METHODS OF MODELING 3D OF DYNAMIC MEDIA BASED ON BAYES’ THEOREM
Article Sidebar
Main Article Content
Abstract
We propose a new probabilistic approach to the study of spatial representations of of dynamic environment using the 3D-laser measurements. Most of the previous developed techniques computationally costly when considering this issue, and the new method can be applied in real time, even in the presence of a large number of dynamic objects. There are ways for studying activity of the foreground image. However, they generally do not take into account the uncertainty generated during sensing. In this paper we consider the problem of detection of dynamic objects can be solved by means of sequential online structure Bayes. All the parameters involved in the detection process are subject to a probabilistic interpretation. When used in real-world conditions, the results obtained by the proposed method can be used for various tasks: navigation robot creation of maps, localization.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Biber, P. Dynamic maps for long-term operation of mobile service robots / P. Biber, T. Duckett // In: Proc. of Robotics: Science and Systems, RSS (2005).
Burgard, W. Mobile robot map learning from range data in dynamic environments / W. Burgard, C. Stachniss, D. Hahnel // STAR, vol. 35 (2007).
Schulz, D. Probabilistic state estimation of dynamic objects with a moving mobile robot / D. Schulz, W. Burgard // Robotics and Autonomous Systems 34(2–3), 107–115 (2001).
Coastal navigation: Mobile robot navigation with uncertainty in dynamic environments / N. Roy [et al.] // In: IEEE International Conference on Robotics and Automation, pp. 35–40. Citeseer (1999).
Jensen, B. Motion detection and path planning in dynamic environments / B. Jensen, R. Philippsen, R. Siegwart // In: Workshop Proceedings Reasoning with Uncertainty in Robotics, International Joint Conference on Artificial Intelligence, IJCAI (2003).
Classifying dynamic objects: An unsupervised learning approach / M. Luber [et al.] // In: Robotics: Science and Systems IV, p. 270 (2009).
Lee, D. A Bayesian framework for Gaussian mixture background modeling / D. Lee, J. Hull, B. Erol // In: Proc. of The IEEE International Conference on Image Processing, vol. 3, pp. 973–976 (2003).
Stauffer, C. Learning patterns of activity using real-time tracking / C. Stauffer, W. Grimson // IEEE Transactions on Pattern Analysis and Machine Intelligence 22(8), 747–757 (2000).
Sheikh, Y. Bayesian object detection in dynamic scenes / Y. Sheikh, M. Shah // In: Proc. of The IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, p. 74 (2005).
Hou, S. Robust estimation of Gaussian mixtures from noisy input data / S. Hou, A. Galata // In: Proc. of The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–8 (2008).
Surmann, H. An autonomous mobile robot with a 3D laser range finder for 3D exploration and digitalization of indoor environments / H. Surmann, A. Nuchter, J. Hertzberg // Journal of Robotics and Autonomous Systems (JRAS) 45(3–4) (2003).
A non-rigid approach to scan alignment and change detection using range sensor data / R. Kaestner [et al.] // In: Field and Service Robotics. STAR, 25th edn., pp. 179–194. Springer (2006).
Bishop, C. [et al.] // Pattern Recognition and Machine Learning, pp. 94–97. Springer, New York (2006).
Lerner, U. Hybrid Bayesian Networks for Reasoning about Complex Systems / U. Lerner // PhD thesis, Stanford University (2002).