Introduction
Pramod K. Varshney, Manoj K. Arora
The Challenge
From time immemorial, man has had the urge to see the unseen, to peer beneath
the earth, and to see distant bodies in the heavens. This primordial curiosity
embedded deep in the psyche of humankind, led to the birth of satellites and
space programs. Satellite images, due to their synoptic view, map like format,
and repetitive coverage are a viable source of gathering extensive information.
In recent years, the extraordinary developments in satellite remote sensing
have transformed this science from an experimental application into a technology for studying many aspects of earth sciences. These sensing systems
provide us with data critical to weather prediction, agricultural forecasting,
resource exploration, land cover mapping and environmental monitoring, to
name a few. In fact, no segment of society has remained untouched by this
technology.
Over the last few years, there has been a remarkable increase in the number
of remote sensing sensors on-board various satellite and aircraft platforms. Noticeable is the availability of data from hyperspectral sensors such as AVIRIS,
HYDICE, HyMap and HYPERION. The hyperspectral data together with geographical information system (GIS) derived ancillary data form an exceptional
spatial database for any scientific study related to Earth's environment. Thus,
significant advances have been made in remote sensing data acquisition, storage and management capabilities.
The availability of huge spatial databases brings in new challenges for the
extraction of quality information. The sheer increase in the volume of data
available has created the need for the development of new techniques that can
automate extraction of useful information to the greatest degree. Moreover,
these techniques need to be objective, reproducible, and feasible to implement
within available resources (DeFries and Chan, 2000). A number of image analysis techniques have been developed to process remote sensing data with varied
amounts of success. A majority of these techniques have been standardized and
implemented in various commercial image processing software systems such
as ERDAS Imagine, ENVI and ER Mapper etc. These techniques are suitable
for the processing of multispectral data but have limitations when it comes to
an efficient processing of the large amount of hyperspectral data available in
hundreds of bands. Thus, the conventional techniques may be inappropriate
P. K. Varshney et al., Advanced Image Processing Techniques for Remotely Sensed Hyperspectral Data
© Springer-Verlag Berlin Heidelberg 2004
Pramod K. Varshney, Manoj K. Arora
The Challenge
From time immemorial, man has had the urge to see the unseen, to peer beneath
the earth, and to see distant bodies in the heavens. This primordial curiosity
embedded deep in the psyche of humankind, led to the birth of satellites and
space programs. Satellite images, due to their synoptic view, map like format,
and repetitive coverage are a viable source of gathering extensive information.
In recent years, the extraordinary developments in satellite remote sensing
have transformed this science from an experimental application into a technology for studying many aspects of earth sciences. These sensing systems
provide us with data critical to weather prediction, agricultural forecasting,
resource exploration, land cover mapping and environmental monitoring, to
name a few. In fact, no segment of society has remained untouched by this
technology.
Over the last few years, there has been a remarkable increase in the number
of remote sensing sensors on-board various satellite and aircraft platforms. Noticeable is the availability of data from hyperspectral sensors such as AVIRIS,
HYDICE, HyMap and HYPERION. The hyperspectral data together with geographical information system (GIS) derived ancillary data form an exceptional
spatial database for any scientific study related to Earth's environment. Thus,
significant advances have been made in remote sensing data acquisition, storage and management capabilities.
The availability of huge spatial databases brings in new challenges for the
extraction of quality information. The sheer increase in the volume of data
available has created the need for the development of new techniques that can
automate extraction of useful information to the greatest degree. Moreover,
these techniques need to be objective, reproducible, and feasible to implement
within available resources (DeFries and Chan, 2000). A number of image analysis techniques have been developed to process remote sensing data with varied
amounts of success. A majority of these techniques have been standardized and
implemented in various commercial image processing software systems such
as ERDAS Imagine, ENVI and ER Mapper etc. These techniques are suitable
for the processing of multispectral data but have limitations when it comes to
an efficient processing of the large amount of hyperspectral data available in
hundreds of bands. Thus, the conventional techniques may be inappropriate
P. K. Varshney et al., Advanced Image Processing Techniques for Remotely Sensed Hyperspectral Data
© Springer-Verlag Berlin Heidelberg 2004