
Ballard and Brown: construction of explicit, meaningful
description of physical objects from images.
Forsyth and Ponce: extracting descriptions of the world
from pictures or sequences of pictures.
CS 484, Spring 2010
©2010, Selim Aksoy
2
Why study computer vision?
Possibility of building intelligent machines is
fascinating.
Capability of understanding the visual world is a
prerequisite for such machines.
Much of the human brain is dedicated to vision.
Humans solve many visual problems effortlessly,
yet we have little understanding of visual
cognition.
CS 484, Spring 2010
©2010, Selim Aksoy
3
Why study computer vision?
Fast growing collections and many useful applications.
Goals of vision research:
Give machines the ability to understand scenes.
Aid understanding and modeling of human vision.
Automate visual operations.
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from CSE 455, U of Washington
4
Applications
Medical image analysis
Security
Biometrics
Surveillance
Tracking
Target recognition
Remote sensing
Robotics
CS 484, Spring 2010
Industrial inspection,
quality control
Document analysis
Multimedia
Assisted living
Human-computer
interfaces
…
©2010, Selim Aksoy
5
Medical image analysis
http://www.clarontech.com
CS 484, Spring 2010
©2010, Selim Aksoy
6
Medical image analysis
http://www.clarontech.com
CS 484, Spring 2010
©2010, Selim Aksoy
7
Medical image analysis
http://www.clarontech.com
CS 484, Spring 2010
©2010, Selim Aksoy
8
Medical image analysis
3D imaging: MRI, CT
CS 484, Spring 2010
Image guided surgery
Grimson et al., MIT
©2010, Selim Aksoy
Adapted from CSE 455, U of Washington
9
Medical image analysis
Cancer
detection
and
grading
CS 484, Spring 2010
©2010, Selim Aksoy
10
Medical image analysis
Slice of
lung
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from Linda Shapiro, U of Washington
11
Medical image analysis
CS 484, Spring 2010
©2010, Selim Aksoy
12
Biometrics
Adapted from
Anil Jain,
Michigan State
CS 484, Spring 2010
©2010, Selim Aksoy
13
Biometrics
Adapted from Anil Jain, Michigan State
CS 484, Spring 2010
©2010, Selim Aksoy
14
Surveillance and tracking
CS 484, Spring 2010
University of Central Florida, Computer Vision Lab
©2010, Selim Aksoy
15
Surveillance and tracking
Adapted from Octavia Camps, Penn State
CS 484, Spring 2010
©2010, Selim Aksoy
16
Surveillance and tracking
Adapted from Martial Hebert, CMU
CS 484, Spring 2010
©2010, Selim Aksoy
17
Surveillance and tracking
Generating traffic patterns
University of Central Florida, Computer Vision Lab
CS 484, Spring 2010
©2010, Selim Aksoy
18
Surveillance and tracking
Tracking in UAV videos
Adapted from Martial Hebert, CMU, and
Masaharu Kobashi, U of Washington
CS 484, Spring 2010
©2010, Selim Aksoy
19
Vehicle and pedestrian protection
Lane departure warning, collision warning, traffic sign recognition,
pedestrian recognition, blind spot warning
CS 484, Spring 2010
©2010, Selim Aksoy
http://www.mobileye-vision.com
20
Smart cars
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from CSE 455, U of Washington
21
Forest fire monitoring system
Early warning of forest fires
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from Enis Cetin, Bilkent University
22
Land cover classification
CS 484, Spring 2010
©2010, Selim Aksoy
23
Land cover classification
CS 484, Spring 2010
©2010, Selim Aksoy
24
Object recognition
CS 484, Spring 2010
©2010, Selim Aksoy
25
Object recognition
Recognition of buildings and building groups
CS 484, Spring 2010
©2010, Selim Aksoy
26
Content-based retrieval
Finding similar regions: airports
CS 484, Spring 2010
©2010, Selim Aksoy
27
Robotics
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from CSE 455, U of Washington
28
Robotics
Adapted from Steven Seitz, U of Washington
CS 484, Spring 2010
©2010, Selim Aksoy
29
Autonomous navigation
Michigan State University
CS 484, Spring 2010
General Dynamics Robotics Systems
http://www.gdrs.com
©2010, Selim Aksoy
30
Industrial automation
Automatic fruit sorting
Color Vision Systems
http://www.cvs.com.au
CS 484, Spring 2010
©2010, Selim Aksoy
31
Industrial automation
Industrial robotics;
bin picking
http://www.braintech.com
CS 484, Spring 2010
©2010, Selim Aksoy
32
Postal service automation
General Dynamics Robotics Systems
http://www.gdrs.com
CS 484, Spring 2010
©2010, Selim Aksoy
33
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 2010
©2010, Selim Aksoy
34
Document analysis
Adapted from Shapiro and Stockman
CS 484, Spring 2010
©2010, Selim Aksoy
35
Document analysis
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from Linda Shapiro, U of Washington
36
Sports video analysis
Tennis review system
CS 484, Spring 2010
©2010, Selim Aksoy
http://www.hawkeyeinnovations.co.uk
37
Scene classification
CS 484, Spring 2010
©2010, Selim Aksoy
38
Organizing image archives
Adapted from Pinar Duygulu, Bilkent University
CS 484, Spring 2010
©2010, Selim Aksoy
39
Photo tourism: exploring photo collections
Building 3D scene models from individual photos
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from Steven Seitz, U of Washington
40
Content-based retrieval
CS 484, Spring 2010
©2010, Selim Aksoy
41
Content-based retrieval
CS 484, Spring 2010
©2010, Selim Aksoy
42
Content-based retrieval
Online shopping catalog search
http://www.like.com
CS 484, Spring 2010
©2010, Selim Aksoy
43
Face detection and recognition
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from CSE 455, U of Washington
44
Object recognition
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from Rob Fergus, MIT
45
3D scanning
Adapted from Linda Shapiro, U of Washington
CS 484, Spring 2010
©2010, Selim Aksoy
46
3D reconstruction
Adapted from David Forsyth, UC Berkeley
CS 484, Spring 2010
©2010, Selim Aksoy
47
3D reconstruction
Adapted from David Forsyth, UC Berkeley
CS 484, Spring 2010
©2010, Selim Aksoy
48
Motion capture
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from Linda Shapiro, U of Washington
49
Visual effects
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from CSE 455, U of Washington
50
Mozaic
Adapted from David Forsyth, UC Berkeley
CS 484, Spring 2010
©2010, Selim Aksoy
51
Mozaic
Adapted from David Forsyth, UC Berkeley
CS 484, Spring 2010
©2010, 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 2010
©2010, Selim Aksoy
53
Challenge
What do you see in
the picture?
A hand holding a man
A hand holding a shiny
sphere
An Escher drawing
Adapted from Octavia Camps, Penn State
CS 484, Spring 2010
©2010, Selim Aksoy
54
Perception and grouping
Subjective
contours
CS 484, Spring 2010
©2010, Selim Aksoy
55
Perception and grouping
Subjective
contours
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
56
Perception and grouping
Adapted from Gonzales and Woods
CS 484, Spring 2010
©2010, Selim Aksoy
57
Perception and grouping
Adapted from Gonzales and Woods
CS 484, Spring 2010
©2010, Selim Aksoy
58
CS 484, Spring 2010
©2010, Selim Aksoy
Copyright A.Kitaoka 2003
60
Perception and grouping
Occlusion
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
61
Perception and grouping
The shape of junctions
constrains the possible
interpretations of the
scene.
Ambiguous: paint and
surface boundaries can
be confused.
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
62
Challenges 1: view point variation
Michelangelo 1475-1564
Adapted from L. Fei-Fei,
R. Fergus, A. Torralba
CS 484, Spring 2010
©2010, Selim Aksoy
63
Challenges 2: illumination
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from L. Fei-Fei, R. Fergus, A. Torralba
64
Challenges 3: occlusion
Magritte, 1957
Adapted from L. Fei-Fei,
R. Fergus, A. Torralba
CS 484, Spring 2010
©2010, Selim Aksoy
65
Challenges 4: scale
Adapted from L. Fei-Fei,
R. Fergus, A. Torralba
CS 484, Spring 2010
©2010, Selim Aksoy
66
Challenges 5: deformation
Xu, Beihong 1943
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from L. Fei-Fei, R. Fergus, A. Torralba
67
Challenges 6: background clutter
Klimt, 1913
Adapted from L. Fei-Fei,
R. Fergus, A. Torralba
CS 484, Spring 2010
©2010, Selim Aksoy
68
Challenges 7: intra-class variation
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from L. Fei-Fei, R. Fergus, A. Torralba
69
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 2010
©2010, Selim Aksoy
70
Color
Adapted from Martial Hebert, CMU
CS 484, Spring 2010
©2010, Selim Aksoy
71
Texture
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from David Forsyth, UC Berkeley
72
Segmentation
Original Images
Color Regions
Texture Regions
Line Clusters
Adapted from Linda Shapiro, U of Washington
CS 484, Spring 2010
©2010, Selim Aksoy
73
Segmentation
CS 484, Spring 2010
©2010, Selim Aksoy
Adapted from Jianbo Shi, U Penn
74
Shape
Recognized objects
Adapted from Enis Cetin, Bilkent University
Model database
CS 484, Spring 2010
©2010, Selim Aksoy
75
Motion
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
76
Recognition
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
77
Recognition
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
78
Recognition
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
79
Recognition
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
80
Recognition
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
81
Recognition
CS 484, Spring 2010
©2010, Selim Aksoy
82
Recognition
Adapted from David Forsyth, UC Berkeley
CS 484, Spring 2010
©2010, Selim Aksoy
83
Detection
Adapted from David Forsyth, UC Berkeley
CS 484, Spring 2010
©2010, Selim Aksoy
84
Detection
Adapted from David Forsyth, UC Berkeley
CS 484, Spring 2010
©2010, Selim Aksoy
85
Detection
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
86
Parts and relations
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
87
Parts and relations
Adapted from Michael Black, Brown University
CS 484, Spring 2010
©2010, Selim Aksoy
88
Context
Adapted from Antonio Torralba, MIT
CS 484, Spring 2010
©2010, Selim Aksoy
89
Context
Adapted from Antonio Torralba, MIT
CS 484, Spring 2010
©2010, Selim Aksoy
90
Context
Adapted from Derek Hoiem, CMU
CS 484, Spring 2010
©2010, Selim Aksoy
91
Context
Adapted from
Derek Hoiem, CMU
CS 484, Spring 2010
©2010, Selim Aksoy
92
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 2010
©2010, Selim Aksoy
93
Low-level
sharpening
blurring
Adapted from Linda Shapiro, U of Washington
CS 484, Spring 2010
©2010, Selim Aksoy
94
Low-level
Canny
original image
Mid-level
edge image
ORT
data
structure
edge image
CS 484, Spring 2010
circular arcs and line segments
©2010, Selim Aksoy
Adapted from Linda Shapiro, U of Washington
95
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 2010
©2010, Selim Aksoy
96
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 2010
©2010, Selim Aksoy
97

Benzer belgeler

Introduction - Bilkent University Computer Engineering Department

Introduction - Bilkent University Computer Engineering Department Adapted from Linda Shapiro, U of Washington CS 484, Spring 2007

Detaylı

Author Index

Author Index Brockers, Roland........................................................ 262

Detaylı

Linear Filtering – Part II - Bilkent University Computer Engineering

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...

Detaylı

Franklin US Opportunities

Franklin US Opportunities spending look attractive to us, specifically areas such as apparel, restaurants, beverages and housing. We believe the technology and health care sectors continue to have solid growth outlooks with...

Detaylı

Fon Günlük Raporu

Fon Günlük Raporu AFA- AKPORTFÖY FT AMERIKA YABANCI HISSE SENED Eylül 2016 I-FONU TANITICI BİLGİLER A-)Fonun Adı

Detaylı