Abstract
Determination of object direction in a multi-camera tracking system is critical. The absence of object direction from other cameras pose challenges if the object is along the optical axis. The problem of determining object direction worsens further if the cameras in the existing infrastructure are improperly placed and are uncontrollable. To determine the direction of an object in such situations, three methods based on optical flow (OF) are presented. The first method uses centroids of optical flow vector magnitudes and Kalman filter for tracking and is suitable for less crowded scenarios. The second method uses geometric moments to evaluate the flow vector distribution and to ascertain the direction in case of crowded scenarios by partitioning the scene and then applying moments to individual partitions independently. The third method is appropriate for small-sized objects near vanishing points where global object motion is less. During surveillance, whether multi-object, single-object or crowded scenarios, the aforementioned methods are applicable accordingly. The results show that the object directions can be accurately inferred from three methods for different scenarios.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 246–252. IEEE (1999)
Lepisk, A.: The use of optic flow within background subtraction. Master’s thesis. Numerisk analys och datalogi, NADA, Stockholm, Sweden (2005)
Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)
Kinoshita, K., Enokidani, M., Izumida, M., Murakami, K.: Tracking of a moving object using one-dimensional optical flow with a rotating observer. In: 9th International Conference on Control, Automation, Robotics and Vision, pp. 1–6. IEEE (2006)
Kinoshita, K., Murakami, K.: Moving object tracking via one-dimensional optical flow using queue. In: 10th International Conference on Control, Automation, Robotics and Vision, pp. 2326–2331. IEEE (2008)
Shibata, M., Makino, T., Ito, M.: Target distance measurement based on camera moving direction estimated with optical flow. In: 10th IEEE International Workshop on Advanced Motion Control, pp. 62–67. IEEE (2008)
Ishii, Y., Hongo, H., Yamamoto, K., Niwa, Y.: Real-time face and head detection using four directional features. In: Proceedingof the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 403–408. IEEE (2004)
Lertniphonphan, K., Aramvith, S., Chalidabhongse, T.H.: Human action recognition using direction histograms of optical flow. In: 2011 11th International Symposium on Communications and Information Technologies, ISCIT, pp. 574–579. IEEE (2011)
Lijia, W., Songmin, J., Xiuzhi, L., Shuang, W.: Human gait recognition based on gait flow image considering walking direction. In: 2012 International Conference on Mechatronics and Automation, ICMA, pp. 1990–1995. IEEE (2012)
Barandiaran, J., Murguia, B., Boto, F.: Real-time people counting using multiple lines. In: Ninth International Workshop on Image Analysis for Multimedia Interactive Services, pp. 159–162. IEEE (2008)
Rizzon, L., Massari, N., Gottardi, M., Gasparini, L.: A low-power people counting system based on a vision sensor working on contrast. In: IEEE International Symposium on Circuits and Systems, pp. 786–786. IEEE (2009)
Garcia, J., Gardel, A., Bravo, I., Lazaro, J., Martinez, M., Rodriguez, D.: Directional people counter based on heads tracking. IEEE Transactions on Industrial Electronics PP, 1–10 (2012)
Horn, B.K.P.: Robot vision. MIT Press, Cambridge (1986)
Teh, C.H., Chin, R.T.: On image analysis by the methods of moments. IEEE Transactions on Pattern Analysis and Machine Intelligence 10, 496–513 (1988)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rao, A.S., Gubbi, J., Marusic, S., Maher, A., Palaniswami, M. (2013). Determination of Object Directions Using Optical Flow for Crowd Monitoring. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2013. Lecture Notes in Computer Science, vol 8034. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41939-3_60
Download citation
DOI: https://doi.org/10.1007/978-3-642-41939-3_60
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41938-6
Online ISBN: 978-3-642-41939-3
eBook Packages: Computer ScienceComputer Science (R0)