A generalized control chart for anomaly detection in SAR imagery. (March 2023)

• Record Type: Journal Article
• Authors: Sagrillo, Murilo; Guerra, Renata Rojas; Machado, Renato; Bayer, Fábio M.
• Is Part Of: Computers & industrial engineering. Volume 177(2023)
• Publication Date: 2023-03
• Subjects: Burr XII distribution -- CARABAS II system -- Digital image monitoring -- Earth observation -- SAR image modeling; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2023.109030
• Languages: English
• ISSNs: 0360-8352

Abstract

Abstract: Synthetic aperture radar (SAR) imagery is widely used in Earth observation (EO) applications such as land-use change monitoring and target detection. For such applications, it is important to have accurate knowledge of the statistical properties of SAR images to make good use of the information available. Therefore, it is essential to have appropriate statistical distributions to model the SAR data. In this context, the goal of this paper is threefold. First, a new parameterization of the Burr XII distribution that generalizes some widely used distributions for modeling SAR data is proposed. Second, based on the reparameterized distribution, a generalized control chart for anomaly detection in digital images is introduced. Using Monte Carlo simulations, the power detection of the proposed control chart by the empirical run length distribution is evaluated. Finally, the proposed methodology is applied to a real problem of anomaly detection. The problem of interest is the detection of military targets concealed in a forest region. The results suggest the relevance of the proposal to detect anomalies in SAR imagery, evidencing its practical applicability in EO problems. Highlights: A new parameterization of the Burr XII model, called Burr b SAR model, is introduced. The Burr b SAR model has the potential to model synthetic aperture radar (SAR) images. The Burr b SAR parameters have physical interpretation for SAR image. The Burr b SAR model generalizes important probabilistic models in the SAR context. A control chart based on the Burr b SAR model is proposed for anomaly detection.