%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2015/07.28.13.56
%2 sid.inpe.br/sibgrapi/2015/07.28.13.56.04
%T Análise de Desempenho de Algoritmos Detectores de Keypoints para um Sistema de Navegação Visual de Robôs Baseados em Smartphones
%D 2015
%A Santana, Bruno A. S.,
%A Maia, Rosiery da S.,
%A Figuerola, Wilfredo B.,
%A Souza, Anderson A. S.,
%@affiliation UERN
%@affiliation UERN
%@affiliation UERN
%@affiliation UERN
%E Vieira, Thales Miranda de Almeida,
%E Mello, Vinicius Moreira,
%B Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)
%C Salvador, BA, Brazil
%8 26-29 Aug. 2015
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K Computer Vision, Visual Navigation System, CellBots.
%X Smartphones have emerged in recent research, as a possible alternative platform for acquisition, processing and control of mobile robotic systems (Cellbots). Having a smartphone as a mobile robot command center became attractive because it can collect data from cameras, GPS, accelerometer and other sensors, besides their communications capabilities. By acquiring and processing the images from the smartphone cameras, for example, it is possible to collect useful data for the implementation of a robotic visual navigation system with visual odometry, visual mapping and object recognition. This paper presents a study of three major keypoints detection algorithms to implement a visual navigation system for a CellBot. A comparative study from the implementations and testing of these algorithms on a smartphone is presented at the end of this work, in order to facilitate the choice of the most appropriate algorithm to be used in the navigation system.
%@language pt
%3 wuw2015.pdf