Title: Detecting Dominant Motion Flows and People Counting in High Density Crowds
Authors: Khan, Sultan Daud
Vizzari, Giuseppe
Bandini, Stefania
Basalamah, Saleh
Citation: Journal of WSCG. 2014, vol. 22, no. 1, p. 21-30.
Issue Date: 2014
Publisher: Václav Skala - UNION Agency
Document type: článek
URI: http://wscg.zcu.cz/WSCG2014/!!_2014-Journal-No-1.pdf
ISSN: 1213–6972 (hardcopy)
1213–6980 (CD-ROM)
1213–6964 (online)
Keywords: analýza davu;klastrování;segmentace toku;počítání lidí;počítačové zpracování obrazu
Keywords in different language: crowd analysis;clustering;flow segmentation;people counting;computer image processing
Abstract: Urbanisation is growingly generating crowding situations which generate potential issues for planning and public safety. This paper proposes new techniques of crowd analysis and precisely crowd flow segmentation and crowd counting framework for estimating the number of people in each flow segment. We use two foreground masks, one generated by Horn-Schunck optical flow, used by crowd flow segmentation, and another by Gaussian background subtraction, used by crowd counting framework. For crowd flow segmentation, we adopt K-means clustering algorithm which segments the crowd in different flows. After clustering, some small blobs can appear which are removed by blob absorption method. After blob absorption, crowd flow is segmented into different dominant flows. Finally, we estimate the number of people in each flow segment by using blob analysis and blob size optimization methods. Our experimental results demonstrate the effectiveness of the proposed method comparing to other stateof- the-art approaches and our proposed crowd counting framework estimates the number of people with about 90% accuracy.
Rights: © Václav Skala - UNION Agency
Appears in Collections:Volume 22, Number 1 (2014)

Files in This Item:
File Description SizeFormat 
Khan.pdfPlný text1,71 MBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/11897

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.