An efficient multi-view image stitching algorithm based on CSIFT features

Ping Zhou; Xiling Luo

doi:10.1007/978-3-642-27314-8_55

An efficient multi-view image stitching algorithm based on CSIFT features

Ping Zhou^*
, Xiling Luo

^*Corresponding author for this work

School of Electronic and Information Engineering

Beihang University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Multi-view image stitching is an efficient approach to resolve the limitation of single view angle, and it can be described as the process of fusing images under different viewpoints into a wide-view picture. This paper presents a multi-view image stitching algorithm based on CSIFT (Color Scale Invariant Features) features. Generally speaking, our proposed method contains two sections. First, multi-view image registration procedure is described based on CSIFT features. In this way, our method is robust to both geometrical and photometric changes. The second section is image blending, in order to smooth the generated wide-view image with a high speed, a linear blending algorithm is illustrated. Experimental results indicate that our proposed algorithm is accurate and effective.

Original language	English
Title of host publication	Future Communication, Computing, Control and Management
Pages	407-413
Number of pages	7
Edition	VOL. 2
DOIs	https://doi.org/10.1007/978-3-642-27314-8_55
State	Published - 2012
Event	2011 International Conference on Future Communication, Computing, Control and Management, ICF4C 2011 - Phuket, Thailand Duration: 16 Dec 2011 → 17 Dec 2011

Publication series

Name	Lecture Notes in Electrical Engineering
Number	VOL. 2
Volume	142 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	2011 International Conference on Future Communication, Computing, Control and Management, ICF4C 2011
Country/Territory	Thailand
City	Phuket
Period	16/12/11 → 17/12/11

Keywords

CSIFT features
image blending
multi-view image stitching

Access to Document

10.1007/978-3-642-27314-8_55

Cite this

@inproceedings{ce9b1457bc004c3fb0477237907e563a,

title = "An efficient multi-view image stitching algorithm based on CSIFT features",

abstract = "Multi-view image stitching is an efficient approach to resolve the limitation of single view angle, and it can be described as the process of fusing images under different viewpoints into a wide-view picture. This paper presents a multi-view image stitching algorithm based on CSIFT (Color Scale Invariant Features) features. Generally speaking, our proposed method contains two sections. First, multi-view image registration procedure is described based on CSIFT features. In this way, our method is robust to both geometrical and photometric changes. The second section is image blending, in order to smooth the generated wide-view image with a high speed, a linear blending algorithm is illustrated. Experimental results indicate that our proposed algorithm is accurate and effective.",

keywords = "CSIFT features, image blending, multi-view image stitching",

author = "Ping Zhou and Xiling Luo",

year = "2012",

doi = "10.1007/978-3-642-27314-8\_55",

language = "英语",

isbn = "9783642273131",

series = "Lecture Notes in Electrical Engineering",

number = "VOL. 2",

pages = "407--413",

booktitle = "Future Communication, Computing, Control and Management",

edition = "VOL. 2",

note = "2011 International Conference on Future Communication, Computing, Control and Management, ICF4C 2011 ; Conference date: 16-12-2011 Through 17-12-2011",

}

Zhou, P & Luo, X 2012, An efficient multi-view image stitching algorithm based on CSIFT features. in Future Communication, Computing, Control and Management. VOL. 2 edn, Lecture Notes in Electrical Engineering, no. VOL. 2, vol. 142 LNEE, pp. 407-413, 2011 International Conference on Future Communication, Computing, Control and Management, ICF4C 2011, Phuket, Thailand, 16/12/11. https://doi.org/10.1007/978-3-642-27314-8_55

TY - GEN

T1 - An efficient multi-view image stitching algorithm based on CSIFT features

AU - Zhou, Ping

AU - Luo, Xiling

PY - 2012

Y1 - 2012

N2 - Multi-view image stitching is an efficient approach to resolve the limitation of single view angle, and it can be described as the process of fusing images under different viewpoints into a wide-view picture. This paper presents a multi-view image stitching algorithm based on CSIFT (Color Scale Invariant Features) features. Generally speaking, our proposed method contains two sections. First, multi-view image registration procedure is described based on CSIFT features. In this way, our method is robust to both geometrical and photometric changes. The second section is image blending, in order to smooth the generated wide-view image with a high speed, a linear blending algorithm is illustrated. Experimental results indicate that our proposed algorithm is accurate and effective.

AB - Multi-view image stitching is an efficient approach to resolve the limitation of single view angle, and it can be described as the process of fusing images under different viewpoints into a wide-view picture. This paper presents a multi-view image stitching algorithm based on CSIFT (Color Scale Invariant Features) features. Generally speaking, our proposed method contains two sections. First, multi-view image registration procedure is described based on CSIFT features. In this way, our method is robust to both geometrical and photometric changes. The second section is image blending, in order to smooth the generated wide-view image with a high speed, a linear blending algorithm is illustrated. Experimental results indicate that our proposed algorithm is accurate and effective.

KW - CSIFT features

KW - image blending

KW - multi-view image stitching

UR - https://www.scopus.com/pages/publications/84856847977

U2 - 10.1007/978-3-642-27314-8_55

DO - 10.1007/978-3-642-27314-8_55

M3 - 会议稿件

AN - SCOPUS:84856847977

SN - 9783642273131

T3 - Lecture Notes in Electrical Engineering

SP - 407

EP - 413

BT - Future Communication, Computing, Control and Management

T2 - 2011 International Conference on Future Communication, Computing, Control and Management, ICF4C 2011

Y2 - 16 December 2011 through 17 December 2011

ER -

An efficient multi-view image stitching algorithm based on CSIFT features

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this