Computer Vision and Photogrammetry

Course description:

In this course will look at different techniques to acquire 3D models from images. During the course labs you will implement a 3D reconstruction pipeline, from 2D images to a 3D geometric model.


Tentative Syllabus 2016-2017

Class DateContentsDetailsLecture notes PDFLab
4 October, TueIntroduction and image formationPhotogrammetry Overview. Details about the course.Lecture 1Lab0: Test vsfm and meshlab reconstruction pipeline
11 October, TueImage formation, camera calibration, pose estimationCamera matrix, calibration with linear methods.Lecture 2Lab 1
18 October, TueHomographies and warping and lens distortion.Homography calculation, Lens distortion. Zhang calibration method. Other camera models.
25 October, TueTwo View GeometryEpipolar constraint, Essential and Fundamental Matrix. Epipolar geometry, Computing F and E. Triangulation
8 Novemeber, TueStereoProblems of stereo matching. Image rectification.
22 Novemeber, TueKeypoint detectorsHarris, LoG, DoG, MESR
29 November, TueFeature Descriptors and MatchingSIFT, NNDR, precision, recall, accuracy.
6 December, TueSelf-CalibrationProjective Geometry, Duality, self-calibration
13 December, TueReconstruction from SequencesProjective Reconstruction, Sequencial recontruction
20 December, TueBundle adjustmentBundle adjustment, sparsity of the bundle adjustment problem.
10 January, TueMeshing PointcloudsSigned Distance Functions, Normal Computation, Radial Basis Functions, Poisson Reconstruction
17 January, TueTexturingMulti-view Texturing, Parameterization, Least-squares conformal Maps
24 January, TueSLAM
31 January, TueReview & ClosureRecapitualtion, Feedback, Closure


Image Processing is advisable. Linear algebra.


There will be no exam. Your mark will depend on your implementation and documentation of the 3D reconstruction system.

Similar Courses at other Universities

in progress…