Presentation is loading. Please wait.

Presentation is loading. Please wait.

3D Computer Vision and Video Computing Introduction Instructor: Zhigang Zhu City College of New York CSc I6716 Fall 2010 3D Computer.

Similar presentations


Presentation on theme: "3D Computer Vision and Video Computing Introduction Instructor: Zhigang Zhu City College of New York CSc I6716 Fall 2010 3D Computer."— Presentation transcript:

1 3D Computer Vision and Video Computing Introduction Instructor: Zhigang Zhu City College of New York zzhu@ccny.cuny.edu CSc I6716 Fall 2010 3D Computer Vision Introduction

2 3D Computer Vision and Video Computing Course Information n Basic Information: l Course participation l Books, notes, etc. l Web page – check often! n Homework, Assignment, Exam l Homework and exams l Grading n Goal l What I expect from you l What you can expect from me l Resources

3 3D Computer Vision and Video Computing Book n Textbook l “Introductory Techniques for 3-D Computer Vision” Trucco and Verri, 1998 n Additional readings when necessary l “Computer Vision – A Modern Approach” Forsyth and Ponce, 2003 l “Three-Dimensional Computer Vision: A Geometric Viewpoint” O. Faugeras, 1998 l “Image Processing, Analysis and Machine VIsion” Sonika, Hlavac and Boyle, 1999 n On-Line References

4 3D Computer Vision and Video Computing Prequisites n Linear Algebra n A little Probability and Statistics n Programming Experience n Reading Literature (A little) n An Inquisitive Nature (Curiosity) n No Fear

5 3D Computer Vision and Video Computing Course Web Page n Lectures available in Powerpoint format n All homework assignments will be distributed over the web n Additional materials and pointers to other web sites n Course bulletin board contains last minute items, changes to assignments, etc. l CHECK IT OFTEN! l You are responsible for material posted there http://www-cs.engr.ccny.cuny.edu/~zhu/CSCI6716-2009/VisionCourse-Fall-2010.html

6 3D Computer Vision and Video Computing Course Outline n Complete syllabus on the web pages (28 meets,10 lectures) n Rough Outline ( 3D Computer Vision): Part 1. Vision Basics (Total 6) 1. Introduction (1) 2. Image Formation and Processing (1) (hw 1, matlab) 3-4. Features and Feature Extraction (4) ( hw 2) Part 2. 3D Vision (Total 15) 5. Camera Models (3) 6. Camera Calibration (3)(hw 3) 7. Stereo Vision (4) (project assignments) 8. Visual Motion (4) (hw 4) Part 3. Exam and Projects (Total 7) 9. Project topics and exam review/discussion (3) 10. Midterm exam (1) 11. Project presentations (3)

7 3D Computer Vision and Video Computing Grading n Homework (4): 40% n Exam (midterm): 40% n Course Project + Presentation: 20% l Groups (I or 2 students) for discussions l Experiments – independently + collaboratively l Written Report - independently + collaboratively n All homework must be yours….but you can work together until the final submission n Teaching Assistant: l Mr. Wai L. Khoo

8 3D Computer Vision and Video Computing C++ and Matlab n C++ l For some simple computation, you may use C++ n Matlab l An interactive environment for numerical computation l Available on Computer Labs machines (both Unix and Windows) u Matlab primer available on line (web page) u Pointers to on-line manuals also available l Good rapid prototyping environment n Use C++ and/or Matlab for your homework assignments and project(s); However Java will also be fine

9 3D Computer Vision and Video Computing Course Goals and Questions n What makes (3D) Computer Vision interesting ? l Image Modeling/Analysis/Interpretation u Interpretation is an Artificial Intelligence Problem F Sources of Knowledge in Vision F Levels of Abstraction u Interpretation often goes from 2D images to 3D structures F since we live in a 3D world l Image Rendering/Synthesis/Composition u Image Rendering is a Computer Graphics problem u Rendering is from 3D model to 2D images 2D images 3D world CVCG

10 3D Computer Vision and Video Computing Related Fields n Image Processing: image to image n Computer Vision: Image to model n Computer Graphics: model to image n Pattern Recognition: image to class l image data mining/ video mining n Artificial Intelligence: machine smarts l Machine perception n Photogrammetry: camera geometry, 3D reconstruction n Medical Imaging: CAT, MRI, 3D reconstruction (2 nd meaning) n Video Coding: encoding/decoding, compression, transmission n Physics & Mathematics: basics n Neuroscience: wetware to concept n Computer Science: programming tools and skills? All three are interrelated! AI Applications basics

11 3D Computer Vision and Video Computing Applications n Visual Inspection (*) n Robotics (*) n Intelligent Image Tools n Image Compression (MPEG 1/2/4/7) n Document Analysis (OCR) n Image and Video on the Web n Virtual Environment Construction (*) n Environment (*) n Media and Entertainment n Medicine n Astronomy n Law Enforcement (*) l surveillance, security n Traffic and Transportation (*) n Tele-Conferencing and e-Learning (*) n Human Computer Interaction (HCI)

12 3D Computer Vision and Video Computing Job Markets n Homeland Security l Port security – cargo inspection, human ID, biometrics l Facility security – Embassy, Power plant, bank l Surveillance – military or civilian n Media Production l Cartoon / movie/ TVs/ photography l Multimedia communication, video conferencing n Research in image, vision, graphics, virtual reality l 2D image processing l 3D modeling, virtual walk-thorugh n Consumer/ Medical Industries l Video cameras, Camcorders, Video phone l Medical imaging 2D -> 3D

13 3D Computer Vision and Video Computing IP vs CV n Image processing (mainly in 2D) l Image to Image transformations l Image to Description transformations l Image Analysis - extracting quantitative information from images: u Size of a tumor u distance between objects u facial expression l Image restoration. Try to undo damage u needs a model of how the damage was made l Image enhancement. Try to improve the quality of an image l Image compression. How to convey the most amount of information with the least amount of data

14 3D Computer Vision and Video Computing What is Computer Vision? Vision is the art of seeing things invisible. -Jonathan Swift (1667-1745) "Thoughts on Various Subjects" Miscellanies in Prose and Verse (published with Alexander Pope), vol. 1, 1727 n Computer vision systems attempt to construct meaningful and explicit descriptions of the world depicted in an image. n Determining from an image or image sequence: l The objects present in the scene l The relationship between the scene and the observer l The structure of the three dimensional (3D) space

15 3D Computer Vision and Video Computing Cues to Space and Time n Spectral Characteristics l Intensity, contrast, colors and their l Spatial distributions n 2D Shape of Contours n Linear Perspective n Highlights and Shadows n Occlusions n Organization n Motion parallax and Optical Flow n Stereopsis and sensor convergence Directly Measurable in an Image

16 3D Computer Vision and Video Computing Cues to Space and Time n Surface connectivity n 3D Volume n Hidden sides and parts n Identity (Semantic category) n Absolute Size n Functional Properties n Goals, Purposes, and Intents n Organization n Trajectories Inferred Properties

17 3D Computer Vision and Video Computing Cues to Depth n Question: l How do we perceive the three-dimensional properties of the world when the images on our retinas are only two- dimensional? n Stereo is not the entire story!

18 3D Computer Vision and Video Computing Cues to Depth n Monocular cues to the perception of depth in images l Interposition: occluding objects appear closer than occluded objects l Relative size: when objects have approximately the same physical size, the larger object appears closer l Relative height: objects lower in the image appear closer l Linear Perspective: objects appear smaller as they recede into the distance u texture gradients l Aerial Perspective: change in color and sharpness as object recede into the distance l Illumination gradients: gradients and shadow lend a sense of depth l Relative Motion: faster moving objects appear closer

19 3D Computer Vision and Video Computing Cues to Depth n Physiological cues to depth: l Focus (accomodation): change in curvature of the lens for objects at different depths l Convergence: eyes turn more inward (nasal) for closer objects l Retinal disparity: greater for objects further away

20 3D Computer Vision and Video Computing Interposition

21 3D Computer Vision and Video Computing Interposition

22 3D Computer Vision and Video Computing Interposition

23 3D Computer Vision and Video Computing Different viewpoint

24 3D Computer Vision and Video Computing Different viewpoint Edgar Degas: Dance Class at the Opéra, 1872

25 3D Computer Vision and Video Computing Different viewpoint Edgar Degas: Green Dancer, c.1880

26 3D Computer Vision and Video Computing Different viewpoint Edgar Degas: Frieze of Dancers, c.1895

27 3D Computer Vision and Video Computing Different viewpoint Edgar Degas: Frieze of Dancers, c.1895

28 3D Computer Vision and Video Computing Different viewpoint Edgar Degas: Frieze of Dancers, c.1895

29 3D Computer Vision and Video Computing Different viewpoint Edgar Degas: Frieze of Dancers, c.1895

30 3D Computer Vision and Video Computing Different viewpoint Edgar Degas: Frieze of Dancers, c.1895

31 3D Computer Vision and Video Computing Different viewpoint Edgar Degas: Frieze of Dancers, c.1895

32 3D Computer Vision and Video Computing Different viewpoint Edgar Degas: Frieze of Dancers, c.1895

33 3D Computer Vision and Video Computing Different viewpoint Edgar Degas: Frieze of Dancers, c.1895

34 3D Computer Vision and Video Computing Different viewpoint Edgar Degas: Frieze of Dancers, c.1895

35 3D Computer Vision and Video Computing Aerial Perspective n Constable

36 3D Computer Vision and Video Computing Aerial Perspective n Classic Chinese Paintings

37 3D Computer Vision and Video Computing Absolute Size

38 3D Computer Vision and Video Computing Relative Size

39 3D Computer Vision and Video Computing Relative Size

40 3D Computer Vision and Video Computing Absolute Size

41 3D Computer Vision and Video Computing Relative Size

42 3D Computer Vision and Video Computing Light and Surfaces

43 3D Computer Vision and Video Computing Light and Surfaces

44 3D Computer Vision and Video Computing Light and Surfaces

45 3D Computer Vision and Video Computing Light and Surfaces

46 3D Computer Vision and Video Computing Light and Surfaces

47 3D Computer Vision and Video Computing Light and Surfaces n C. H. Stoelting Company

48 3D Computer Vision and Video Computing Light and Surfaces

49 3D Computer Vision and Video Computing Light and Surfaces

50 3D Computer Vision and Video Computing Light and Surfaces

51 3D Computer Vision and Video Computing Light and Surfaces

52 3D Computer Vision and Video Computing The Effect of Perspective

53 3D Computer Vision and Video Computing Texture Gradient Sunflowers in Fargo, ND Photo by Bruce Fitz http://www.ars.usda.gov/is/graphics/photos/

54 3D Computer Vision and Video Computing Texture Gradients

55 3D Computer Vision and Video Computing Edges

56 3D Computer Vision and Video Computing Texture Edges

57 3D Computer Vision and Video Computing Who Knows

58 3D Computer Vision and Video Computing Next Anyone who isn't confused really doesn't understand the situation. --Edward R. Murrow Next: Image Formation Reading: Ch 1, Ch 2- Section 2.1, 2.2, 2.3, 2.5 Questions: 2.1. 2.2, 2.3, 2.5 Exercises: 2.1, 2.3, 2.4


Download ppt "3D Computer Vision and Video Computing Introduction Instructor: Zhigang Zhu City College of New York CSc I6716 Fall 2010 3D Computer."

Similar presentations


Ads by Google