Development of a forward-hemispherical vision sensor for acquisition of a panoramic integration map

Abstract

The target of this research is to develop a common-use sensor which is useful for navigation and mission for rescue operation. By combined use of an ODV (omnidirectional vision) with a hemispherical forward-visual-field using a direct and reflection hybrid optical system, a RTK-GPS (real time kinematics-global positioning system) and a MEMS (micro electro mechanical systems) IMU (inertial measurement unit), this sensor outputs a realtime image for remote control of a mobile robot and a panoramic integration map, including information on three-dimensional own-position, with a continuous panoramic image for searching victims and for making a rescue plan. The evaluation of the panoramic integration map and the Kalman filter based self-positioning reveals that the proposed method is valid and effective

DOI: 10.1109/ROBIO.2004.1521755

Cite this paper

@article{Eino2004DevelopmentOA, title={Development of a forward-hemispherical vision sensor for acquisition of a panoramic integration map}, author={Jyun-ichi Eino and Masakazu Araki and Jun-ichi Takiguchi and Takumi Hashizume}, journal={2004 IEEE International Conference on Robotics and Biomimetics}, year={2004}, pages={76-81} }