An Adaptive Semi-Parametric and Context-Based Approach to Unsupervised Change Detection in Multitemporal Remote-Sensing Images

In this paper, a novel automatic approach to the unsupervised identification of changes in multitemporal remote-sensing images is proposed. This approach, unlike classical ones, is based on the formulation of the unsupervised change-detection problem in terms of the Bayesian decision theory. In this context, an adaptive semi-parametric technique for the unsupervised estimation of the statistical terms associated with the gray levels of changed and unchanged pixels in a difference image is presented. Such a technique exploits the effectivenesses of two theoretically well-founded estimation procedures: the reduced Parzen estimate (RPE) procedure and the expectation-maximization (EM) algorithm. Then, thanks to the resulting estimates and to a Markov Random Field (MRF) approach used to model the spatial-contextual information contained in the multitemporal images considered, a change detection map is generated. The adaptive semi-parametric nature of the proposed technique allows its application to different kinds of remote-sensing images. Experimental results, obtained on two sets of multitemporal remote-sensing images acquired by two different sensors, confirm the validity of the proposed approach. Index terms Change detection, multitemporal images, remote sensing, adaptive semi-parametric estimation, Bayes theory, reduced Parzen estimate, expectation-maximization algorithm.

[1]  Shyang Chang,et al.  A motion estimation algorithm under time-varying illumination , 1989, Pattern Recognit. Lett..

[2]  Mark J. Carlotto Detection and analysis of change in remotely sensed imagery with application to wide area surveillance , 1997, IEEE Trans. Image Process..

[3]  J. Besag On the Statistical Analysis of Dirty Pictures , 1986 .

[4]  Rafael Wiemker,et al.  An Iterative Spectral-Spatial Bayesian Labeling Approach for Unsupervised Robust Change Detection on Remotely Sensed Multispectral Imagery , 1997, CAIP.

[5]  R. Nelson Detecting forest canopy change due to insect activity using Landsat MSS , 1983 .

[6]  Shyang Chang,et al.  A video tracking system with adaptive predictors , 1992, Pattern Recognit..

[7]  Lorenzo Bruzzone,et al.  Unsupervised change detection in multisource and multisensor remote sensing images , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[8]  M. S. Moran,et al.  Three methods for the absolute calibration of the NOAA AVHRR sensors in-flight , 1990 .

[9]  D. F. Prieto,et al.  An adaptive parcel-based technique for unsupervised change detection , 2000 .

[10]  Peng Gong,et al.  Registration-noise reduction in difference images for change detection , 1992 .

[11]  Anil K. Jain,et al.  Random field models in image analysis , 1989 .

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

[13]  Shyang Chang,et al.  Statistical change detection with moments under time-varying illumination , 1998, IEEE Trans. Image Process..

[14]  Jan Flusser,et al.  A moment-based approach to registration of images with affine geometric distortion , 1994, IEEE Trans. Geosci. Remote. Sens..

[15]  Christopher O. Justice,et al.  Spatial variability of images and the monitoring of changes in the Normalized Difference Vegetation Index , 1995 .

[16]  R. L. McKinney,et al.  LANDSAT image differencing as an automated land cover change detection technique , 1978 .

[17]  Keinosuke Fukunaga,et al.  The Reduced Parzen Classifier , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  R. Redner,et al.  Mixture densities, maximum likelihood, and the EM algorithm , 1984 .

[19]  M. S. Moran,et al.  Reflectance- and radiance-based methods for the in-flight absolute calibration of multispectral sensors , 1987 .

[20]  Lorenzo Bruzzone,et al.  Detection of changes in remotely-sensed images by the selective use of multi-spectral information , 1997 .

[21]  Paul L. Rosin Unimodal thresholding , 2001, Pattern Recognit..

[22]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  P. Chavez Radiometric calibration of Landsat Thematic Mapper multispectral images , 1989 .

[25]  Harvey F. Silverman,et al.  A Class of Algorithms for Fast Digital Image Registration , 1972, IEEE Transactions on Computers.

[26]  David A. Landgrebe,et al.  The development of a spectral-spatial classifier for earth observational data , 1980, Pattern Recognit..

[27]  Håkan Olsson,et al.  Reflectance calibration of thematic mapper data for forest change detection , 1995 .

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

[29]  Edward J. Delp,et al.  Adaptive gray scale mapping to reduce registration noise in difference images , 1986, Comput. Vis. Graph. Image Process..

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

[31]  James V. Krogmeier,et al.  MODEL-BASED VEHICLE TRACKING FROM IMAGE SEQUENCES WITH AN APPLICATION TO ROAD SURVEILLANCE , 1996 .

[32]  Lorenzo Bruzzone,et al.  An iterative technique for the detection of land-cover transitions in multitemporal remote-sensing images , 1997, IEEE Trans. Geosci. Remote. Sens..

[33]  Didier Le Gall,et al.  MPEG: a video compression standard for multimedia applications , 1991, CACM.

[34]  P. S. Chavez,et al.  Automatic detection of vegetation changes in the southwestern United States using remotely sensed images , 1994 .

[35]  T. Fung An Assessment Of Tm Imagery For Land Cover Change Detection , 1989, 12th Canadian Symposium on Remote Sensing Geoscience and Remote Sensing Symposium,.

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

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

[38]  Lorenzo Bruzzone,et al.  Automatic analysis of the difference image for unsupervised change detection , 2000, IEEE Trans. Geosci. Remote. Sens..

[39]  Rama Chellappa,et al.  Segmentation of polarimetric synthetic aperture radar data , 1992, IEEE Trans. Image Process..

[40]  Anil K. Jain,et al.  Registering Landsat images by point matching , 1989 .