Study and development of new Kernel functions with applications on remote sensing image classification

• Grant number: 14/14830-8
• Support Opportunities: Regular Research Grants
• Start date: November 01, 2014
• End date: October 31, 2017
• Field of knowledge: Physical Sciences and Mathematics - Geosciences
• Principal Investigator: Rogério Galante Negri
• Grantee: Rogério Galante Negri
• Host Institution: Instituto de Ciência e Tecnologia (ICT). Universidade Estadual Paulista (UNESP). Campus de São José dos Campos. São José dos Campos , SP, Brazil
• Associated researchers: Luciano Vieira Dutra ; Sidnei João Siqueira Sant'Anna ; Tatiana Sussel Gonçalves Mendes

Abstract

Pattern Recognition is a Computer Science area which aims to deal with classification problems. Remote Sensing image classification is one of the most important applications of Pattern Recognition in environmental studies. Face to the importance of achieve more accurate classification results, develop and enhance image classification techniques is a constant motivation. The emergence of kernel functions has revolutionized Pattern Recognition researches and consequently image classification application, further expanding the research area. This project proposes the study and development of new kernel functions for image classification, aiming to produce more accurate results compared to usual kernels. The validation of the kernels developed from this research will be done using simulated images and practical studies about land use and land cover classification in Brazilian Amazon. (AU)

Scientific publications

(8)

(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)

NEGRI, R. G.; DUTRA, L. V.; SANT'ANNA, S. J. S.; LU, D.. Examining region-based methods for land cover classification using stochastic distances. International Journal of Remote Sensing, v. 37, n. 8, p. 1902-1921, 2016. (14/14830-8)

NEGRI, ROGERIO GALANTE; DA SILVA, ERIVALDO ANTONIO; CASACA, WALLACE. Inducing Contextual Classifications With Kernel Functions Into Support Vector Machines. IEEE Geoscience and Remote Sensing Letters, v. 15, n. 6, p. 962-966, JUN 2018. (13/07375-0, 17/03595-6, 14/08822-2, 14/14830-8)

NEGRI, ROGERIO GALANTE; DUTRA, LUCIANO VIEIRA; FREITAS, CORINA DA COSTA; LU, DENGSHENG. Exploring the Capability of ALOS PALSAR L-Band Fully Polarimetric Data for Land Cover Classification in Tropical Environments. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, v. 9, n. 12, 1, SI, p. 5369-5384, DEC 2016. (07/02139-5, 14/14830-8)

SAPUCCI, GABRIELA RIBEIRO; NEGRI, ROGERIO GALANTE. Hierarchical clustering and stochastic distance for indirect semi-supervised remote sensing image classification. SN APPLIED SCIENCES, v. 1, n. 3, MAR 2019. (18/01033-3, 16/06242-4, 14/14830-8)

E SILVA, R. A.; NEGRI, R. G.; DE MATTOS VIDAL, D.. A new image-based technique for measuring pore size distribution of nonwoven geotextiles. GEOSYNTHETICS INTERNATIONAL, v. 26, n. 3, p. 261-272, JUN 2019. (14/14830-8)

NEGRI, ROGERIO G.; FRERY, ALEJANDRO C.; SILVA, WAGNER B.; MENDES, TATIANA S. G.; DUTRA, LUCIANO V.. Region-based classification of PolSAR data using radial basis kernel functions with stochastic distances. INTERNATIONAL JOURNAL OF DIGITAL EARTH, v. 12, n. 6, p. 699-719, 2019. (14/14830-8)

NEGRI, R. G.; DUTRA, L. V.; SANT'ANNA, S. J. S.. Comparing support vector machine contextual approaches for urban area classification. REMOTE SENSING LETTERS, v. 7, n. 5, p. 485-494, MAY 3 2016. (14/14830-8)

NEGRI, ROGERIO GALANTE; DUTRA, LUCIANO VIEIRA; FREITAS, CORINA DA COSTA; LU, DENGSHENG. Exploring the Capability of ALOS PALSAR L-Band Fully Polarimetric Data for Land Cover Classification in Tropical Environments. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, v. 9, n. 12, p. 16-pg., 2016-12-01. (14/14830-8, 07/02139-5)

Filed patent(s) as a result of this research project