A LOCATION SYSTEM BASED ON COMPARING IMAGE PROCESSING WITH SURROUNDING MODEL USING CORNER FEATURE POINTS
In this paper, we develop a location system based on comparing of three-dimensional surrounding model with input images of a camera.In this system, corner features such as corners of doors or furniture, are extracted from input images of a camera by ORB.A position and a posture of the camera are estimated by matching these corner features and those of three-dimensional surrounding model.Then, the estimation of the position and the posture is continued by tracking these features using FREAK.The location system can estimate the position and the posture of the camera in a case that the camera is rotated on its optical axis.Furthermore, a mobile robot system which is used the developed location system is constructed.Using the mobile robot system, a traveling experiment is performed.As a result, the mobile robot system was able to follow the reference path based on the estimated position and posture of the camera, when the camera was rotated on its optical axis.Thus, an effectiveness of the location system is demonstrated.
Self-position recognition Image processing 3D surrounding model Location system Mobile robot
Mitsuru Jindai Saori Kohyama Shunsuke Ota Hitoshi Yamauchi Hironori Takimoto Masahiro Kameda
Graduate School of Science and Engineering, University of Toyama, 3190, Gofuku, Toyama, Toyama, 930- Graduate School of Systems Engineering, Okayama Prefectural University, 111, Kuboki, Soja, Okayama, Faculty of Computer Science and System Engineering, Okayama Prefectural University, 111, Kuboki, Soj Kougakukiso Co., Ltd., 6-28, Teppocho, Matsuyama, Ehime, 790-0827, Japan
国际会议
The 12th International Conference on Industrial Management(第十二届工业管理国际会议)
成都
英文
327-332
2014-09-03（万方平台首次上网日期，不代表论文的发表时间）