Dades generals

Curs acadèmic:
2017
Descripció:
Crèdits:
6

Grups

Grup A

Durada:
Semestral, 2n semestre
Professorat:
RAFAEL GARCIA CAMPOS
Idioma de les classes:

Altres Competències

  • Apply techniques of modelling and calibrating computer vision systems.
  • Compute 3D information of the real world from 2D image projections
  • Apply the principles of stereovision, triangulation and pattern projection
  • Understand the limitations of some feature detecting and feature matching algorithms and how to remove false data associations
  • Oral expression
  • Team work
  • Building creative proposals

Continguts

1. Introduction

          1.1. Course organization: Objectives, Overview, Contents, Bibliography, Evaluation, Practical Sessions

          1.2. Review of rigid body transformations

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

8. Pattern Projection Techniques

          8.1. The principle of codification

          8.2. State of the art

          8.3. Time multiplexing, spatial codification, direct codification

          8.4. Steps to implement a pattern projection technique

Activitats

Tipus d’activitat Hores amb professor Hores sense professor Total
Aprenentatge basat en problemes (PBL) 5 24 29
Classes expositives 18 0 18
Classes pràctiques 14 37 51
Prova d'avaluació 4 8 12
Seminaris 20 20 40
Total 61 89 150

Bibliografia

  • Hartley, Richard (2003). Multiple view geometry in computer vision (2nd ed.). Cambridge [etc.]: Cambridge University Press. Catàleg
  • Ma, Yi (2004). An Invitation to 3-D vision : from images to geometric models. New York [etc.]: Springer, cop.. Catàleg

Avaluació i qualificació

Activitats d'avaluació:

Descripció de l'activitat Avaluació de l'activitat %
Seminars Attendance to all the seminars, punctuality in all the activities related to the module and active participation in the seminars. 10
Lab assignment 1: Calibration of a simulated camera. This lab assignment is evaluated on the basis of the matlab code delivered by the students and a report explaining what has been done, what problems have aroused, and how the students have solved these problems. 15
Lab assignment 2: Project Based Learning activity on Invariant Features This lab assignment involves teamwork and oral presentation. The students will be evaluated on the basis of the oral presentation of their project (in teams of 3 students) and the code that they present. 30
Lab assignment 3: Epipolar Geometry This lab assignment is evaluated on the basis of the matlab code delivered by the students and a report explaining what has been done, what problems have aroused, and how the students have solved these problems. 15
Lab assignment 4: 3D Reconstruction This lab assignment is evaluated on the basis of the matlab code delivered by the students and a report explaining what has been done, what problems have aroused, and how the students have solved these problems. 10
Exam Coherence of answers with respect to the reviewed contents. Synthesis ability. 20

Qualificació

About evaluation:

50 % Exams (first exam 30%, final exam 70%). Summative evaluation (all contents apply to the second exam)
50 % Practical Sessions (Every exercise Mark >= 5/10)

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.