Classify-normalize-classify

Changing atmospheric conditions often result in a data distribution shift in remote sensing images for different dates and locations making it difficult to discriminate between various classes of interest. To alleviate this data shift issue, we introduce a novel supervised classification framework, called Classify-Normalize-Classify (CNC). The proposed scheme uses a two classifier approach where the first classifier performs a rough segmentation of the class of interest (COI) in the input image. Then, the median signal of the estimated COI regions is subtracted from all image pixels values to normalize them. Finally, the second classifier is applied to the normalized image to produce the refined COI segmentation. The proposed methodology was tested to detect deforestation using bitemporal Landsat 8 OLI images over the Amazon rainforest. The CNC framework compared favorably to benchmark masks of the PRODES program and state-of-the-art classifiers run on surface reflectance images provided by USGS.

[1]  Belinda A. Margono,et al.  Humid tropical forest disturbance alerts using Landsat data , 2016 .

[2]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[3]  Luis Gómez-Chova,et al.  Graph Matching for Adaptation in Remote Sensing , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Didier Tanré,et al.  Second Simulation of the Satellite Signal in the Solar Spectrum, 6S: an overview , 1997, IEEE Trans. Geosci. Remote. Sens..

[5]  Alex M. Lechner,et al.  Comparison of relative radiometric normalization methods using pseudo-invariant features for change detection studies in rural and urban landscapes , 2012 .

[6]  D. Roy,et al.  A method for integrating MODIS and Landsat data for systematic monitoring of forest cover and change in the Congo Basin , 2008 .

[7]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[8]  C. Justice,et al.  High-Resolution Global Maps of 21st-Century Forest Cover Change , 2013, Science.

[9]  P. Chavez.  An improved dark-object subtraction technique for atmospheric scattering correction of multispectral data , 1988 .

[10]  C. Nobre,et al.  Extreme climatic events in the Amazon basin , 2011, Theoretical and Applied Climatology.

[11]  Ali Shamsoddini,et al.  A monitoring framework for land use around kaolin mining areas through Landsat TM images , 2014, Earth Science Informatics.

[12]  Daniel D. Lee,et al.  Semisupervised alignment of manifolds , 2005, AISTATS.

[13]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[14]  Martha C. Anderson,et al.  Landsat-8: Science and Product Vision for Terrestrial Global Change Research , 2014 .

[15]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[16]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[17]  Lorenzo Bruzzone,et al.  Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances , 2016, IEEE Geoscience and Remote Sensing Magazine.

[18]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[19]  D. C. Robertson,et al.  MODTRAN: A Moderate Resolution Model for LOWTRAN , 1987 .

[20]  Olivier Hagolle,et al.  A Software Tool for Atmospheric Correction and Surface Temperature Estimation of Landsat Infrared Thermal Data , 2016, Remote. Sens..

[21]  A. Branchini,et al.  Impact of a Probiotic-Based Cleaning Intervention on the Microbiota Ecosystem of the Hospital Surfaces: Focus on the Resistome Remodulation , 2016, PloS one.

[22]  Clemens Eisank,et al.  An object-based approach for semi-automated landslide change detection and attribution of changes to landslide classes in northern Taiwan , 2015, Earth Science Informatics.

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

[24]  Elías F. Combarro,et al.  Automatic arable land detection with supervised machine learning , 2016, Earth Science Informatics.

[25]  M. Claverie,et al.  Preliminary analysis of the performance of the Landsat 8/OLI land surface reflectance product. , 2016, Remote sensing of environment.

[26]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[27]  Lorenzo Bruzzone,et al.  Semisupervised Transfer Component Analysis for Domain Adaptation in Remote Sensing Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[28]  O. Mutanga,et al.  Investigating the robustness of the new Landsat-8 Operational Land Imager derived texture metrics in estimating plantation forest aboveground biomass in resource constrained areas , 2015 .

[29]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[30]  C. Woodcock,et al.  Classification and Change Detection Using Landsat TM Data: When and How to Correct Atmospheric Effects? , 2001 .

[31]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[32]  Guido Rossum,et al.  Python Reference Manual , 2000 .

[33]  Gustau Camps-Valls,et al.  Kernel Manifold Alignment for Domain Adaptation , 2015, PloS one.

[34]  William J. Volchok,et al.  Radiometric scene normalization using pseudoinvariant features , 1988 .