12-07-2014, 04:11 PM
Traffic density estimation, vehicle classification and stopped vehicle detection
for traffic surveillance system using predefined traffic videos
Traffic density estimation.pdf (Size: 272.32 KB / Downloads: 51)
ABSTRACT
In thi s paper we present vehicle dens i ty es t imat ion, vehicle clas si f ic at ion
and s topped vehicle de tec t ion sys tem for outdoor t raf f ic surve i l lance is
presented. It i s impor tant to know the road t raf f ic dens i ty in predef ined
t raf f ic videos e specia l ly in mega ci t ies for s ignal cont rol and ef f ect ive
t raf f ic management . In recent yea r s , video moni tor ing and survei l lance
sys tems have been widely used in t raf f ic survei l lance sys tem. Hence,
t raf f ic dens i ty e st ima t ion and vehicle clas s i f ica t ion can be achieved using
video moni tor ing sys tems . In vehicl e detect ion methods for sever al review
of l i ter atur e, onl y the detect ion of vehicles in f rames of the given video.
The s topped vehicle de tec t ion i s based on the pixel hi s tor y. Thi s
me thodology ha s proved to be qui te robus t in terms of di f ferent weather
condi t ions , l ight ing and image qual i ty. Some exper iment s car r ied out on
some highwa y scenar ios demons t rate the robustnes s of the proposed
solut ion.
Introduction
The traffic video monitoring and surveillance systems have
been widely used in traffic management. Most of the companies
have started to use several cameras for the use of traffic
surveillance system. The surveillance system extracting useful
information such as traffic density, vehicle types from these
camera systems has become a hassle due to the high number of
cameras in use. Manual analysis of these camera systems is now
unapplicable. Development of intellegent systems that extract
traffic density and vehicle classification information from traffic
surveillance systems is crucial in traffic management.
It is important to know the traffic density of the roads real
time especially in mega cities for signal control and effective
traffic management. Time estimation of reaching from one
location to another and recommendation of different route
alternatives using real time traffic density information are very
valuable for mega city residents. In addition, vehicle
classification (big: truck, middle: van, or small: car) is also
important for traffic control centers. For example, the effects of
banning big vehicles from a road can be analyzed using vehicle
classification information in a simulation program. This paper
presents an automatic traffic density estimation and vehicle
classification method for traffic surveillence system using neural
networks.
Several other vehicle detectors such as loop, radar, infrared,
ultrasonic, and microwave detectors exist in the literature. These
sensors are expensive with limited capacity and involve
installation, maintenance, and implementation difficulties. For
example, loop sensor might need maintenance due to road
ground deformation or metal barrier near the road might prevent
effective detection using radar sensors [1]. In resent years, video
processing techniques have attracted researchers for vehicle
detection [2-7].
Detection of moving objects including vehicle, human, etc.
in video can be achieved in three main approaches: Temporal
difference, optical flow, and background substraction. In
temporal difference, the image difference of two consecutive
image frames are obtained [12-18]. However, this approach has
some limitations such as visual homogeneity requirement and its
effectiveness depends on the speeds of moving objects [2].
Optical flow method was developed to obtain effective
background modification, which bases on the detection of
intensity changes [2]. However, illumunation change due to
weather or sun-light reflections decreases its effectiveness. It is
also computationally inefficient [2]. The third method,
background subtraction, is the mostly seen method in the
literature for effective motion tracking and moving object
identification [2, 4, 6, 9, 10, 11]. In background subtraction,
background can be static, in which a fixed background is
obtained beforehand and used in the entire process; or dynamic,
in which background is dynamically updated with changing
external effects like weather. Static background may not be
effective in most applications, many methods include dynamic
background subtraction. In [19], the background is detected
dynamically by using dynamic threshold selection method. In
[22], land mark based method and BS&Edge method are used to
remove the shadow from the scene.
Different classification techniques have been employed
after the moving objects are detected in order to identify the
Tele:
E-mail addresses: p_rajesh_1981[at]yahoo.com
© 2013 Elixir All rights reserved
Traffic density estimation, vehicle classification and stopped vehicle detection
for traffic surveillance system using predefined traffic videos
P. Rajesh1, M. Kalaiselvi Geetha2 and R.Ramu3
1Mathematics Section, Faculty of Engineering and Technology, Annamalai University, Annamalainagar-608002,
2Department of Computer Science and Engineering, Faculty of Engineering and Technology, Annamalai University, Annamalainagar-
608002,
3Department of Computer Science, Thiru A. Govindasamy Government Arts College, Tindivanam- 604 002,
ABSTRACT
In thi s paper we present vehicle dens i ty es t imat ion, vehicle clas si f ic at ion
and s topped vehicle de tec t ion sys tem for outdoor t raf f ic surve i l lance is
presented. It i s impor tant to know the road t raf f ic dens i ty in predef ined
t raf f ic videos e specia l ly in mega ci t ies for s ignal cont rol and ef f ect ive
t raf f ic management . In recent yea r s , video moni tor ing and survei l lance
sys tems have been widely used in t raf f ic survei l lance sys tem. Hence,
t raf f ic dens i ty e st ima t ion and vehicle clas s i f ica t ion can be achieved using
video moni tor ing sys tems . In vehicl e detect ion methods for sever al review
of l i ter atur e, onl y the detect ion of vehicles in f rames of the given video.
The s topped vehicle de tec t ion i s based on the pixel hi s tor y. Thi s
me thodology ha s proved to be qui te robus t in terms of di f ferent weather
condi t ions , l ight ing and image qual i ty. Some exper iment s car r ied out on
some highwa y scenar ios demons t rate the robustnes s of the proposed
solut ion.
© 2013 Elixir All rights reserved.
ARTICLE INFO
Art icle hi s tory:
Received: 3 August 2012;
Received in revised form:
15 February 2013;
Accepted: 21 March 2013;
Keywords
Vehicle Identification,
Motion Detection,
Traffic Density Estimation and
Stopped Vehicle Detection.
Elixir Comp. Sci. & Engg. 56A (2013) 13671-13676
Computer Science and Engineering
Available online at www.elixirpublishers.com (Elixir International Journal)
P. Rajesh et al./ Elixir Comp. Sci. & Engg. 56A (2013) 13671-13676
13672
moving object. In [4], support vector machines is used to
idenfity if the detected moving object is a vehicle or not.
Support vector machine is a two class classification method and
requires modification for multi class classification. The vehicles
are detected using mathematical modeling in [21]. The expected
parameters of a moving vehicle is matematically modeled using
the position of the camera, vechile, and sun; it is compared with
the values obtained from the video. However, this model
requires very sensitive calibration of the camera and it works for
cases with short distance between camera and vehicles. The
traffic videos used in Istanbul do not satisfy these needs. In [20],
rule based reasoning is used for vehicle detection, in which the
results highly depend on the rules decided by humans.
Conclusion
Automatic traffic density estimation and vehicle
classification through video processing and artificial systems are
important for traffic management companies especially in mega
cities. Traditional traffic density estimation methods such as
radars, loop sensors, ultrasonic waves etc. have some
limitations. A stopped vehicles detection system based on a
pixel history cache was presented. The experiments conducted
on a large number of scenes demonstrate that this system is able
to robustly detect stopped vehicles under different weather
conditions, lighting, image quality and image compression
variation. In this paper, automatic traffic density estimation,
vehicle classification method and stopped vehicle detection is
presented.