lec12

lec12 - Lecture 12 October 4 10 HW3 due this Wednesday...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
USC CS574: Computer Vision, Fall 2010 Copyright 2010, by R. Nevatia 1 Lecture 12: October 4, 10 • HW3 due this Wednesday – Questions? • Hw 0, 1 returned, solutions posted – Problems 3 and 4 are good practice for use of projective geometry! • Exam 1, Oct 13, class time – Close book, material covered listed in following slides • Last Class – Uncalibrated cameras • Essential and Fundamental matrices • Estimation from matched point pairs • RANSAC algorithm • Today’s objective – Structure from Motion
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
USC CS574: Computer Vision, Fall 2010 Copyright 2010, by R. Nevatia 2 Stereo Example
Background image of page 2
USC CS574: Computer Vision, Fall 2010 Copyright 2010, by R. Nevatia 3 Stereo Steps • Search for the best match (using the given cost function) – Square window size (51 x 51) – Search along horizontal line only – Set a disparity range for efficiency and to avoid some false matches – Search only to the “left” in the “right” image – Boundary effects – May skip pixels where disparity is computed (not the same as sub-sampling the images) • Segment info comes from the mean shift segmentor • Store disparity in image format (invert the negative numbers). Scale for display.
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
USC CS574: Computer Vision, Fall 2010 Copyright 2010, by R. Nevatia 4 Exam #1: Topics • Defined by material covered in class (note some topics not covered in FP book) • Image formation: geometry – Pinhole camera model, homogeneous coordinates, coordinate transformations, mapping of points and lines, camera calibration – FP ch 1 (1.1,1.2.2, 1.3), ch2,, ch3 (3.2) • Image formation: radiometry – Local shading model (summary only) – Color coordinates: (R,G,B), (H,S,V), – FP ch 5 (5.3), ch6 (6.1, 6.3 parts only, 6.4.1)
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 15

lec12 - Lecture 12 October 4 10 HW3 due this Wednesday...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online