%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi@80/2006/08.24.15.02
%2 sid.inpe.br/sibgrapi@80/2006/08.24.15.02.09
%@doi 10.1109/SIBGRAPI.2006.11
%T Detection of Unusual Motion Using Computer Vision
%D 2006
%A Jung, Claudio Rosito,
%A Jacques Jr, Julio C. S.,
%A Soldera, John,
%A Musse, Soraia Raupp,
%@affiliation PIPCA - Graduate School on Applied Computing - Universidade do Vale do Rio dos Sinos
%@affiliation PIPCA - Graduate School on Applied Computing - Universidade do Vale do Rio dos Sinos
%@affiliation PIPCA - Graduate School on Applied Computing - Universidade do Vale do Rio dos Sinos
%@affiliation PIPCA - Graduate School on Applied Computing - Universidade do Vale do Rio dos Sinos
%E Oliveira Neto, Manuel Menezes de,
%E Carceroni, Rodrigo Lima,
%B Brazilian Symposium on Computer Graphics and Image Processing, 19 (SIBGRAPI)
%C Manaus, AM, Brazil
%8 8-11 Oct. 2006
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%K computer vision, human motion analysis, object tracking.
%X In this paper, we propose different criteria for detecting unusual motion in surveillance cameras. Initially, a certain environment is observed within a time interval, and captured trajectories are used as examples of usual trajectories. These trajectories are used to build a Spatial Occupancy Map (SpOM, which is introduced in this paper) of the observed people, as well as main flow directions. In the test period, each new trajectory is classified as normal or unusual with respect to spatial occupancy and trajectory consistency. The spatial occupancy criterion considers the relation of space occupancy between the new tracked trajectory and the observed period. The trajectory consistency criterion considers the agreement of the new trajectory with the main flows extracted in the training period. Experimental results showed that these criteria can be used as an automatic pre-screening of suspect motion in surveillance applications.
%@language en
%3 jungc-unusual.pdf