Abnormality detection using low-level co-occurring events

  • Authors:

  • Yannick Benezeth;Pierre-Marc Jodoin;Venkatesh Saligrama

  • Affiliations:

  • Orange Labs, France Telecom R&D 4, rue du Clos Courtel, 35512 Cesson Séévigné, France;Université de Sherbrooke 2500 bd. de l'Université Sherbrooke, Canada J1K 2R1;Boston University, Department of Electrical and Computer Engineering, 8 Saint Mary's Street, Boston, MA 02215, USA

  • Venue:
  • Pattern Recognition Letters
  • Year:
  • 2011

Quantified Score

Hi-index 0.10

Visualization

Abstract

We propose in this paper a method for behavior modeling and abnormal events detection which uses low-level features. In conventional object-based approaches, objects are identified, classified, and tracked to locate those with suspicious behavior. We proceed directly with event characterization and behavior modeling using low-level features. We first learn statistics about co-occurring events in a spatio-temporal volume in order to build the normal behavior model, called the co-occurrence matrix. The notion of co-occurring events is defined using mutual information between motion labels sequences. Then, in the second phase, the co-occurrence matrix is used as a potential function in a Markov random field framework to describe, as the video streams in, the probability of observing new volumes of activity. The co-occurrence matrix is thus used for detecting moving objects whose behavior differs from the ones observed during the training phase. Interestingly, the Markov random field distribution implicitly accounts for speed, direction, as well as the average size of the objects without any higher-level intervention. Furthermore, when the spatio-temporal volume is sufficiently large, the co-occurrence distribution contains the average normal path followed by moving objects. Our method has been tested on various indoor and outdoor videos representing various challenges.