Land cover change detection at coarse spatial scales based on iterative estimation and previous state information

Abstract This study focuses on the use of coarse spatial resolution (CR, pixel size about 1 km 2 ) remote sensing data for land cover change detection and qualification. Assuming the linear mixing model for CR pixels, the problem is that both the multitemporal class features and the pixel composition in terms of classes are unknown. The proposed algorithm is then based on the iterative alternate estimation of each unknown variable. At each iteration, the class features are estimated, thanks to the knowledge of the composition of some pixels, and then the pixel composition is re-estimated knowing the class features. The subset of known composition pixels is the subset of pixels where no change has occurred, i.e. the previous land cover map is still valid. It is derived automatically by removing at each iteration the pixels where the new composition estimation disagrees with the former one. Finally, for the final estimation of the pixel composition, a Markovian chain model is used to guide the solution, i.e. the previous land cover map is used as a ‘reminder’ or ‘memory’ term. This approach has been first validated using simulated data with different spatial resolution ratios. Then, the detection of forest change with SPOT/VGT-S10 has been considered as an actual application case. Finally, the method has been applied to change detection on the Val de Saone watershed between the 1980s and 2000. The results obtained from three coarse resolution series, NOAA/AVHRR, SPOT/VGT-S10 and SPOT/VGT-P, have been compared.

[1]  Christopher Justice,et al.  The impact of misregistration on change detection , 1992, IEEE Trans. Geosci. Remote. Sens..

[2]  J. Mas.  Monitoring land-cover changes: A comparison of change detection techniques , 1999 .

[3]  F. Baret,et al.  Validation of neural net techniques to estimate canopy biophysical variables from remote sensing data , 2002 .

[4]  P. Gill,et al.  Fortran package for constrained linear least-squares and convex quadratic programming. User's Guide for LSSOL (Version 1. 0) , 1986 .

[5]  Siamak Khorram,et al.  The effects of image misregistration on the accuracy of remotely sensed change detection , 1998, IEEE Trans. Geosci. Remote. Sens..

[6]  Knut Conradsen,et al.  Multivariate Alteration Detection (MAD) and MAF Postprocessing in Multispectral, Bitemporal Image Data: New Approaches to Change Detection Studies , 1998 .

[7]  Catherine Ottlé,et al.  Modelisation hydro-meteorologique du bassin du Rhone: apport de la teledetection spatiale , 2002 .

[8]  G. Celeux,et al.  L'algorithme SEM: un algorithme d'apprentissage probabiliste: pour la reconnaissance de mélange de densités , 1986 .

[9]  Etienne Leblois,et al.  Simulation of the water budget and the river flows of the Rhone basin , 1999 .

[10]  Ashbindu Singh,et al.  Review Article Digital change detection techniques using remotely-sensed data , 1989 .

[11]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[12]  M. Goulard,et al.  Functional approaches for predicting land use with the temporal evolution of coarse resolution remote sensing data , 2003 .

[13]  Wojciech Pieczynski,et al.  SEM algorithm and unsupervised statistical segmentation of satellite images , 1993, IEEE Trans. Geosci. Remote. Sens..

[14]  Paul C. Smits,et al.  Toward specification-driven change detection , 2000, IEEE Trans. Geosci. Remote. Sens..

[15]  B. Pinty,et al.  GEMI: a non-linear index to monitor global vegetation from satellites , 1992, Vegetatio.

[16]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[17]  Norm Campbell,et al.  On the errors of two estimators of sub-pixel fractional cover when mixing is linear , 1998, IEEE Trans. Geosci. Remote. Sens..

[18]  Michael A. Saunders,et al.  Procedures for optimization problems with a mixture of bounds and general linear constraints , 1984, ACM Trans. Math. Softw..

[19]  A. Fischer,et al.  Predicting Crop Reflectances Using Satellite Data Observing Mixed Pixels , 1997 .

[20]  Dominique Thiéry,et al.  Hydro-meteorological modelling of the Rhone basin: general presentation and objectives , 2001 .

[21]  R. Okafor.  Maximum likelihood estimation from incomplete data , 1987 .

[22]  S. L. Hégarat-Mascle,et al.  Automatic change detection by evidential fusion of change indices , 2004 .

[23]  Lorenzo Bruzzone,et al.  An adaptive semiparametric and context-based approach to unsupervised change detection in multitemporal remote-sensing images , 2002, IEEE Trans. Image Process..

[24]  David P. Roy,et al.  The impact of misregistration upon composited wide field of view satellite data and implications for change detection , 2000, IEEE Trans. Geosci. Remote. Sens..

[25]  S. Le Hegarat-Mascle,et al.  Applications of simulated annealing to SAR image clustering and classification problems , 1996 .

[26]  Philip E. Gill,et al.  Practical optimization , 1981 .

[27]  Pierre Lanchantin,et al.  Statistical image segmentation using triplet Markov fields , 2003, SPIE Remote Sensing.

[28]  A. Strahler,et al.  Indicators of land-cover change for change-vector analysis in multitemporal space at coarse spatial scales , 1994 .

[29]  John M. Laflen.  Corine Soil Erosion Risk and Important Land Resources , 1994 .

[30]  A. Strahler,et al.  The use of temporal metrics for land cover change detection at coarse spatial scales , 2000 .

[31]  Pol Coppin,et al.  Digital change detection methods in natural ecosystem monitoring: a review , 2002 .