Abstract
The performance of Active Contours in tracking is highly dependent on the availability of an appropriate model of shape and motion, to use as a predictor. Models can be hand-built, but it is far more effective and less time-consuming to learn them from a training set. Techniques to do this exist both for shape, and for shape and motion jointly. This paper extends the range of shape and motion models in two significant ways. The first is to model jointly the random variations in shape arising within an object-class and those occuring during object motion. The resulting algorithm is applied to tracking of plants captured by a video camera mounted on an agricultural robot. The second addresses the tracking of coupled objects such as head and lips. In both cases, new algorithms are shown to make important contributions to tracking performance.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Y. Bar-Shalom and T.E. Fortmann. Tracking and Data Association. Academic Press, 1988.
A. Baumberg and D. Hogg. Generating spatiotemporal models from examples. In Proc. BMVC, 413–422, 1995.
A. Blake, R. Curwen, and A. Zisserman. A framework for spatio-temporal control in the tracking of visual contours. Int. Journal of Computer Vision, 11(2):127–145, 1993.
A. Blake, M. Isard, and D. Reynard. Learning to track the visual motion of contours. Artificial Intelligence, 78:101–133, 1995.
A. Blake and M.A. Isard. 3D position, attitude and shape input using video tracking of hands and lips. In Proc. Siggraph, 185–192. ACM, 1994.
T.F. Cootes, C.J. Taylor, A. Lanitis, D.H. Cooper, and J. Graham. Buiding and using flexible models incorporating grey-level information. In Proc. 4th Int. Conf. on Computer Vision, 242–246, 1993.
A. Gelb, editor. Applied Optimal Estimation. MIT Press, Cambridge, MA, 1974.
D.B. Gennery. Visual tracking of known three-dimensional objects. Int. Journal of Computer Vision, 7:3:243–270, 1992.
C.G. Goodwin and K.S. Sin. Adaptive filtering prediction and control. Prentice-Hall, 1984.
C. Harris. Tracking with rigid models. In A. Blake and A. Yuille, editors, Active Vision, 59–74. MIT, 1992.
D.G. Lowe. Robust model-based motion tracking through the integration of search and estimation. Int. Journal of Computer Vision, 8(2):113–122, 1992.
Y. Moses, D. Reynard, and A. Blake. Determining facial expressions in real time. In Fifth International Conference on Computer Vision, 296–301, Massachusetts, USA, 1995.
A. Pentland and B. Horowitz. Recovery of nonrigid motion and structure. IEEE Trans. Pattern Analysis and Machine Intelligence, 13:730–742, 1991.
R.S. Stephens. Real-time 3D object tracking. Image and Vision Computing, 8(1):91–96, 1990.
R. Szeliski and D. Terzopoulos. Physically-based and probabilistic modeling for computer vision. In B. C. Vemuri, editor, Proc. SPIE 1570, Geometric Methods in Computer Vision, 140–152, San Diego, CA, July 1991. Society of Photo-Optical Instrumentation Engineers.
D. Terzopoulos and R. Szeliski. Tracking with Kaiman snakes. In A. Blake and A. Yuille, editors, Active Vision, 3–20. MIT, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Reynard, D., Wildenberg, A., Blake, A., Marchant, J. (1996). Learning dynamics of complex motions from image sequences. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015550
Download citation
DOI: https://doi.org/10.1007/BFb0015550
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61122-6
Online ISBN: 978-3-540-49949-7
eBook Packages: Springer Book Archive