Warning
This page is located in archive. Go to the latest version of this course pages. Go the latest version of this page.

Upload system Forum
Schedule: B4M33TDV BE4M33TDVXP33VID
Students: B4M33TDV BE4M33TDVXP33VID
Faculty web: B4M33TDVBE4M33TDVXP33VID

Distant teaching in MS Teams Virtual office of Martin Matoušek

TDV − 3D Computer Vision (Winter 2020)

Important: Due to official regulations, the lectures and labs will proceed remotely in an on-line way. We will use the MS Teams tool both for lectures and labs. All enrolled students should have access to 'Team-TDV' team in the MS Teams application. There is also direct link above.

Motivation

This course introduces methods and algorithms for 3D geometric scene reconstruction from images. The student will understand these methods and their essence well enough to be able to build variants of simple systems for reconstruction of 3D objects from a set of images or video, for inserting virtual objects to video-signal source, or for computing ego-motion trajectory from a sequence of images. The labs will be hands-on, the student will be gradually building a small functional 3D scene reconstruction system.

Fig. 1: an example of input images Fig. 2: resulting vrml model

Lectures: Tuesday 12:45-14:15

Place: KN:E-127 on-line, see the link above

Lecturer: Radim Šára

Updated lecture slides are ready for download before the lecture. They get annotated during the lecture and appear here after the lecture.

New: All slides in a single file (last updated 2021-01-05, without course overview)

Week Date Updated Slides Annotated Slides Recording Lecture Content
01 22.09. Introduction (large!) Course Overview 3D computer vision, its goals and applications, course overview
Lecture 1 L1 R1 basic geometry of points and lines
02 29.09. Lecture 2 L2 R2 homography, perspective camera, projection matrix decomposition
03 06.10. Lecture 3 L3 R3 optical center, optical ray, axis, plane; vanishing point, cross-ratio
04 13.10. Lecture 4 L4 R4 camera calibration from vanishing points, camera resection from 6 points, critical configurations for resection, the exterior orientation problem
05 20.10. Lecture 5 L5 R5 the relative orientation problem, epipolar geometry, epipolar constraint, essential matrix decomposition
06 27.10. Lecture 6 L6 R6 7-point algorithm for fundamental matrix estimation, 5-point algorithm for essential matrix estimation, triangulation by algebraic error minimization
07 03.11. Lecture 7 L7 R7 reprojection error, Sampson error correction, the golden standard triangulation method, local optimization for fundamental matrix estimation
08 10.11. Lecture 8 L8 R8 joint matching and epipolar geometry estimation, robust error function, optimization by random sampling
09 17.11. National holiday
10 24.11. Lecture 10 L10 R10 MH sampler, RANSAC
11 01.12. Lecture 11 L11 R11 camera system reconstruction, bundle adjustment, gauge freedom in bundle adjustment
12 08.12. Lecture 12 L12 R12 minimal representations, introduction to stereovision
13 15.12. Lecture 13 L13 R13 epipolar rectification, occlusion constraints
14 05.01. Lecture 14 L14 R14 matching table, Marroquin's WTA matching algorithm, maximum-likelihood matching algorithm, ordering constraint, stereo matching algorithm comparison

The English-Czech and Czech-English dictionary of 3D Vision and its print-ready A5 booklet version

Exercises (requirements)

Teacher: Martin Matoušek

Details about exercises (technical content and assessment) are in the separate section Exercises.

Notice: according to the study and examination code of CTU1), attendance at lectures is not mandatory (but recommended). However, students attending exercises are required to be theoretically prepared. The necessary theory is explained at the preceding lectures and can be also found in the recommended literature.

Requirements for the Credit

  1. Attending the exercises is mandatory, two absences are allowed.
  2. Submission/presentation of all required intermediate results.
  3. Submission of all required elementary methods that must pass automatic check.
  4. Submission of results of the term project.
  5. Submission of all homework problems assigned during lectures.

Assessment

Student assessment is based on scoring in the nominal range 0−100 points. There is also possibility to obtain some additional bonus points. The points are allocated to lectures, labs, homework problems and exam as follows:

Nominal points Minimal points Bonus points
Exercises 45
Homework assignments given at lectures 9 14
Midterm test 10 3
Exam test 24 6
Exam – oral 12
Total 100 +14

Assessment of Exercises is described in detail in the section of exercises.

The total of all points, including the bonuses is arithmetically rounded up and clipped at 100.

The grade is then given by the standard table (100−90⇒A, 89−80⇒B, 79−70⇒C, 69−60⇒D, 59−50⇒E, ≤ 49 ⇒ F).

Exam

The first test is done during the semester. The second test is a part of the exam at the end. The exam has two parts, usually, one day we do the test and the other day we have the oral part. The oral part is mandatory to achieve the A–B grades; it tests the ability to solve small problems; at least 5 points must be achieved, otherwise the final grade is C.

Additional Info

There is also a discussion forum (see link in the page head). Questions, feedback and comments on lectures or exercises are welcome.

Contacts

Lectures: Radim ŠáraExercises: Martin Matoušek
sara@cmp.felk.cvut.czMartin.Matousek@cvut.cz
KN, room 103Dejvice, CIIRC, room B606
virtual office
phone (22435) 7203phone (22435) 4221
Usermap Usermap
1)
Rev. Oct 1, 2015, in Czech, or Rev, Oct 1, 2015, in English: Article 7, Paragraph 5
courses/tdv/start.txt · Last modified: 2021/01/21 16:23 by sara