Share Email Print
cover

Proceedings Paper

Feature-aided multiple hypothesis tracking using topological and statistical behavior classifiers
Author(s): David Rouse; Adam Watkins; David Porter; John Harer; Paul Bendich; Nate Strawn; Elizabeth Munch; Jonathan DeSena; Jesse Clarke; Jeff Gilbert; Sang Chin; Andrew Newman
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper introduces a method to integrate target behavior into the multiple hypothesis tracker (MHT) likelihood ratio. In particular, a periodic track appraisal based on behavior is introduced that uses elementary topological data analysis coupled with basic machine learning techniques. The track appraisal adjusts the traditional kinematic data association likelihood (i.e., track score) using an established formulation for classification-aided data association. The proposed method is tested and demonstrated on synthetic vehicular data representing an urban traffic scene generated by the Simulation of Urban Mobility package. The vehicles in the scene exhibit different driving behaviors. The proposed method distinguishes those behaviors and shows improved data association decisions relative to a conventional, kinematic MHT.

Paper Details

Date Published: 21 May 2015
PDF: 12 pages
Proc. SPIE 9474, Signal Processing, Sensor/Information Fusion, and Target Recognition XXIV, 94740L (21 May 2015); doi: 10.1117/12.2179555
Show Author Affiliations
David Rouse, Johns Hopkins Univ. Applied Physics Lab. (United States)
Adam Watkins, Johns Hopkins Univ. Applied Physics Lab. (United States)
David Porter, Johns Hopkins Univ. Applied Physics Lab. (United States)
John Harer, Duke Univ. (United States)
Paul Bendich, Duke Univ. (United States)
Nate Strawn, Duke Univ. (United States)
Elizabeth Munch, Duke Univ. (United States)
Jonathan DeSena, Johns Hopkins Univ. Applied Physics Lab. (United States)
Jesse Clarke, Johns Hopkins Univ. Applied Physics Lab. (United States)
Jeff Gilbert, Johns Hopkins Univ. Applied Physics Lab. (United States)
Sang Chin, The Charles Stark Draper Lab. (United States)
Boston Univ. (United States)
Andrew Newman, Johns Hopkins Univ. Applied Physics Lab. (United States)


Published in SPIE Proceedings Vol. 9474:
Signal Processing, Sensor/Information Fusion, and Target Recognition XXIV
Ivan Kadar, Editor(s)

© SPIE. Terms of Use
Back to Top