Dynamic classifier selection using spectral-spatial information for hyperspectral image classification

Abstract This paper presents a dynamic classifier selection approach for hyperspectral image classification, in which both spatial and spectral information are used to determine a pixel’s label once the remaining classified pixels’ neighborhood meets the threshold. For volumetric texture feature extraction, a volumetric gray level co-occurrence matrix is used; for spectral feature extraction, a minimum estimated abundance covariance-based band selection is used. Two hyperspectral remote sensing datasets, HYDICE Washington DC Mall and AVIRIS Indian Pines, are employed to evaluate the performance of the developed method. The classification accuracies of the two datasets are improved by 1.13% and 4.47%, respectively, compared with the traditional algorithms using spectral information. The experimental results demonstrate that the integration of spectral information with volumetric textural features can improve the classification performance for hyperspectral images.

[1]  Jon Atli Benediktsson,et al.  Advances in Spectral-Spatial Classification of Hyperspectral Images , 2013, Proceedings of the IEEE.

[2]  Kagan Tumer,et al.  Error Correlation and Error Reduction in Ensemble Classifiers , 1996, Connect. Sci..

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

[4]  James C. Bezdek,et al.  Decision templates for multiple classifier fusion: an experimental comparison , 2001, Pattern Recognit..

[5]  Jon Atli Benediktsson,et al.  Multiple Spectral–Spatial Classification Approach for Hyperspectral Data , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[6]  J. Dubois,et al.  Evaluation Of The Grey-level Co-occurrence Matrix Method For Land-cover Classification Using Spot Imagery , 1990 .

[7]  Paolo Gamba,et al.  Improved VHR Urban Area Mapping Exploiting Object Boundaries , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Chen Chen,et al.  Reconstruction of Hyperspectral Imagery From Random Projections Using Multihypothesis Prediction , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Qiong Jackson,et al.  Adaptive Bayesian contextual classification based on Markov random fields , 2002, IEEE Trans. Geosci. Remote. Sens..

[10]  Thomas G. Dietterich,et al.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[11]  N. Younan,et al.  Noise-Adjusted Principal Component Analysis for Buried Radioactive Target Detection and Classification , 2010, IEEE Transactions on Nuclear Science.

[12]  Kevin W. Bowyer,et al.  Combination of multiple classifiers using local accuracy estimates , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Wei Zhang,et al.  Multiple Classifier System for Remote Sensing Image Classification: A Review , 2012, Sensors.

[14]  Alberto Del Bimbo.  Image Analysis and Processing , 1997, Lecture Notes in Computer Science.

[15]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[16]  Chen Chen,et al.  Spectral–Spatial Preprocessing Using Multihypothesis Prediction for Noise-Robust Hyperspectral Image Classification , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[17]  G. Foody.  Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy , 2004 .

[18]  Chen Chen,et al.  Spectral-Spatial Classification of Hyperspectral Image Based on Kernel Extreme Learning Machine , 2014, Remote. Sens..

[19]  Jon Atli Benediktsson,et al.  Multiple Classifier Systems in Remote Sensing: From Basics to Recent Developments , 2007, MCS.

[20]  Paul C. Smits,et al.  Multiple classifier systems for supervised remote sensing image classification based on dynamic classifier selection , 2002, IEEE Trans. Geosci. Remote. Sens..

[21]  Wei Tang,et al.  Ensembling neural networks: Many could be better than all , 2002, Artif. Intell..

[22]  Ludmila I. Kuncheva,et al.  Switching between selection and fusion in combining classifiers: an experiment , 2002, IEEE Trans. Syst. Man Cybern. Part B.

[23]  Kurt H. Riitters,et al.  An indicator of forest dynamics using a shifting landscape mosaic , 2009 .

[24]  Fabio Roli,et al.  Methods for dynamic classifier selection , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[25]  Fabio Roli,et al.  Adaptive Selection of Image Classifiers , 1997, ICIAP.

[26]  W. Tobler.  A Computer Movie Simulating Urban Growth in the Detroit Region , 1970 .

[27]  Emmanuel Tonye,et al.  Evaluation of speckle filtering and texture analysis methods for land cover classification from SAR images , 2002 .

[28]  Qian Du,et al.  Improving urban land use and land cover classification from high-spatial-resolution hyperspectral imagery using contextual information , 2010 .

[29]  Qian Du,et al.  Optical Flow and Principal Component Analysis-Based Motion Detection in Outdoor Videos , 2010, EURASIP J. Adv. Signal Process..

[30]  Chun-Kai Chang,et al.  3D Computation of Gray Level Co-occurrence in Hyperspectral Image Cubes , 2007, EMMCVPR.

[31]  Anne M. P. Canuto,et al.  Investigating the influence of the choice of the ensemble members in accuracy and diversity of selection-based and fusion-based methods for ensembles , 2007, Pattern Recognit. Lett..

[32]  Gian Luca Marcialis,et al.  A study on the performances of dynamic classifier selection based on local accuracy estimation , 2005, Pattern Recognit..

[33]  Jon Atli Benediktsson,et al.  Classification of Hyperspectral Images by Using Extended Morphological Attribute Profiles and Independent Component Analysis , 2011, IEEE Geoscience and Remote Sensing Letters.

[34]  Johannes R. Sveinsson,et al.  Classification of hyperspectral data from urban areas based on extended morphological profiles , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[35]  N. P. Angelo,et al.  On the application of Gabor filtering in supervised image classification , 2003 .

[36]  Qian Du,et al.  An Efficient Method for Supervised Hyperspectral Band Selection , 2011, IEEE Geoscience and Remote Sensing Letters.

[37]  Peijun Du,et al.  Adaptive affinity propagation with spectral angle mapper for semi-supervised hyperspectral band selection. , 2012, Applied optics.

[38]  Robert Sabourin,et al.  From dynamic classifier selection to dynamic ensemble selection , 2008, Pattern Recognit..

[39]  Q. M. Jonathan Wu,et al.  Gaussian-Mixture-Model-Based Spatial Neighborhood Relationships for Pixel Labeling Problem , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).