Abstract
In this chapter we describe the initial steps of the Big-Four Geometrical Dimensions model presented in this book: tracking process and data extraction. The first step in extracting the characteristics of a pedestrian or a crowd in the video is the detection of people and, based on this, the achievement of their trajectories. After that, homogeneous planar projection is performed in order to obtain the parameters in world coordinates (once the trajectories obtained in the tracking process are in image coordinates). Section 5.3 describes the detection of groups and the extraction of their information.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Haar-like attributes: also known as Haar-like features, are features or fragments of digital images used in object recognition.
References
Bassi B (2006) Computer simulation of crowd dynamics and destructive crowd behavior. Honors scholar theses. http://digitalcommons.uconn.edu/srhonors_theses/20
Bins J, Dihl LL, Jung CR (2013) Target tracking using multiple patches and weighted vector median filters. J Math Imaging Vis 45(3):293–307. https://doi.org/10.1007/s10851-012-0354-y
Dreyfuss H, Tilley AR (2002) The measure of man and woman: human factors in design. Wiley, New York
Favaretto RM, Knob P, Musse SR, Vilanova F, Costa AB (2018) Detecting personality and emotion traits in crowds from video sequences. Mach Vis Appl 30(5):1–14
Hall ET (1966) The hidden dimension. In: A doubleday anchor book, vol 609. Random House, Inc., Doubleday, Garden City
J DLKT (2005) Unearthed: The other side of group cohesiveness. J Soc Sci 10(3):185–190
Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition, 2001, CVPR 2001, vol 1. Kauai, pp I-511–I-518
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Favaretto, R.M., Musse, S.R., Costa, A.B. (2019). Tracking and Data Extraction. In: Emotion, Personality and Cultural Aspects in Crowds. Springer, Cham. https://doi.org/10.1007/978-3-030-22078-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-22078-5_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-22077-8
Online ISBN: 978-3-030-22078-5
eBook Packages: Computer ScienceComputer Science (R0)