[1] Zhang Tao, Fei Shumin, Li Xiaodong, Lu Hong, et al. Fast global motion estimation and moving object extractionalgorithm in image sequences [J]. Journal of Southeast University (English Edition), 2008, 24 (2): 192-196. [doi:10.3969/j.issn.1003-7985.2008.02.014]

Copy

Fast global motion estimation and moving object extractionalgorithm in image sequences()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

24

Issue:

2008 2

Page:

192-196

Research Field:

Computer Science and Engineering

Publishing date:

2008-06-03

Info

Title:

Fast global motion estimation and moving object extractionalgorithm in image sequences

Author(s):

Zhang Tao;  Fei Shumin;  Li Xiaodong;  Lu Hong

Key Laboratory of Measurement and Control of Complex Systems of Engineering of Ministry of Education, Southeast University, Nanjing 210096, China

Keywords:

global motion estimation;  edge projection;  higher-order statistics;  moving object extraction

PACS:

TP391.41

DOI:

10.3969/j.issn.1003-7985.2008.02.014

Abstract:

A novel and effective approach to global motion estimation and moving object extraction is proposed.First, the translational motion model is used because of the fact that complex motion can be decomposed as a sum of translational components.Then in this application, the edge gray horizontal and vertical projections are used as the block matching feature for the motion vectors estimation.The proposed algorithm reduces the motion estimation computations by calculating the one-dimensional vectors rather than the two-dimensional ones.Once the global motion is robustly estimated, relatively stationary background can be almost completely eliminated through the inter-frame difference method.To achieve an accurate object extraction result, the higher-order statistics(HOS)algorithm is used to discriminate backgrounds and moving objects.Experimental results validate that the proposed method is an effective way for global motion estimation and object extraction.

References:

[1] Namuduri K R, Aiyuan J.Computation and performance trade-offs in motion estimation algorithms [C]//Proc of Intl Conf on Information Technology:Coding and Computing.Las Vegas, USA, 2001:263-267.
[2] Chimienti A, Ferraris C, Pau D.A complexity-bounded motion estimation algorithm [J].IEEE Trans on Image Processing, 2002, 11(4):387-392.
[3] Chang Meng-Chou.Chien Jung-Shan.An adaptive search algorithm based on block classification for fast block motion estimation [C]//Proc of IEEE Intl Symp on Circuits and Systems.Kos, Greece, 2006:3982-3985.
[4] Kim S E, Han J K, Kim J G.An efficient scheme for motion estimation using multireference frames in H.264/AVC [J].IEEE Trans on Multimedia, 2006, 8(3):457-466.
[5] Zan J, Ahmad M O, Swamy M N S.Comparison of wavelets for multiresolution motion estimation [J].IEEE Trans on Circuits and Systems for Video Technology, 2006, 16(3):439-446.
[6] Demir B, Erturk S.Block motion estimation using adaptive modified two-bit transform [J].IET Image Processing, 2007, 1(2):215-222.
[7] Braun M, Hahn M, Ohm J R, et al.Motion-compensating real-time format converter for video on multimedia displays [C]//Proc of Intl Conf on Image Processing. Santa Barbara, CA, 1997:125-128.
[8] Namazi N M, Penafiel P, Fan C M.Nonuniform image motion estimation using Kalman filtering [J].IEEE Trans on Image Processing, 1994, 3(5):678-683.
[9] Schreer O, Brandenburg N, Kauff P.Real-time disparity analysis for applications in immersive teleconference scenarios-a comparative study [C]//Proc of the 11th Intl Conf on Image Analysis and Processing. Palermo, 2001:346-351.
[10] Moschetti F, Kunt M, Debes E.A statistical adaptive block-matching motion estimation [J].IEEE Trans on Circuits and Systems for Video Technology, 2003, 13(5):417-431.
[11] Yang M, Cui H, Tang K.Efficient tree structured motion estimation using successive elimination [J].IEE Proceedings Vision, Image and Signal Processing, 2004, 151(5):369-377.
[12] Patras I, Hendriks E A, Lagendijk R L.Probabilistic confidence measures for block matching motion estimation [J].IEEE Trans on Circuits and Systems for Video Technology, 2007, 17(8):988-995.
[13] Huang Yu-Wen, Chien Shao-Yi, Hsieh Bing-Yu, et al.Global elimination algorithm and architecture design for fast block matching motion estimation [J].IEEE Trans on Circuits and Systems for Video Technology, 2004, 14(6):898-907.
[14] Zhong Xingrong, Huang Xianwu, Wang Jiajun, et al.Video object segmentation based on HOS and multi-resolution watershed [C]//Proc of the 2004 Intl Symp on Intelligent Multimedia, Video and Speech Processing.Hong Kong, China, 2004:274-277.
[15] Stiller C, Konrad J.Estimating motion in image sequences [J].IEEE Signal Processing Magazine, 1999, 16(4):70-91.
[16] Blanco D, Mulgrew B, Ruiz D P, et al.Independent component analysis in signals with multiplicative noise using fourth-order statistics [J].Signal Processing, 2007, 87(8):1917-1932.
[17] Weiss M, van de Beld D.A generalized shaping filter method for higher order statistics [J].Probabilistic Engineering Mechanics, to appear.
[18] Neri A, Colonnese S, Russo G, et al.Automatic moving object and background separation [J].Signal Processing, 1998, 66(2):219-232.

Memo

Memo:

Biographies: Zhang Tao(1981—), male, graduate;Fei Shumin(corresponding author), male, doctor, professor, smfei@seu.edu.cn.
Foundation item: The National Natural Science Foundation of China(No.60574006).
Citation: Zhang Tao, Fei Shumin, Li Xiaodong, et al.Fast global motion estimation and moving object extraction algorithm in image sequences[J].Journal of Southeast University(English Edition), 2008, 24(2):192-196.

Common functions