CMRT09: Object Extraction for 3D City Models, Road Databases and Traffic Monitoring - Concepts, Algorithms, and Evaluation
46
Table 3. Comparison of results for hyperbolas fits achieved
by Coboid and KNN-Classifier
Figure 7 shows a clear separation of the feature space. A high
classification rate is achieved by both elementary classifiers
(see table 3).
5. CONCLUSION AND OUTLOOK
Table 3 affirms a high reliability on these elementary func
tions, with respect to the used basic classification methods.
Mistakes within the classification mostly reside due to scene
behaviour that occurs fairly rare (e.g. car turning at the inter
section) or is not modelled by the underlying functions (e.g.
pedestrians or cyclists crossing in very custom patterns). The
shown approaches have been tested and verified in a real
time environment with a multi-camera system.
The system shall to automatically observe the traffic on
crossroads in future. For example source-destination depend
ences can be determined with that.
6. REFERENCES
Anderson, B. and J. Moor (1979). Optimal filtering. Enle-
wood Cliffs, New Jersey, Prentice-Hall, Inc.
Beynon, M. D., D. J. V. Hook, et al. (2003). Detecting Aban
doned Packages in a Multi-Camera Video Surveillance Sys
tem. IEEE International Conference on Advanced Video and
Signal Based Surveillance (AVSS'03).
Brown, D. C. (1971). "Close range camera calibration." Pho-
togrammetric Engineering 37(8): 12.
Fitzgibbon, A., M. Pilu, et al. (1999). "Direct least square
fitting of ellipses." Pattern Analysis and Machine Intelli
gence, IEEE Transactions on 21(5): 476-480.
Fitzgibbon, A. W., M. Pilu, et al. (1996). Direct least squares
fitting of ellipses. Pattern Recognition, 1996., Proceedings of
the 13th International Conference on.
Forbes, A. B. (1989). Least-squares best fit geometric ele
ments, National Physical Laboratory of Great Britain.
Harker, M., P. O'Leary, et al. (2008). "Direct type-specific
conic fitting and eigenvalue bias correction." Image Vision
Comput 26(3): 372-381.
Harlow, C. and Y. Wang (2001). "Automated Accident De
tection System." Transportation Research Record 1746(-1):
90-93.
Kastrinaki, V., M. Zervakis, et al. (2003). "A survey of video
processing techniques for traffic applications." Image and
Vision Computing 21(4): 359-381.
Kumar, P., S. Ranganath, et al. (2005). "Framework for real
time behavior interpretation from traffic video." Intelligent
Transportation Systems, IEEE Transactions on 6(1): 43-53.
Leykin , A. and M. Tuceryan (2005). A Vision System for
Automated Customer Tracking for Marketing Analysis: Low
Level Feature Extraction. International Workshop on Human
Activity Recognition and Modelling. Oxford, UK.
Liscano, R. and D.Green (1989). Design and implementation
of a trajectory generator for an indoor mobile robot. Proceed
ings of the IEEE/RJS International Conference on Intelligent
Robots and Systems. Tsukuba, Japan: 380-385.
Luhmann, T. (2006). "Close Range Photogrammetry: Princi
ples, Methods and Applications."
Michalopoulos, P. G. (1991). "Vehicle detection video
through image processing: the Autoscope system." Vehicular
Technology, IEEE Transactions on 40( 1): 21 -29.
Nelson, W. L. (1989). "Continuous steering-function control
of robot carts." IEEE Transactions on Industrial Electronics
36(3): 330-337.
Reichardt, D. (1995). A Real-time Approach to Traffic Situa
tion Representation from Image Processing Data. Intelligent
Vehicles Symposium. Detroit, MI, USA.
Reulke, R., S. Bauer, et al. (2008a). Multi-Camera Detection
and Multi-Target Tracking. VISAPP 2008. Funchal, Madeira
(Portugal).
Reulke, R., S. Bauer, et al. (2008b). Situation Analysis and
Atypical Event Detection with Multiple Cameras and Multi-
Object Tracking. Robot Vision. Auckland (New Zeeland),
Springer-Verlag Berlin Heidelberg.
Setchell, C. and E. L. Dagless (2001). "Vision-based road-
traffic monitoring sensor." Vision, Image and Signal Process
ing, IEE Proceedings - 148(1): 78-84.
Wei, C.-H., C.-C. Chang, et al. (1996). "Vehicle Classifica
tion Using Advanced Technologies." Transportation Re
search Record 1551(-1): 45-50.
Wigan, M. R. (1992). "Image-Processing Techniques Ap
plied to Road Problems." Journal of Transportation Engineer-
jng 118(1): 21.
Yung, N. H. C. and A. H. S. Lai (2001). "An effective video
analysis method for detecting red light runners." Vehicular
Technology, IEEE Transactions on 50(4): 1074-1084.