Banca de DEFESA: FILIPE CAMPOS DE ALCANTARA LINS

Uma banca de DEFESA de DOUTORADO foi cadastrada pelo programa.
STUDENT : FILIPE CAMPOS DE ALCANTARA LINS
DATE: 28/07/2023
TIME: 09:00
LOCAL: Sala do Google Meet (meet.google.com/avg-wnkv-hfb)
TITLE:
DPO: Direct Planar Odometry with Stereo Camera

KEY WORDS:

Visual Odometry; SLAM; Direct Method; Planar Features; Second-Order Optimization; Stereo Camera.


PAGES: 70
BIG AREA: Engenharias
AREA: Engenharia Elétrica
SUBÁREA: Eletrônica Industrial, Sistemas e Controles Eletrônicos
SPECIALTY: Automação Eletrônica de Processos Elétricos e Industriais
SUMMARY:

Contemporary Visual Odometry (VO) methodologies generally are created upon point-based approaches to estimate the camera's pose and a representation of the environment explored. Direct Sparse Odometry (DSO) is the most popular point-based technique of a class of approaches called direct methods. Many works presented improvements in the point-based VO area using DSO characteristics as the fundamentals of these approaches. However, only recently, two new monocular plane-based DSO have been presented. The first approach utilizes a learning-based plane estimator to generate initial plane estimates, which may lead to optimization issues. The second approach restricts plane detection to horizontal and vertical orientations, making it more suitable for structured environments.

This thesis presents a stereo plane-based VO technique - Direct Planar Odometry (DPO) - that employs planes as features in a Sliding window optimization framework and utilizes unit dual quaternion as the pose parameter. Our experiments show that the proposed methods achieved comparable results to the Stereo DSO point-based approach.


COMMITTEE MEMBERS:
Presidente - 1242315 - PABLO JAVIER ALSINA
Interno - 350751 - ADELARDO ADELINO DANTAS DE MEDEIROS
Externo ao Programa - 4523538 - MARCELO BORGES NOGUEIRA - UFRNExterno à Instituição - VALDIR GRASSI JUNIOR - USP
Externo à Instituição - ANDERSON ABNER DE SANTANA SOUZA - UERN
Notícia cadastrada em: 30/06/2023 09:11
SIGAA | Superintendência de Tecnologia da Informação - (84) 3342 2210 | Copyright © 2006-2024 - UFRN - sigaa02-producao.info.ufrn.br.sigaa02-producao