Dissertação de Mestrado de Lucas Nedel Kirsten

DEFESA DE DISSERTAÇÃO DE MESTRADO

Aluno: Lucas Nedel Kirsten
Orientador: Prof. Dr. Claudio Rosito Jung

Título: Detecting and Tracking Cells in Microscopic Images using Oriented Representations
Linha de Pesquisa: Processamento de Imagens, Visão Computacional e Reconhecimento de Padrões

Data: 23/05/2023
Horário: 15h30min
Local: Esta banca ocorrerá de forma remota. Acesso público disponibilizado pelo link: https://meet.google.com/yah-awew-cqv?hs=224

Banca Examinadora:
– Profa. Dra. Mariana Recamonde Mendoza (UFRGS)
– Prof. Dr. Eduardo Antônio Barros da Silva (UFRJ)
– Prof. Dr. Thiago Lopes Trugillo da Silveira (UFRGS)

Presidente da Banca: Prof. Dr. Claudio Rosito Jung

Abstract: Cell detection and tracking are paramount for bio-analysis. Recent approaches rely on the tracking-by-model evolution paradigm, which usually consists of training end-to-end deep learning models to detect and track the cells on the frames with promising results. However, such methods require extensive amounts of annotated data, which is time-consuming and often requires specialized annotators. This work proposes a new approach based on the classical tracking-by-detection paradigm that alleviates the requirement of annotated data. More precisely, it approximates the cell shapes as oriented ellipses and then uses generic-purpose oriented object detectors to identify the cells in each frame. We then rely on a global data association algorithm that explores temporal cell similarity using probability distance metrics, considering that the ellipses relate to two-dimensional Gaussian distributions. Our results show that our method can achieve detection and tracking results competitively with state-of-the-art techniques that require considerably more extensive data annotation. Our code is available at: <https://github.com/LucasKirsten/Deep-Cell-Tracking-EBB>.

Keywords: Oriented object detection. Cell detection. Cell tracking.