Title :
Mobile robot path drift estimation using Visual Streams
Author :
Filho, H.P. ; Ohya, A.
Author_Institution :
Intell. Robot Lab., Univ. of Tsukuba, Tsukuba, Japan
Abstract :
Differential Visual Streams (DiVS) is an image processing method to quantify changes in picture sequences. It works on monocular images captured by a single uncalibrated camera. Experiments show DiVS provides a sound basis for an appearance-based navigation system effective under a variety of lighting conditions (both controlled and natural), landmark occlusions and the presence of moving objects.
Keywords :
image motion analysis; image sequences; lighting; mobile robots; object detection; path planning; robot vision; DiVS; appearance-based navigation system; differential visual streams; image processing method; landmark occlusions; lighting conditions; mobile robot path drift estimation; monocular images; moving objects; picture sequences; uncalibrated camera; visual streams; Cameras; Navigation; Robot vision systems; Streaming media; Vectors; Visualization;
Conference_Titel :
System Integration (SII), 2014 IEEE/SICE International Symposium on
Conference_Location :
Tokyo
Print_ISBN :
978-1-4799-6942-5
DOI :
10.1109/SII.2014.7028036
