Our ability to create algorithms for automatically processing gridded spatial data is increasingly important as the volume of remotely sensed imagery expands. This text provides a comprehensive foundation in digitally processing and mining geospatial datasets.

The ability to create automated algorithms to process gridded spatial data is increasingly important as remotely sensed datasets increase in volume and frequency. Whether in business, social science, ecology, meteorology or urban planning, the ability to create automated applications to analyze and detect patterns in geospatial data is increasingly important. This book provides students with a foundation in topics of digital image processing and data mining as applied to geospatial datasets. The aim is for readers to be able to devise and implement automated techniques to extract information from spatial grids such as radar, satellite or high-resolution survey imagery.

Contains a distillation of practical techniques from multiple fields Features techniques illustrated on an easy to understand (and included) population density data set Includes software implementation in Java of the techniques described in the text

Autorentext
Dr. Valliappa Lakshmanan is an expert in machine intelligence R&D for meteorological applications, and in designing and developing large-scale software systems. He is skilled in communicating technical and non-technical material to diverse audiences. He has studied at the Indian Institute of Technology in Madras, the Ohio State University in Columbus and the University of Oklahoma.
Dr. Lakshmanan is currently employed as a Research Scientist at CIMMS, being the technical lead on several software projects and research groups.
He also develops automated real-time pattern recognition algorithms and visualization techniques for weather phenomena.
He has (co-)written many journal articles.

Inhalt
Automated Analysis of Spatial Grids: Motivation and Challenges.-
-Geographic Information Systems.-
-GIS Operations.-
-Need for Automation.-
-Spatial Grids.-
-Challenges in Automated Analysis.-
-Spatial Data Mining Algorithms.-
Geospatial grids.-
-Representation.-
-Linearity of data values.-
-Instrument geometry.-
-Gridding point observations.-
-Rasterization.-
-Example Applications.-
Data Structures for Spatial Grids.-
-Array.-
-Pixels.-
-Level set.-
-Topographical surface.-
-Markov chain.-
-Matrix.-
-Parametric approximation.-
-Relational structure.-
-Applications.-
Global and Local Image Statistics.-
-Types of statistics.-
-Distances.-
-Distance transform.-
-Probability Functions.-
-Local measures.-
-Example Applications.-
Neighborhood and Window Operations.-
-Preprocessing.-
-Window operations.-
-Median filter.-
-Morphological operations.-
-Skeletonization.-
-Frequency Domain Convolution.-
-Example Applications.-
Identifying Objects.-
-Object identification.-
-Region growing.-
-Region properties.-
-Hysteresis.-
-Active contours.-
-Watershed Transform.-
-Enhanced watershed.-
-Contiguity-enhanced Clustering.-
-Choosing an object-identification technique.-
-Example Applications.-
Change and Motion Estimation.-
-Estimating change.-
-Optical Flow.-
-Object-tracking.-
-Choosing a change or motion estimation technique.-
-Example Applications.-
Data Mining Attributes from Spatial Grids.-
-Data Mining.-
-A Fuzzy Logic Application.-
-Supervised learning models.-
-Clustering.-
-Example Applications.