Image Sequences

o Yosemite sequence. Synthetic sequence with ground truth. Frequently asked questions about the Yosemite sequence including pseduo-code for reading the data.

o Human Motion Sequences from:
Sidenbladh, H., Black, M. J., and Fleet, D.J., Stochastic tracking of 3D human figures using 2D image motion, European Conference on Computer Vision, D. Vernon (Ed.), Springer Verlag, LNCS 1843, Dublin, Ireland, pp. 702-718 June 2000. (postscript), (abstract)

o Transparency sequence containing the reflection of a face in glass. From:

Black, M. J. and Anandan, P., The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields, Computer Vision and Image Understanding, CVIU, 63(1), pp. 75-104, Jan. 1996. (abstract)

o SRI tree sequence. Taken in 1986 at SRI by Bob Bolles and Harlyn Baker. Size 256X233.

o Skaters sequence. Synthetic with two (roughly planar) layers. Provided by Jim Bergen.

o Flower garden sequence.

o Soda-can sequence. Provided by Joe Heel.

o Two 100-image sequences. Hand data used in EigenTracking paper. The sequence in data/gesture1/crop-*.pgm contains the training data while data/gesture2/*.pgm contains the sequence used for tracking.


o EigenTracking training data.

o EigenTracking looming sequence.

o EigenTracking pickup sequence.

o EigenTracking moving sequence.

o EigenTracking apparent motion sequence.

o Person walking with camera motion. Thanks to Dan Huttenlocher for the sequence. The sequence appears in Fig. 15 in:

Black, M. J. and Jepson, A., Estimating multiple independent motions in segmented images using parametric models with local deformations, Workshop on Non-rigid and Articulate Motion, Austin, Texas, Nov. 1994, pp. 220-227. (postscript), (abstract)