Instructor:%20Zhigang%20Zhu - PowerPoint PPT Presentation

About This Presentation
Title:

Instructor:%20Zhigang%20Zhu

Description:

Instructor: Zhigang Zhu – PowerPoint PPT presentation

Number of Views:84
Avg rating:3.0/5.0
Slides: 93
Provided by: allenh2
Category:

less

Transcript and Presenter's Notes

Title: Instructor:%20Zhigang%20Zhu


1
Introduction
CSc I6716 Fall 2006 3D Computer Vision and
Video Computing
Topic 1 of Part I Introduction
  • Instructor Zhigang Zhu
  • City College of New York
  • zzhu_at_ccny.cuny.edu

2
Acknowledgements
  • Some slides in this lecture were kindly provided
    by
  • Professor Allen Hanson
  • University of Massachusetts at Amherst

3
Course Information
  • Basic Information
  • Course participation
  • Books, notes, etc.
  • Web page check often!
  • Homework, Assignment, Exam
  • Homework and exams
  • Grading
  • Goal
  • What I expect from you
  • What you can expect from me
  • Resources

4
Book
  • Textbook
  • Introductory Techniques for 3-D Computer Vision
    Trucco and Verri, 1998
  • Additional readings when necessary
  • Computer Vision A Modern Approach Forsyth and
    Ponce, 2003
  • Three-Dimensional Computer Vision A Geometric
    Viewpoint O. Faugeras, 1998
  • Image Processing, Analysis and Machine VIsion
    Sonika, Hlavac and Boyle, 1999
  • On-Line References

5
Prequisites
  • Linear Algebra
  • A little Probability and Statistics
  • Programming Experience
  • Reading Literature (Lots!)
  • An Inquisitive Nature (Curiosity)
  • No Fear

6
Course Web Page
http//www-cs.engr.ccny.cuny.edu/zhu/CSC6716-2006
/VisionCourse-2006.html
  • Lectures available in Powerpoint format
  • All homework assignments will be distributed over
    the web
  • Additional materials and pointers to other web
    sites
  • Course bulletin board contains last minute items,
    changes to assignments, etc.
  • CHECK IT OFTEN!
  • You are responsible for material posted there

7
Course Outline
  • Complete syllabus on the web pages (10-12
    lectures)
  • Rough Outline ( 3D Computer Vision and Video
    Computing)
  • Part 1. Vision Basics
  • 1. Introduction
  • 2. Visual Sensors
  • 3. Image Formation and Processing ((hw 1,
    matlab)
  • 4. Features and Feature Extraction ( hw 2)
  • Part 2. 3D Vision
  • 5. Camera Models and Omnidirectional Cameras
    (2 lectures)
  • 6. Camera Calibration (hw 3)
  • 7. Stereo Vision (project assignment)
  • 8. Visual Motion (midterm exam)
  • Part 3. Video Computing
  • 9. Video Mosaicing and Image-based rendering
  • 10. Omnidirectional Stereo ( project
    presentations)

8
Grading
  • Homework (about 3) 30
  • Exam (midterm) 40
  • Course Project Exit Interview 30
  • Groups (I or 2 students) for discussions
  • Experiments independently collaboratively
  • Written Report - independently collaboratively
  • All homework must be yours.but you can work
    together until the final submission

9
C and Matlab
  • C
  • For some simple computation, you may use C
  • Matlab
  • An interactive environment for numerical
    computation
  • Available on Computer Labs machines (both Unix
    and Windows)
  • Matlab primer available on line (web page)
  • Pointers to on-line manuals also available
  • Good rapid prototyping environment
  • You should use C and/or Matlab for your
    homework assignments and project(s) Java will
    also be fine

10
Dumb Questions
  • There is no such thing as a dumb question.
  • If you don't understand something in the text or
    lectures, others in the class may be confused as
    well.
  • Questions and answers are an important form of
    communication that aids the education process (to
    say nothing of the scientific process).
  • Students are encouraged - nay, required - to ask
    questions during class.
  • If I feel that a line of questioning is not
    productive, I will suggest taking it off-line
    (e-mail, office hours).

11
Course Goals and Questions
  • What makes (3D) Computer Vision interesting ?
  • Image Modeling/Analysis/Interpretation
  • Interpretation is an Artificial Intelligence
    Problem
  • Sources of Knowledge in Vision
  • Levels of Abstraction
  • Interpretation often goes from 2D images to 3D
    structures
  • since we live in a 3D world
  • Image Rendering/Synthesis/Composition
  • Image Rendering is a Computer Graphics problem
  • Rendering is from 3D model to 2D images
  • What is Computer Vision (bigger picture)?
  • Goals
  • Approaches

2D images
CV
CG
3D world
12
Related Fields
  • Image Processing image to image
  • Computer Vision Image to model
  • Computer Graphics model to image
  • Pattern Recognition image to class
  • image data mining/ video mining
  • Artificial Intelligence machine smarts
  • Machine perception
  • Photogrammetry camera geometry, 3D
    reconstruction
  • Medical Imaging CAT, MRI, 3D reconstruction (2nd
    meaning)
  • Video Coding encoding/decoding, compression,
    transmission
  • Physics Mathematics basics
  • Neuroscience wetware to concept
  • Computer Science programming tools and skills?

All three are interrelated!
AI
Applications
basics
13
Applications
  • Visual Inspection ()
  • Robotics ()
  • Intelligent Image Tools
  • Image Compression (MPEG 1/2/4/7)
  • Document Analysis (OCR)
  • Image Libraries (DL)
  • Virtual Environment Construction ()
  • Environment ()
  • Media and Entertainment
  • Medicine
  • Astronomy
  • Law Enforcement ()
  • surveillance, security
  • Traffic and Transportation ()
  • Tele-Conferencing and e-Learning ()
  • Computer Input

14
Job Markets
  • Homeland Security
  • Port security cargo inspection, human ID,
    biometrics
  • Facility security Embassy, Power plant, bank
  • Surveillance military or civilian
  • Media Production
  • Cartoon / movie/ TVs/ photography
  • Multimedia communication, video conferencing
  • Research in image, vision, graphics, virtual
    reality
  • 2D image processing
  • 3D modeling, virtual walk-thorugh
  • Consumer/ Medical Industries
  • Video cameras, Camcorders, Video phone
  • Medical imaging 2D -gt 3D

15
Example
  • Volume rendering for medical applications
  • Clean up the image (image processing)
  • Separate regions of interest (2D vision -
    segmentation)
  • Build 3D Model (3D Vision)
  • Render (graphics)
  • Visible Human Project (Link to my local archive)

Color Cryosections
Head
Torso
Feet
16
Volume Rendering
  • Rendered model

http//www.nlm.nih.gov/research/visible/visible_hu
man.html
17
IP vs CV
  • Image processing (mainly in 2D)
  • Image to Image transformations
  • Image to Description transformations
  • Image Analysis - extracting quantitative
    information from images
  • Size of a tumor
  • distance between objects
  • facial expression
  • Image restoration. Try to undo damage
  • needs a model of how the damage was made
  • Image enhancement. Try to improve the quality of
    an image
  • Image compression. How to convey the most amount
    of information with the least amount of data

18
Zooming
Geometric Transformation
19
Rotation
Geometric Transformation
20
Subtraction
Brightness Transformation
21
Contrast Stretching
Brightness Transformation
22
Histogram Equalization
Brightness Transformation
23
False Color
pseudo-color
Brightness Transformation
24
Sharpening
Brightness/Contrast Transformation
25
Smoothing
Structure Transformation
26
Noise Removal
Structure Transformation
27
Spatial Frequency Filtering
Structure Transformation
28
Warping
Geometric Transformation
29
Compression
Spatial Transformation
30
What is Computer Vision?
  • Vision is the art of seeing things invisible.

-Jonathan Swift (1667-1745) "Thoughts on
Various Subjects" Miscellanies in Prose and
Verse (published with Alexander Pope),
vol. 1, 1727
  • Computer vision systems attempt to construct
    meaningful and explicit descriptions of the world
    depicted in an image.
  • Determining from an image or image sequence
  • The objects present in the scene
  • The relationship between the scene and the
    observer
  • The structure of the three dimensional (3D) space

31
Approaches
  • Three interesting approaches
  • Computational Vision Image Structure
  • David Marr (MIT)
  • Knowledge-Based Vision Image Structure
  • Active Vision
  • Applied Vision Images Function(Control)
  • many others
  • Different methodological assumptions
  • Different methods
  • Different results
  • Where is Video Computing?
  • an example.... draw your own conclusions!

general
specific
32
Mosaics
_at_Zhigang Zhu
Spatial Transformation
33
Stereo
34
Stereo
35
What do we see when we look?
  • Some Questions we might ask
  • How can we determine the 3D structure of the
    scene from which the image was derived?
  • Do our current steps have an effect on how an
    image is interpreted?
  • How important is context in recognition?
  • How important is 3D in recognition?
  • What is the role of a-priori knowledge during
    interpretation?
  • What might be the representation of useful
    internalized models of objects and scenarios?
  • And many more!

36
Cues to Space and Time
37
Cues to Time and Space
38
Cues to Space and Time
Directly Measurable in an Image
  • Spectral Characteristics
  • Intensity, contrast, colors and their
  • Spatial distributions
  • 2D Shape of Contours
  • Linear Perspective
  • Highlights and Shadows
  • Occlusions
  • Organization
  • Motion parallax and Optical Flow
  • Stereopsis and sensor convergence

39
Cues to Space and Time
Inferred Properties
  • Surface connectivity
  • 3D Volume
  • Hidden sides and parts
  • Identity (Semantic category)
  • Absolute Size
  • Functional Properties
  • Goals, Purposes, and Intents
  • Organization
  • Trajectories

40
Cues to Depth
  • Question
  • How do we perceive the three-dimensional
    properties of the world when the images on our
    retinas are only two-dimensional?
  • Stereo is not the entire story!

41
Cues to Depth
  • Monocular cues to the perception of depth in
    images
  • Interposition occluding objects appear closer
    than occluded objects
  • Relative size when objects have approximately
    the same physical size, the larger object appears
    closer
  • Relative height objects lower in the image
    appear closer
  • Linear Perspective objects appear smaller as
    they recede into the distance
  • texture gradients
  • Aerial Perspective change in color and sharpness
    as object recede into the distance
  • Illumination gradients gradients and shadow lend
    a sense of depth
  • Relative Motion faster moving objects appear
    closer

42
Cues to Depth
  • Physiological cues to depth
  • Focus (accomodation) change in curvature of the
    lens for objects at different depths
  • Convergence eyes turn more inward (nasal) for
    closer objects
  • Retinal disparity greater for objects further
    away

43
Interposition
44
Interposition
45
Interposition
46
Different viewpoint
47
Different viewpoint
Edgar Degas Dance Class at the Opéra, 1872
48
Different viewpoint
Edgar Degas Green Dancer, c.1880
49
Different viewpoint
Edgar Degas Frieze of Dancers, c.1895
50
Different viewpoint
Edgar Degas Frieze of Dancers, c.1895
51
Different viewpoint
Edgar Degas Frieze of Dancers, c.1895
52
Different viewpoint
Edgar Degas Frieze of Dancers, c.1895
53
Different viewpoint
Edgar Degas Frieze of Dancers, c.1895
54
Different viewpoint
Edgar Degas Frieze of Dancers, c.1895
55
Different viewpoint
Edgar Degas Frieze of Dancers, c.1895
56
Different viewpoint
Edgar Degas Frieze of Dancers, c.1895
57
Different viewpoint
Edgar Degas Frieze of Dancers, c.1895
58
Aerial Perspective
  • Constable

59
Aerial Perspective
  • Classic Chinese Paintings

60
Absolute Size
61
Relative Size
62
Relative Size
63
Absolute Size
64
Relative Size
65
Absolute Size
66
Relative Size
67
Light and Surfaces
68
Light and Surfaces
69
Light and Surfaces
70
Light and Surfaces
71
Light and Surfaces
72
Light and Surfaces
  • C. H. Stoelting Company

73
Light and Surfaces
74
Light and Surfaces
75
Light and Surfaces
76
Light and Surfaces
77
The Effect of Perspective
78
Texture Gradient
Sunflowers in Fargo, ND Photo by Bruce Fitz
http//www.ars.usda.gov/is/graphics/photos/
79
Texture Gradients
80
Edges
81
Texture Edges
82
Who Knows?
83
Who Knows?
84
Who Knows?
  • From the Centre for Microscopy and Microanalysis
    at The University of Queensland
  • http//www.uq.edu.au/nanoworld/images_1.html

85
Who Knows?
  • From the Centre for Microscopy and Microanalysis
    at The University of Queensland
  • http//www.uq.edu.au/nanoworld/images_1.html

86
Who Knows?
87
Who Knows?
88
Some Final Thoughts
89
Some Final Thoughts
90
Some Final Thoughts
91
Some Final Thoughts
92
Next
  • Sensors

Vision and Robotics Lecture Series at CCNY
Check CS homepage
Write a Comment
User Comments (0)
About PowerShow.com