Localization for mobile robots using skyline in panoramic images


KOKU A. B.

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, cilt.34, sa.3, ss.1630-1644, 2019 (SCI-Expanded) identifier identifier

Özet

Advances in robotics liberated robots from factory floors by the end of 20th century. Use of robots in our daily lives is only expected to increase in time. Robots, while relieving us of the burden of tedious, hard and dangerous tasks, most of them are still expected to be territorial, i.e. they will operate in a predefined or rather bounded environment. For enhanced performance, a robot should be familiar with its territory. In this work, use of skylines extracted from panoramic images is studied in order to provide localization. To achieve localization, first a special map is prepared using a series of panoramic images taken from the territory. Images, those taken from the vicinity of this map at different times and under different weather conditions, are localized on this map. Given that the proposed method only focuses on a small portion of the panoramic image, it is relatively easier to implement in various hardware platforms (especially those with limited computational capabilities) in comparison to the methods that process the whole image.