Automatic detection of suspicious behavior of pickpockets with track-based features in a shopping mall

Abstract

Rest, "Automatic detection of suspicious behavior of pickpockets with track-based features in a shopping mall," Proc. SPIE, Vol. 9253, (2014). http://dx.doi. org/10.1117/12.2066851 Copyright 2014 Society of Photo-Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only.Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. Automatic detection of suspicious behavior of pickpockets with trackbased features in a shopping mall ABSTRACTProactive detection of incidents is required to decrease the cost of security incidents. This paper focusses on the automatic early detection of suspicious behavior of pickpockets with track-based features in a crowded shopping mall. Our method consists of several steps: pedestrian tracking, feature computation and pickpocket recognition. This is challenging because the environment is crowded, people move freely through areas which cannot be covered by a single camera, because the actual snatch is a subtle action, and because collaboration is complex social behavior. We carried out an experiment with more than 20 validated pickpocket incidents. We used a top-down approach to translate expert knowledge in features and rules, and a bottom-up approach to learn discriminating patterns with a classifier. The classifier was used to separate the pickpockets from normal passers-by who are shopping in the mall. We performed a cross validation to train and evaluate our system. In this paper, we describe our method, identify the most valuable features, and analyze the results that were obtained in the experiment. We estimate the quality of these features and the performance of automatic detection of (collaborating) pickpockets. The results show that many of the pickpockets can be detected at a low false alarm rate.

A Cost Effective Security Technology Integrated with RFID Based Automated Toll Collection System

“…A tracker based automatic detection of suspicious behavior of pickpockets in a shopping mall related work is also been proposed in a research paper [7].…”

“…In the first processor, the system embarks by sending a tag request. If the vehicle carries a valid RFID tag, it sets or resets corresponding bits to the second processor [7]. After executing all these steps, it reveals the information in Liquid Crystal Display.…”

Snatch theft detection in unconstrained surveillance videos using action attribute modelling

“…Using factor analysis, the essential attributes useful for describing snatch thefts are extracted and represented in the form of action-vectors. We show that action-vectors perform better than existing 1 http://www.iith.ac.in/vilg/datasets/ state-of-the-art feature descriptors while leveraging a lot of existing video data containing human actions to effectively represent snatch thefts.…”

“…Most of the existing literature on detecting anomalous activities like snatching uses datasets collected in controlled laboratory settings with no crowd or background and with an excellent viewing angle of the activity. Even when conducted in crowded scenes as in [1], the entire pickpocket incident is staged with apriori knowledge of how the incident is going to take place which makes anal-ysis a lot easier. So, to analyze real-life thefts, we present a dataset called Snatch 1.0 1 collected from unconstrained surveillance footage.…”

“Psyosphere”: A GPS Data-Analysing Tool for the Behavioural Sciences

“…Positioning technologies are now omnipresent in mobile devices, such as smart phones, tablets, and laptops, which makes them potentially interesting for the study of behaviour in naturalistic settings. It could, for instance, be used to identify people with early warnings signs for depression ( Saeb et al, 2015 ; Palmius et al, 2017 ), partly or fully replace self-reported diaries in traffic research ( Stopher et al, 2002 ; Wolf, 2006 ; Bohte and Maat, 2009 ; Schuessler and Axhausen, 2009 ), determine how populations behave after a disaster, such as an earthquake ( Bengtsson et al, 2011 ), or to automatically detect active pickpockets in a shopping mall ( Bouma et al, 2014 ). Surprisingly, behavioural scientists have so far used positioning technologies only sparingly.…”