Тексты на английском
<<  The Art of Research: Digital theses in the arts The Julian calendar  >>
Computer Vision
Computer Vision
Announcements
Announcements
Course Schedule – Done
Course Schedule – Done
Course Schedule
Course Schedule
Binocular Stereo
Binocular Stereo
Optical Flow
Optical Flow
Range Scanning and Structured Light
Range Scanning and Structured Light
Binocular Stereo Lecture #14
Binocular Stereo Lecture #14
Recovering 3D from Images
Recovering 3D from Images
Visual Cues for 3D
Visual Cues for 3D
Visual Cues for 3D
Visual Cues for 3D
Visual Cues for 3D
Visual Cues for 3D
Visual Cues for 3D
Visual Cues for 3D
Visual Cues for 3D
Visual Cues for 3D
Stereo Reconstruction
Stereo Reconstruction
Why do we have two eyes
Why do we have two eyes
1. Two is better than one
1. Two is better than one
2. Depth from Convergence
2. Depth from Convergence
3. Depth from binocular disparity
3. Depth from binocular disparity
Computer Vision
Computer Vision
Disparity and Depth
Disparity and Depth
Disparity and Depth
Disparity and Depth
Vergence
Vergence
Binocular Stereo
Binocular Stereo
Binocular Stereo
Binocular Stereo
Stereo Correspondence
Stereo Correspondence
Stereo Image Rectification
Stereo Image Rectification
Stereo Image Rectification
Stereo Image Rectification
Stereo Rectification
Stereo Rectification
Basic Stereo Algorithm
Basic Stereo Algorithm
Size of Matching window
Size of Matching window
Stereo Results
Stereo Results
Results with Window Search
Results with Window Search
Better methods exist
Better methods exist
Stereo Example
Stereo Example
Stereo Example
Stereo Example
Stereo Example
Stereo Example
Stereo Matching
Stereo Matching
Next Class
Next Class

Презентация: «Computer Vision». Автор: . Файл: «Computer Vision.ppt». Размер zip-архива: 4064 КБ.

Computer Vision

содержание презентации «Computer Vision.ppt»
СлайдТекст
1 Computer Vision

Computer Vision

Spring 2006 15-385,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm Lecture #14

2 Announcements

Announcements

Homework 4 went out Tuesday. Due April 4. Start early.

3 Course Schedule – Done

Course Schedule – Done

1/17/2006: Introduction and Course Fundamentals PART 1 : Cameras and Imaging 1/19/2006: Image Formation and Projection 1/24/2006: Matlab Review 1/26/2006: Image Sensing [Homework 1 OUT] PART 2 : Signal and Image Processing 1/31/2006: Binary Image Processing 2/2/2006: 1D Signal Processing [Homework 1 DUE; Homework 2 OUT] 2/7/2006: 2D Image Processing 2/9/2006: Edge Detection 2/14/2006: Image Pyramids 2/16/2006: Hough Transform [Homework 2 DUE; Homework 3 OUT] PART 3: Physics of the World 2/21/2006: Basic Principles of Radiometry 2/23/2006: Retinex Theory 2/28/2006: Surface Reflectance and BRDF 3/2/2006: Photometric Stereo [Homework 3 DUE] 3/7/2006: Midterm Review 3/9/2006: Midterm Exam 3/13/2006: Midterm Grades Due 3/21/2006: Shape from Shading [Homework 4 OUT]

4 Course Schedule

Course Schedule

PART 4 : 3D Geometry 3/23/2006: Binocular Stereo 1 3/28/2006: Binocular Stereo 2 3/30/2006: Motion and Optical Flow 4/4/2006: Line Drawing [Homework 4 DUE; Homework 5 OUT] 4/6/2006: Structured Light PART 5 : Statistical Techniques 4/11/2006: Linear Least Squares 4/13/2006: Principle Components Analysis 4/18/2006: Applications of PCA [Homework 5 DUE; Homework 6 OUT] PART 6: Current Trends and Challenges in Vision Research 4/27/2006: Novel Cameras and Displays 5/2/2006: Open challenges in vision research 5/4/2006: Review Class [Homework 6 DUE] 5/9/2006: Final Exam 5/18/2006: Final Grades Due

*** Use as a guide…changes possible

5 Binocular Stereo

Binocular Stereo

6 Optical Flow

Optical Flow

7 Range Scanning and Structured Light

Range Scanning and Structured Light

8 Binocular Stereo Lecture #14

Binocular Stereo Lecture #14

9 Recovering 3D from Images

Recovering 3D from Images

How can we automatically compute 3D geometry from images? What cues in the image provide 3D information?

10 Visual Cues for 3D

Visual Cues for 3D

Shading

Merle Norman Cosmetics, Los Angeles

11 Visual Cues for 3D

Visual Cues for 3D

Shading Texture

The Visual Cliff, by William Vandivert, 1960

12 Visual Cues for 3D

Visual Cues for 3D

Shading Texture Focus

From The Art of Photography, Canon

13 Visual Cues for 3D

Visual Cues for 3D

Shading Texture Focus Motion

14 Visual Cues for 3D

Visual Cues for 3D

Shading Texture Focus Motion

Others: Highlights Shadows Silhouettes Inter-reflections Symmetry Light Polarization ...

Shape From X X = shading, texture, focus, motion, ... We’ll focus on the motion cue

15 Stereo Reconstruction

Stereo Reconstruction

The Stereo Problem Shape from two (or more) images Biological motivation

known camera viewpoints

16 Why do we have two eyes

Why do we have two eyes

Cyclope vs. Odysseus

17 1. Two is better than one

1. Two is better than one

18 2. Depth from Convergence

2. Depth from Convergence

Human performance: up to 6-8 feet

19 3. Depth from binocular disparity

3. Depth from binocular disparity

P: converging point

C: object nearer projects to the outside of the P, disparity = +

F: object farther projects to the inside of the P, disparity = -

Sign and magnitude of disparity

20 Computer Vision
21 Disparity and Depth

Disparity and Depth

scene

22 Disparity and Depth

Disparity and Depth

scene

inverse proportional to depth

disparity increases with baseline b

23 Vergence

Vergence

Field of view decreases with increase in baseline and vergence Accuracy increases with baseline and vergence

24 Binocular Stereo

Binocular Stereo

scene point

image plane

optical center

25 Binocular Stereo

Binocular Stereo

Basic Principle: Triangulation Gives reconstruction as intersection of two rays

Requires calibration point correspondence

26 Stereo Correspondence

Stereo Correspondence

Determine Pixel Correspondence Pairs of points that correspond to same scene point

Epipolar Constraint Reduces correspondence problem to 1D search along conjugate epipolar lines Java demo: http://www.ai.sri.com/~luong/research/Meta3DViewer/EpipolarGeo.html

27 Stereo Image Rectification

Stereo Image Rectification

28 Stereo Image Rectification

Stereo Image Rectification

reproject image planes onto a common plane parallel to the line between optical centers pixel motion is horizontal after this transformation C. Loop and Z. Zhang. Computing Rectifying Homographies for Stereo Vision. IEEE Conf. Computer Vision and Pattern Recognition, 1999.

29 Stereo Rectification

Stereo Rectification

30 Basic Stereo Algorithm

Basic Stereo Algorithm

compare with every pixel on same epipolar line in right image

pick pixel with minimum match cost

31 Size of Matching window

Size of Matching window

Better results with adaptive window T. Kanade and M. Okutomi, A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment,, Proc. International Conference on Robotics and Automation, 1991. D. Scharstein and R. Szeliski. Stereo matching with nonlinear diffusion. International Journal of Computer Vision, 28(2):155-174, July 1998

Effect of window size

Smaller window Good/bad ? Larger window Good/bad ?

32 Stereo Results

Stereo Results

Data from University of Tsukuba

Scene

Ground truth

33 Results with Window Search

Results with Window Search

Window-based matching (best window size)

Ground truth

34 Better methods exist

Better methods exist

..

State of the art method Boykov et al., Fast Approximate Energy Minimization via Graph Cuts, International Conference on Computer Vision, September 1999.

Ground truth

35 Stereo Example

Stereo Example

input image (1 of 2)

36 Stereo Example

Stereo Example

H. Tao et al. “Global matching criterion and color segmentation based stereo”

37 Stereo Example

Stereo Example

H. Tao et al. “Global matching criterion and color segmentation based stereo”

38 Stereo Matching

Stereo Matching

Features vs. Pixels? Do we extract features prior to matching?

Julesz-style Random Dot Stereogram

39 Next Class

Next Class

Binocular Stereo (relative and absolute orientation) Reading: Horn, Chapter 13.

«Computer Vision»
http://900igr.net/prezentacija/anglijskij-jazyk/computer-vision-252433.html
cсылка на страницу

Тексты на английском

46 презентаций о текстах на английском
Урок

Английский язык

29 тем
Слайды