Vision-based Camera Localization using DEM and Mountain Image

Jeonghee Cha

Journal of The Korea Society of Computer and Information

Abbr : JKSCI
2005, 10(6), pp.177-186
Publisher : The Korean Society Of Computer And Information
Research Area : Computer Science

Jeonghee Cha ¹

¹백석문화대학교

ABSTRACT

In this paper, we propose vision-based camera localization technique using 3D information which is created by mapping of DEM and mountain image. Typically, image features for localization have drawbacks, it is variable to camera viewpoint and after time information quantity increases. In this paper, we extract invariance features of geometry which is irrelevant to camera viewpoint and estimate camera extrinsic parameter through accurate corresponding points matching by proposed similarity evaluation function and Graham search method. we also propose 3D information creation method by using graphic theory and visual clues, The proposed method has the three following stages; point features invariance vector extraction, 3D information creation, camera extrinsic parameter estimation. In the experiments, we compare and analyse the proposed method with existing methods to demonstrate the superiority of the proposed methods.
KEYWORDS

DEM(Digital Elevation Model), Invariance feature, Similarity Evaluation Function, Graham Search Method, Camera Extrinsic Parameter
REFERENCES (12)

[journal] / 1995 / “High-Precision Localization of Circular Landmarks in Aerial Images : 594 13~601 15

[journal] / 1994 / “Point Configuration Invariants under Simultaneous Projective and Permutation Transformations : 1523~1532

[journal] / An Implementation of the Kanade-Lucas-Tomasi Feature Tracker

[journal] / 1997 / “Visual Landmark Extraction and Recognition for Autonomous Robot Navigation : 1036~97 1042

[journal] / 1976 / “The Ordering of Multivariate Data ” Jornal of Royal Statistical Society A : 318~343

[journal] / 2002 / “Object Recognition by Means of Projective Invariants Considering Corner-Points : 105~112

[journal] / 1992 / “Geometric Invariance in Computer Vision ” MIT Press

[journal] / 2004 / “전역탐색 알고리즘을 이용한 이동 무선통신 네트워크의 최적화에 대한 연구

[journal] / 2002 / “가변탐색창을 이용한 실시간 객체추적 시스템 7(4)

[journal] / 1981 / A Paradigm for Model Fitting with Application to Image Analysis and Automated Cartography : 381~395

[journal] / 2001 / “A Hybrid Registration Method for Outdoor Augmented Reality : 67~76

[journal] / 1986 / “An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision” of IEEE Conference on Computer Vision and Pattern Recognition : 364~374
KCI Citation (0)

KJC Korea
Journal Central

Statistics

Tools