®®®® SIIA Público

Título del libro: 19th Ieee International Conference On Autonomous Robot Systems And Competitions, Icarsc 2019
Título del capítulo: Feature detection using Hidden Markov Models for 3D-visual recognition

Autores UNAM:
CARLOS ADRIAN SARMIENTO GUTIERREZ; JESUS SAVAGE CARMONA; LUIS ANGEL CONTRERAS TOLEDO; ABEL PACHECO ORTEGA; JOSE MAURICIO MATAMOROS DE MARIA Y CAMPOS;
Autores externos:

Idioma:
Inglés
Año de publicación:
2019
Palabras clave:

Anthropomorphic robots; Computer vision; Feature extraction; Object recognition; Pattern recognition; Trellis codes; 3-D feature extraction; Feature detection; Place recognition; Point cloud; Probabilistic models; Service robots; Visual recognition; Hidden Markov models


Resumen:

In this work, we present a novel implementation for visual recognition using probabilistic models. Given a scene view, we first propose a 3D feature extraction from a point cloud as a series of observations for a Hidden Markov Model; then, we evaluate the Profile HMM in the place recognition task using a publicly available dataset. Furthermore, we evaluated a classical HMM in the object recognition task in the context of anthropomorphic service robots. Results show that our approach performs well in the aforementioned tasks with high recognition rates. © 2019 IEEE.


Entidades citadas de la UNAM: