Banca de DEFESA: LUIS ENRIQUE ORTIZ FERNANDEZ

Uma banca de DEFESA de DOUTORADO foi cadastrada pelo programa.
STUDENT : LUIS ENRIQUE ORTIZ FERNANDEZ
DATE: 02/08/2021
TIME: 09:00
LOCAL: Videoconferência
TITLE:

Method to Measure, Model, and Predict Depth and Positioning Errors of RGB-D Cameras in Function of Distance, Velocity, and Vibration

KEY WORDS:

RGB-D Cameras; Smart Markers; Visual Mapping; Visual Localization; Depth Error; Positioning Error; Deep Learning.

PAGES: 138
BIG AREA: Outra
AREA: Robótica, Mecatrônica e Automação
SUMMARY:

This thesis proposes a versatile methodology for measuring, modeling, and predicting errors as the RMSE in the depth and the RPE in the camera positioning using data captured from an RGB-D camera mounted on the top of a low-cost mobile robot platform. The proposed method is divided in three stages, with the very first one consisting on the creation of ground truth data for both 3d points (mapping) and camera poses (localization). The next stage is the acquisition of a data set for RMSE and RPE errors calculation using the mobile platform with the RGB-D camera. Finally, the third step is to model and predict the errors in the measurements of depth and positioning of the camera as a function of distance, speed, and vibration. For this modeling and prediction stage, a simple approach based on MLP neural networks is used. This results in two networks, the N rmse Z for the depth error prediction and the N RPE for the prediction of camera positioning error. Experiments show that the N rmse Z and N RPE have an accuracy of ± 1% and ± 2.5%, respectively. The proposed methodology can be straight used in techniques that require an estimation of the error dynamics, as for example probabilistic robotics for localization and mapping, with RGB-D cameras mounted on UAVs, UGVs, and also USVs (including sailboats). Tasks that use RGB-D sensors, such as environmental monitoring, maintenance of engineering works, and public security, could rely on this approach to obtain the error information associated to the camera measurements (depth and positioning).

BANKING MEMBERS:
Presidente - 2929823 - RAFAEL BESERRA GOMES
Interno - 1345674 - LUIZ MARCOS GARCIA GONCALVES
Externo ao Programa - 1170845 - BRUNO MARQUES FERREIRA DA SILVA
Externo à Instituição - COSIMO DISTANTE - US
Externo à Instituição - ESTEBAN WALTER GONZALEZ CLUA - UFF