Anomaly detection in hyperspectral images via regularization by denoising

Mauro Luiz Brandão Junior; Victor Carneiro Lima; Thomás Antônio Portugal Pereira Teixeira; Eduardo Rodrigues de Lima; Renato da Rocha Lopes

Anomaly detection in hyperspectral images via regularization by denoising

Mauro Luiz Brandão Junior, Victor Carneiro Lima , Thomás Antônio Portugal Pereira Teixeira, Eduardo Rodrigues de Lima, Renato da Rocha Lopes

Material

ARTIGO

Idioma

Inglês

Nota geral Agradecimentos: This work was supported in part by the R&D Project PD-07130-0062/2020 "Predictive Failure Analysis by Artificial Intelligence," funded by Transmissora Aliança de Energia Elétrica SA (TAESA) with resources from ANEEL R&D Program, and in part by the National Council for Scientific and... Ver mais Agradecimentos: This work was supported in part by the R&D Project PD-07130-0062/2020 "Predictive Failure Analysis by Artificial Intelligence," funded by Transmissora Aliança de Energia Elétrica SA (TAESA) with resources from ANEEL R&D Program, and in part by the National Council for Scientific and Technological Development, under Grant 305480/2018-9 Ver menos

Acompanhado de errata

Resumo Abstract: In a recent work, Fu et al. (2021) proposed an anomaly detector (AD) for hyperspectral images called DeCNN-AD, which decomposes the image in a low rank representation of the background and the anomalies. DeCNN-AD is regularized by an implicit plug and play prior (PnP), providing... Ver mais Abstract: In a recent work, Fu et al. (2021) proposed an anomaly detector (AD) for hyperspectral images called DeCNN-AD, which decomposes the image in a low rank representation of the background and the anomalies. DeCNN-AD is regularized by an implicit plug and play prior (PnP), providing state-of-the-art anomaly detection performance in hyperspectral images. In this article, we propose a different AD using the Regularization by Denoising (RED) framework. The regularizer that emerges in RED algorithms is advantageous in the sense that it can be minimized by many solvers, unlike PnP, which has to be rederived for each specific solver like the alternating direction method of multipliers or the proximal gradient method. The proposed detector was compared to DeCNN-AD in several experiments, and was shown to present a more stable behavior better convergence properties, to be less sensitive to the choice of parameters, while leading to very similar performance in terms of optimal AUC of receiver operating characteristic curves Ver menos

Nota de informação sobre financiamento

CONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO - CNPQ

305480/2018-9

Direito de acesso

Aberto

Assuntos

Artigo original

Monitoramento do ruído

Detecção de anomalias

Imagem hiperespectral

Autoria

Brandão Junior, Mauro Luiz, 1995 Autor