Fast matching algorithm for scene matching aided navigation based on invariant moments

Yan Jun Fu; Yong Mei Cheng; Quan Pan; Kai Feng Sun

doi:10.3969/j.issn.1001-506X.2011.04.27

Fast matching algorithm for scene matching aided navigation based on invariant moments

Yan Jun Fu, Yong Mei Cheng, Quan Pan, Kai Feng Sun

School of Automation

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

To improve the speed of scene matching based on invariant moments, a wavelet transform is used to compress searching space before matching, and then, to reduce the computational complexity of similarity measure at each point to be matched, the moments computation of each sub-image is simplified by using ten sum-tables in terms of the calculation characteristic of moments during matching. By integrating these two speed-up methods, a fast moment based scene matching algorithm is proposed, which decreases the computational cost greatly. Simulation results show that the proposed method takes less time with good precision compared with the pure wavelet transform matching.

Original language	English
Pages (from-to)	847-850+861
Journal	Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics
Volume	33
Issue number	4
DOIs	https://doi.org/10.3969/j.issn.1001-506X.2011.04.27
State	Published - Apr 2011

Keywords

Camberra distance
Invariant moment
Matching time
Wavelet transform

Access to Document

10.3969/j.issn.1001-506X.2011.04.27

Cite this

@article{814ea739f35747a49b02da2b96af9183,

title = "Fast matching algorithm for scene matching aided navigation based on invariant moments",

abstract = "To improve the speed of scene matching based on invariant moments, a wavelet transform is used to compress searching space before matching, and then, to reduce the computational complexity of similarity measure at each point to be matched, the moments computation of each sub-image is simplified by using ten sum-tables in terms of the calculation characteristic of moments during matching. By integrating these two speed-up methods, a fast moment based scene matching algorithm is proposed, which decreases the computational cost greatly. Simulation results show that the proposed method takes less time with good precision compared with the pure wavelet transform matching.",

keywords = "Camberra distance, Invariant moment, Matching time, Wavelet transform",

author = "Fu, {Yan Jun} and Cheng, {Yong Mei} and Quan Pan and Sun, {Kai Feng}",

year = "2011",

month = apr,

doi = "10.3969/j.issn.1001-506X.2011.04.27",

language = "英语",

volume = "33",

pages = "847--850+861",

journal = "Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics",

issn = "1001-506X",

publisher = "Chinese Institute of Electronics",

number = "4",

}

TY - JOUR

T1 - Fast matching algorithm for scene matching aided navigation based on invariant moments

AU - Fu, Yan Jun

AU - Cheng, Yong Mei

AU - Pan, Quan

AU - Sun, Kai Feng

PY - 2011/4

Y1 - 2011/4

N2 - To improve the speed of scene matching based on invariant moments, a wavelet transform is used to compress searching space before matching, and then, to reduce the computational complexity of similarity measure at each point to be matched, the moments computation of each sub-image is simplified by using ten sum-tables in terms of the calculation characteristic of moments during matching. By integrating these two speed-up methods, a fast moment based scene matching algorithm is proposed, which decreases the computational cost greatly. Simulation results show that the proposed method takes less time with good precision compared with the pure wavelet transform matching.

AB - To improve the speed of scene matching based on invariant moments, a wavelet transform is used to compress searching space before matching, and then, to reduce the computational complexity of similarity measure at each point to be matched, the moments computation of each sub-image is simplified by using ten sum-tables in terms of the calculation characteristic of moments during matching. By integrating these two speed-up methods, a fast moment based scene matching algorithm is proposed, which decreases the computational cost greatly. Simulation results show that the proposed method takes less time with good precision compared with the pure wavelet transform matching.

KW - Camberra distance

KW - Invariant moment

KW - Matching time

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=79956311029&partnerID=8YFLogxK

U2 - 10.3969/j.issn.1001-506X.2011.04.27

DO - 10.3969/j.issn.1001-506X.2011.04.27

M3 - 文章

AN - SCOPUS:79956311029

SN - 1001-506X

VL - 33

SP - 847-850+861

JO - Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics

JF - Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics

IS - 4

ER -

Fast matching algorithm for scene matching aided navigation based on invariant moments

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this