Positioning Weather Systems from Remote Sensing Data Using Genetic Algorithms
Remote sensing technology is widely used in meteorology for weather system positioning. Yet, these remote sensing data are often analyzed manually based on forecasters’ experience, and results may vary among forecasters. In this chapter, we briefly introd
- PDF / 4,470,500 Bytes
- 30 Pages / 430 x 660 pts Page_size
- 61 Downloads / 223 Views
roduction Hyperspectral imaging is concerned with the measurement, analysis, and interpretation of spectra acquired from a given scene (or specific object) at a short, medium or long distance by an airborne or satellite sensor [1]. The concept of hyperspectral imaging originated at NASA’s Jet Propulsion Laboratory in California, which developed instruments such as the Airborne Imaging Spectrometer (AIS), then called AVIRIS, for Airborne Visible Infra-Red Imaging Spectrometer [2]. This system is now able to cover the wavelength region from 0.4 to 2.5 μm using more than two hundred spectral channels, at nominal spectral resolution of 10 nm. As a result, each pixel vector collected by a hyperspectral instrument can be seen as a spectral signature or fingerprint of the underlying materials within the pixel (see Fig. 7.1). The special characteristics of hyperspectral datasets pose different processing problems, which must be necessarily tackled under specific mathematical formalisms, such as feature extraction, classification and segmentation, spectral M. Gra˜ na and R.J. Duro (Eds.): Comput. Intel. for Remote Sensing, SCI 133, pp. 163–192, 2008. c Springer-Verlag Berlin Heidelberg 2008 springerlink.com
164
A.J. Plaza
Fig. 7.1. The concept of hyperspectral imaging
mixture analysis, or data compression [3]. For instance, several computational intelligence-related techniques have been applied to extract relevant information from hyperspectral data during the last decade [4]. Taxonomies of remote sensing data processing algorithms (including hyperspectral analysis methods) have been developed in the literature [5]. It should be noted, however, that most available hyperspectral data processing techniques have focused on analyzing the data without incorporating information on the spatially adjacent data, i.e., hyperspectral data are usually not treated as images, but as unordered listings of spectral measurements where the spatial coordinates can be randomly shuffled without affecting the analysis [6]. However, one of the distinguishing properties of hyperspectral data, as collected by available imaging spectrometers, is the multivariate information coupled with a two-dimensional pictorial representation amenable to image interpretation. Subsequently, there is a need to incorporate the image representation of the data in the development of appropriate application-oriented techniques for the understanding of hyperspectral data [7].
7 Parallel Spatial-Spectral Processing of Hyperspectral Images
165
Specifically, the importance of analyzing spatial and spectral patterns simultaneously has been identified as a desired goal by many scientists devoted to hyperspectral data analysis [6], [8]. This type of processing has been approached in the past from various points of view. For instance, techniques have discussed the refinement of results obtained by applying spectral-based techniques to multispectral images (with tens of spectral channels) through a second step based on spatial context [9]. Such contextual classification, extended
Data Loading...
