IEEE-ICET 2006
2
nd
International Conference on Emerging Technologies
Peshawar, Pakistan, 13-14 November 2006
1-4244-0502-5/06/$20.00©2006 IEEE 174
Object Tracking using Correlation, Kalman Filter
and Fast Means Shift Algorithms
Ahmad Ali
1
, Dr. Sikander Majid Mirza
2
1,2
Pakistan Institute of Engineering & Applied Sceinces,Islamabad,Pakistan.
1
ahmadali1655@hotmail.com ,
2
sikander_majid@yahoo.com
Abstract: Object detection in videos involves
verifying the presence of an object in image
sequences and possibly locating it precisely for
recognition. Object tracking is to monitor an object’s
spatial and temporal changes during a video
sequence, including its presence, position, size,
shape, etc. This is done by solving the temporal
correspondence problem, the problem of matching
the target region in successive frames of a sequence
of images taken at closely-spaced time intervals.
These two processes are closely related because
tracking usually starts with detecting objects, while
detecting an object repeatedly in subsequent image
sequence is often necessary to help and verify
tracking. In this paper, a novel approach is being
presented for object tracking. It includes combination
of 2D normalized correlation, Kalman filter and fast
mean shift algorithm.
1. INTRODUCTION
Videos are actually sequences of images, each
of which called a frame, displayed in fast
enough frequency so that human eyes can
percept the continuity of its content. It is obvious
that all image processing techniques can be
applied to individual frames. Besides, the
contents of two consecutive frames are usually
closely related.
Visual content can be modeled as a hierarchy
of abstractions. At the first level are the raw
pixels with color or brightness information.
Further processing yields features such as edges,
corners, lines, curves, and color regions. A
higher abstraction layer may combine and
interpret these features as objects and their
attributes. At the highest level are the human
level concepts involving one or more objects and
relationships among them.
Object detecting and tracking has a wide
variety of applications in computer vision such
as video compression, video surveillance,
vision-based control, human-computer
interfaces, medical imaging, augmented reality,
and robotics. Additionally, it provides input to
higher level vision tasks, such as 3D
reconstruction and 3D representation. It also
plays an important role in video database such as
content-based indexing and retrieval. This paper
describes a novel way for tracking of a general
purpose object which is fail-safe.
2. TRACKING ALGORITHM
In a very abstract way, tracking algorithm can
be described by following diagram.
Fig.1 Tracking Algorithm
The core of the algorithm is to search the
target of interest (TOI) in the image frame and
the replacement of template by the target found
in current image frame, called template-updating
stage.
A. Template Searching
To develop fail-safe tracking algorithm, first
template matching technique was tested.
Normalized 2D correlation based method was
used for template matching.[2] In every next
frame, template was matched, if correlation is
greater than threshold value then it is assumed
that target is detected. After confirmation of
target, template is updated with new detected
target. This updating of template helps to cater
the problem of any change in target shape or
Searching of Target of
Interest (TOI)
Updating of
Template
Image Frame