CS 143: Introduction to Computer Vision
Instructor: James Hays TAs: Hari Narayanan (HTA), Libin Geoffrey Sun, Greg Yauney, Bryce Aebi, Charles Yeh, Kurt Spindler
Image by [Link]
Todays Class
Introductions What is Computer Vision? Computer Vision at Brown Specifics of this course Questions
A bit about me
Thesis: Large Scale Scene Matching for Graphics and Vision
Scene Completion
[Hays and Efros. Scene Completion Using Millions of Photographs. SIGGRAPH 2007 and CACM October 2008.]
Nearest neighbor scenes from database of 2.3 million photos
Graph cut + Poisson blending
My Research
An Empirical Study of Context in Object Detection
Categories of the SUN database
CS 143 TAs Hari Narayanan (HTA) Libin Geoffrey Sun Greg Yauney Bryce Aebi Charles Yeh Kurt Spindler
What is Computer Vision?
What are examples of computer vision being used in the world?
Computer Vision
Make computers understand images and video.
What kind of scene? Where are the cars? How far is the building?
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?
Why computer vision matters
Safety
Health
Security
Comfort
Fun
Access
Ridiculously brief history of computer vision
1966: Minsky assigns computer vision as an undergrad summer project 1960s: interpretation of synthetic worlds 1970s: some progress on interpreting selected images 1980s: ANNs come and go; shift toward geometry and increased mathematical rigor 1990s: face recognition; statistical analysis in vogue 2000s: broader recognition; large annotated datasets available; video processing starts 2030s: robot uprising?
Guzman 68
Ohta Kanade 78
Turk and Pentland 91
How vision is used now
Examples of state-of-the-art
Some of the following slides by Steve Seitz
Optical character recognition (OCR)
Technology to convert scanned docs to text
If you have a scanner, it probably came with OCR software
Digit recognition, AT&T labs [Link]
License plate readers
[Link]
Face detection
Many new digital cameras now detect faces
Canon, Sony, Fuji,
Smile detection
Sony Cyber-shot T70 Digital Still Camera
3D from thousands of images
Building Rome in a Day: Agarwal et al. 2009
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
[Link]
Object recognition (in mobile phones)
Point & Find, Nokia Google Goggles
Special effects: shape capture
The Matrix movies, ESC Entertainment, XYZRGB, NRC
Special effects: motion capture
Pirates of the Carribean, Industrial Light and Magic
Sports
Sportvision first down line Nice explanation on [Link] [Link]
Smart cars
Slide content courtesy of Amnon Shashua
Mobileye
Vision systems currently in high-end BMW, GM, Volvo models By 2010: 70% of car manufacturers.
Google cars
Oct 9, 2010. "Google Cars Drive Themselves, in Traffic". The New York Times. John Markoff June 24, 2011. "Nevada state law paves the way for driverless cars". Financial Post. Christine Dobby Aug 9, 2011, "Human error blamed after Google's driverless car sparks five-vehicle crash". The Star (Toronto)
Interactive Games: Kinect
Object Recognition: [Link] Mario: [Link] 3D: [Link] Robot: [Link]
Vision in space
NASA'S Mars Exploration Rover Spirit captured this westward view from atop a low plateau where Spirit spent the closing months of 2007.
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.
Industrial robots
Vision-guided robots position nut runners on wheels
Mobile robots
NASAs Mars Spirit Rover [Link]
[Link]
Saxena et al. 2008 STAIR at Stanford
Medical imaging
3D imaging MRI, CT
Image guided surgery Grimson et al., MIT
Computer Vision and Nearby Fields
Computer Graphics: Models to Images Comp. Photography: Images to Images Computer Vision: Images to Models
Computer Vision at Brown
Pedro Felzenszwalb James Hays Erik Sudderth
Thomas Serre
Stu Geman
David Mumford
Gabriel Taubin
David Cooper
Ben Kimia
Joe Mundy
See also: Brown Center for Vision Research (CVR)
Course Syllabus (tentative)
[Link]
Grading
80% programming projects (5 total) 20% quizzes (2 total)
Computer Vision
Machine Learning
Robotics
Scope of CS 143
Image Processing Feature Matching Recognition
Human Computer Interaction
Graphics
Medical Imaging
Computational Photography Optics
Neuroscience
Course Topics
Interpreting Intensities
What determines the brightness and color of a pixel? How can we use image filters to extract meaningful information from the image?
Correspondence and Alignment
How can we find corresponding points in objects or scenes? How can we estimate the transformation between them?
Grouping and Segmentation
How can we group pixels into meaningful regions?
Categorization and Object Recognition
How can we represent images and categorize them? How can we recognize categories of objects?
Advanced Topics
Action recognition, 3D scenes and context, human-in-the-loop vision
Textbook
[Link]
Prerequisites
Linear algebra, basic calculus, and probability Experience with image processing or Matlab will help but is not necessary
Projects
Image Filtering and Hybrid Images Local Feature Matching Scene Recognition with Bag of Words Object Detection with a Sliding Window Boundary Detection with Sketch Tokens
Proj1: Image Filtering and Hybrid Images
Implement image filtering to separate high and low frequencies Combine high frequencies and low frequencies from different images to create an image with scale-dependent interpretation
Proj2: Local Feature Matching
Implement interest point detector, SIFT-like local feature descriptor, and simple matching algorithm. Feed feature matches to a structure-from-motion system
Proj3: Scene Recognition with Bag of Words
Quantize local features into a vocabulary, describe images as histograms of visual words, train classifiers to recognize scenes based on these histograms.
Proj4: Object Detection with a Sliding Window
Train a face detector based on positive examples and mined hard negatives, detect faces at multiple scales and suppress duplicate detections.
Proj5: Boundary Detection with Sketch Tokens
Quantize human-annotated boundaries into sketch tokens, train a multi-way classifier to recognize such tokens.
![Scene Completion
[Hays and Efros. Scene Completion Using Millions of Photographs.
SIGGRAPH 2007 and CACM October 2008.]](https://screenshots.scribd.com/Scribd/252_100_85/189/215330478/5.jpeg)
