CS 678 Computer Vision Instructor Guodong Guomail wvu

CS 678 Computer Vision Instructor: Guodong. Guo@mail. wvu. edu

Welcome! Introductions n Administrative Matters n Course Outline n Applications of Computer Vision n Computer Vision Focus n Computer Vision Publications n Journals n Conferences n

Instructor Guodong Guo n http: //cs. wisc. edu/~gdguo n Major Research Interest n n Computer Vision, Machine Learning, Pattern Recognition, Biometrics, Multimedia, and HCI

About You … What do you know already? C/C++ (Visual C++) n Matlab n Images n Open. CV http: //sourceforge. net/projects/opencvlibrar y/ Install Open. CV in your PC or laptop, Read the manual introduction Try to load and save images (homework n

Outline Introductions n Administrative Matters n Course Outline n Applications of Computer Vision n Computer Vision Focus n Computer Vision Publications n

Meeting Times n Lectures W 5: 00 -7: 20 pm n Room: ESB 215 n n Office hours Thursday 4: 00 -6: 00 pm (AER 345, or AER 321) n Or by appointment n

Grading n The final grade depends on: Homework and programming assignments: 40% n Exam: 40% n Final project (may include class presentation): 20% n Presentation (not determined) n Class participation: (-5%, if absent = 3 times or more) n Extra: 1~10% (for creative ideas, paper submission based on this course, etc. ) n

Textbook n Computer Vision: Algorithms and Applications, Richard Szeliski, http: //szeliski. org/Book/

Optional Textbook n Computer Vision: A Modern Approach, 2 th Edition, by David Forsyth and Jean Ponce, Prentice Hall, 2003

Optional Textbook n Introductory Techniques for 3 -D Computer Vision, E. Trucco and A. Verri, Prentice Hall, 1998. ISBN 0 -13 -261108 -2

Look at the Syllabus Course Objectives n Expected learning outcomes n Detailed list of topics (maybe updated) n

Outline Introductions n Administrative Matters n Course Outline n Applications of Computer Vision n Computer Vision Focus n Computer Vision Publications n

What is Computer Vision? n Given an image or more, extract properties of the 3 D world • Traffic scene • Number of vehicles • Type of vehicles • Location of closest obstacle • Assessment of congestion • Location of the scene captured • …

Computer Vision vs. Graphics n 3 D 2 D implies information loss graphics vision sensitivity to errors n need for models n

Computer Vision vs. Machine Learning Machine learning is a scientific discipline that is concerned with the design and development of algorithms that allow computers to change behavior based on data, such as from sensor databases (from Wikipedia) n A major focus of machine learning research is to automatically learn to recognize complex patterns and make intelligent decisions based on data. n

Computer Vision vs. Machine Learning is very useful for Computer Vision (e. g. , learning for vision) n Computer Vision is more than just learning n Modeling n Example based learning n In Machine Learning, it usually does not care about how to obtain the data or sensors n In Computer Vision, we care how to obtain n

Vision n Vision is the process of discovering what is present in the world and where it is by looking.

Computer Vision n Computer Vision is the study of analysis of pictures and videos in order to achieve results similar to those as by people.

Why Computer Vision An image is worth 1000 words n Many biological systems rely on vision n The world is 3 D and dynamic n Cameras and computers are cheap n … n

Computer Vision Examples Finding People in images Problem 1: Given an image I Question: Does image I contain an image of a person?

“Yes” Instances

“No” Instances

Some Computer Vision Topics

Imaging Geometry

Camera Modeling Pinhole Cameras n Lenses n Camera Parameters and Calibration n

Image Filtering and Enhancing Linear Filters and Convolution n Image Smoothing n Edge Detection n Pyramids n

Image Filtering and Enhancing (cont. )

Region Segmentation

Color

Texture

Image Restoration Original Synthetic

Perceptual Organization

Perceptual Organization

Shape Analysis

Stereo

Motion and Optical Flow

High Level Vision

Image Mosaic

One Very Successful Example n Face detection in a digital camera n The camera detects faces in a scene and then automatically focuses (AF) and optimizes exposure (AE) and, if needed, flash output.

Outline Introductions n Administrative Matters n Course Outline n Applications of Computer Vision n Computer Vision Focus n Computer Vision Publications n

Applications n n n n autonomous cars, planes, missiles, robots, . . . space exploration aid to the blind, ASL recognition manufacturing, quality control surveillance, security, biometrics image retrieval medical imaging and analysis. . .

Current State of the Art Earth viewers (3 D modeling) Image from Microsoft’s Virtual Earth (see also: Google Earth)

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 http: //www. research. att. com/~yann/ License plate readers http: //en. wikipedia. org/wiki/Automatic_number_plate_recognition

Face detection n Many new digital cameras now detect faces n Canon, Sony, Fuji, …

Smile detection? Sony Cyber-shot® T 70 Digital Still Camera

Object recognition (in supermarkets) Lane. Hawk by Evolution. Robotics “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 Lane. Hawk, you are assured to get paid for it… “

Face recognition Who is she?

Vision-based biometrics “How the Afghan Girl was Identified by Her Iris Patterns” Read the story

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) n This is becoming real: Microsoft Research n Point & Find, Nokia n

Special effects: shape capture The Matrix movies, ESC Entertainment, XYZRGB, NRC

Special effects: motion capture Pirates of the Carribean, Industrial Light and Magic Click here for interactive demo

Smart cars n Slide content courtesy of Amnon Shashua Mobileye n n Vision systems currently in high-end BMW, GM, Volvo models By 2010: 70% of car manufacturers.

Vision-based interaction (and games) Digimask: put your face on a 3 D avatar. Nintendo Wii has camera-based IR tracking built in. See Lee’s work at CMU on clever tricks on using it to create a multi-touch display! “Game turns moviegoers into Human Joysticks”, CNET Camera tracking a crowd, based on this work.

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 3 D terrain modeling Obstacle detection, position tracking For more, read “Computer Vision on Mars” by Matthies et al.

Robotics NASA’s Mars Spirit Rover http: //en. wikipedia. org/wiki/Spirit_rover http: //www. robocup. org/

Medical imaging 3 D imaging MRI, CT Image guided surgery Grimson et al. , MIT

Current state of the art n You just saw examples of current systems. n This is a very active research area, and rapidly changing n n Many new apps in the next 5 years To learn more about vision applications and companies n David Lowe maintains an excellent overview of vision companies n http: //www. cs. ubc. ca/spider/lowe/vision. html

Outline Introductions n Administrative Matters n Course Outline n Applications of Computer Vision n Computer Vision Focus n Computer Vision Publications n

Computer Vision focuses on: What information should be extracted? n How can it be extracted? n How should it be represented? n How can it be used to achieve the goal? n

Related disciplines Image processing n Pattern recognition n Photogrammetry n Computer graphics n Artificial intelligence n Machine learning n Projective geometry n Control theory n

Active Research Topics Object recognition n Human behavior analysis n Internet and computer vision n Biometrics and soft biometrics n Large scale 3 D reconstruction (city level) n Medical image processing n Vision for robotics n … n

Outline Introductions n Administrative Matters n Course Outline n Applications of Computer Vision n Computer Vision Focus n Computer Vision Publications n

Computer Vision Publications n Journals n IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI) n #1 IEEE, Thompson-ISI impact factor: 5. 96 n #1 in both electrical engineering and artificial intelligence n #3 in all of computer science n Internal Journal of Computer Vision (IJCV) n ISI impact factor: 5. 358, Rank 2 of 94 in “CS, artificial intelligence IEEE Trans. on Image Processing n… n

Importance of CV n From these major journal rankings, we can see the importance of Computer Vision research in the whole areas of Computer Science n Electrical Engineering n

Computer Vision Publications n Conferences International Conference on Computer Vision (ICCV), once every two years n Conf. of Computer Vision and Pattern Recognition (CVPR), once a year n Europe Conference on Computer Vision (ECCV), once every two years n… n