Computer Vision Spring 2012 15 385 685 Instructor

Computer Vision Spring 2012 15 -385, -685 Instructor: S. Narasimhan Wean Hall 5409 T-R 10: 30 am – 11: 50 am

A Picture is Worth 100 Words

A Picture is Worth 10, 000 Words

A Picture is Worth a Million Words

A Picture is Worth a. . . ? Necker’s Cube Reversal

A Picture is Worth a. . . ? Checker Shadow Illusion – [E. H. Adelson]

A Picture is Worth a. . . ? Checker Shadow Illusion – [E. H. Adelson]

Human Vision • Can do amazing things like: • • Recognize people and objects Navigate through obstacles Understand mood in the scene Imagine stories • But still is not perfect: • • Suffers from Illusions Ignores many details Ambiguous description of the world Doesn’t care about accuracy of world

Computer Vision What we see What a computer sees

Computer Vision What we see What a computer sees

What is Computer Vision? • Inverse Optics • Intelligent interpretation of Imagery • Building a Visual Cortex • No matter what your definition is… – Vision is hard. – But is fun. . .

Components of a Computer Vision System Camera Lighting Computer Scene Interpretation

Topics covered

Image Processing Fourier Transform Sampling, Convolution Image enhancement Feature detection

Surface Reflectance [CURET]

Lightness and Perception Checker Shadow Illusion – [E. H. Adelson]

Understanding Optical Illusions Which is bigger? Dots White? Or Black? Straight Lines? Spinning Wheels?

3 D from Shading Shape from Shading Photometric Stereo

Cameras and their Optics Today’s Digital Cameras The Camera Obscura

Biological Cameras Human Eye Mosquito Eye

Optical Flow

Tracking

Binocular Stereo

Range Scanning and Structured Light

Range Scanning and Structured Light

Microsoft Kinect IR LED Emitter RGB Camera IR Camera

Statistical Techniques Least Squares Fitting

Face detection

Face Recognition • Principle Components Analysis (PCA) • Face Recognition

Some Recent Trends in Vision Novel Cameras and Displays *** Topics change every year

Advanced Related Courses at CMU • Graduate Level Computer Vision (Hebert, Fall) • Computational Photography (Efros, Fall) • Physics-based methods in Comp Vision (Narasimhan) • Learning-based methods in Comp. Vision (Efros) • Geometry-based methods in Comp. Vision (Hebert)

Course Logistics

Text and Reading • Class Notes (required) • Text, Robot Vision, B. K. P. Horn, MIT Press (recommended) • Supplementary Material (papers, tutorials)

Course Schedule 1/17/2012: 1/19/2012: Introduction and Course Fundamentals Matlab Review PART 1 : Signal and Image Processing 1/24/2012 1/26/2012: 1/31/2012: 2/2/2012: 2/7/2012: 1 D Signal Processing 2 D Image Processing Image Pyramids and Sampling Edge Detection Hough Transform [Project 1 OUT] PART 2: Physics of the World 2/9/2012: 2/14/2012: 2/16/2012: 2/21/2012: Surface appearance and BRDF Photometric Stereo Shape from Shading Direct and Global Illumination [Project 1 DUE, Project 2 OUT] PART 4 : 3 D Geometry 2/23/2012: 2/28/2012: 3/1/2012: 3/6/2012: 3/8/2012: 3/20/2012: 3/22/2012: 3/27/2012: Image Formation and Projection Motion and Optical Flow Lucas Kanade Tracking Midterm Review Midterm Exam Binocular Stereo 1 Binocular Stereo 2 Structured Light and Range Imaging [Project 2 DUE Project 3 OUT] [Project 3 DUE, Project 4 OUT]

Course Schedule PART 4 : Statistical Techniques 3/29/2012: 4/03/2012: 4/05/2012: 4/10/2012: 4/12/2012: Feature Detection 1 Classification 2 Principle Components Analysis Applications of PCA [Project 4 DUE] [Project 5 OUT] [Grad project description due] PART 6: Trends and Challenges in Vision Research 4/17/2012: 4/24/2012: 4/26/2012: 5/1/2012: Image Based Rendering Novel Cameras and Displays Optical Illusions Open challenges in vision research 5/3/2012: 5/8/2012: DUE] 5/13/2012: Project presentations by undergraduate students Project presentations by graduate students [Project 5 DUE] [Grad Project 6 Final Grades Due *** Use as a guide…changes possible

Prerequisites • Basic Linear Algebra, Probability, Calculus Required • Basic Data structures/Programming knowledge • No Prior knowledge of Computer Vision Required

Grading • FIVE Projects – 90 % (15%, 20%, 20%) • ONE Midterm – 10 % • ONE Extra Project for Graduate Students – 20 % • Most projects include analytic and programming parts. • All projects must be done individually. • Programming Environment – Matlab. • Projects due before midnight on due-date. • Written parts due in class on the due-date. • 3 Late Days for the semester. No more extensions. • Class attendance – 5 % extra credit

Office Hours Narasimhan: Smith Hall 223, By Appointment Email: srinivas@cs. cmu. edu Supreeth Achar: Wednesdays 6: 00 pm – 8: 00 pm Email: supreeth@cmu. edu Gunhee Kim: Thursdays, Thursdays 6: 00 pm – 8: 00 pm Email: gunhee@cs. cmu. edu • Technical Questions: Post on bboard. TAs will answer.