Detection of Anomalies Produced by Buried Archaeological Structures Using Nonlinear Principal Component Analysis Applied to Airborne Hyperspectral Image

In this paper, airborne hyperspectral data have been exploited by means of Nonlinear Principal Component Analysis (NLPCA) to test their effectiveness as a tool for archaeological prospection, evaluating their potential for detecting anomalies related to buried archaeological structures. In the literature, the NLPCA was used to decorrelate the information related to a hyperspectral image. The resulting nonlinear principal components (NLPCs) contain information related to different land cover types and biophysical properties, such as vegetation coverage or soil wetness. From this point of view, NLPCA applied to airborne hyperspectral data was exploited to test their effectiveness and capability in highlighting the anomalies related to buried archaeological structures. Each component obtained from the NLPCA has been interpreted in order to assess any tonal anomalies. As a matter of a fact, since every analyzed component exhibited anomalies different in terms of size and intensity, the Separability Index (SI) was applied for measuring the tonal difference of the anomalies with respect to the surrounding area. SI has been evaluated for determining the potential of anomalies detection in each component. The airborne Multispectral Infrared and Visible Imaging Spectrometer (MIVIS) images, collected over the archaeological Park of Selinunte, were analyzed for this purpose. In this area, the presence of remains, not yet excavated, was reported by archaeologists. A previous analysis of this image, carried out to highlight the buried structures, appear to match the archaeological prospection. The results obtained by the present work demonstrate that the use of the NLPCA technique, compared to previous approaches emphasizes the ability of airborne hyperspectral images to identify buried structures. In particular, the adopted data processing flow chart (i.e., NLPCA and SI techniques, data resampling criteria and anomaly evaluations criteria) applied to MIVIS airborne hyperspectral data, collected over Selinunte Archaeological Park, highlighted the ability of the NLPCA technique in emphasizing the anomalies related to the presence of buried structure.

[1]  R. Cavalli,et al.  Remote hyperspectral imagery as a support to archaeological prospection , 2007 .

[2]  Fabio Del Frate,et al.  Feature reduction of hyperspectral data using Autoassociative neural networks algorithms , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[3]  Fabio Del Frate,et al.  Pixel Unmixing in Hyperspectral Data by Means of Neural Networks , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Stefano Pignatti,et al.  Optimal Spectral Domain Selection for Maximizing Archaeological Signatures: Italy Case Studies , 2009, Sensors.

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

[6]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[7]  B. Aminzadeh,et al.  Identifying the boundaries of the historical site of Persepolis using remote sensing , 2006 .

[8]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[9]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[10]  Bo Du,et al.  Hybrid Detectors Based on Selective Endmembers , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Stefano Pignatti,et al.  Laboratory activity for a new procedure of MIVIS calibration and relative validation with test data , 2006 .

[12]  Antonio J. Plaza,et al.  Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformations , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[13]  P. Switzer,et al.  A transformation for ordering multispectral data in terms of image quality with implications for noise removal , 1988 .

[14]  Jon Atli Benediktsson,et al.  Linear Versus Nonlinear PCA for the Classification of Hyperspectral Data Based on the Extended Morphological Profiles , 2012, IEEE Geoscience and Remote Sensing Letters.

[15]  Gary A. Shaw,et al.  Hyperspectral subpixel target detection using the linear mixing model , 2001, IEEE Trans. Geosci. Remote. Sens..

[16]  Lori M. Bruce,et al.  Automated detection of subpixel hyperspectral targets with continuous and discrete wavelet transforms , 2001, IEEE Trans. Geosci. Remote. Sens..

[17]  Apostolos Sarris,et al.  Detection of Neolithic Settlements in Thessaly (Greece) Through Multispectral and Hyperspectral Satellite Imagery , 2009, Sensors.

[18]  M. Altaweel.  The use of ASTER satellite imagery in archaeological contexts , 2005 .

[19]  Dominic Powlesland,et al.  Enhancing the record through remote sensing: the application and integration of multi-sensor, non-invasive remote sensing techniques for the enhancement of the Sites and Monuments Record. Heslerton Parish Project, N. Yorkshire, England , 1997 .

[20]  C. A. Murthy,et al.  Unsupervised Feature Selection Using Feature Similarity , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Alain De Wulf,et al.  Satellite imagery and archaeology: the example of CORONA in the Altai Mountains , 2006 .

[22]  Christian Jutten,et al.  Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture , 1991, Signal Process..

[23]  Joachim Selbig,et al.  Non-linear PCA: a missing data approach , 2005, Bioinform..

[24]  G. M. Foody,et al.  Relating the land-cover composition of mixed pixels to artificial neural network classification outpout , 1996 .

[25]  A F Goetz,et al.  Imaging Spectrometry for Earth Remote Sensing , 1985, Science.

[26]  Daniel N. M. Donoghue,et al.  Remote sensing in archaeological research , 1991 .

[27]  G. Licciardi.  Neural network architectures for information extraction from hyper-spectral images , 2010 .

[28]  M. Kramer.  Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[29]  Kostas Stamatiou,et al.  Combining GeoEye-1 Satellite Remote Sensing, UAV Aerial Imaging, and Geophysical Surveys in Anomaly Detection Applied to Archaeology , 2011, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[30]  I. Scollar.  Archaeological Prospecting and Remote Sensing , 1990 .

[31]  A. Sarris,et al.  Detection of exposed and subsurface archaeological remains using multi-sensor remote sensing , 2007 .

[32]  V. D. Laet,et al.  Methods for the extraction of archaeological features from very high-resolution Ikonos-2 remote sensing imagery, Hisar (southwest Turkey) , 2007 .

[33]  Stefano Pignatti,et al.  Aerosol Optical Retrieval and Surface Reflectance from Airborne Remote Sensing Data over Land , 2010, Sensors.

[34]  Teuvo Kohonen,et al.  An introduction to neural computing , 1988, Neural Networks.

[35]  Fred A. Kruse,et al.  The Spectral Image Processing System (SIPS) - Interactive visualization and analysis of imaging spectrometer data , 1993 .

[36]  Eyal Ben-Dor,et al.  Airborne Thermal Video Radiometry and Excavation Planning at Tel Leviah, Golan Heights, Israel , 1999 .

[37]  Fabio Del Frate,et al.  Dimensionality reduction of hyperspectral data: Assessing the performance of Autoassociative Neural Networks , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[38]  Diofantos G. Hadjimitsis,et al.  Hyperspectral Ground Truth Data for the Detection of Buried Architectural Remains , 2010, EuroMed.

[39]  S. Pascucci,et al.  Specific spectral bands for different land cover contexts to improve the efficiency of remote sensing archaeological prospection: The Arpi case study , 2009 .

[40]  Qian Du,et al.  Anomaly Detection and Reconstruction From Random Projections , 2012, IEEE Transactions on Image Processing.

[41]  A. Kahle.  Surface emittance, temperature, and thermal inertia derived from Thermal Infrared Multispectral Scanner (TIMS) data for Death Valley, California , 1987 .

[42]  M. J. F. Fowler.  A high-resolution satellite image of archaeological features to the south of Stonehenge , 2001 .

[43]  Eyal Ben-Dor,et al.  Detection of buried ancient walls using airborne thermal video radiometry , 2001 .

[44]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[45]  D. Donoghue,et al.  Evaluation of Corona and Ikonos high resolution satellite imagery for archaeological prospection in western Syria , 2007, Antiquity.