Abstract
In this paper, we describe an unsupervised learning framework to segment a scene into semantic regions and to build semantic scene models from long-term observations of moving objects in the scene. First, we introduce two novel similarity measures for comparing trajectories in far-field visual surveillance. The measures simultaneously compare the spatial distribution of trajectories and other attributes, such as velocity and object size, along the trajectories. They also provide a comparison confidence measure which indicates how well the measured image-based similarity approximates true physical similarity. We also introduce novel clustering algorithms which use both similarity and comparison confidence. Based on the proposed similarity measures and clustering methods, a framework to learn semantic scene models by trajectory analysis is developed. Trajectories are first clustered into vehicles and pedestrians, and then further grouped based on spatial and velocity distributions. Different trajectory clusters represent different activities. The geometric and statistical models of structures in the scene, such as roads, walk paths, sources and sinks, are automatically learned from the trajectory clusters. Abnormal activities are detected using the semantic scene models. The system is robust to low-level tracking errors.
Chapter PDF
Similar content being viewed by others
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
Kaucic, R., Perera, A., Brooksby, G., Kaufhold, J., Hoogs, A.: A Unified Framework for Tracking through Occlusions and across Sensor Gaps. In: Proceedings of CVPR (2005)
Stauffer, C., Grimson, E.: Learning Patterns of Activity Using Real-Time Tracking. IEEE Trans. on PAMI 22(8), 747–757 (2000)
Makris, D., Ellis, T.: Path Detection in Video Surveillance. Image and Vision Computing 20, 859–903 (2002)
Fernyhough, J.H., Cohn, A.G., Hogg, D.C.: Generation of Semantic Regions from Image Sequences. In: Proc. of ECCV (1996)
Makris, D., Ellis, T.: Automatic Learning of an Activity-Based Semantic Scene Model. In: Proc. of IEEE Conference on Advanced Video and Signal Based Surveillance (2003)
Mckenna, S.J., Nait-Charif, H.: Learning Spatial Context from Tracking Using Penalized Likelihood. In: Proc. of ICPR (2004)
Bose, B., Grimson, E.: Improving Object Classification in Far-Field Video. In: Proc. CVPR (2004)
Stauffer, C.: Minimally-Supervised Classification using Multiple Observation Sets. In: ICCV (2003)
Dubuisson, M.P., Jain, A.K.: A Modified Hausdorff distance for Object Matching. In: Proc. of ICPR (1994)
Meila, M., Shi, J.: A Random Walk View of Spectral Segmentation. In: Proc. of AISTATS (2001)
Wang, X., Tieu, K., Grimson, E.: Learning Semantic Scene Models by Trajectory Analysis. Tech. Rep. MIT-CSAIL-TR-2006-08, http://hdl.handle.net/1721.1/31208
Gumbel, E.J., Greenwood, J.A.: The Circular Normal Distribution: Theory and Tables. J. Amer. Stat. Soc. 48(261), 131–152 (1953)
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
Wang, X., Tieu, K., Grimson, E. (2006). Learning Semantic Scene Models by Trajectory Analysis. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3953. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744078_9
Download citation
DOI: https://doi.org/10.1007/11744078_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33836-9
Online ISBN: 978-3-540-33837-6
eBook Packages: Computer ScienceComputer Science (R0)