X

AutoWitness

Project Goal 

The goal of this project is to build a scalable, yet affordable, wireless sensor network system that can be used for large scale tracking of assets such as lost or stolen objects.  

Results 

In an ACM SenSys 2010 paper, we present AutoWitness, a system to deter, detect, and track personal property theft, improve historically dismal stolen property recovery rates, and disrupt stolen property distribution networks. A property owner embeds a small tag inside the asset to be protected, where the tag lies dormant until it detects vehicular movement. Once moved, the tag uses inertial sensor-based dead reckoning to estimate position changes, but to reduce integration errors, the relative position is reset whenever the sensors indicate the vehicle has stopped. The sequence of movements, stops, and turns are logged in compact form and eventually transferred to a server using a cellular modem after both sufficient time has passed (to avoid detection) and RF power is detectable (hinting cellular access may be available). Eventually, the trajectory data are sent to a server which attempts to match a path to the observations. The algorithm uses a Hidden Markov Model of city streets and Viterbi decoding to estimate the most likely path. The proposed design leverages low-power radios and inertial sensors, is immune to intransit cloaking, and supports post hoc path reconstruction.

A picture of the AutoWitness tag appears on the right. Also, on the right, an overview of the operation of the AutoWitness is depicted in a diagram. Finally, two pictures on the right show the reconstruction of two paths in the city of Memphis where AutoWitness tag was driven.

The AutoWitness system is to be deployed for real-life tracking of burglars in the city of Memphis in early 2011.

Given the high incidence of burgalries (e.g., more than 2 million reported annually in the U.S. alone that account for over $17 billion in losses), we expect the AutoWitness systems to improve the quality of life by addressing property crimes.


Team Members

Lead Faculty Member: Dr. Santosh Kumar

Collaborator: Dr. Prabal Dutta, EECS, University of Michigan

Post Doctoral Fellows

Dr. Kurt Plarre (2008-) - On the job market


Ph.D. Students

Shantanu Guha (2007-) - sguha@memphis.edu

Somnath Mitra (2007-) - smitra3@memphis.edu 


M.S. Students

Bhagavathy Krishna (2007) - bhagavathy.krishna@memphis.edu


Undergraduate Students

Daniel Lissner (2009) - dlissner@memphis.edu


Alumni

Animikh Ghosh (M.S., 2010) - GE Global Research, India


Sponsors

National Science Foundation (CISE, CNS, NeTS-NOSS)
Fedex Institute of Technology, University of Memphis


Updates:

  • 8/11/2008  FIT Grant awarded.

  • 8/14/2007 NSF Grant awarded