Spatial Fusion of Multisensor Visual Information for Crowding Evaluation
Evaluation of crowding in complex environments is a problem currently addressed in the context of surveillance systems both to detect potentially dangerous situations (overcrowding) and for statistical purposes related to activity planning.
The project DIMUS (Data Integration in Multisensor Systems, ESPRIT P 5345) aims to attain such goals. In this paper, attention is focused on probabilistic Knowledge-Based techniques for statistical evaluation of crowding. To this end, a set of visual sensors are placed in a monitored scene to have different views of the scene itself.
The multilevel architecture of the system is modelled as a Bayesian Belief Network (BBN) of message-passing nodes. Each node corresponds to a virtual distributed processor that is used to obtain a probabilistic value of the locally detected crowding level.
Laboratory results, simulating real-life conditions, show that a good crowding evaluation can be achieved by the proposed approach.
KeywordsVisual Sensor Vertical Edge Bayesian Belief Network Virtual Sensor Edge Extraction
Unable to display preview. Download preview PDF.
- 1.G. Capocaccia, A. Damasio, C. S. Regazzoni, and G. Vernazza, “Dynamic Evaluation of multiple Sensors for Obstacle Detection and Identification”, in Time-Varying Image Processing and Moving Object Recognition, vol. 2, Proceedings of the 3rd International Workshop, Florence, Italy, May 29th-31st 1989, Elsevier, 1990.Google Scholar
- 2.J. Pearl, “Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference”, Morgan-Kaufmann, San Mateo, CA, 1988.Google Scholar
- 3.J. Pearl, “Uncertainty Management in Expert System”, Tutorial IJCAI’87, Milano, Aug. 1987.Google Scholar
- 5.G. L. Foresti, V. Murino, C. S. Regazzoni and G. Vernazza, “Distributed Spatial Reasoning for Multisensory Image Interpretation”, Signal Processing (in press).Google Scholar
- 6.B. Cox, “Programmazione Orientata agli Oggetti—Teoria, Tecniche e Sviluppo”, Addison-Wesley Editoriale Italia, 1990.Google Scholar
- 7.B. Cox, “Message/Object Programming: an evolutionary Change in Programming Technology”, IEEE Software, pp. 50–61, Jan. 1984.Google Scholar
- 8.D. Halbert, P. O’Brien, “Using Types and Inheritance in Object Oriented Programming”, IEEE Software, pp. 71–79, Sept. 1987.Google Scholar
- 9.M. Ferrettino, A. Bozzoli, “A Surveillance System Project”, ESPRIT Day ECCV, 1992.Google Scholar
- 10.P. Antognetti, A. De Gloria, P. Delucca, G. Vernazza, A. Tesei, “DIBE Activities after Intermediate Demo”, DIMUS Project Internal Report, Jan. 1992.Google Scholar
- 11.C. Ottonello, M. Peri, C. Regazzoni, A. Tesei, “Integration of Multisensor Data for Crowding Evaluation”, Proc. of IEEE International Conference on SMC, Chicago, pp. 791–796, Oct. 1992.Google Scholar
- 12.R. E. Kaiman, “A New Approach to Linear Filtering and Prediction Problems”, Trans. ASME, Series D, J. Basic Eng., pp. 35–45, 1960.Google Scholar
- 13.E. R. Davies, “Machine Vision”, Academic Press, 1990.Google Scholar
- 15.G. Foresti and C. S. Regazzoni, “Hough-based Recognition of Complex 3D Road Scenes”, 1991 SPIE Conference on Advances in Intelligent Robotic Systems, Boston, MA, USA, Nov. 1991.Google Scholar
- 16.S. Bittanti, “Teoria della Predizione e del Filtraggio”, Pitagora Editrice Bologna, 1991.Google Scholar