In this course, basic concepts of remote sensing and of the analysis of the resulting imagery are discussed.
Remote Sensing — Based on the concepts ruling the generation and propagation of electromagnetic wave fields, the objective is to provide the students with basic knowledge about the fundamentals and basic definitions of remote sensing; passive remote sensing in the optical, microwaves, and infrared frequency bands; active remote sensing and radar imaging; instrumentation for remote sensing. Satellite Images — The objective is to provide the students with basic knowledge about past, current, and forthcoming space missions for Earth observation; computational methods for the display, the modeling, and the filtering of satellite imagery; change detection techniques for multitemporal data; and regression techniques for bio/geophysical parameter retrieval from remote sensing. In this framework, machine learning techniques rooted in the areas of ensemble learning, neural networks, and kernel machines will be discussed as well.
Based on the concepts ruling the generation and propagation of electromagnetic wave fields, after the course the student shall have basic knowledge about the fundamentals and definitions of remote sensing; passive remote sensing in the optical, microwaves, and infrared frequency bands; active remote sensing and radar imaging; and instrumentation for remote sensing. The student shall also know about models and techniques to operate with remote sensing imagery for statistical modeling, despeckling, spatial-contextual classification, multitemporal analysis, and supervised regression. The methodological bases of these techniques are framed within the image processing, pattern recognition, and machine learning disciplines. In general terms, after the course, the student shall be familiar with specific topics of prominent interest in the Earth observation field.
Class lectures (approximately 45 hours) and laboratory exercises (approximately 5 hours)
Basic concepts ruling the generation and propagation of electromagnetic waves and fields - Fundamentals and definitions of remote sensing - Passive remote sensing in the optical, microwaves, and infrared frequency bands - Active remote sensing and radar imaging - Instrumentation for remote sensing - Space missions for Earth observation - Statistical modeling, filtering, and despeckling of remote sensing imagery - Spatial-contextual classification of remote sensing images through probabilistic graphical models - Change detection with multitemporal remote sensing images - Bio/geophysical parameter regression from remote sensing data through ensemble learning, kernel machines, and neural networks
Bishop C., Pattern recognition and machine learning, Springer, 2006 Campbell J. B. and Wynne R. H., Introduction to remote sensing, Guilford Press, 2011 Goodfellow I., Bengio Y., and Courville A., Deep learning, MIT Press, 2016 Hastie T., Tibshirani R., and Friedman J., The elements of statistical learning, Springer, 2008 Ulaby F. T. and Long D., Microwave radar and radiometric remote sensing, Artech House, 2015 Manolakis D. G., Lockwood R. B., and Cooley T. W., Hyperspectral imaging remote sensing, Cambridge University Press, 2016 Moser G., Analisi di immagini telerilevate per osservazione della Terra, ECIG, 2007 Moser G. and Zerubia J. (eds.), Mathematical models for remote sensing image processing, Springer, 2018 Class slides will be provided to the students through AulaWeb.
Ricevimento: By appointment
Ricevimento: By appointment.
SILVANA DELLEPIANE (President)
FEDERICA FERRARO
MATTEO PASTORINO
ANDREA RANDAZZO
SEBASTIANO SERPICO
ALESSANDRO FEDELI (President Substitute)
GABRIELE MOSER (President Substitute)
https://corsi.unige.it/10378/p/studenti-orario
Oral examination
