Rule Based Visual Surveillance System for the Retail Domain

  • S. R. RashmiEmail author
  • Krishnan Rangarajan
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 14)


Identifying anomalous activities based on contextual/Scene knowledge has lots of open challenges for researchers of video analytics domain. Rule based approach to build on contextual/Scene knowledge is gaining popularity in the artificial intelligence community. Especially in the Visual Surveillance domain, adding on the rule base of contextual/Scene knowledge to the existing vision based systems would be very advantageous to make the system intelligent. Symbolizing of contextual knowledge through strong rule sets is an ongoing active research area offering a lot of options to explore and adapt. In this paper, we propose a rule-based system for intelligent monitoring of visual surveillance system taking retail domain as example. In this work we have tried to capture Contextual/Scene knowledge as a strong rule-base to fire against the annotated video input.


Visual surveillance Annotation Rule-base Facts Rules Inferences 


  1. 1.
    Nam Y et al (2010) Intelligent video surveillance system: 3-tier context-aware surveillance system with metadata. Multimedia Tools ApplGoogle Scholar
  2. 2.
    Gómez-Romero J, Patricio MA, García J, Molina JM (2011) Ontology-based context representation and reasoning for object tracking and scene interpretation in video. Expert Syst Appl 7494–7510Google Scholar
  3. 3.
    Gomez-Romero J, Serrano MA, Patricio MA, García J, Molina JM (2012) Context-based scene recognition from visual data in smart homes: an information fusion approach. Pers Ubiquit Comput 835–857Google Scholar
  4. 4.
    Tani YK, Lablack A, Ghomari A, Bilasco IM Events detection using a video-surveillance ontology and a rule-based approach In: ECCV workshop, at Zurich, SuisseGoogle Scholar
  5. 5.
    SanMiguel JC, Martínez JM, García A (2009) An ontology for event detection and its application in surveillance video. In: Sixth IEEE international conference on advanced video and signal based surveillance (AVSS’09)Google Scholar
  6. 6.
    Akdemir U, Turaga P, Chellappa R (2003) An ontology based approach for activity recognition from video. University of Maryland, College ParkGoogle Scholar
  7. 7.
    Kaczmarek PL, Zielonka P (2009) A video monitoring system using ontology-driven identification of threats. Gdańsk University of TechnologyGoogle Scholar
  8. 8.
    Wang E, Kim YS (2006) A teaching strategies engine using translation from SWRL to Jess. In: Creative design and intelligent tutoring systems research center. Sungkyunkwan University, Suwon, KoreaGoogle Scholar
  9. 9.
    Thirugnanam M, Thirugnanam T, Mangayarkarasi R (2013) An ontology based system for predicting disease using SWRL rules. VIT University, Vellore, IndiaGoogle Scholar
  10. 10.
    Noy NF, McGuinness DL (2001) Ontology development a guide to creating your first ontology. Stanford University, Stanford, CAGoogle Scholar
  11. 11.
    Sasa A (2011) Faculty of Computer and Information Science, University of Ljubljana, Traka 25, Ljubljana, Slovenia. O Vasilecas Information Systems Research Laboratory, Vilnius Gediminas Technical University, Saulėtekio al., Vilnius, Lithuania. Ontology-based support for complex events Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of CSEDayananda Sagar College of EngineeringBengaluruIndia
  2. 2.Department of CSECMR Institute of TechnologyBengaluruIndia

Personalised recommendations