Self-localization of mobile robots is often performed visually, whereby the resolution of the images influences a lot the computation time. This paper examines how a reduction of the image resolution affects localization accuracy. The images will be downscaled, preserving their aspect ratio, up to a tiny resolution of 15x11 and 20x15 pixels. The results are based on extensive tests on different datasets that have been recorded indoors by a small differential drive robot and outdoors by a flying quadrocopter. Four well-known global image features and a pixelwise image comparison method are compared under realistic conditions such as illumination changes and translations. The results show that even when reducing the image resolution down to the tiny resolutions above, accurate localization is achievable. In this way, the localization process can be speeded up considerably.
Visual self-localization with tiny images
Visuelle Selbstlokalisierung mittels kleinsten Bildern
2009
8 Seiten, 2 Bilder, 1 Tabelle, 11 Quellen
Aufsatz (Konferenz)
Englisch
Tiny solar cells power tiny MEMS machines
British Library Online Contents | 2009
Kraftfahrwesen | 1981
|Online Contents | 1996
SAE | 2000
|