Professional Documents
Culture Documents
Computer Vision
Mubarak Shah
shah@crcv.ucf.edu
Computer Vision
Image Understanding
Machine Vision
Robot Vision
Image Analysis
Video Understanding
8/20/2014
A HUNT
8/20/2014
Image
Red
Green
Blue
128X128
256X256
512X512
640X480
8/20/2014
Image Formats
TIF
PGM
PBM
GIF
JPEG
RAW
Video
Sequence of frames
30 frames per second
Formats
AVI
MPEG
Quick Time
8/20/2014
Video Clip
Sequence of Images
8/20/2014
Image Formation
Light Source
Camera (extrinsic and intrinsic
parameters)
Scene (Surface reflectance, Surface
shape )
Image Plane
f
y
image
Lens
Z
8/20/2014
Orthographic Projection
Image Plane
(X,Y,Z)
World
point
y
image
Shape from X
Stereo
Motion
Shading
Texture
Contours
8/20/2014
Stereo
http://www.vision3d.com/stereo.html
8/20/2014
Depth Map
8/20/2014
Lambertian Model
S=L, light
source
I=S.N
10
8/20/2014
Vase
(1, 0, 1)
(-1, 1, 1)
(-1,-1, 1)
11
8/20/2014
Visual Motion
12
8/20/2014
Photosynth
13
8/20/2014
Sequence
27
14
8/20/2014
Applications of Computer
Vision
Face Recognition
Object Recognition
Video Surveillance and Monitoring
Object Recognition
Finding People in images
Problem 1: Given an image I
Question: Does I contain an image of a
person?
15
8/20/2014
Yes Instances
No Instances
16
8/20/2014
Human Detection
17
8/20/2014
Airplanes
Motor Cycles
18
8/20/2014
Face Recognition
UniversityofCentralFlorida
CRCV|CenterforResearchinComputerVision
TamingWildFaces:WebScale,OpenUniverseFaceRecognition
19
8/20/2014
UniversityofCentralFlorida
CRCV|CenterforResearchinComputerVision
Pair-Matching Task
Most Realistic
Scenario
TamingWildFaces:WebScale,OpenUniverseFaceRecognition
UniversityofCentralFlorida
CRCV|CenterforResearchinComputerVision
Alice
TamingWildFaces:WebScale,OpenUniverseFaceRecognition
24
8/20/2014
UniversityofCentralFlorida
CRCV|CenterforResearchinComputerVision
TamingWildFaces:WebScale,OpenUniverseFaceRecognition
UniversityofCentralFlorida
CRCV|CenterforResearchinComputerVision
TamingWildFaces:WebScale,OpenUniverseFaceRecognition
25
8/20/2014
UniversityofCentralFlorida
CRCV|CenterforResearchinComputerVision
Gwenyth Paltrow
Robert Downey Jr.
TamingWildFaces:WebScale,OpenUniverseFaceRecognition
FaceRecognitioninMovieTrailersvia
MeanSequenceSparseRepresentationbasedClassification
CVPR2013
26
8/20/2014
Recognition Qualitative
Known:
PaulRudd
SteveCarell
Recognition Qualitative
Known:
PaulRudd
SteveCarell
27
8/20/2014
Recognition Qualitative
Known:
OwenWilson
ReeseWitherspoon
PaulRudd
Recognition Qualitative
Known:
BruceWillis
MorganFreeman
28
8/20/2014
Recognition Qualitative
Known:
TomCruise
CameronDiaz
FACIAL EXPRESSIONS
SMILE
29
8/20/2014
Lipreading
30
8/20/2014
Object detection
Object tracking
Object categorization
and classification
Event or Activities
Recognition
A.IPersonTracking
A.IIPartTracking
31
8/20/2014
Current Sensor
Next Generation
NONA SysmtemAirport
Sequence 1
32
8/20/2014
Predator
Global Hawk
Microdrone
33
8/20/2014
8/20/2014
67
COCOA SystemFlow
Registered Images
Motion Detection
Object Tracking
Accumulative Frame
Differencing + Background
Modeling + Object
Segmentation
Motion Detection
Tracks
COCOA
Aerial Video
Telemetry*
Ego Motion
Compensation
34
8/20/2014
RegistrationResult I
Aerial Video - EO
Alignment
Mosaic
Mask
RegistrationResult II
Aerial Video - IR
Alignment
Mosaic
Mask
35
8/20/2014
DetectionResults
TrackingResults
36
8/20/2014
WideAreaSurveillance
WideAreaSurveillance
37
8/20/2014
TrackingResults
RobotVision(UnmannedGround
Vehicle)
UGV
38
8/20/2014
UGV
HumanActionRecognition
39
8/20/2014
Events,Actions,Activities,
Action
Event
Movement
Activity
Interaction
Verb
.
WeizmannActionDataset
10actions
9actorsperaction
Bend
Jack
Sidestep
Hop
Wave 2 hands
Walk
Wave 1 hand
Skip
Jump in place
Run
40
8/20/2014
Political Rallies
Religious Festivals
Marathons
High Density
Moving Objects
Tracking in Crowds
48
8/20/2014
Results
Experiment 1
49
8/20/2014
Experiment-3
Experiment 3
50
8/20/2014
BehaviorsinCrowdedScenes
Bottleneck
Departure
Lanes
Arch/Rings
Blockings
51
8/20/2014
52
8/20/2014
53
8/20/2014
Ground truth=2322
Proposed Method=2203
54
8/20/2014
Where Am I?
Where Am I?
Problem:
Output
55
8/20/2014
QualitativeImageLocalizationResults:
68.3%:Thebestmatchfound:
Query
Match Error:9.01m
Query
Match Error:7.5m
Query
Query
Match Error:6.4m
Match Error:62.7m
QualitativeImageLocalizationResults:
68.3%:Thebestmatchfound:
13.2%:Acorrectmatchfound,butnotthebestone:
Query
Query
Match Error:244.7m
Match Error:307.7m
Query
Query
Match Error:157.3m
Match Error:71.3m
56
8/20/2014
VisualBusinessRecognition
ACMMultimedia2013
57
8/20/2014
Video Completion
58
8/20/2014
Results of Doll
59
8/20/2014
Results of Mom-Daughter
Multimedia: Segmentation of
Moving-Sounding Objects
120
60