Abstract
Detection of independently moving objects (IMOs) is a demanding task especially in situations, where the observer is moving himself. In such situations detection of IMOs as well as estimation of egomotion depend on each other and thus have to be handled simultaneously. We present an algorithm based on the Expectation/Maximization algorithm, which is capable of sharply separating background and independently moving objects, whilst the observer itself is moving. Furthermore it incorporates temporal integration of extracted information to improve estimation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
D. Baehring, S. Simon, W. Niehsen, and C. Stiller. Detection of close cut-in and overtaking vehicles for driver assistance based on planar parallax. Proc. Intelligent Vehicles, pages 289–294, 2005.
P. Bayerl and H. Neumann. Disambiguating visual motion through contextual feedback modulation. Neural Computation, 16:2041–2066, 2004.
A.P. Dempster, N.M. Laird, and D.B. Rubin. Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society, Ser. B 39:1–38, 1977.
Michael Isard and Andrew Blake. Condensation — conditional density propagation for visual tracking. Intl. Journal of Computer Vision, 29:5–28, 1998.
Allan D. Jepson and David J. Heeger. Linear subspace methods for recovering translational direction. In Proceedings of the 1991 York conference on spatial vision in humans and robots, pages 39–62, New York, NY, USA, 1993. Cambridge University Press.
N. Krüger, M. Lappe, and F. Wörgötter. Biologically motivated multi-modal rocessing of visual primitives. Journal of Artificial Intelligence and Simulation of Behaviour, 1:417–428, 2004.
B.D. Lucas and T. Kanade. An iterative image registration technique with an application to stereo vision. In Int. Joint Conf. on Artificial Intelligence, pages 674–679, 1981.
J. MacLean, A. Jepson, and R. Frecker. Recovery of egomotion and segmentation of indepedent object motion using the em-algorithm. In British Machine Vision Conference, pages 175–184, 1994.
D. Marr. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. W. H. Freeman, New York, 1982.
K. Pauwels and M. van Hulle. Segmenting independently moving objects from egomotion flow fields. Early Cognitive Vision Workshop, 2004.
Harpreet S. Sawhney, Yanlin Guo, and Rakesh Kumar. Independent motion detection in 3d scenes. IEEE Trans. Pattern Anal. Mack Intell., 22(10):1191–1199, 2000.
S. M. Smith and J. M. Brady. Asset-2: Real-time motion segmentation and shape tracking. IEEE Trans. Pattern Anal. Mach. Intell., 17:814–820, 1995.
Emanuele Trucco and Alessandro Verri. Introductory Techniques for 3-D Computer Vision. Prentice Hall PTR, Upper Saddle River, NJ, USA, 1998.
Felix Woelk and Reinhard Koch. Fast monocular bayesian detection of independently moving objects by a moving observer. In DAGM-Symposium, volume 3175 of Lecture Notes in Computer Science, pages 27–35. Springer, 2004.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Clauss, M., Bayerl, P., Neumann, H. (2006). Segmentation of Independently Moving Objects Using a Maximum-Likelihood Principle. In: Levi, P., Schanz, M., Lafrenz, R., Avrutin, V. (eds) Autonome Mobile Systeme 2005. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-30292-1_11
Download citation
DOI: https://doi.org/10.1007/3-540-30292-1_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-30291-9
Online ISBN: 978-3-540-30292-6
eBook Packages: Computer Science and Engineering (German Language)