Conference Paper

Land cover classification methods for multiyear AVHRR data

Dept. of Geogr., Maryland Univ., College Park, MD ;
DOI: 10.1109/IGARSS.1998.702265 Conference: Geoscience and Remote Sensing Symposium Proceedings, 1998. IGARSS '98. 1998 IEEE International, Volume: 5
Source: IEEE Xplore

ABSTRACT AVHRR data have been extensively used for global land cover classification, but few studies have taken direct and full advantage of the multiyear properties of AVHRR data. The authors generated three types of signatures from 12-year monthly composite NDVI (normalized difference vegetation index) and channel 4 brightness temperature (T4) of NOAA/NASA Pathfinder AVHRR Land data for land cover classification. Both quadrature discriminate analysis (QDA) and linear discriminate analysis (LDA) are explored for classification. A global land cover training database created from Landsat TM and MSS imagery is used for training and validation. It turns out that QDA performs much better than LDA, and the overall classification rate is as high as 95.9%

0 Bookmarks
 · 
50 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Since the first edition of this book appeared in 1994, see the review Zbl 0806.62002, S-PLUS has continued to grow in popularity, not least on personal computers as the Windows version now has equivalent capabilities to the versions running on Unix workstations. This edition gives equal weight to the Windows and Unix versions, and covers many of the features that have been added to S-PLUS, for example Trellis and object-oriented editable graphics, linear and nonlinear mixed effects models and factor analysis. It also builds on further experience in the classroom and in using S-PLUS. This edition is designed for users of S-PLUS 3.3 or later. It was written whilst S-PLUS 4.0 for Windows was under development, and covers what we see as the most exciting new features, but not new interfaces to existing functionality. (Some of the simpler statistical operations can be accessed via a menu system or customized buttons, but for the full power of S the command-line interface is still needed, and many users will still prefer it.) The new features are indexed under ‘version 4.0’. Some of the more specialised or rapidly changing functionality is covered in the on-line complements (see page 497 for sites) which will be updated frequently. The datasets and S functions that we use are available on-line, and will help greatly in making use of the book. Also on-line are further exercises and answers to selected exercises.
    3rd 01/1999; Springer.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Red and near-infrared satellite data from the Advanced Very High Resolution Radiometer sensor have been processed over several days and combined to produce spatially continuous cloud-free imagery over large areas with sufficient temporal resolution to study green-vegetation dynamics. The technique minimizes cloud contamination, reduces directional reflectance and off-nadir viewing effects, minimizes sun-angle and shadow effects, and minimizes aerosol and water-vapor effects. The improvement is highly dependent on the state of the atmosphere, surface-cover type, and the viewing and illumination geometry of the sun, target and sensor. An example from southern Africa showed an increase of 40 percent from individual image values tothe final composite image. Limitations associated with the technique are discussed, and recommendations are given to improve this approach.
    International Journal of Remote Sensing 12/1986; · 1.36 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The International Geosphere-Biosphere Programme Data and Information System (IGBP-DIS) is co-ordinating the development of global land data sets from Advanced Very High Resolution Radiometer (AVHRR) data. The first is a 1 km spatial resolution land cover product 'DISCover', based on monthly Normalized Difference Vegetation Index composites from 1992 and 1993. DISCover is a 17 class land cover dataset based on the science requirements of IGBP elements. Mapping uses unsupervised classification with post-classification refinement using ancillary data. Draft Africa, North America and South America products are now available for peer review.
    International Journal of Remote Sensing 01/1997; 18(15):3289 - 3295. · 1.36 Impact Factor

Full-text

View
1 Download
Available from