Pages 101-108
This paper proposes a new self-localization method using an omnidirectional image sensor which can observe a surrounding environment with 360-degrees of view. The method extracts information which is identical for the position of a sensor and invariant against the rotation of the sensor by generating an autocorrelation image from an observed omnidirectional image. The location of the sensor is identified by evaluating the similarity among the autocorrelation images in low dimensional eigenspaces. We have conducted experiments with real image sequences and examined the performance of the proposed method. The results show that accurate and robust estimation of the sensor's position is possible.