Improved global motion estimation via motion vector clustering for video stabilization

被引：17

作者：

Chen, Bo-Hao ^{[1
]}

Kopylov, Andrey ^{[2
]}

Huang, Shih-Chia ^{[3
]}

Seredin, Oleg ^{[2
]}

Karpov, Roman ^{[2
]}

Kuo, Sy-Yen ^{[4
]}

Lai, K. Robert ^{[1
]}

Tan, Tan-Hsu ^{[5
,6
]}

Gochoo, Munkhjargal ^{[7
]}

Bayanduuren, Damdinsuren ^{[7
]}

Gong, Cihun-Siyong ^{[8
]}

Hung, Patrick C. K. ^{[9
]}

机构：

[1] Yuan Ze Univ, Dept Comp Sci & Engn, Taoyuan, Taiwan

[2] Tula State Univ, Inst Appl Math & Comp Sci, Tula, Russia

[3] Natl Taipei Univ Technol, Dept Elect Engn, Taipei, Taiwan

[4] Natl Taiwan Univ, Dept Elect Engn, Taipei, Taiwan

[5] Natl Taipei Univ Technol, Dept Elect Engn, Taipei, Taiwan

[6] Natl Taipei Univ Technol, Dept Elect Engn, Taipei, Taiwan

[7] Mongolian Univ Sci & Technol, Sch Informat & Commun Technol, Ulaanbaatar, Mongolia

[8] Chang Gung Univ, Dept Elect Engn, Taoyuan, Taiwan

[9] Univ Ontario Inst Technol, Fac Business & Informat Technol, Oshawa, ON, Canada

来源：

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE | 2016年 / 54卷

基金：

俄罗斯基础研究基金会;

关键词：

Video stabilization; Motion vector clustering; Shortest spanning path; TRACKING; SYSTEM;

D O I：

10.1016/j.engappai.2016.05.004

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Video stabilization technique is often used in handheld multimedia devices, whereas the difficulties in the accurate extraction aspect of global motion vectors restrict its development. This paper proposes a novel video stabilization approach that is based on the shortest spanning path clustering algorithm for effective and reliable estimation of the global motion vectors. As demonstrated in our experimental results, the proposed approach achieves superior stabilized effectiveness compared with the other state-of-the-art approaches based on both qualitative and quantitative measurements. (C) 2016 Elsevier Ltd. All rights reserved.

引用

页码：39 / 48

页数：10

共 24 条

[1]

Alahi A, 2012, PROC CVPR IEEE, P510, DOI 10.1109/CVPR.2012.6247715

[2]

[Anonymous], 2008, COMPUT VIS IMAGE UND, DOI DOI 10.1016/j.cviu.2007.09.014

[3]

[Anonymous], 2013, VISUAL COMMUNICATION

[4] SIFT features tracking for video stabilization [J].

Battiato, Sebastiano ;

Gallo, Giovanni ;

Puglisi, Giovanni ;

Scellato, Salvatore .

14TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS, 2007, :825-+

[5] A robust and efficient video stabilization algorithm [J].

Chang, HC ;

Lai, SH ;

Lu, KR .

2004 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXP (ICME), VOLS 1-3, 2004, :29-32

[6] Video Stabilization Based on Multi-scale Local Color Invariants [J].

Feng, Kang ;

Han Yonghua ;

Zhang Huaxiong .

2013 FOURTH INTERNATIONAL CONFERENCE ON NETWORKING AND DISTRIBUTED COMPUTING (ICNDC), 2013, :65-69

[7] Efficient Contrast Enhancement Using Adaptive Gamma Correction With Weighting Distribution [J].

Huang, Shih-Chia ;

Cheng, Fan-Chieh ;

Chiu, Yi-Sheng .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (03) :1032-1041

[8]

Kang SJ, 2012, 2012 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE), P416, DOI 10.1109/ICCE.2012.6161955

[9] Online adaptive motion model-based target tracking using local search algorithm [J].

Karami, Amir Hossein ;

Hasanzadeh, Maryam ;

Kasaei, Shohreh .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2015, 37 :307-318

[10] On-line Arabic handwriting recognition system based on visual encoding and genetic algorithm [J].

Kherallah, M. ;

Bouri, F. ;

Alimi, A. M. .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2009, 22 (01) :153-170

← 1 2 3 →