Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: OPTIMAL SENSOR SELECTION FOR VIDEO-BASED TARGET TRACKING IN A WIRELESS SENSOR NETWORK Peshala V. Pahalawatta, Thrasyvoulos N. Pappas, and Aggelos K. Katsaggelos Department of Electrical and Computer Engineering Northwestern University, Evanston, IL 60208, USA (pesh, pappas, aggk)@ece.northwestern.edu ABSTRACT The use of wireless sensor networks for target tracking is an active area of research. Imaging sensors that obtain video-rate images of a scene can have a significant impact in such networks, as they can measure vital information on the identity, position, and veloc- ity of moving targets. Since wireless networks must operate under stringent energy constraints, it is important to identify the optimal set of imagers to be used in a tracking scenario such that the net- work lifetime is maximized. We formulate this problem as one of maximizing the information utility gained from a set of sensors subject to a constraint on the average energy consumption in the network. We use an unscented Kalman filter framework to solve the tracking and data fusion problem with multiple imaging sen- sors in a computationally efficient manner, and use a lookahead algorithm to optimize the sensor selection based on the predicted trajectory of the target. Simulation results show the effectiveness of this method of sensor selection. 1. INTRODUCTION Video-based tracking for applications, such as surveillance and traffic analysis, is a well-studied topic in computer vision. Sys- tems with multiple cameras can be used to detect and localize mov- ing objects while also providing vital information on the objects, such as shape, color, and size, which can be used for identifica- tion. [1] and [2] are examples of multiple camera tracking systems proposed for wired networks of cameras. The computational cost associated with image and video processing, however, has driven recent research on tracking with wireless sensor networks towards less complex and less energy consuming sensors. An analysis of the energy consumption and information rate of visual sensors relative to other sensors is provided in [3]. It is shown in [3] that, while visual sensors cost more in terms of energy consumption per sample than acoustic or seismic sensors, they can still be valuable partners in a wireless sensor network. Therefore, it is important to develop scalable schemes for collaboratively using multiple imaging sensors in a sensor network. In this paper, we demonstrate a method for selecting the opti- mal set of imaging sensors to use for tracking a moving target such that the energy consumed in the network is within a reasonable constraint. In order to achieve this, we use the concept of sensor utility [4]-[6]. In [4], this idea is introduced in terms of selecting subsets of sensors at each time step such that the sum utility gain over the total time is maximized subject to a total power constraint for each sensor. However, they use a simple model for the utility function where it is assumed to monotonically increase with the...
View Full Document

This note was uploaded on 06/13/2011 for the course CAP 6412 taught by Professor Staff during the Spring '08 term at University of Central Florida.

Page1 / 4


This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online