1. Introduction
1.1. Course organization: Objectives, Overview, Contents, Bibliography, Evaluation, Practical Sessions
2. Camera Modelling and Calibration
2.1. The pinhole camera
2.2. Intrinsic and extrinsic parameters
2.3. Computing the calibration matrix
2.4. Accuracy Evaluation
3. Image Primitives
3.1. Interest point detectors
3.2. Harris and Hessian detectors
3.3. Similarity measures: SAD, SSD, Correlation
3.4. Introduction to Scale invariant features
4. Correspondence and Planar Transformations
4.1. Review of SIFT
4.2. A hierarchy of transformations: Euclidean, Similarity, Affine, Projective
5. Outlier Rejection
5.1. Probabilistic methods
5.2. Computing the homography matrix
5.3. Random Sampling Consensus
5.4. Applications: Planar motion estimation, Mosaicing, etc.
6. Reconstruction from 2 views
6.1. The principle of Triangulation
6.2. Epipolar geometry
6.3. Computing the Fundamental matrix
6.4. Accuracy Evaluation
6.5. Experimental Results
7. Cameras in the real world
7.1. Comercial cameras
7.2. Camera characteristics
15% Practical Sessions: Lab on corner detection
40% Practical Sessions: Lab on Invariant features
15% Practical Sessions: Lab on 3D laser
(Every lab requires a mark >= 5/10)
30% Final exam
(the grade of the exam should be >=4/10)
To pass the module, the global mark must be >= 5/10
Criteris específics de la nota «No Presentat»:
Lab assignments are mandatory. Failure to deliver a lab assignment implies that the student will not be evaluated in the module.