Aligning Overlapping Image Sequences by the Combination of Feature-Based and Direct Methods

A new method for the spatio-temporal alignment of overlapping image sequences from static cameras is presented in this paper. This method first estimates the initial spatial transformation by registering the background images. Then the temporal transformation is estimated in a feature-based manner, using the Hausdorff distance and linear regression. The parameters of the estimated spatio-temporal transformation are then refined by a direct method to give a more precise result. The combination of both feature-based estimation and direct method can cope with large displacements in the temporal domain and provide high spatial alignment accuracy as well.

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

[2]  Tinne Tuytelaars,et al.  Synchronizing video sequences , 2004, CVPR 2004.

[3]  Yaron Caspi,et al.  Aligning Non-Overlapping Sequences , 2004, International Journal of Computer Vision.

[4]  Prosenjit Bose,et al.  Temporal Synchronization of Video Sequences in Theory and in Practice , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[5]  Qian Ma,et al.  A practical two-step image registration method for two-dimensional images , 2004, Inf. Fusion.

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

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

[8]  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).

[9]  C. V. Jawahar,et al.  Video frame alignment in multiple views , 2002, Proceedings. International Conference on Image Processing.

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