The aim of this course is to help the student understand the fundamentals behind collaborative multi-camera video analysis, which is nowadays the main practical way to confront many challenging computer vision scenarios.
UNIT I: The projected reality
Introduction to projection
Fundamentals of Projective Geometry
Calibration of a single camera
UNIT II: Detection, description and matching of reference points
Pyramids and scale-space theory.
Detection and description of feature points: theory and methods.
Comparison and searching strategies for the matching of local descriptions.
UNIT III: Analysis in multi-camera scenarios
Calibration in camera networks
Collaborative objects detection
R. Hartley, A. Zisserman, “Multiple view geometry in computer vision”, Cambridge UP, 2003
T. Lindeberg, “Scale-Space Theory”, Kluwer Academic Publishers, Boston, MA, 1997.
Awad A., Hassaballah M. (eds) “Image Feature Detectors and Descriptors. Studies in Computational Intelligence”, vol 630. Springer, Cham
O. Javed, M. Shah, “Automated Multi-camera Surveillance: Algorithms and Practice”, Springer 2008 H. Aghajan, and A. Cavallaro, eds. Multi-camera networks: principles and applications. Academic press, 2009.
S. Gong, M. Cristani, S. Yan and C. Loy, eds. Person Re-identification. Springer, 2014.
P. Spagnolo, P. Mazzeo, and C. Distante. Human behavior understanding in networked sensing. Springer, 2014.
Additional lecturers, if exist(name, position, degree): Juan Carlos San Miguel, Ph.D., Assistant Professor; Jesús Bescós, Ph.D., Associate Professor