Transcript CVVC_Lecture1_Intro-ppt

3D Computer Vision
Introduction
and Video Computing
CSc 83300 Spring 2006
Reading in
3D Computer Vision
and Video Computing
Instructor: Zhigang Zhu
[email protected]
Lecture 1: Introduction
http://www-cs.engr.ccny.cuny.edu/~zhu/GC-Spring2006/CSc83300-Video-Computing-2006.html
3D Computer Vision
and Video Computing

Research at CcvcL
Research Projects at

The City College Visual Computing Lab




C
CVC L
3D video mosaicing, representation and rendering
Multimodal human signature detection
Robotized Sensor networks
3D cargo and vehicle inspection
http://www-cs.engr.ccny.cuny.edu/~zhu/research.html


The NSF PI Meeting Talk
The UTRC Hi-Tech Meeting Talk
3D Computer Vision
and Video Computing

A slightly new approach: purpose-driven reading




Purpose-Driven Reading
Goals come first
Readings come second
Projects come last
Some more details





Get to know what you want to do
Figure out potential projects and the goals
Find related papers to read and present
Try out something new and/or interesting
Write out something

Ideally publications for a conference or journal
3D Computer Vision
and Video Computing

Homework # 1
Submit your resume with





Education (where/what/how good)
Skills (what you are good at: GUI, algorithm, hardware)
Work Experiences ( R&D)
Publications (if any)
Projects related to imaging, vision and graphics (IVG)


Your advisors (if any)
Courses taken


Particularly math, CS, EE related to IVG
Algorithms, Signal processing, etc
3D Computer Vision
and Video Computing





Course Organization
Lectures by me (4 lectures)
 Basics in 3D computer vision
 Camera models, calibration, stereo, motion
Talks by others
 CCNY lecture series, GC CS Colloquium
Project Ideas by us
 3D vision, video and robotics
 Some ongoing work at the CCNY Visual Computing Lab
 Your research interests (2nd level up)
Presentations by you ( ~ 3 times each, 2 – 3 each class meet)
 Others’ work (1~2)
 Your work proposals and work reports (1~2)
Office Hours

Tuesday 4:30 – 6:00 pm
3D Computer Vision
and Video Computing
Course Web Page
http://www-cs.engr.ccny.cuny.edu/~zhu/GC-Spring2006/CSc83300-Video-Computing-2006.html




Lectures available in Powerpoint format
Reading schedule will be posted on the web
All assignments will be distributed over the web
Additional materials and pointers to other web sites
March 6-10: A talk by Prof. Harvey Rhody @ RIT
Monday or Tuesday ?
3D Computer Vision
and Video Computing



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
On-Line References and Reading Materials
3D Computer Vision
and Video Computing
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
3D Computer Vision
and Video Computing

Homework (about 2~3): 20%

Course Work: 40%




Reading – Related work by others
Experiments – Results by yourselves
Written Report – Papers or TRs
Presentations (2~3 per student): 40%
Grading
3D Computer Vision
and Video Computing

3D Computer Vision
What makes (3D) Computer Vision interesting ?
 Image
Modeling/Analysis/Interpretation

Interpretation is an Artificial Intelligence Problem



Sources of Knowledge in Vision
Levels of Abstraction
CV
since we live in a 3D world
 Image
Rendering/Synthesis/Composition

CG
Interpretation often goes from 2D images to 3D structures


2D
images
Image Rendering is a Computer Graphics problem
Rendering is from 3D model to 2D images
3D
world
3D Computer Vision
and Video Computing

IP vs CV
Image processing (mainly in 2D)



Image to Image transformations
Image to Description transformations
Image Analysis - extracting quantitative information from
images:




Image restoration. Try to undo damage



Size of a tumor
distance between objects
facial expression
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
3D Computer Vision
and Video Computing

Video Computing
Some Examples on Video Computing






Video compression
Video surveillance
Video manipulation (video texture, video composition)
Video mosaicing
Video segmentation
3D video
3D Computer Vision
Approaches
and Video Computing

Three interesting approaches:
general

Computational Vision:
Image
Structure
Knowledge-Based Vision: Image
Structure




David Marr (MIT)
Active Vision
Applied Vision

Images
many others

Different methodological assumptions
Different methods
Different results

Where is Video Computing?



Function(Control)
an example.... draw your own conclusions!
specific
3D Computer Vision
and Video Computing

Image Processing: image to image
Computer Vision: Image to model
Computer Graphics: model to image

Pattern Recognition: image to class







All three are
interrelated!
image data mining/ video mining
Artificial Intelligence: machine smarts

Related Fields
AI
Machine perception
Applications
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?

basics
3D Computer Vision
and Video Computing














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 (*)
Applications
3D Computer Vision
and Video Computing




Job Markets
Homeland Security
 Port security – cargo inspection, human ID, biometrics
 Facility security – Embassy, Power plant, bank
 Surveillance – military or civil
Media Production
 Cartoon / movie/ TVs/ photography
 Multimedia communication, video conferencing
Research in image, vision, graphics, virtual reality
 2D image processing
 3D modeling, virtual walk-through
Consumer/ Medical Industries
 Video cameras, Camcorders, Video phone
 Medical imaging 2D -> 3D
3D Computer Vision
and Video Computing

Research at CcvcL
Research Projects at

The City College Visual Computing Lab




C
CVC L
3D video mosaicing, representation and rendering
Multimodal human signature detection
Robotized Sensor networks
3D cargo and vehicle inspection
http://www-cs.engr.ccny.cuny.edu/~zhu/research.html


The NSF PI Meeting Talk
The UTRC Hi-Tech Meeting Talk
3D Computer Vision
and Video Computing

Research at CcvcL
Research Projects at

The City College Visual Computing Lab




C
CVC L
3D video mosaicing, representation and rendering
Multimodal human signature detection
Robotized Sensor networks
3D cargo and vehicle inspection
http://www-cs.engr.ccny.cuny.edu/~zhu/research.html


The NSF PI Meeting Talk
The UTRC Hi-Tech Meeting Talk