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

Rosa Maria Cavalli (1) , Giorgio Licciardi (2) , Jocelyn Chanussot (2)

1 IIA - Institute of Atmospheric Pollution Research
2 GIPSA-SIGMAPHY - GIPSA - Signal Images Physique

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.

Mots clés: Hyperspectral image processing; nonlinear PCA; anomaly detection; archaeological prospection

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Rosa Maria Cavalli, Giorgio Licciardi, Jocelyn Chanussot. Detection of Anomalies Produced by Buried Archaeological Structures Using Nonlinear Principal Component Analysis Applied to Airborne Hyperspectral Image. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2013, 6 (2), pp.659-669. ⟨10.1109/JSTARS.2012.2227301⟩. ⟨hal-00798517⟩