Modeling Patterns of Activity and Detecting Abnormal Events with Low-level Co-occurrences - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Book Sections Year : 2011

Modeling Patterns of Activity and Detecting Abnormal Events with Low-level Co-occurrences

Yannick Benezeth
Pierre-Marc Jodoin
  • Function : Author
  • PersonId : 884870

Abstract

We explore in this chapter a location-based approach for behavior modeling and abnormality detection. In contrast to conventional object-based approaches for which objects are identified, classified, and tracked to locate objects with suspicious behavior, we proceed directly with event characterization and behavior modeling using low-level features. Our approach consists of two-phases. In the first phase, co-occurence of activity between temporal sequences of motion labels are used to build a statistical model for normal behavior. This model of co-occurrence statistics is embedded within a co-occurence matrix which accounts for spatio-temporal co-occurence of activity. In the second phase, the co-occurence 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-occurence 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 large enough, the co-occurrence distribution contains the average normal path followed by moving objects. Our method has been tested on various outdoor videos representing various challenges.
Fichier principal
Vignette du fichier
DVSN_Chapter.pdf (1.15 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00545497 , version 1 (16-10-2012)

Identifiers

  • HAL Id : inria-00545497 , version 1

Cite

Yannick Benezeth, Pierre-Marc Jodoin, Venkatesh Saligrama. Modeling Patterns of Activity and Detecting Abnormal Events with Low-level Co-occurrences. Bhanu, B. and Ravishankar, C.V. and Roy-Chowdhury, A.K. and Aghajan, H. and Terzopoulos, D. Distributed Video Sensor Networks, Springer, 2011, 978-0-85729-126-4. ⟨inria-00545497⟩
50 View
189 Download

Share

Gmail Facebook X LinkedIn More