Lucas Tsutsui da Silva
Semi-Supervised Learning for Automatic Improvement of Onboard Object Detection Models on Small Satellites
University New South Wales Sydney
Lucas Tsutsui da Silva holds a Bachelors degree in Computer Engineering from Federal University of Mato Grosso do Sul (UFMS) in Brazil, and Masters of Computer Science and Computational Mathematics from the University of São Paulo, also in Brazil. In his master’s research, Tsutsui da Silva worked on lightweight classification models for resource-constrained hardware, such as low-power microcontrollers. Currently, he is pursuing a PhD at the University of New South Wales (UNSW) Sydney. Tsutsui da Silva’s research aims to produce a new class of intelligent satellite systems capable of automatically refining onboard object detection models on small satellites in orbit. He is developing a solution based on semi-supervised learning to improve the model performance using unlabeled images captured by the satellite. Tsutsui da Silva believes his research will potentially impact various satellite applications that employ object detection algorithms, regardless of the domain.
Project Title: Semi-Supervised Learning for Automatic Improvement of Onboard Object Detection Models on Small Satellites