Fighting Volume Crime : an Intelligent, Scalable, and Low Cost Approach

• Autorzy: Arraiza J. , Aginako N. , Kioumourtzis S. , Leventakis G. , Stavropoulos G. , Tzovaras D. , Zotos N. , Sideris A. , Charalambous E. , Koutras N.
• Języki publikacji: EN

Abstrakty

EN

Volume Crimes (aka petty crimes) take place on a daily basis affecting citizens, local communities, as well as business and infrastructure owners. In this paper, we present a novel intelligent surveillance solution (P-REACT) that integrates video and audio analytics both on-site (using an embedded platform connected to local sensors) and centrally on a cloud service. This intelligent surveillance system has been conceived and designed to anticipate volume crimes in areas where video surveillance is allowed by current legislation and more specifically in shops and public transportation systems; intended as a modular and low cost solution. The capability of dynamically adapting the analytic algorithms that are performed on-site provides a more accurate detection of crime evidences.

Słowa kluczowe

EN

volume crime; petty crime; surveillance systems

• Wydawca: Polskie Towarzystwo Bezpieczeństwa i Niezawodności
• Czasopismo: Journal of Polish Safety and Reliability Association
• Rocznik: 2015
• Tom: Vol. 6, No. 3
• Strony: 1--8
• Opis fizyczny: Bibliogr. 20 poz., rys., tab.

Twórcy

autor

Arraiza J.

• Vicomtech-IK4, San Sebastián, Spain

autor

Aginako N.

• Vicomtech-IK4, San Sebastián, Spain

autor

Kioumourtzis S.

• Center for Security Studies, Athens, Greece

autor

Leventakis G.

• Center for Security Studies, Athens, Greece

autor

Stavropoulos G.

• CERTH-ITI, Thessaloniki, Greece

autor

Tzovaras D.

• CERTH-ITI, Thessaloniki, Greece

autor

Zotos N.

• Future Intelligence, London, UK

autor

Sideris A.

• Future Intelligence, London, UK

autor

Charalambous E.

• ADITESS, Nicosia, Cyprus

autor

Koutras N.

• ADITESS, Nicosia, Cyprus

Bibliografia

• [1] ACPO, (2011). Practice Advice on the use of CCTV in criminarl investigations, London.
• [2] Blunsden S.J. & Fisher, R.B. (2005). Pre-fight detection: Classification of fighting situations using heirachical AdaBoost, VISAPP 2009 - Proc. Fourth Int. Conf. Comput. Vis. Theory Appl., vol. 2, pp. 3003-308.
• [3] Blunsden, S. & Fisher, R.B. (2010). The BEHAVE video dataset: Ground truthed video for multi-person behavior classification, BMVA, No. 4, 1-12.
• [4] Breiman, L., Random, F., Machine Learning, Kluwer Academic Publishers, 2001, doi=10.1023/A:1010933404324.
• [5] Burrows, J.N. (1979). The impact of closed circuit television on crime in the London Underground, London.
• [6] Dadashi, N., Stedmon, W. & Pridmore, T.P. (2013). Semi-automated CCTV surveillance: the effects of system confidence, system accuracy and task complexity on operator vigilance, reliance and workload. Appl. Ergon., vol. 44, no. 5, 730-8.
• [7] Ditton, E. & Short, J., (1998). Evaluating Scotland’s first town centre CCTV scheme. In Surveillance, Closed Circuit Television and Social Control, 55-73.
• [8] Efron, B., & Tibshirani, R. (1986). Bootstrap methods for standard errors, confidence intervals, and other measures of statistical accuracy. Statistical science, 54-75.
• [9] FORMAT, “FORMAT research.”. Available: https://www.formatresearch.com/eng/home/.
• [10] Ganchev, T., Fakotakis, N., & Kokkinakis, G. (2005). Comparative evaluation of various MFCC implementations on the speaker verification task. Proc. of the SPECOM, Vol. 1, 191-194.
• [11] Grant, D. & Williams, D. (2004). The importance of perceiving social contexts when predicting crime and antisocial behaviour in CCTV images. J. Pers. Soc. Psychol. vol. 16, no. 2, 307-322.
• [12] HomeOffice, (2004). Defining and measuring anti-social behaviour, London.
• [13] Krishan, S.K. & Yoshiura, N. (2010). Restrained surveillance towards community benefit. Procedia - Soc. Behav. Sci., vol. 2, no. 1, 28-35.
• [14] Kuhn, M., & Johnson, K. (2013). Applied predictive modeling, New York: Springer.
• [15] Little S., Connor, N.E.O., Smeaton, A.F., Clawson, K., Wang, H. & Nieto, M. (2013). An Information Retrieval Approach to Identifying Infrequent Events in Surveillance Video. ACM International Conference on Multimedia Retrieval, 16-19.
• [16] Macnish, K., (2012). Unblinking eyes: the ethics of automating surveillance. Ethics Inf. Technol., vol. 14, no. 2, 151-167.
• [17] Oreifej, O. & Liu, Z. (2013). HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences, CVPR 2013
• [18] P-REACT related projects, PREACT, 2014. [Online]. Available: http://P-REACT.eu/links/. [Accessed: 14-Nov-2014].
• [19] Rossy, Q., Ioset, S. Dessimoz, D. & Ribaux, O. (2013). Integrating forensic information in a crime intelligence database. Forensic Sci. Int., vol. 230, no. 1-3, 137-46.
• [20] Van Droogenbroeck, M. & Barnich, O. (2014). ViBe: A Disruptive Method for Background Subtraction. In T. Bouwmans, F. Porikli, B. Hoferlin, and A. Vacavant, editors, Background Modeling and Foreground Detection for Video Surveillance, chapter 7, pages 7.1-7.23. Chapman and Hall/CRC.