Robust Global Motion Estimation Oriented to Video Object Segmentation

Most global motion estimation (GME) methods are oriented to video coding while video object segmentation methods either assume no global motion (GM) or directly adopt a coding-oriented method to compensate for GM. This paper proposes a hierarchical differential GME method oriented to video object segmentation. A scheme which combines three-step search and motion parameters prediction is proposed for initial estimation to increase efficiency. A robust estimator that uses object information to reject outliers introduced by local motion is also proposed. For the first frame, when the object information is unavailable, a robust estimator is proposed which rejects outliers by examining their distribution in local neighborhoods of the error between the current and the motion-compensated previous frame. Subjective and objective results show that the proposed method is more robust, more oriented to video object segmentation, and faster than the referenced methods.

[1]  Ebroul Izquierdo,et al.  A generic video analysis and segmentation system , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Peter J. Huber,et al.  Robust Statistics , 2005, Wiley Series in Probability and Statistics.

[3]  T. Vlachos,et al.  On the estimation of global motion using phase correlation for broadcast applications , 1999 .

[4]  Bo Feng,et al.  Fast global motion estimation for global motion compensation coding , 2001, ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196).

[5]  Azriel Rosenfeld,et al.  Robust regression methods for computer vision: A review , 1991, International Journal of Computer Vision.

[6]  G. Shevlyakov,et al.  Robustness in Data Analysis: Criteria and Methods , 2001 .

[7]  Truong Q. Nguyen,et al.  Global motion estimation in frequency and spatial domain , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Murat Kunt,et al.  A new two-stage global/local motion estimation based on a background/foreground segmentation , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[9]  Chiou-Ting Hsu,et al.  Mosaics of video sequences with moving objects , 2004, Signal Process. Image Commun..

[10]  Yao Wang,et al.  Video Processing and Communications , 2001 .

[11]  이진성,et al.  움직임 벡터의 신뢰도에 기반한 이동 목표물 추적 기법 ( Moving Target Tracking Algorithm based on the Confidence Measure of Motion Vectors ) , 2001 .

[12]  Haifeng Xu,et al.  Automatic moving object extraction for content-based applications , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[13]  Wing Cheong Chan Oscar,et al.  Improved global motion estimation using prediction and early termination , 2002, Proceedings. International Conference on Image Processing.

[14]  William H. Press,et al.  Numerical recipes in C , 2002 .

[15]  G. de Haan,et al.  Memory integrated noise reduction IC for television , 1996 .

[16]  Charles V. Stewart,et al.  Robust Parameter Estimation in Computer Vision , 1999, SIAM Rev..

[17]  Frédéric Dufaux,et al.  Efficient, robust, and fast global motion estimation for video coding , 2000, IEEE Trans. Image Process..

[18]  Seong-Dae Kim,et al.  Moving target tracking algorithm based on the confidence measure of motion vectors , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[19]  T Koga,et al.  MOTION COMPENSATED INTER-FRAME CODING FOR VIDEO CONFERENCING , 1981 .

[20]  A. Murat Tekalp,et al.  Performance measures for video object segmentation and tracking , 2003, IEEE Transactions on Image Processing.

[21]  B. Ripley,et al.  Robust Statistics , 2018, Encyclopedia of Mathematical Geosciences.

[22]  Aishy Amer.  Memory-based spatio-temporal real-time object segmentation for video surveillance , 2003, IS&T/SPIE Electronic Imaging.

[23]  Eric Dubois,et al.  Fast and reliable structure-oriented video noise estimation , 2005, IEEE Transactions on Circuits and Systems for Video Technology.