ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Initial Closed-Form Solution to Mapping from Unknown Planar Motion of an Omni-Directional Vision Sensor
Cited 1 time in scopus Download 1 time Share share facebook twitter linkedin kakaostory
Authors
Kim Jae Hean, Choi Jin Sung
Issue Date
201412
Source
International Symposium on Visual Computing (ISVC) 2014 (LNCS 8888), v.8888, pp.609-619
DOI
https://dx.doi.org/10.1007/978-3-319-14364-4_59
Project Code
14MS5600, 3D Content Creation and Editing Technology Based on Real Objects for 3D Printing, Choi Jin Sung
Abstract
This paper proposes a novel method to construct a stationary environment map and estimate the ego-motion of a sensor system from unknown planar motion by using an omni-directional vision sensor. Most environments where sensor moves to obtain maps are limited to two-dimensional space. However, conventional ?쒾tructure from Motion (SFM)?? algorithms cannot be applied to planar motion and onedimensional measurements because they use the epipolar geometry. We propose an algorithm that can be applied to two-dimensional space. Since the number of parameters to be estimated is reduced, computational advantages can be obtained for large map reconstruction. Proposed algorithm exploits the azimuths of features which are obtained from an omni-directional vision sensor and gives robust results against the noise of image information by taking advantage of large field of view. A relation between observed azimuth and motion parameters of a vision sensor are constrained by a nonlinear equation. The proposed method obtains closed form solutions to all the motion parameters and an environment map through a two-step procedure. These estimation results can be used as a good initial seed for the incremental reconstruction of a large map.
KSP Keywords
Ego-motion, Environment map, Epipolar geometry, Field of view(FOV), Image information, Motion parameters, Nonlinear equations, Omni-directional vision, Planar motion, Sensor system, Two-dimensional space