Handling uncertainties in image mining for remote sensing studies

This paper presents an overview of uncertainty handling in remote sensing studies. It takes an image-mining perspective and identifies different ways of handling uncertainties. It starts with the pixel, and through object identification and modelling, proceeds towards monitoring and decision making. Methods presented originate both from probability- and fuzzy-logic-based approaches. The paper is illustrated with three examples, one from a geographic information system stored object, one from an object identified from a remotely sensed image directly and a practical case study from the Tibet plateau. An important remaining topic is to combine and integrate errors and uncertainties collected during the whole image-mining process.

[1]  Wenzhong Shi,et al.  Principles of Modeling Uncertainties in Spatial Data and Spatial Analyses , 2009 .

[2]  Giles M. Foody What is the difference between two maps? A remote senser’s view , 2006, J. Geogr. Syst..

[3]  Feng Chen,et al.  Glacier variations in the Naimona’nyi region, western Himalaya, in the last three decades , 2006, Annals of Glaciology.

[4]  Shi-chang Kang,et al.  Monitoring glacier variations on Geladandong mountain, central Tibetan Plateau, from 1969 to 2002 using remote-sensing and GIS technologies , 2006 .

[5]  L. Thompson,et al.  Thirty‐year history of glacier melting in the Nepal Himalayas , 2006 .

[6]  J. Berger Statistical Decision Theory and Bayesian Analysis , 1988 .

[7]  Giles M. Foody,et al.  Training set size requirements for the classification of a specific class , 2006 .

[8]  Wietske Bijker,et al.  Optimization of sampling schemes for vegetation mapping using fuzzy classification , 2005 .

[9]  Thomas Blaschke,et al.  A comparison of three image-object methods for the multiscale analysis of landscape structure , 2003 .

[10]  F. Maselli Monitoring forest conditions in a protected Mediterranean coastal area by the analysis of multiyear NDVI data , 2004 .

[11]  A. Cracknell Review article Synergy in remote sensing-what's in a pixel? , 1998 .

[12]  Shang-Lien Lo,et al.  Application of two-stage fuzzy set theory to river quality evaluation in Taiwan. , 2003, Water research.

[13]  Isam Kaysi,et al.  Identifying urban boundaries: application of remote sensing and geographic information system technologies , 2003 .

[14]  David Martin,et al.  Zone design for environment and health studies using pre-aggregated data. , 2005, Social science & medicine.

[15]  A S Fotheringham,et al.  The Modifiable Areal Unit Problem in Multivariate Statistical Analysis , 1991 .

[16]  Jennifer L. Dungan,et al.  A balanced view of scale in spatial statistical analysis , 2002 .

[17]  M. Molenaar,et al.  Objects with fuzzy spatial extent , 1999 .

[18]  J. Stoer,et al.  Introduction to Numerical Analysis , 2002 .

[19]  Gerard B. M. Heuvelink,et al.  Error Propagation in Environmental Modelling with GIS , 1998 .

[20]  Stan Openshaw,et al.  A geographical solution to scale and aggregation problems in region-building, partitioning and spatial modelling , 1977 .

[21]  Alfred Stein,et al.  Incorporating Uncertainty via Hierarchical Classification Using Fuzzy Decision Trees , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Eric D. Kolaczyk,et al.  On the choice of spatial and categorical scale in remote sensing land cover classification , 2005 .

[23]  H. Miller Societies and cities in the age of instant access , 2007 .

[24]  Sucharita Gopal,et al.  The evolving social geography of blogs , 2007 .

[25]  W. Shi,et al.  Modelling positional and thematic uncertainties in integration of remote sensing and geographic information systems , 1994 .

[26]  F. D. van der Meer,et al.  International institute for Geo - information Science and Earth Observation : ITC , 2009 .

[27]  S. de Bruin,et al.  Propagation of positional measurement errors to agricultural field boundaries and associated costs , 2008 .

[28]  A. Stein,et al.  Use of a multi - temporal grid method to analyze changes in glacier coverage in the Tibetan plateau , 2009 .

[29]  Marco Bindi,et al.  Modelling carbon budget of Mediterranean forests using ground and remote sensing measurements , 2005 .

[30]  P. Fisher The pixel: A snare and a delusion , 1997 .

[31]  Peter M. Atkinson,et al.  On estimating measurement error in remotely sensed images with the variogram , 1997 .

[32]  T. Ramachandra,et al.  Urban sprawl: metrics, dynamics and modelling using GIS , 2004 .

[33]  Suha Berberoglu,et al.  Assessing different remote sensing techniques to detect land use/cover changes in the eastern Mediterranean , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[34]  G. Christakos A Bayesian/maximum-entropy view to the spatial estimation problem , 1990 .

[35]  Alfred Stein Modern developments in image mining , 2008 .

[36]  Fabio Maselli,et al.  Improved Estimation of Environmental Parameters through Locally Calibrated Multivariate Regression Analyses , 2002 .

[37]  Jianguo Wu,et al.  The modifiable areal unit problem and implications for landscape ecology , 1996, Landscape Ecology.

[38]  Alfred Stein,et al.  Image Mining for Modeling of Forest Fires From Meteosat Images , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[39]  S. de Bruin,et al.  Integrating spatial statistics and remote sensing , 1998 .

[40]  J. Jaquet,et al.  Glacial cover mapping (1987-1996) of the Cordillera Blanca (Peru) using satellite imagery , 2005 .

[41]  Giles M. Foody,et al.  Localized soft classification for super‐resolution mapping of the shoreline , 2006 .

[42]  A. Barbati,et al.  Modelling of Italian forest net primary productivity by the integration of remotely sensed and GIS data , 2007 .

[43]  Giles M. Foody,et al.  The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM , 2006 .

[44]  Dorothy K. Hall,et al.  Comparison of satellite-derived with ground-based measurements of the fluctuations of the margins of Vatnajökull, Iceland, 1973–92 , 1997, Annals of Glaciology.