Understanding people motion in video sequences using Voronoi diagrams: Detecting and classifying groups

  • Authors:

  • Julio Cezar Silveira Jacques, Jr.;Adriana Braun;John Soldera;Soraia Raupp Musse;Cláudio Rosito Jung

  • Affiliations:

  • Universidade do Vale do Rio dos Sinos, Graduate School of Applied Computing, Av. Unisinos 950, 93022-000, São Leopoldo, RS, Brazil;Universidade do Vale do Rio dos Sinos, Graduate School of Applied Computing, Av. Unisinos 950, 93022-000, São Leopoldo, RS, Brazil;Universidade do Vale do Rio dos Sinos, Graduate School of Applied Computing, Av. Unisinos 950, 93022-000, São Leopoldo, RS, Brazil;Pontificia Universidade Catolica do Rio Grande do Sul, Graduate Program on Computer Science, Av. Ipiranga, 6681 - Building 32 - Room 609, 90619-900, Porto Alegre, RS, Brazil;Universidade do Vale do Rio dos Sinos, Graduate School of Applied Computing, Av. Unisinos 950, 93022-000, São Leopoldo, RS, Brazil

  • Venue:
  • Pattern Analysis & Applications
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

This work describes a model for understanding people motion in video sequences using Voronoi diagrams, focusing on group detection and classification. We use the position of each individual as a site for the Voronoi diagram at each frame, and determine the temporal evolution of some sociological and psychological parameters, such as distance to neighbors and personal spaces. These parameters are used to compute individual characteristics (such as perceived personal space and comfort levels), that are analyzed to detect the formation of groups and their classification as voluntary or involuntary. Experimental results based on videos obtained from real life as well as from a crowd simulator were analyzed and discussed.