Sudden event recognition: a survey

Abstract

Event recognition is one of the most active research areas in video surveillance fields. Advancement in event recognition systems mainly aims to provide convenience, safety and an efficient lifestyle for humanity. A precise, accurate and robust approach is necessary to enable event recognition systems to respond to sudden changes in various uncontrolled environments, such as the case of an emergency, physical threat and a fire or bomb alert. The performance of sudden event recognition systems depends heavily on the accuracy of low level processing, like detection, recognition, tracking and machine learning algorithms. This survey aims to detect and characterize a sudden event, which is a subset of an abnormal event in several video surveillance applications. This paper discusses the following in detail: (1) the importance of a sudden event over a general anomalous event; (2) frameworks used in sudden event recognition; (3) the requirements and comparative studies of a sudden event recognition system and (4) various decision-making approaches for sudden event recognition. The advantages and drawbacks of using 3D images from multiple cameras for real-time application are also discussed. The paper concludes with suggestions for future research directions in sudden event recognition.

Figure 1.

Images from the GERHOME Laboratory. Reproduced with permission from www-sop.inria.fr/stars/projects/Gerhome/Videos/ (on 20 February 2013)

Figure 2.

Common structure of video-based sudden event recognition system.

Figure 3.

Semantic hierarchy level description.

Figure 4.

(a) Sudden fall. Reproduced with permission from www.iro.umontreal.ca/labim-age/Dataset/(accessed on 20 February 2013) [31]; and (b) snatch theft. Adapted from [32].

Figure 5.

Diagram of sudden event recognition.

Figure 6.

Example of a human-centered sudden event. (a) Patient falls out of bed. ©2011 IEEE. Reprinted, with permission, from [33]; (b) group interaction shows the sequence of a sudden assault. Reproduced with permission from [34]. With kind permission from Springer Science and Business Media.

Figure 7.

Example of vehicle-centered sudden event. (a) Car makes a U-turn in the middle of the road. ©2008 IEEE. Reprinted, with permission, from [35]; (b) a car suddenly stops and makes a U-turn. ©2011 IEEE. Reprinted, with permission, from [36].

Figure 8.

Example of a space-centered sudden event. (a) Elevator cage monitoring. ©2009 IEEE. Reprinted, with permission, from [39]); (b) staircase monitoring. ©2006 IEEE. Reprinted, with permission, from [37]).