This book covers the state-of-art image classification methods for
discrimination of earth objects from remote sensing satellite data
with an emphasis on fuzzy machine learning and deep learning
algorithms. Both types of algorithms are described in such details
that these can be implemented directly for thematic mapping of
multiple-class or specific-class landcover from multispectral optical
remote sensing data. These algorithms along with multi-date,
multi-sensor remote sensing are capable to monitor specific stage (for
e.g., phenology of growing crop) of a particular class also included.
With these capabilities fuzzy machine learning algorithms have strong
applications in areas like crop insurance, forest fire mapping,
stubble burning, post disaster damage mapping etc. It also provides
details about the temporal indices database using proposed Class Based
Sensor Independent (CBSI) approach supported by practical examples. As
well, this book addresses other related algorithms based on distance,
kernel based as well as spatial information through Markov Random
Field (MRF)/Local convolution methods to handle mixed pixels,
non-linearity and noisy pixels. Further, this book covers about
techniques for quantiative assessment of soft classified fraction
outputs from soft classification and supported by in-house developed
tool called sub-pixel multi-spectral image classifier (SMIC). It is
aimed at graduate, postgraduate, research scholars and working
professionals of different branches such as Geoinformation sciences,
Geography, Electrical, Electronics and Computer Sciences etc., working
in the fields of earth observation and satellite image processing.
Learning algorithms discussed in this book may also be useful in other
related fields, for example, in medical imaging. Overall, this book
aims to: exclusive focus on using large range of fuzzy classification
algorithms for remote sensing images; discuss ANN, CNN, RNN, and
hybrid learning classifiers application on remote sensing images;
describe sub-pixel multi-spectral image classifier tool (SMIC) to
support discussed fuzzy and learning algorithms; explain how to assess
soft classified outputs as fraction images using fuzzy error matrix
(FERM) and its advance versions with FERM tool, Entropy, Correlation
Coefficient, Root Mean Square Error and Receiver Operating
Characteristic (ROC) methods and; combines explanation of the
algorithms with case studies and practical applications.
Les mer
Produktdetaljer
ISBN
9781000091540
Publisert
2020
Utgave
1. utgave
Utgiver
Vendor
CRC Press
Språk
Product language
Engelsk
Format
Product format
Digital bok