![](bg6.png)
goal until he meets an obstacle and then surrounds the
obstacle in the direction of the potential gradient.
5 CONCLUSIONS
Typical mathematical models for the fusion of infor-
mation sources have got many parameters, which has
to be learned automatically by real world scenarios.
In this paper, the information sources are modeled as
potential fields accelerating a pedestrian in the field,
which minimizes the number of parameters and gives
an intuitive interpretation of them. The proposed
model is configured for a simple real world scenario.
In this scenario, two information sources, the inten-
tion and the map information, are considered. The
model is evaluated using real camera based trajec-
tories. The RMSE is calculated and shows a devia-
tion of 0.29 m between the predicted and observed
trajectory. For future research more complex scenar-
ios can be considered. These scenarios shall include
multi-hypotheses and more information sources like
dynamic pedestrian interactions and group behaviors.
REFERENCES
Alberti, E. and Belli, G. (1978). Contributions to the
boltzmann-like approach for traffic flow. a model for
concentration dependent driving programs. Trans-
portation Research, 12(1):33–42.
Ali, S. and Shah, M. (2008). Floor fields for tracking in
high density crowd scenes. In European conference
on computer vision, pages 1–14. Springer.
Bandyopadhyay, T., Jie, C. Z., Hsu, D., Ang Jr, M. H., Rus,
D., and Frazzoli, E. (2013a). Intention-aware pedes-
trian avoidance. In Experimental Robotics, pages
963–977. Springer.
Bandyopadhyay, T., Won, K. S., Frazzoli, E., Hsu, D., Lee,
W. S., and Rus, D. (2013b). Intention-aware motion
planning. In Algorithmic Foundations of Robotics X,
pages 475–491. Springer.
Dijkstra, J., Jessurun, J., and Timmermans, H. J. (2001).
A multi-agent cellular automata model of pedestrian
movement. Pedestrian and evacuation dynamics,
pages 173–181.
Dirk Helbing and Peter Molnar (1995). Social force model
for pedestrian dynamics. Phys. Rev. E, 51:4282–4286.
Edinburgh Informatics Forum Pedestrian Database (2010).
Edinburgh informatics forum pedestrian database.
http://homepages.inf.ed.ac.uk/rbf/FORUMTRACK
ING/. Accessed: 2016-10-04.
Fugger, T., Randles, B., Stein, A., Whiting, W., and Gal-
lagher, B. (2000). Analysis of pedestrian gait and
perception-reaction at signal-controlled crosswalk in-
tersections. Transportation Research Record: Journal
of the Transportation Research Board, 1(1705):20–
25.
Heinemann, P., Becker, H., and Zell, A. (2006). Improved
path planning in highly dynamic environments based
on time variant potential fields. VDI BERICHTE,
1956:177.
Helbing, D. (1998). A fluid dynamic model for the
movement of pedestrians. arXiv preprint cond-
mat/9805213.
Ibisch, A., Houben, S., Michael, M., Kesten, R., and
Schuller, F. (2015). Arbitrary object localization and
tracking via multiple-camera surveillance system em-
bedded in a parking garage. In Loce, R. P. and Saber,
E., editors, Proceedings of Spie, page 94070G.
Keller, C. G. and Gavrila, D. M. (2014). Will the Pedes-
trian Cross? A Study on Pedestrian Path Prediction.
IEEE Transactions on Intelligent Transportation Sys-
tems, 15(2):494–506.
Kretz, T. and Schreckenberg, M. (2006). FAST-floor
field-and agent-based simulation tool. arXiv preprint
physics/0609097.
Luber, M., Stork, J. A., Tipaldi, G. D., and Arras, K. O.
(2010). People tracking with human motion predic-
tions from social forces. In Robotics and Automa-
tion (ICRA), 2010 IEEE International Conference on,
pages 464–469. IEEE.
L
¨
uders, K. . O. G. (2008). Mechanik, Akustik, W
¨
arme -
Walter de Gruyter, Berlin.
Niemeier, W. (2008). Ausgleichungsrechnung - statistische
Auswertemethoden. Walter de Gruyter, Berlin, 2. aufl.
edition.
Prigogine, I. (1900). A boltzmann-like approach to the sta-
tistical theory of traffic flow. Theory of traffic flow.
Robin, T., Antonini, G., Bierlaire, M., and Cruz, J. (2009).
Specification, estimation and validation of a pedes-
trian walking behavior model. Transportation Re-
search Part B: Methodological, 43(1):36–56.
Sigloch, H. (2009). Technische Fluidmechanik -. Springer-
Verlag, Berlin Heidelberg New York, 7. aufl. edition.
Tamura, Y., Dai Le, P., Hitomi, K., Chandrasiri, N. P.,
Bando, T., Yamashita, A., and Asama, H. (2012). De-
velopment of pedestrian behavior model taking ac-
count of intention. In 2012 IEEE/RSJ International
Conference on Intelligent Robots and Systems, pages
382–387. IEEE.
Tiemann, N. (2012). Ein Beitrag zur Situationsanalyse
im vorausschauenden Fussg
¨
angerschutz. PhD thesis,
Universit
¨
at Duisburg-Essen, Fakult
¨
at f
¨
ur Ingenieur-
wissenschaften Maschinenbau und Verfahrenstechnik
Institut f
¨
ur Mechatronik und Systemdynamik.
Wakim, C. F., Capperon, S., and Oksman, J. (2004). A
Markovian model of pedestrian behavior. In Systems,
Man and Cybernetics, 2004 IEEE International Con-
ference on, volume 4, pages 4028–4033. IEEE.
Yi, S., Li, H., and Wang, X. (2015). Understanding pedes-
trian behaviors from stationary crowd groups. In Pro-
ceedings of the IEEE Conference on Computer Vision
and Pattern Recognition, pages 3488–3496.
VISAPP 2017 - International Conference on Computer Vision Theory and Applications
514