Improved classification of Landsat Thematic Mapper data using modified prior probabilities in large and complex landscapes

The use of modified prior probabilities to exploit ancillary data and increase classification accuracy has been proposed before. However, this method has not been widely applied because it has heavy computing requirements and because obtaining prior probability estimates has presented practical problems. This article presents a procedure that generates large sets of prior probability estimates from class frequencies modelled with ancillary data and a Mahalanobis Distance selection of previously classified pixels. The method produces a pixel sample size that is large enough to estimate class frequencies in numerous strata, which is particularly desirable for the study of large and complex landscapes. A case study is presented in which the procedure made it possible to estimate 537 sets of prior probabilities for an entire Landsat Thematic Mapper (TM) scene of central Costa Rica. After modifying the class prior probabilities, the overall classification consistency of the training sites improved from 74.6% to 91.9%, while the overall classification accuracy of sites controlled in the field by independent studies improved from 68.7% to 89.0%. The classification accuracy was most improved for spectrally similar classes. The method improves classification accuracy in large and complex landscapes with spectrally mixed land-cover categories.

[1]  G H Ball,et al.  A clustering technique for summarizing multivariate data. , 1967, Behavioral science.

[2]  L. Holdridge,et al.  Forest environments in tropical life zones: a pilot study. , 1971 .

[3]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[4]  Brian Everitt,et al.  Cluster analysis , 1974 .

[5]  Keinosuke Fukunaga,et al.  A Graph-Theoretic Approach to Nonparametric Cluster Analysis , 1976, IEEE Transactions on Computers.

[6]  Alan H. Strahler,et al.  The Use of Prior Probabilities in Maximum Likelihood Classification , 1980 .

[7]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .

[8]  Philip H. Swain,et al.  Remote Sensing: The Quantitative Approach , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  D. Toll,et al.  Detecting residential land use development at the urban fringe , 1982 .

[10]  Paul M. Mather,et al.  A computationally-efficient maximum-likelihood classifier employing prior probabilities for remotely-sensed data , 1985 .

[11]  John R. Jensen,et al.  Introductory Digital Image Processing: A Remote Sensing Perspective , 1986 .

[12]  John A. Richards,et al.  Remote Sensing Digital Image Analysis , 1986 .

[13]  E. LeDrew,et al.  Application of principal components analysis to change detection , 1987 .

[14]  W. Cibula,et al.  Use of topographic and climatological models in a geographical data base to improve Landsat MSS classification for Olympic National Park , 1987 .

[15]  Morgan P. Conrad,et al.  A rapid, non-parametric clustering scheme for flow cytometric data , 1987, Pattern Recognit..

[16]  N. Myers,et al.  Tropical deforestation and remote sensing , 1988 .

[17]  Andrew K. Skidmore,et al.  Forest mapping accuracies are improved using a supervised nonparametric classifier with SPOT data , 1988 .

[18]  C. Hall,et al.  Tropical Forests and the Global Carbon Cycle , 1988, Science.

[19]  Robert B. Waide,et al.  Tropical forest biomass and successional age class relationships to a vegetation index derived from Landsat TM data , 1989 .

[20]  D. J. Booth,et al.  A comparison of classification algorithms in terms of speed and accuracy after the application of a post-classification modal filter , 1989 .

[21]  Jeff Dozier,et al.  Information Analysis of a Spatial Database for Ecological Land classification , 1990 .

[22]  P. Gong,et al.  The use of structural information for improving land-cover classification accuracies at the rural-urban fringe. , 1990 .

[23]  Keinosuke Fukunaga,et al.  Introduction to statistical pattern recognition (2nd ed.) , 1990 .

[24]  Steven A. Sader,et al.  Migratory bird habitat monitoring through remote sensing , 1991 .

[25]  Richard A. Houghton,et al.  Tropical deforestation and atmospheric carbon dioxide , 1991 .

[26]  D.A. Landgrebe,et al.  Classification with spatio-temporal interpixel class dependency contexts , 1992, IEEE Trans. Geosci. Remote. Sens..

[27]  F. Maselli,et al.  Inclusion of prior probabilities derived from a nonparametric process, into the maximum-likelihood classifer , 1992 .

[28]  Steven E. Franklin,et al.  A three-stage classifier for remote sensing of mountain environments , 1992 .

[29]  N. Campbell,et al.  Derivation and applications of probabilistic measures of class membership from the maximum-likelihood classification , 1992 .

[30]  I. G. Staritsky,et al.  Deforestation trends in the Atlantic Zone of Costa Rica: A case study , 1992 .

[31]  Fabio Maselli,et al.  Selection of optimum bands from TM scenes through mutual information analysis , 1993 .

[32]  C. Tucker,et al.  Tropical Deforestation and Habitat Fragmentation in the Amazon: Satellite Data from 1978 to 1988 , 1993, Science.

[33]  Eduardo S. Brondizio,et al.  Spectral identification of successional stages following deforestation in the Amazon , 1993 .

[34]  A. Setzer,et al.  Spectral characteristics of fire scars in Landsat-5 TM images of Amazonia , 1993 .

[35]  Giampiero Maracchi,et al.  Improvement in maximum likelihood classification performance on highly rugged terrain using principal components analysis , 1993 .

[36]  William Salas,et al.  Physical and human dimensions of deforestation in Amazonia , 1994 .

[37]  Giles M. Foody,et al.  Separability of tropical rain-forest types in the Tambopata-Candamo Reserved Zone, Peru , 1994 .

[38]  Giles M. Foody,et al.  Estimation of tropical forest extent and regenerative stage using remotely sensed data , 1994 .

[39]  Robert C. Kohberger,et al.  Cluster Analysis (3rd ed.) , 1994 .

[40]  Billie Turner,et al.  The human causes of Deforestation in Southeast Asia , 1994 .

[41]  J. C. Price.  How unique are spectral signatures , 1994 .

[42]  R. K. Dixon,et al.  Carbon Pools and Flux of Global Forest Ecosystems , 1994, Science.

[43]  M. Lewis,et al.  Species composition related to spectral classification in an Australian spinifex hummock grassland , 1994 .

[44]  B. Csuti,et al.  A Gap Analysis of the Management Status of the Vegetation of Idaho (U.S.A.) , 1995 .

[45]  Fabio Maselli,et al.  Integration of ancillary data into a maximum-likelihood classifier with nonparametric priors , 1995 .

[46]  M. Kappelle,et al.  Ecology of mature and recovering Talamancan montane Quercus forests , 1995 .

[47]  Hanna Tuomisto,et al.  Dissecting Amazonian Biodiversity , 1995, Science.

[48]  Mary W. Downton,et al.  Measuring Tropical Deforestation: Development of the Methods , 1995, Environmental Conservation.

[49]  V. Heywood,et al.  Global Biodiversity Assessment , 1996 .

[50]  B. Finegan.  Pattern and process in neotropical secondary rain forests: the first 100 years of succession. , 1996, Trends in ecology & evolution.

[51]  Eduardo S Brondízio,et al.  Analysis Restoration of vegetation cover in the eastern Amazon , 1996 .

[52]  R. Lucas,et al.  Identifying terrestrial carbon sinks: Classification of successional stages in regenerating tropical forest from Landsat TM data , 1996 .

[53]  Giles M. Foody,et al.  An assessment of radiance in Landsat TM middle and thermal infrared wavebands for the detection of tropical forest regeneration , 1996 .

[54]  E. Duffey.  Global biodiversity assessment , 1997 .

[55]  E. Helmer,et al.  The landscape ecology of secondary tropical forest in montane Costa Rica , 1998 .

[56]  Harini Nagendra,et al.  Satellite imagery as a tool for monitoring species diversity: an assessment , 1999 .

[57]  C. Kleinn,et al.  Forest Area in Costa Rica: A Comparative Study of Tropical Forest Cover Estimates over Time , 2002, Environmental monitoring and assessment.