SPS Talks 2026 - Dr. Lucas Pedroso ramos

Title: Robust Principal Component Analysis for SAR Change Detection: From Matrix to Tensor Decomposition Presenter: Dr. Lucas Pedroso Ramos Link: meet.google.com/yoy-bmne-twe Date: October, 30th (Friday) (30/10/2026) Time: 10:00 am (GMT-3) Abstract: Synthetic Aperture Radar (SAR) change detection plays an important role in remote sensing applications, enabling the identification and monitoring of changes in the Earth's surface under different environmental and acquisition conditions. However, accurately distinguishing meaningful changes from background variations, speckle noise, and other unwanted effects remains a challenging task.This talk explores the application of Robust Principal Component Analysis (RPCA) to SAR change detection, focusing on the evolution from matrix-based approaches to higher-order tensor decomposition techniques. By exploiting low-rank and sparse representations, these methods aim to separate background information from relevant changes while preserving the underlying spatial and temporal structures of SAR data. The presentation will discuss the main concepts, methodological developments, and research findings, highlighting the advantages and challenges associated with matrix and tensor-based formulations.In addition to the technical contributions, the talk will provide insights into the research journey behind these developments, from academic investigations and international collaborations to current research activities involving advanced SAR signal processing and real-world applications. Short Bio: Lucas Pedroso Ramos received his Bachelor's degree in Electrical Engineering from the Federal University of Pampa (UNIPAMPA), Alegrete, Brazil, and his Master's and Ph.D. degrees from the Aeronautics Institute of Technology (ITA), Brazil, with his doctoral degree completed in 2025. His doctoral research focused on Robust Principal Component Analysis and matrix and tensor decomposition techniques for Synthetic Aperture Radar (SAR) change detection. During his doctoral studies, he was a visiting researcher at Blekinge Institute of Technology (BTH), Sweden, for one year, through an international research collaboration supported by the Brazilian Ministry of Science, Technology and Innovation (MCTI), CNPq, CISB, and Saab AB. His research has been published in international journals such as IEEE Transactions on Geoscience and Remote Sensing, IEEE Geoscience and Remote Sensing Letters, and IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. His doctoral research received the Best Ph.D. Thesis Award at the 2026 Brazilian Symposium on Telecommunications and Signal Processing (SBrT 2026). He also received an Honorable Mention in the Cecchini Award for his master's research. He is currently a Senior Researcher at the Technology Innovation Institute (TII), Abu Dhabi, United Arab Emirates, where his research focuses on SAR signal processing, advanced data analysis, and artificial intelligence techniques for remote sensing applications, including subsurface target detection. His research interests include robust matrix and tensor decomposition, statistical signal processing, SAR image analysis, change detection, and machine learning.