Proceedings of the ASEE New England Section 2006 Annual Conference. Copyright © 2006
A Centralized Evolutionary Target Tracking System
Yaser Khalifa and Ehi Okoene
Electrical and Computer Engineering Department,
State University of New York at New Paltz
Electrical & Computer Engineering
Abstract: In this paper, a surveillance system is presented. The system is
composed of two stages. To insure the optimization of the usage of sensors
provided, yet maintaining maximum coverage, the first stage is the optimization of
a network of agents containing ultrasonic sensors within a pre-specified coverage
area. Stage two is the target tracking phase. Sensors are activated based on need
according to the tracking requirement of the moving object. To optimize power
usage and hence minimize human intervention for maintenance purpose,
unneeded sensors are kept in a low-power stand-by state. Sensor agents have the
capability of communicating with a centralized server to report on target location
and direction. The central server powers-up those agent sensors needed for
proper tracking of the moving object.
1. Introduction
One of the main applications for surveillance systems is in military. The design and development
of surveillance systems for military purposes is experiencing an increased growth. Such systems
are intended to detect, locate and track moving targets, which include humans, trucks, tanks etc.
The accuracy of these systems depends on a number of factors. Some of theses are 1) the
integration of information from several sensors, 2) the optimization of the location of sensors in
order to achieve complete coverage of the desired area, 3) the efficient use of the system’s
resources (e.g. maintenance of sensor’s battery life for a longer life-span), and 4) reliable real-
time communication in the midst of harsh environmental conditions and/or changes in the
system. As a result of such a dynamic environment a lot of research has been done into the
development of autonomous systems, capable of achieving the goals of surveillance (target
detection, location, tracking etc) in the midst of constantly changing conditions.
The work presented in this paper focuses on two aspects of surveillance: the optimization of the
location of sensors (with the intent of maximizing the amount of area covered by the sensors)
and target tracking. Genetic Algorithm is utilized to achieve an optimum solution for the
location of sensors. The rest of this paper is organized as follows: Sections II provides the
following information: a) a detailed description of the Optimization Program and how it is
implemented in order to achieve goal of maximizing the area covered by these sensors, and b) a
description of the techniques used to track objects that enter the surveillance area.
The results obtained so far are presented in section III, while section IV gives a summary and a
conclusion.