Time series analysis of remote sensing images for anomaly detection

• Grant number: 20/06477-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2020
• End date: July 31, 2021
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Maurício Araújo Dias
• Grantee: Giovanna Carreira Marinho
• Host Institution: Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil

Abstract

The use of techniques for the analysis of remote sensing images aided by different classifiers has contributed significantly to the development of new methodologies by the scientific community, and these methodologies have been successfully used in numerous applications. Recently, a strategy was proposed to use classifiers to locate water pollution in remote sensing images, which is based on a taxonomy for detecting anomalies. Despite this, studies on the application of this strategy in time series of images are still needed. This work proposes to analyze time series of remote sensing images in order to increase the number of tools, approaches and methodologies that may contribute to the area of anomaly detection with a focus on water pollution localization. The methodology which will be used for achieving this goal initially performs pre-processing on the images (based on the application of contrast enhancement and pan-sharpening) and sampling. Next, training of classifiers for contextual and non-contextual classifications are performed. The metrics accuracy, precision, recall and F-measure (or F1-score) will be used to validate the results, in order to perform a quantitative analysis.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

MARINHO, GIOVANNA CARREIRA; MARCILIO JUNIOR, WILSON ESTECIO; DIAS, MAURICIO ARAUJO; ELER, DANILO MEDEIROS; NEGRI, ROGERIO GALANTE; CASACA, WALLACE. Dimensionality Reduction and Anomaly Detection Based on Kittler's Taxonomy: Analyzing Water Bodies in Two Dimensional Spaces. REMOTE SENSING, v. 15, n. 16, p. 24-pg., 2023-08-01. (16/24185-8, 21/03328-3, 20/06477-7, 21/01305-6)

DIAS, MAURICIO ARAUJO; MARINHO, GIOVANNA CARREIRA; NEGRI, ROGERIO GALANTE; CASACA, WALLACE; MUNOZ, IGNACIO BRAVO; ELER, DANILO MEDEIROS. A Machine Learning Strategy Based on Kittler's Taxonomy to Detect Anomalies and Recognize Contexts Applied to Monitor Water Bodies in Environments. REMOTE SENSING, v. 14, n. 9, p. 38-pg., 2022-05-01. (20/06477-7, 21/01305-6, 16/24185-8, 21/03328-3)