Research Article

overratedbeltAI and Robotics

Nov 25, 2013 (3 years and 7 months ago)

211 views

Research Article

Market
-
Based Approach to Mobile Surveillance
Systems

Ahmed M. Elmogy, Alaa M. Khamis, and Fakhri O. Karray



The active surveillance of public and private sites is increasingly becoming a very
important and critical issue. It is, therefore, imperative to develop mobile surveillance
systems to protect these sites. Modern surveillance systems encompass spatially
di
stributed mobile and static sensors in order to provide e

ective monitoring of persistent
and transient objects and events in a given area of interest (AOI). The realization of the
potential of mobile surveillance requires the solution of di

erent challeng
ing problems
such as task allocation, mobile sensor deployment, multisensor management, cooperative
object detection and tracking, decentralized data fusion, and interoperability and
accessibility of system nodes. This paper proposes a market
-
based approac
h that can be
used to handle di

erent problems of mobile surveillance systems. Task allocation and
cooperative target tracking are studied using the proposed approach as two challenging
problems of mobile surveillance systems. These challenges are addresse
d individually and
collectively.


Journal of Robotics, Volume 2012, Article ID 841291



Market
-
based Framework for Mobile Surveillance Systems

Ahmed M. Elmogy*, Alaa M. Khamis**, and Fakhri O. Karray***

*Tanta Univ., Egypt,** GUC, Egypt, *** Waterloo
Univ., Canada


Abstract. The active surveillance of public and private sites is increasingly

becoming a very
important and critical issue. It is therefore, imperative

to develop mobile surveillance
systems to protect these sites.

Modern surveillance system
s encompass spatially
distributed mobile and

static sensors in order to provide e
ff
ective monitoring of persistent
and

transient objects. The realization of the potential of mobile surveillance

requires the
solution of diff
erent challenging problems such a
s task allocation,

mobile sensor
deployment, multisensor management, and cooperative

object tracking. This paper
proposes a market
-
based framework that

can be used to handle di
ff
erent problems of
mobile surveillance systems.

Task allocation and cooperative

target
-
tracking are studied
using the

proposed framework as two challenging problems of mobile surveillance

systems. These challenges are addressed individually and collectively
.


Published in AIS conference, 2012




C
OOPERATIVE
M
ULTI
T
ARGET
T
RACKING

USING
M
ULTI
S
ENSOR
N
ETWORK

Ahmed M. Elmogy , Fakhreddine O. Karray



Abstract


Sensors provide a key feedback link allowing robotic and
autonomous systems to react to their environments. Without this feedback,
robotic and autonomous systems will operate in

an uncontrolled manner, since
they don’t have the ability to perceive and respond to their environments. The
limited capabilities of static sensors especially in complex applications and
environments force the use of multiple sensors operating dynamically
. This
paper addresses the development of multiple objects tracking system using
multiple mobile sensors. For the purposes of surveillance and security, trackers
use an Extended Kohonen neural network to track the moving targets in their
environments. The
proposed tracking algorithm can be used for single and
multiple target tracking. A clustering algorithm is used in order to minimize the
number of active trackers over time and hence save energy. An auction based
algorithm is used for the purpose of optimi
zing the cooperation between
trackers. Quantitative and qualitative comparisons with other recent multi target
tracking approaches show that our proposed tracking algorithm can provide a
good coverage, and a better energy saving.



INTERNATIONAL JOURNAL
ON SMART SENSING A
ND
INTELLIGENT SYSTEMS, VOL. 1,
NO. 3, SEPTEMBER
2008


Index terms: Mobile sensors, target tracking, Kohonen neural network, clustering



Complex Task Allocation in Mobile Surveillance Systems

Alaa M. Khamis, Ahmed M. Elmogy,, and Fakhri
O. Karray


Abstract
:

In mobile surveillance systems, complex task

allocation addresses
how to optimally assign a set of

surveillance tasks to a set of mobile sensing
agents to

maximize overall expected performance, taking into account

the
priorities of the

tasks and the skill ratings of

the mobile sensors. This paper
presents a market
-
based

approach to complex task allocation. Complex tasks
are

the tasks that can be decomposed into subtasks. Both

centralized and
hierarchical allocations are investigated

as
winner determination strategies for
di
ff
erent levels of

allocation and for static and dynamic search tree structures.

The objective comparison results show that hierarchical

dynamic tree task
allocation outperforms all

the other techniques especially in co
mplex
surveillance

operations where large number of robots is used to scan

large
number of areas.



Keywords Surveillance systems,
task allocation
,
market
-
based techniques


Published in Springer

Journal of Robotics 2012.


Market
-
based Dynamic Task
Allocation in
Mobile Surveillance Systems


Ahmed M. Elmogy

Alaa M. Khamis, Fakhri O. Karray



Abstract


Mobile surveillance systems include a vast array of mobile sensing nodes with varying sensing
modalities that can sense continuously

the volume of interest. These distributed nodes are capable of sensing,
processing, mobilization and communication with other nodes. One of the fundamental problems of mobile sur
-
veillance systems is how to assign a set of tasks to a set of mobile sensor
s and how to coordinate the behavior of
these mobile sensing nodes in order to perform cooperative tasks efficiently. This problem is known as multi
-
robot
task allocation (MRTA). This paper presents centralized and hierarchical dynamic and fixed tree task
allocation
approaches to solve the MRTA problem. The objective comparison results show that hierarchical dynamic tree task
allocation outperforms all the other techniques especially in complex surveillance operations where large number of
robots is used t
o scan large number of areas.


Keywords
:

Mobile sensors, Surveillance systems, task allocation,

Market based techniques


Published In SSRR Workshop,

USA, 2010