Optimal key-frame selection for video-based structure-from-motion

被引：6

作者：

Park, M. -G. ^{[1
]}

Yoon, K. -J. ^{[1
]}

机构：

[1] Gwangju Inst Sci & Technol, Sch Informat & Commun, Kwangju, South Korea

来源：

ELECTRONICS LETTERS | 2011年 / 47卷 / 25期

基金：

新加坡国家研究基金会;

关键词：

D O I：

10.1049/el.2011.2674

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Proposed is a novel key-frame selection method for the video-based structure-from-motion technique. This method consists of two main steps. First, unreliable features are eliminated by analysing the lifetimes of the tracked features. Next, an optimal set of key-frames is selected considering sufficient baselines between key-frames, data redundancy, and the avoidance of degeneracy. The proposed method is experimentally verified in terms of accuracy and stability for various video sequences.

引用

页码：1367 / 1368

页数：2

共 5 条

[1]

Dong ZL, 2009, IEEE I CONF COMP VIS, P1538

[2] Accurate camera calibration for off-line, video-based augmented reality [J].

Gibson, S ;

Cook, J ;

Howard, T ;

Hubbold, R ;

Oram, D .

INTERNATIONAL SYMPOSIUM ON MIXED AND AUGMENTED REALITY, PROCEEDINGS, 2002, :37-46

[3]

Nister David., 2000, Workshop on 3D Structure from Multiple Images of Large-Scale Environments (SMILE), P17

[4] 3D models from extended uncalibrated video sequences: Addressing key-frame selection and projective drift [J].

Repko, J ;

Pollefeys, M .

FIFTH INTERNATIONAL CONFERENCE ON 3-D DIGITAL IMAGING AND MODELING, PROCEEDINGS, 2005, :150-157

[5]

Seo Y.H., 2008, OPT ENG, V47

← 1 →