Abstract – Moving object detection is very important in modern
world for fast video surveillance. There are various methods used
for detecting moving objects out of which frame differencing
method is widely used and is most efficient method. In this paper
we focus on the surveillance at the most secured areas such as
airports, defense establishments, power stations etc. Similarly, the
area where no human is allowed without authority to enter such as
bank locker rooms, restricted military area etc. automotive
surveillance and traffic monitoring plays a vital role. In real time
surveillance system, storing the captured video and detecting object
are two most important issues. Storing such videos needs more
memory and the detection of the object is also need to be fast. To
solve these problems compression and fast object detection is
required. To detect the moving object, detection of its edges and
location in the frame are important steps. In this paper we propose
a mechanism to use discrete wavelet transform (DWT) for two
purposes for compression and edge detection, whereas to locate the
object we propose variance method on to the 2-D DWT outputs of
video frames. For this analysis HAAR wavelet is used as reference.
Abstract – Moving object detection is very important in modernworld for fast video surveillance. There are various methods usedfor detecting moving objects out of which frame differencingmethod is widely used and is most efficient method. In this paperwe focus on the surveillance at the most secured areas such asairports, defense establishments, power stations etc. Similarly, thearea where no human is allowed without authority to enter such asbank locker rooms, restricted military area etc. automotivesurveillance and traffic monitoring plays a vital role. In real timesurveillance system, storing the captured video and detecting objectare two most important issues. Storing such videos needs morememory and the detection of the object is also need to be fast. Tosolve these problems compression and fast object detection isrequired. To detect the moving object, detection of its edges andlocation in the frame are important steps. In this paper we proposea mechanism to use discrete wavelet transform (DWT) for twopurposes for compression and edge detection, whereas to locate theobject we propose variance method on to the 2-D DWT outputs ofvideo frames. For this analysis HAAR wavelet is used as reference.
การแปล กรุณารอสักครู่..
