Rotation invariant distance measures for trajectories

For the discovery of similar patterns in 1D time-series, it is very typical to perform a normalization of the data (for example a transformation so that the data follow a zero mean and unit standard deviation). Such transformations can reveal latent patterns and are very commonly used in datamining applications. However, when dealing with multidimensional time-series, which appear naturally in applications such as video-tracking, motion-capture etc, similar motion patterns can also be expressed at different orientations. It is therefore imperative to provide support for additional transformations, such as rotation. In this work, we transform the positional information of moving data, into a space that is translation, scale and rotation invariant. Our distance measure in the new space is able to detect elastic matches and can be efficiently lower bounded, thus being computationally tractable. The proposed methods are easy to implement, fast to compute and can have many applications for real world problems, in areas such as handwriting recognition and posture estimation in motion-capture data. Finally, we empirically demonstrate the accuracy and the efficiency of the technique, using real and synthetic handwriting data.

[1]  Eamonn J. Keogh,et al.  Dimensionality Reduction for Fast Similarity Search in Large Time Series Databases , 2001, Knowledge and Information Systems.

[2]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[3]  Dennis Shasha,et al.  Warping indexes with envelope transforms for query by humming , 2003, SIGMOD '03.

[4]  Eric Mjolsness,et al.  New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence , 1998, NIPS.

[5]  Nicholas Ayache,et al.  Medical image registration using geometric hashing , 1997 .

[6]  Brian Scassellati,et al.  Retrieving images by 2D shape: a comparison of computation methods with human perceptual judgments , 1994, Electronic Imaging.

[7]  Eamonn Keogh.  Exact Indexing of Dynamic Time Warping , 2002, VLDB.

[8]  Dimitrios Gunopulos,et al.  Discovering similar multidimensional trajectories , 2002, Proceedings 18th International Conference on Data Engineering.

[9]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[10]  Dimitrios Gunopulos,et al.  Indexing multi-dimensional time-series with support for multiple distance measures , 2003, KDD '03.

[11]  Leonidas J. Guibas,et al.  Partial matching of planar polylines under similarity transformations , 1997, SODA '97.

[12]  Michael T. Goodrich,et al.  Geometric Pattern Matching Under Euclidean Motion , 1993, Comput. Geom..

[13]  Ambuj K. Singh,et al.  Similarity searching for multi-attribute sequences , 2002, Proceedings 14th International Conference on Scientific and Statistical Database Management.

[14]  Kurt Mehlhorn,et al.  Congruence, similarity, and symmetries of geometric objects , 1987, SCG '87.

[15]  Abraham Kandel,et al.  3-Dimensional curve similarity using string matching , 2004, Robotics Auton. Syst..