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.

– Camera geometry and calibration

– Feature detection and Matching

– Stereo and Structure from Motion

– Shape from Shading and Photometric Stereo

– Registration, Meshing and Texturing

Resources

http://www.cs.unc.edu/~marc/tutorial/

http://www.cs.unc.edu/~marc/tutorial04/

Tentative Syllabus 2016-2017

Class DateContentsDetailsLecture notesLecture notes PDFLab
4 October, TueIntroduction and image formationPhotogrammetry Overview and Projection Matrix. Details about the course.Lecture 1Lecture 1Lab0: Install Python (Anaconda) and get familiar with image processing libraries
11 October, TueImage formation, camera calibration, pose estimationCamera matrix, calibration with linear methodsLecture 2Lecture 2
18 October, TueHomographies and Epipolar geometryHomography calculation, epipolar constraint, Essential and Fundamental Matrix Lecture 3Lecture 3Lab 1
25 October, TueTwo View GeometryEpipolar geometry, Computing F and E. TriangulationLecture 4Lecture 4Lab 2
8 Novemeber, TueStereoProblems of stereo matching. Image rectification.Lecture 5Lecture 5Lab 3
22 Novemeber, TueKeypoint detectorsHarris, LoG, DoG, MESRLecture 6Lecture 6Lab 4
29 November, TueFeature Descriptors and MatchingSIFT, NNDR, precision, recall, accuracy.Lecture 7Lecture 7Lab 5
6 December, TueSelf-CalibrationProjective Geometry, Duality, self-calibrationLecture 8Lecture 8Lab 5+
13 December, TueReconstruction from SequencesProjective Reconstruction, Sequencial recontructionLecture 9Lecture 9Marking Lab 5
20 December, TueBundle adjustmentBundle adjustment, sparsity of the bundle adjustment problem.Lecture 10Lecture 10Marking Delayed Labs
10 January, TueMeshing PointcloudsSigned Distance Functions, Normal Computation, Radial Basis Functions, Poisson ReconstructionLecture 9Lecture 11Lab 6
17 January, TueTexturingMulti-view Texturing, Parameterization, Least-squares conformal MapsLecture 12Lecture 12
24 January, TueSLAMLecture 13Lecture 13Marking Lab 6
31 January, TueReview & ClosureRecapitualtion, Feedback, ClosureLecture 14Lecture 14

Requirements

Image Processing is advisable. Linear algebra.

References

http://www.robots.ox.ac.uk/~vgg/hzbook/

Examination

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…