Time registration of two image sequences by dynamic time warping

The time registration between two image sequences for creating virtual reality (VR) is important. In this research, the dynamic time warping (DTW) method is used to scale in time between two image sequences. Most registration researches are focused on non-sequential image registration. Moreover, matching the images from a large image dataset is very tedious. After finding the matching images from two image sequences, it would be practical that making image synthesis automatically from the large image dataset.

[1]  Rae A. Earnshaw,et al.  Virtual Reality Systems , 1993 .

[2]  Thaddeus Beier,et al.  Feature-based image metamorphosis , 1998 .

[3]  Václav Hlavác,et al.  Rendering real-world objects using view interpolation , 1995, Proceedings of IEEE International Conference on Computer Vision.

[4]  Ramesh Jain.  Multiple Perspective Interactive Video Surveillance and Monitoring System , 2000 .

[5]  Lance Williams,et al.  View Interpolation for Image Synthesis , 1993, SIGGRAPH.

[6]  Hideyuki Tamura,et al.  Viewpoint-dependent stereoscopic display using interpolation of multiviewpoint images , 1995, Electronic Imaging.

[7]  Michitaka Hirose.  Image-Based Virtual World Generation , 1997, IEEE Multim..

[8]  Guoqing Chen,et al.  Discovering similar time-series patterns with fuzzy clustering and DTW methods , 2001, Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569).