Computer Science - The City College of New York
CSc 59866/59867 Capstone I/II Fall 2015-Spring 2016

Assignment 2(revised).  Stereo and Motion ( Deadline: October 14 extended to Oct 21 by midnight)
(Those marked with * are optional for extra credits)


Note: All the writings must be in soft copies (PDF)  Please send the report (PDF) and the matlab code (*.m)  of your assignment to Prof. Zhu <zhu@cs.ccny.cuny.edu> as email attachments. You are responsible for the lose of your submissions if you don’t include  “Capstone 2015 ” (exactly) in the subject of your email. Send your source code ONLY – please don’t send in your images and executable. Do write your names and IDs (last four digits) in both your report and your matlab code files.



1.  (Stereo- 25 points ) Estimate the accuracy of  the simple stereo system (Figure 3 in the online lecture notes of stereo vision) assuming that the only source of noise is the localization of corresponding points in the two images. Discuss the dependence of the error in depth estimation as a function of disparity error, depth itself, the baseline width and the focal length, respectively.

Hint: Z = fB/d; Take the partial derivatives of Z with respect to d, B, f,  respectively.

2. (Motion- 25 points) Could you obtain 3D information of a scene by viewing the scene by a camera  rotating around its optical center? Show why or why not. What about moving the camera along its optical axis?

3. (25 points) Discussion the similarities (at least 2 ) and differences (at least 2) between stereo vision and visual motion .

4. (25 points) Give five examples where humans use stereo and motion, and Google another five examples that use machine vision algorithms of stereo and motion.

3. (Stereo Programming - 15 bonus points ) Use the image pair ( Image 1, Image 2) for the following exercises.

(1). Fundamental Matrix (5 points). - Design and implement a program that , given a stereo pair, determines at least eight point matches, then recovers the fundamental matrix . Check the accuracy of the result by measuring the distance between the estimated epipolar lines and image points not used by the matrix estimation . Also, overlay the epipolar lines of control points and test points on one of the images (say Image 1- I already did this in the starting code below). Control points are the correspondences (matches)  used in computing the fundamental matrix,  and test points are those  used to check the accuracy of the computation.

Hint: As a first step, you can pick up the matches of both the control points and the test points manually. You may use my revised matlab code (FmatGUI.m)  as a starting point - where I provided an interface to pick up point matches by mouse clicks. The epipolar lines should be (almost)  parallel in this stereo pair. If not, something is wrong either with your code or the point matches.

(2). Feature-based matching (5 points). - Design a stereo vision system to do "feature-based matching" and explain your algorithm in writing.. The system should have a user interface that allows a user to select a point on the first image, say by a mouse click.  The system should then find and highlight the corresponding point on the second image, say using a cross hair points). Try to use the epipolar geometry derived from (1) in searching  correspondences along epipolar lines.

(3) Discussions (5 points). Show your results on points with different properties like those in corners, edges, smooth regions, textured regions, and occluded regions that are visible only in one of the images. Discuss for each case, why your vision system succeeds or fails in finding the correct matches. Compare the performance of your system against a human user (e.g. yourself) who marks the corresponding matches on the second image by a mouse click.