CSE 803: Computer Vision

Naveed Sarfraz Khattak

What is Computer Vision?

What is Computer Vision?

• Computer vision is the science and technology of machines that see.

• Concerned with the theory for building artificial systems that obtain information from images.

• The image data can take many forms, such as a video sequence, depth images, views from multiple cameras, or

multi-dimensional data from a medical scanner

Computer Vision

Make computers understand images and videos.

What kind of scene?

Where are the cars?

How far is the building?

…

Components of a computer vision system

Lighting

Scene

Camera

Computer

Scene Interpretation

Srinivasa Narasimhan’s slide

Computer vision vs human vision

What we see What a computer sees

Vision is really hard

• Vision is an amazing feat of natural intelligence

– Visual cortex occupies about 50% of Macaque brain– More human brain devoted to vision than anything else

Is that a queen or a bishop?

Vision is multidisciplinary

From wiki

Computer Graphics

HCI

Why computer vision matters

Safety Health Security

Comfort AccessFun

A little story about Computer Vision

In 1966, Marvin Minsky at MIT asked his undergraduate student Gerald Jay Sussman to “spend the summer linking a camera to a

computer and getting the computer to describe what it saw”. We now know that the problem is slightly more difficult than that. (Szeliski 2009, Computer Vision)

A little story about Computer Vision

In 1966, Marvin Minsky at MIT asked his undergraduate student Gerald Jay Sussman to “spend the summer linking a camera to a

computer and getting the computer to describe what it saw”. We now know that the problem is slightly more difficult than that.

Founder, MIT AI project

A little story about Computer Vision

In 1966, Marvin Minsky at MIT asked his undergraduate student Gerald Jay Sussman to “spend the summer linking a camera to a

computer and getting the computer to describe what it saw”. We now know that the problem is slightly more difficult than that.

Image UnderstandingImage Understanding

Ridiculously brief history of computer vision

• 1966: Minsky assigns computer vision as an undergrad summer project

• 1960’s: interpretation of synthetic worlds

• 1970’s: some progress on interpreting selected images

• 1980’s: ANNs come and go; shift toward geometry and increased mathematical rigor

• 1990’s: face recognition; statistical analysis in vogue

• 2000’s: broader recognition; large annotated datasets available; video processing starts; vision & graphis; vision for HCI; internet vision, etc.

Guzman ‘68

Ohta Kanade ‘78

Turk and Pentland ‘91

How vision is used now• Examples of state-of-the-art

Optical character recognition (OCR)

Digit recognition, AT&T labshttp://www.research.att.com/~yann/

Technology to convert scanned docs to text• If you have a scanner, it probably came with OCR software

License plate readershttp://en.wikipedia.org/wiki/Automatic_number_plate_recognition

Face detection

• Many new digital cameras now detect faces– Canon, Sony, Fuji, …

Smile detection

Sony Cyber-shot® T70 Digital Still Camera

Object recognition (in supermarkets)

LaneHawk by EvolutionRobotics“A smart camera is flush-mounted in the checkout lane, continuously

watching for items. When an item is detected and recognized, the cashier verifies the quantity of items that were found under the basket, and continues to close the transaction. The item can remain under the basket, and with LaneHawk,you are assured to get paid for it… “

Vision-based biometrics

“How the Afghan Girl was Identified by Her Iris Patterns” Read the story wikipedia

Login without a password…

Fingerprint scanners on many new laptops,

other devices

Face recognition systems now beginning to appear more widely

http://www.sensiblevision.com/

Object recognition (in mobile phones)

Point & Find, NokiaGoogle Goggles

The Matrix movies,

Special effects: shape capture

Pirates of the Carribean, Industrial Light and Magic

Special effects: motion capture

Sports

Sportvision first down lineNice explanation on www.howstuffworks.com

http://www.sportvision.com/video.html

Smart cars

• Mobileye [wiki article]– Vision systems currently in high-end BMW, GM,

Volvo models – By 2010: 70% of car manufacturers.

Slide content courtesy of Amnon Shashua

Google cars

http://www.nytimes.com/2010/10/10/science/10google.html?ref=artificialintelligence

Interactive Games: Kinect• Object Recognition: http://www.youtube.com/watch?feature=iv&v=fQ59dXOo63o• Mario: http://www.youtube.com/watch?v=8CTJL5lUjHg• 3D: http://www.youtube.com/watch?v=7QrnwoO1-8A• Robot: http://www.youtube.com/watch?v=w8BmgtMKFbY

• 3D tracking, reconstruction, and interaction: http://research.microsoft.com/en-

us/projects/surfacerecon/default.aspx

Vision in space

Vision systems (JPL) used for several tasks• Panorama stitching• 3D terrain modeling• Obstacle detection, position tracking• For more, read “Computer Vision on Mars” by Matthies et al.

NASA'S Mars Exploration Rover Spirit captured this westward view from atop a low plateau where Spirit spent the closing months of 2007.

Industrial robots

Vision-guided robots position nut runners on wheels

Mobile robots

http://www.robocup.org/NASA’s Mars Spirit Rover

http://en.wikipedia.org/wiki/Spirit_rover

Saxena et al. 2008STAIR at Stanford

Medical imaging

Image guided surgeryGrimson et al., MIT

3D imagingMRI, CT

Prerequisites

• A good working knowledge of C/C++, Java or Matlab

• A good understand of math (linear algebra, basic calculus, basic probability)

• Willing to learn new stuffs (optimization, statistical learning etc.)

34

Course ObjectivesCourse Objectives

• Develop an Understanding of Basic Computer Develop an Understanding of Basic Computer Vision Techniques Through Lecture, Study, and Vision Techniques Through Lecture, Study, and ExercisesExercises

• Develop a Fluency With a Computer Vision (CV) Develop a Fluency With a Computer Vision (CV) Software.Software.

• Implement an Independent Computer Vision Implement an Independent Computer Vision Project Which Demonstrates Your Ability to Project Which Demonstrates Your Ability to Integrate the Mathematical Theory With the Integrate the Mathematical Theory With the Practical Issues Practical Issues

35

CPS-803 Computer Vision CPS-803 Computer Vision

PreRequisitesPreRequisites As already givenAs already given

11 IntroductionIntroduction CV and IP; applications ; images and imaging devices CV and IP; applications ; images and imaging devices ; perspective projection ; binary image processing; perspective projection ; binary image processing

22 Pattern Recognition ConceptsPattern Recognition Concepts; filtering and edge detection; color ; filtering and edge detection; color and shading , including 3D effectsand shading , including 3D effects

33 TextureTexture, IBM Veggie Vision, image database, motion, motion , IBM Veggie Vision, image database, motion, motion vectors, optical flowvectors, optical flow

44 SegmentationSegmentation, 2D matching, 2D matching

55 3D perception3D perception; stereo and structured light; shape from shading, 3D ; stereo and structured light; shape from shading, 3D sensing; 3D Transformations, Camera calibrationsensing; 3D Transformations, Camera calibration

66 3D reconstruction3D reconstruction, 3D Object modelling and matching, 3D Object modelling and matching

77 Augmented realityAugmented reality, review entire course, review entire course

36

Books

TextBookTextBook 1. Computer Vision by Linda Shapiro and 1. Computer Vision by Linda Shapiro and George Stockman, Prentice- Hall 2001George Stockman, Prentice- Hall 2001

ReferenceReference 1.1. Computer Vision: a modern approach, Computer Vision: a modern approach, Forsyth and Ponce, Prentice- Hall 2002Forsyth and Ponce, Prentice- Hall 2002

2.2. Digital Image Processing by R. C. Gonzalez and Digital Image Processing by R. C. Gonzalez and R. E. Woods, Addison Wesley, Second Ed., R. E. Woods, Addison Wesley, Second Ed., 2002.2002.

37

CSE803 Computer Vision

• Credits: 3 • Class:

– On every Thursday

• Phone: 03215109216• Office: Computer Science Building • Office hours: Any working day in the morning or by

appointment. Emails and telephone calls are not good for asking questions.

38

• Homework: There will be 3 homework assignments. • Projects: Four projects. You may use any language

available to you, but C is suggested. • Exams: Three exams are planned: 2 OHTs and final. • Grading: Homework and projects: 30%, all equally

weighted. OHTs 15%each; final: 40%. • Work Deposit: Work will be due at the beginning of the

class. No late work will be accepted. In case of official leave work will be deposited in the next class.

• Final Exam: will be cumulative (complete syllabus) exam of 2 hours.

• Changes: This syllabus is subject to change. The changes will be announced in the class.

39

Table 2: Project and Homework ScheduleTable 2: Project and Homework Schedule

Day Date SubjectThursday 2nd Wk Project 1 (Binary Image Analysis)

HandoutsThursday 4th Wk Project 1 due, Homework 1 HandoutsThursday 5th Wk Homework 1 due, Project 2(Calibration)

HandoutsThursday 7th Wk Project 2 due, Homework 2 HandoutThursday 8th Wk Homework 2 due, Project 3 (Shape

detection) HandoutThursday 10th Wk Project 3 dueThursday 10th Wk Project 4 (Face recognition) HandoutThursday 12th Wk Project 4 dueThursday 13th Wk Homework 3 handed outThursday 14th Wk Homework 3 due

Grading Schemes

• Assignments (10%)

• Quizes (10%)

• Projects(10%)

• OHTs(30%)

• Final Comprehansive Exam (40%)

Project

Student can work in a group of two

Submit your code and project report

Final presentation & in class demos

Late policy: 20% reduction per day if you do not have good reasons

Other Information

My email: khattakn@mcs.edu.pk

My office: Trg Office Shoa ul Qammer Block

Office hours: any time in the Morning or by appointment

Email Me Today

Your background

• Vision, Graphics, machine learning, image processing

• Math (linear algebra, statistics, calculus, optimization, etc.)

• Coding (C++, java, matlab, etc.)

Your research Interest?

Master/Ph.D. (year)?

Why do you take this class?