Reduced egomotion estimation drift using omnidirectional views

Autor:	Bastanlar, Yalin
Rok vydání:	2013
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Robotics
Zdroj:	Electronic Letters on Computer Vision and Image Analysis, vol.13(3), p.1-12, 2014
Druh dokumentu:	Working Paper
Popis:	Estimation of camera motion from a given image sequence becomes degraded as the length of the sequence increases. In this letter, this phenomenon is demonstrated and an approach to increase the estimation accuracy is proposed. The proposed method uses an omnidirectional camera in addition to the perspective one and takes advantage of its enlarged view by exploiting the correspondences between the omnidirectional and perspective images. Simulated and real image experiments show that the proposed approach improves the estimation accuracy. Comment: Another publisher does not want this article to be shared at arxiv.org in order to publish it
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1307.6962 Zobrazit plný text záznamu View this record from Arxiv