Sequence image registration based on motion trajectory

In this paper, we propose a registration algorithm for image sequences based on motion trajectories. The method includes four steps: feature detection, trajectory presentation, trajectories matching, and registration parameter estimation. The algorithm can reduce the matching complexity greatly. The experiments show the effectiveness of our registration method.

[1]  Kiriakos N. Kutulakos,et al.  Linear sequence-to-sequence alignment , 2004, CVPR 2004.

[2]  Denis Simakov,et al.  Feature-Based Sequence-to-Sequence Matching , 2006, International Journal of Computer Vision.

[3]  Ravi K. Sharma,et al.  Registration of video sequences from multiple sensors , 1997 .

[4]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[5]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[6]  M. Irani,et al.  Spatio-Temporal Alignment of Sequences , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  László Havasi,et al.  Video camera registration using accumulated co-motion maps , 2007 .

[8]  Yaron Caspi,et al.  A step towards sequence-to-sequence alignment , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[9]  Gideon P. Stein,et al.  Tracking from multiple view points: Self-calibration of space and time , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[10]  Yee-Hong Yang,et al.  The background primal sketch: An approach for tracking moving objects , 1992, Machine Vision and Applications.

[11]  B. S. Manjunath,et al.  A contour-based approach to multisensor image registration , 1995, IEEE Trans. Image Process..

[12]  Kiriakos N. Kutulakos,et al.  Linear Sequence-to-Sequence Alignment , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.