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

TDV − labs

The goal of labs is to practice the 3D reconstruction techniques explained at lectures. The labs are divided into two main parts. In the first part a small independent tasks (Task 0-1 to 0-4) are solved. During the second part, students will build up complete system for reconstruction of a 3D scene given its images. Implementation if this system and its use for the reconstruction is solved as a term project, and it is subject of the lab sessions.

Whole system is build from several building blocks − elementary methods. These methods will be explained in the lectures gradually. Students will implement some methods, another methods are already available and the task is to integrate them into the system.

Whole problem is separated into following four phases. These consist of methods that are related and possibly cooperates. Each phase represents relatively independent part, and it covers several week classes. There are defined required results for each phase. Whole project is finished by submission of a final results of reconstruction.

Phases

  1. Input data capture and preprocessing.
  2. Epipolar geometry on image pairs.
  3. Multiple cameras and structure of the scene.
  4. Surface reconstruction.

Implementation

The term project and other tasks should be solved using the Python or Matlab environment. There are some methods, that students need not implement 1). These methods can be obtained from the code repository. These codes can be subject of small evolution and bug-fixing. It is thus recommended always to use the latest revision. In case that you found a bug, please announce this using the forum.

During the implementation, students should build a set (library, toolbox) of general elementary tools and methods. The functions of this Toolbox of Elementary and Helper Functions will be specified during the term. This toolbox should be submitted (repeatedly, as the number of functions will grow) to the upload system for the automatic check of validity (_toolbox assignment).

Important: Without prior permission from the teacher, it is not allowed to use different software tools than the ones specified in the description. However, this does not apply for visualization and presentation of results (vrml and so).

Schedule of Exercises

Week Date Phase Details Submission Points
1. 22.9. IntroductionIntroduction, organization of labs
0. Basic geometryPoints and lines in a plane (0-1)
2. 29.9. Perspective camera (0-2) Task 0-1 (*) 2
3. 6.10. Robust maximum likelihood estimation of a planar line (0-3) Task 0-2 (*) 2
4. 13.10. Estimation of two homographies and homology (0-4) Task 0-3 3
5. 20.10. 1. Input data - images and correspondences Term project specification, data and calibration.
6. 27.10. 2. Robust estimation of calibrated epipolar geometry of image pairs Task 0-4 6
7. 3.11. –continued
8. 10.11. 3. Multiple cameras and structure of the scene Calibration of poses of a set of cameras
9. 17.11. State holiday
10. 24.11. Sparse point cloud reconstruction Task2 10
11. 1.12. Test 1
14. 8.12. Optimisation of points and cameras by bundle adjustment
13. 15.12. 4. Surface reconstruction Epipolar rectification and dense matching. Dense point cloud reconstruction. Final 3D surface reconstruction. Task 3 14
14. 5.1. Consultation, reserve, credit (if eligible) Task 4 (12.1.2019) 8

(*) No penalty for late fullfillment.

Assessment of Exercises

Continuous work

There is 45 pts assigned for a continuous work during exercises.

Small problems and the term project are solved during the labs. The small problems and intermediate results of the term projects are fulfilled by demonstrating it to the teacher (on your screen) during the lab session or additional consultation hours. Nothing is submitted, only the final results (3D models) and code is should be submitted to the BRUTE system. Successfully solved problem is credited by appropriate number of points. All problems and project sub-tasks have deadlines. Later demonstration/submission will be penalized by -15% of the nominal points for the task if one week later or by -30% if two and more weeks later. This does not apply to the tasks 0-1 and 0-2.

Upload of final results

Final results of your work should be submitted to the Upload system. Upload the following parts:

  1. three vrml models (in archive, assignment vrml),
    • cameras and sparse point cloud,
    • dense point cloud,
    • surface,
  2. your codes (in archive, assignment codes).

Students who wants to obtain the credit in the last week of the term should submit the results in time. In the case of later submission, the credit will be granted after consultation with the teacher.

1)
but of course they can, in the interest of intimate understanding
courses/tdv/labs/start.txt · Last modified: 2020/10/26 16:26 by xmatousm