A multivariate geostatistical approach for landscape classification from remotely sensed image data

详细信息    查看全文

• 作者：Ronny Vallejos (1)
  Adriana Mallea (2)
  Myriam Herrera (3)
  Silvia Ojeda (4)
  
  1. Departamento de Matem谩tica ; Universidad T茅cnica Federico Santa Mar铆a ; Avenida Espa帽a 1680 ; Valparaiso ; Chile
  2. Departamento de Matem谩tica ; Universidad Nacional de San Juan ; San Juan ; Argentina
  3. Facultad de Ciencias Exactas F铆sicas y Naturales ; Universidad Nacional de San Juan ; San Juan ; Argentina
  4. Facultad de Matem谩tica ; Astronom铆a y F铆sica ; Universidad Nacional de C贸rdoba ; Valparaiso ; Argentina
  
• 关键词：Multivariate spatial process ; Spatial association ; Codispersion matrix ; Dimensionality reduction ; Image classification
• 刊名：Stochastic Environmental Research and Risk Assessment (SERRA)
• 出版年：2015
• 出版时间：February 2015
• 年：2015
• 卷：29
• 期：2
• 页码：369-378
• 全文大小：1,161 KB
• 参考文献：1. Bernard-Michel C, Dout茅 S, Fauvel M, Gardes M, Girard S (2009) Retrieval of mars surface physical properties from omega hyperspectral images using regularized sliced inverse regression. J Geophys Res 114:E06005
  2. Bolthausen R (1982) On the central limit theorem for stationary random fields. Ann Probab 10:1047鈥?050 CrossRef
  3. Bosch A, Mu帽oz X, Mart铆 R (2007) A review: which is the best way to organize/classify images by content? Image Vis Comput 25:778鈥?91 CrossRef
  4. Cohen A (1960) A coefficient of agreement for nominal scales. Educ Psychol Meas 20:37鈥?6 CrossRef
  5. Comon P (1994) Independent component analysis: a new concept? Signal Process 36:287鈥?14 CrossRef
  6. Cuevas F, Porcu E, Vallejos R (2013) Study of spatial relationships between two sets of variables: a nonparametric approach. J Nonparametric Stat 25:695鈥?14 CrossRef
  7. de Almeida E, de Medeiros A, Rosso O, Frery A (2012) Generalized statistical complexity of SAR imagery. Lectures Notes in Computer Science. Springer, Berlin, pp 656鈥?63
  8. Du J, Ma C (2012) Variogram matrix funtions for vector random fields with second-order increments. Math Geosci 44:411鈥?25 CrossRef
  9. Duda R, Hart P, Stork D (2001) Pattern classification. Wiley, New York
  10. Geniting T, Kleiber W, Schlather M (2010) Matrn cross-covariance functions for multivariate random fields. J Am Stat Assoc 105:1167鈥?177 CrossRef
  11. G贸mez D, Montero J (2011) Determining the accuracy in image supervised classification problems. EUSFLAT 1:342鈥?49
  12. G贸mez D, Biging G, Montero J (2008) Accuracy statistics for judging soft classification. Int J Remote Sens 29:693鈥?09 CrossRef
  13. Goovaerts P (1997) Geostatistics for natural resources evaluation. Oxford University Press, Oxford
  14. Guyon X (1982) Parameter estimation for a stationary process on a \(d\) -dimensional lattice. Biometrika 69:95鈥?05 CrossRef
  15. Jolliffe IT (2002) Principal component analysis. Springer, New York
  16. Kullback S, Leibler R (1951) On information and sufficiency. Ann Math Stat 22:79鈥?6 CrossRef
  17. Li KC (1991) Sliced inverse regression for dimensional reduction (with discussion). J Am Stat Assoc 86:316鈥?42 CrossRef
  18. Li KC (1992) On principal hessian directions for data visualization and dimension reduction another application of stein鈥檚 lemma. J Am Stat Assoc 87:025鈥?039 CrossRef
  19. Lutkepohl H (2007) New introduction to multivariate time series analysis. Springer, Berlin
  20. Loog M, Duin PW (2004) Linear dimensionality reduction via heteroscedastic extension of lda: the chernoff criterion. IEEE Trans Pattern Anal Mach Intell 26:732鈥?39 CrossRef
  21. Ma C (2008) Recent developments on the construction of spatio-temporal covariance models. Stoch Environ Res Risk Assess 22:S39鈥揝47 CrossRef
  22. Ma C (2010) Elliptically contoured random fields in space and time. J Phys A 43:165209 CrossRef
  23. Ma C (2011) Vector random fields with second-order moments ot second-order increments. Stoch Anal Appl 29:197鈥?15 CrossRef
  24. Matheron C (1965) Les Variables R茅gionalis茅es et leur Estimation. Masson, Paris
  25. Moustakas A, Hristopulos DT (2009) Estimating tree abundance from remotely sensed imagery in semi-arid and arid environments: bringing small trees to the light. Stoch Environ Res Risk Assess 23:111鈥?18 CrossRef
  26. Murray R (2011) Classification images: a review. J Vis 11:1鈥?5 CrossRef
  27. Ojeda S, Vallejos R, Lamberti P (2012) Measure of similarity between images based on the codispersion coefficient. J Electron Imaging 21:023019 CrossRef
  28. Osorio F, Vallejos R, Cuevas, F (2012) SpatialPack: a package to assess the association between two spatial processes. R package version 0.2. http://cran.r-project.org/web/packages/SpatialPack/
  29. Pontius RG (2009) Quantification error versus location error in comparison of categorical maps. Photogramm Eng Remote Sens 66:1011鈥?016
  30. Porcu E, Gregori P, Mateu J (2006) Nonseparable stationary anisotropic spacetime covariance functions. Stoch Environ Res Risk Assess 21:113鈥?22 CrossRef
  31. Pringle MJ, Lark RM (2006) Spatial analysis of model error: illustrated by soil carbon dioxide emissions. Vadose Zone J 5:168鈥?83 CrossRef
  32. Richards JA (1993) Remote sensing digital image analysis, 2nd edn. Springer, New York CrossRef
  33. Rueda L, Herrera M (2008) Linear dimensionality reduction by maximizing the chernoff distance in the transformed space. Pattern Recognit 41:3138鈥?152 CrossRef
  34. Rukhin AL (2006) Association characteristics in spatial statistics. Math Methods Stat 15:309鈥?26
  35. Rukhin AL, Vallejos R (2008) Codispersion coefficient for spatial and temporal series. Stat Probab Lett 78:1290鈥?300 CrossRef
  36. Stehman SV, Czaplewski RL (2003) Introduction to special issue on map accuracy. Environ Ecol Stat 10:301鈥?08 CrossRef
  37. Swain PH, King RC (1973) Two effective feature selection criteria for multispectral remote sensing. In: Proceedings of the First International Conference on the Pattern Recognition. pp 536鈥?40
  38. Vallejos R (2008) Assessing the association between two spatial or temporal sequences. J Appl Stat 35:1323鈥?343 CrossRef
  39. Vallejos R (2012a) Testing for the absence of correlation between two spatial or temporal sequences. Pattern Recognit Lett 33:1741鈥?748 CrossRef
  40. Vallejos R, Ojeda S (2012b) Image segmentation and time series clustering based on spatial and temporal ARMA processes. In: Advances in Image Segmentation, P-G Peter Ho (ed) INTECH
  41. ver Hoef JM, Barry RP (1998) Constructing and fittiing models for cokriging and multivariate spatial prediction. J Stat Plan Inference 69:275鈥?94 CrossRef
  42. Whittle P (1954) On stationary processes in the plane. Biometrika 41:434鈥?49 CrossRef
  43. Wu HM, Lu HH (2007) Iterative sliced inverse regression for segmentation of ultrasound and mr images. Pattern Recognit 40:3492鈥?502 CrossRef
  44. Zou H, Hastie T, Tibshirani R (2006) Sparse principal component analysis. J Comput Graph Stat 15:265鈥?86 CrossRef
  45. Zukovic M, Hristopulos DT (2013) Reconstruction of missing data in remote sensing images using conditional stochastic optimization with global geometric constraints. Stoch Environ Res Risk Assess 27:785鈥?06 CrossRef
  
• 刊物类别：Earth and Environmental Science
• 刊物主题：Environment
  Mathematical Applications in Environmental Science
  Mathematical Applications in Geosciences
  Probability Theory and Stochastic Processes
  Statistics for Engineering, Physics, Computer Science, Chemistry and Geosciences
  Numerical and Computational Methods in Engineering
  Waste Water Technology, Water Pollution Control, Water Management and Aquatic Pollution
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1436-3259

文摘

This paper proposes a methodology to address the classification of images that have been acquired from remote sensors. One common problem in classification is the high dimensionality of multivariate characteristics. The methodology we propose consists of reducing the dimensionality of the spectral bands associated with a multispectral satellite image. Such dimensionality reduction is accomplished by the use of the divergence of a modified Mahalanobis distance. Instead of using the covariance matrix of a multivariate spatial process, the codispersion matrix is considered which have some desirable asymptotic properties under very precise conditions. The consistency and asymptotic normality hold for a general class of processes that are a natural extension of the one-dimensional spatial processes for which the asymptotic properties were first established. The results allow the selection of a set of spectral bands to produce the highest value of divergence. Then, a supervised maximum likelihood method using the selected spectral bands is employed for landscape classification. An application with a real LANDSAT image is introduced to explore and visualize how our method works in practice.