ORIGINAL ARTICLE
A novel framework for intelligent surveillance system based
on abnormal human activity detection in academic environments
Malek Al-Nawashi
1
•
Obaida M. Al-Hazaimeh
1
•
Mohamad Saraee
1
Received: 4 January 2016 / Accepted: 17 May 2016 / Published online: 3 June 2016
Ó The Author(s) 2016. This article is published with open access at Springerlink.com
Abstract Abnormal activity detection plays a crucial role
in surveilla nce applications, and a surveillance system that
can perform robustly in an academic environment has
become an urgent need. In this paper, we propose a novel
framework for an automatic real-time video-based
surveillance system which can simultaneously perform the
tracking, semantic scene learning, and abnormality detec-
tion in an academic environment. To develop our system,
we have divided the work into three phases: preprocessing
phase, abnormal human activity detection phase, and con-
tent-based image retrieval phase. For motion object
detection, we used the temporal-differencing algorithm and
then located the motions region using the Gaussian func-
tion. Furthermore, the shape model based on OMEGA
equation was used as a filter for the detected objects (i.e.,
human and non-human). For object activities analysis, we
evaluated and analyzed the human activities of the detected
objects. We classified the human activities into two groups:
normal activities and abnormal activities based on the
support vector machine. The machine then provides an
automatic warning in case of abnormal human activities. It
also embeds a method to retrieve the detected object from
the database for object recognition and identification using
content-based image retrieval. Finally, a software-based
simulation using MATLAB was performed and the results
of the conducted experiments showed an excellent
surveillance system that can simultaneously perform the
tracking, semantic scene learning, and abnormality detec-
tion in an academic environment with no human
intervention.
Keywords Surveillance system Abnormal activity
detection OMEGA equation Support vector machines
(SVM) MATLAB programming Computer simulat ion
1 Introduction
Cameras attached to monitor screens are generally a tra-
ditional video surveillance system. A limited number of
operators are responsible to constantly monitor a large area
with the help of the cameras installed in various places as
shown in Fig. 1 [1, 2]. When any unwanted incident hap-
pens, the operators warn the security or police. While some
monitors show a video stream of a single camera, in other
instances, a single monitor can show multiple streams
simultaneously or seque ntially [2].
But, in a few areas, the screens are not observed contin-
ually. The output of every camera is recorded by the video
recorders. If there is an incident, the video footage can be
utilized as proof. One weakness of this methodology is that
operators are not ready to countera ct the incidents or limit
their harm because the recordings are only watched after-
ward. Another limitation is that it requires a lot of time to
search for the right video pictures, partic ularly when the
suspect is at the scene long before the incident takes place
and when there are many cameras involved [3– 5 ]. Because of
these limitations, there is a need for a technique or method
that can automatically detect and analyze human activities.
Over the last 10 years, there has been an increased
attention to modern video surveillance in the wider com-
munity of computer vision. However, today, the visual
surveillance community has a more focused attention to
automated video surveillance system [6, 7], which is a net-
work of video sensors that can observe human and non-hu-
man objects in a given environment. The system can analyze
& Obaida M. Al-Hazaimeh
dr_obaida@bau.edu.jo
1
Al-Balqa’ Applied University, Irbid, Jordan
123
Neural Comput & Applic (2017) 28 (Suppl 1):S565–S572
DOI 10.1007/s00521-016-2363-z