Dissertação de Mestrado Integrado em Engenharia Electrotécnica e de Computadores apresentada à Faculdade de Ciências e TecnologiaEste trabalho foi desenvoolvido no contexto de uma dissertação de mestrado do ramo de Automação e tem como objectivo explorar métodos baseados em "machine learning", capazes de estimar poses para objectos e implementar um método com a capacidade de gerar estimativas acerca de objectos variados, presentes num ambiente de trabalho monitorizado por um camera RGB-D (Kinect). O método de [Kehl et al., 2016] explora redes neuronais simples e convolucionais, com arquitecturas de "Auto-Encoder", para codificar amostras de imagens RGB-D em vectores de características e, de seguida, descodificá-los de volta nas amostras in...
Several challenges in computer vision and robotics involve developing algorithms capable of using pa...
This project focuses on creating a system for human body segmentation meant to be used for pose esti...
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Com...
Dissertação de Mestrado Integrado em Engenharia Electrotécnica e de Computadores apresentada à Facul...
As part of the doctoral thesis, the objective is to develop a Human-Machine Interface to control a a...
Orientador : Prof. Dr. Leandro dos Santos CoelhoDissertação (mestrado) - Universidade Federal do Par...
Dissertação de Mestrado Integrado em Engenharia Electrotécnica e de Computadores apresentada à Facul...
This thesis presents a learning based approach for fast orientation estimation from RGB-D images. Fo...
Reconhecer a identidade de seres humanos a partir de imagens digitais gravadas de suas faces é uma e...
Usage of real objects as links between real and virtual information is one key aspect in augmented r...
Estimating object’s 6D pose is an important aspect of automating even complicated processes, especia...
Pose estimation is a topic of important research in the fields of robotic and computer vision, parti...
With the rise of robotic and camera systems and the success of deep learning in computer vision, th...
Trabajo presentado a la IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), ...
This thesis proposes, develops and evaluates different convolutional neural network based methods fo...
Several challenges in computer vision and robotics involve developing algorithms capable of using pa...
This project focuses on creating a system for human body segmentation meant to be used for pose esti...
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Com...
Dissertação de Mestrado Integrado em Engenharia Electrotécnica e de Computadores apresentada à Facul...
As part of the doctoral thesis, the objective is to develop a Human-Machine Interface to control a a...
Orientador : Prof. Dr. Leandro dos Santos CoelhoDissertação (mestrado) - Universidade Federal do Par...
Dissertação de Mestrado Integrado em Engenharia Electrotécnica e de Computadores apresentada à Facul...
This thesis presents a learning based approach for fast orientation estimation from RGB-D images. Fo...
Reconhecer a identidade de seres humanos a partir de imagens digitais gravadas de suas faces é uma e...
Usage of real objects as links between real and virtual information is one key aspect in augmented r...
Estimating object’s 6D pose is an important aspect of automating even complicated processes, especia...
Pose estimation is a topic of important research in the fields of robotic and computer vision, parti...
With the rise of robotic and camera systems and the success of deep learning in computer vision, th...
Trabajo presentado a la IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), ...
This thesis proposes, develops and evaluates different convolutional neural network based methods fo...
Several challenges in computer vision and robotics involve developing algorithms capable of using pa...
This project focuses on creating a system for human body segmentation meant to be used for pose esti...
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Com...