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.

Resources

Tentative Syllabus 2016-2017

ContentsDetails
Introduction and image formationPhotogrammetry Overview and Projection Matrix. Details about the course.
Image formation, camera calibration, pose estimationCamera matrix, calibration with linear methods
Homographies and Epipolar geometryHomography calculation, epipolar constraint, Essential and Fundamental Matrix
Two View GeometryEpipolar geometry, Computing F and E. Triangulation
StereoProblems of stereo matching. Image rectification.
Keypoint detectorsHarris, LoG, DoG, MESR
Feature Descriptors and MatchingSIFT, NNDR, precision, recall, accuracy.
Self-CalibrationProjective Geometry, Duality, self-calibration
Reconstruction from SequencesProjective Reconstruction, Sequencial recontruction
Bundle adjustmentBundle adjustment, sparsity of the bundle adjustment problem.
Meshing PointcloudsSigned Distance Functions, Normal Computation, Radial Basis Functions, Poisson Reconstruction
TexturingMulti-view Texturing, Parameterization, Least-squares conformal Maps
SLAM
Review & ClosureRecapitualtion, Feedback, Closure

Requirements

Image Processing is advisable. Linear algebra.

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…