Use of Markov Random Fields for automatic cloud/shadow detection on high resolution optical images

In this study, we propose an automatic detection algorithm for cloud/shadow on remote sensing optical images. It is based on physical properties of clouds and shadows, namely for a cloud and its associated shadow: both are connex objects of similar shape and area, and they are related by their relative locations. We show that these properties can be formalized using Markov Random Field (MRF) framework at two levels: one MRF over the pixel graph for connexity modelling, and one MRF over the graph of objects (clouds and shadows) for their relationship modelling. Then, we show that, practically, having performed an image pre-processing step (channel inter-calibration) specific to cloud detection, the local optimization of the proposed MRF models leads to a rather simple image processing algorithm involving only six parameters. Using a 39 image database, performance is shown and discussed, in particular in comparison with the Marked Point Process approach.

[1]  Laveen N. Kanal,et al.  Classification of binary random patterns , 1965, IEEE Trans. Inf. Theory.

[2]  van Marie-Colette Lieshout,et al.  Markov Point Processes and Their Applications , 2000 .

[3]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[4]  R. Richter,et al.  De‐shadowing of satellite/airborne imagery , 2005 .

[5]  Van Nostrand,et al.  Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm , 1967 .

[6]  R. Srinivasan,et al.  An automated cloud detection method for daily NOAA-14 AVHRR data for Texas, USA , 2002 .

[7]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  James J. Simpson,et al.  A procedure for the detection and removal of cloud shadow from AVHRR data over land , 1998, IEEE Trans. Geosci. Remote. Sens..

[9]  C. Thorncroft,et al.  African Monsoon Multidisciplinary Analysis: An International Research Project and Field Campaign , 2006 .

[10]  Xavier Descombes.  Méthodes stochastiques en analyse d'image : des champs de Markov aux processus ponctuels marqués , 2004 .

[11]  J. Cihlar,et al.  An image transform to characterize and compensate for spatial variations in thin cloud contamination of Landsat images , 2002 .

[12]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[13]  Rudolf Richter,et al.  Atmospheric correction of satellite data with haze removal including a haze/clear transition region , 1996 .

[14]  P. Green.  Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[15]  Josiane Zerubia,et al.  Marked point process in image analysis , 2002, IEEE Signal Process. Mag..

[16]  Anthony T. S. Ho,et al.  Cloud detection in satellite images for tropical regions , 1996, Optics & Photonics.

[17]  Xavier Descombes,et al.  Ant Colony Optimization for Image Regularization Based on a Nonstationary Markov Modeling , 2007, IEEE Transactions on Image Processing.

[18]  P. Peskun,et al.  Optimum Monte-Carlo sampling using Markov chains , 1973 .

[19]  Wojciech Pieczynski,et al.  Unsupervised image segmentation using triplet Markov fields , 2005, Comput. Vis. Image Underst..

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

[21]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[22]  Josef Cihlar,et al.  Detection and removal of cloud contamination from AVHRR images , 1994, IEEE Trans. Geosci. Remote. Sens..

[23]  D. Greig,et al.  Exact Maximum A Posteriori Estimation for Binary Images , 1989 .

[24]  Wojciech Pieczynski,et al.  Multisensor triplet Markov fields and theory of evidence , 2006, Image Vis. Comput..

[25]  B. Ripley,et al.  Markov Point Processes , 1977 .

[26]  W. Rossow,et al.  Cloud Detection Using Satellite Measurements of Infrared and Visible Radiances for ISCCP , 1993 .

[27]  Vladimir Kolmogorov,et al.  An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  R. Kauth,et al.  The tasselled cap - A graphic description of the spectral-temporal development of agricultural crops as seen by Landsat , 1976 .