Multimodal sensor fusion for personnel detection

Brian Maguire; Sachi Desai; Shafik A. Quoraishee

doi:10.1117/12.888874

23 May 2011 Multimodal sensor fusion for personnel detection

Brian Maguire, Sachi Desai, Shafik A. Quoraishee

Proceedings Volume 8046, Unattended Ground, Sea, and Air Sensor Technologies and Applications XIII; 80460E (2011) https://doi.org/10.1117/12.888874
Event: SPIE Defense, Security, and Sensing, 2011, Orlando, Florida, United States

Abstract

Proposed herein is a framework between disparate multiple sensing modalities with correlated biometrics between the orthogonal modalities to aide in actor identification and discrimination within a particular defined scene. For the purposes of detection and classification, there are advantages and disadvantages to using either seismic or ultrasonic-sensing modalities individually to detect, identify, and classify successfully a subject to some degree. The seismic modality provides a clean, separable set of results for walkers close to the sensor but in general fails to be as successful at a larger stand-off due to ground wave attenuation and provides only some level of detection. The ultra-sonic modality provides stronger detection results from a greater stand-off distance in direct comparison to the seismic sensor due to higher fidelity of the signal. However, the resulting signature is harder to separate into individual walk-cycle events due to the broadband nature of the ultrasonic profile. In light of the advantages and disadvantages, it is desirable to utilize the capabilities of both sensors to create a framework for a robust singular solution for detection, identification, and classification of the actor(s) within the scene. In this particular case, data fusion techniques such as Hidden Markov Models and Dempster Shafer Theory provide a framework and methodology for exploiting each modality in an optimized and complementary fashion. In a probabilistic sense, this means that the chance of a successful detection is increased through a decision model that uses both the seismic and ultrasonic detection results to detect a target with high confidence.

Citation Download Citation

Brian Maguire, Sachi Desai, and Shafik A. Quoraishee "Multimodal sensor fusion for personnel detection", Proc. SPIE 8046, Unattended Ground, Sea, and Air Sensor Technologies and Applications XIII, 80460E (23 May 2011); https://doi.org/10.1117/12.888874

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
11 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Sensors

Data fusion

Data modeling

Ultrasonics

Sensor fusion

Sensor networks

Target detection

Show All Keywords

Keywords/Phrases

Search In:

Publication Years