fabio scotti - manuel roveri universit à degli studi, milano, italy
DESCRIPTION
Soft Computing for Environmental Applications and Remote Sensing Soft computing for Remote Sensing Image Processing and Interpretation. Fabio Scotti - Manuel Roveri Universit à degli studi, Milano, Italy. Introduction (I). - PowerPoint PPT PresentationTRANSCRIPT
U N I V E R S I T À D E G L I S T U D I D I M I L A N O
C17 SC for Environmental Applications and Remote Sensing I M S C I A
Soft Computing for Environmental Applications and Remote Sensing
Soft computing for Remote Sensing Image Processing and
Interpretation
Fabio Scotti - Manuel Roveri
Università degli studi, Milano, Italy
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
Introduction (I)
• In order to take advantage and make good use of remote sensing data, we must be able to extract meaningful information from the imagery.
• Interpretation and analysis of remote sensing imagery involves the identification and/or measurement of various targets in an image in order to extract useful information about them.
• Soft computing methods can be used in many applications and in many modules of a remote sensing systems (i.e., the design of the system, preprocessing modules, enhancement modules, classification modules)
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
Introduction (II)
• In this lecture we firstly introduce the basics in image processing, in particular the following techniques:– Preprocessing;– Enhancement;– automatic Classification and Interpretation.
• In the second part of the lesson we will present the main soft-computing techniques used in Remote Sensing and in the environmental applications.
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
PART A Classical
techniques
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
The basics of the Remote Sensing Image Processing and Automatic Interpretation (I)
• Our goal is to understand the basic techniques to analyze the RS images, in particular:– Element of visual interpretation;– Basic of Digital Image Processing;– Preprocessing;– Image enhancement;– Image Transformations;– Image Classification, Analysis and Data Integration;
• Please read carefully the tutorial L3_Analysis1.pdf (*) linked in the course page.
(*) Goddard Space Flight Center, NASA
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
The basics of the Remote Sensing Image Processing and Automatic Interpretation (II)
• Our goals are to understand the first techniques to extract information from RS image, focalizing on an applicative example. Important issues are:– Band Information Characteristics;– False Color View;– True Color View;– Contrast Stretching and Spatial Filtering;– Principal Components Analysis;– Image Ratioing;
• Please read carefully the tutorial L3_Analysis2.pdf (*) linked in the course page. (*) Goddard Space Flight Center, NASA
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
PART B Soft-computing
techniques
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
Towards advanced Remote Sensing Image Processing and Automatic Interpretation (III)
• Let’s face the problem of interpretation/classification. Our goals are now to understand:– Unsupervised Classification;– Supervised Classification;– Minimum Distance Classification;– Maximum Likelihood Classification;– Application of a Probabilistic Neural Network Classifier.
• Please read carefully the tutorial L3_Analysis3.pdf (*) linked in the course page. (*) Goddard Space Flight Center, NASA
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
An overview of Soft Computing methods for Spectral Image Analysis
• Exploitation of the wealth of information in spectral images has yet to match up to the sensors' capabilities, as conventional methods often prove inadequate.
• ANNs hold the promise to revolutionize this area by overcoming many of the mathematical obstacles that traditional techniques fail at.
• By providing high speed when implemented in parallel hardware, (near-)real time processing of extremely high data volumes, typical in remote sensing spectral imaging, will also be possible.
Please read the paper L3_Paper1.pdf
linked in the course page.
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
Knowledge discovery from multispectral Satellite Images by Fuzzy Neural Networks
• Fuzzy Neural Networks can provide approaches to extract knowledge from multispectral images. For example it is possible to optimize classification rules using fuzzy neural networks.
• The goal of the reading is to understand how the knowledge can be transferred and exploited into the Fuzzy-NN with respect to this application.
Please read the paper L3_Paper2.pdf
linked in the course page.
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
A temporally neural adaptive classifier for multispectral imagery
• In this work we can see how a probabilistic neural network (PNN) is devised to account for the changes in the feature space as a result of environmental variations.
• The proposed methodology is used to develop a pixel-based cloud classification system.
Please read the paper L3_Paper3.pdf
linked in the course page.
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
Satellite constellation design using genetic algorithm
• The automatic satellite constellation design with satellite diversity and radio resource management is a problem that can be successfully solved using genetic algorithms methods.
• The automatic satellite constellation design means that some parameters of satellite constellation design can be determined simultaneously. The total number of satellites, the altitude of a satellite, the angle between planes, the angle shift between satellites and the inclination angle are considered in the design.
• Satellite constellation design can modeled using a multiobjective genetic algorithm.
Please read the paper L3_Paper4.pdf
linked in the course page.
Fabio Scotti - Manuel Roveri
C17 SC for Environmental Applications and Remote Sensing I M S C I A
End of the lecture