Share Email Print
cover

Optical Engineering

Tracking a large number of closely spaced objects based on the particle probability hypothesis density filter via optical sensor
Author(s): Liangkui Lin; Hui Xu; Wei An; Weidong Sheng; Dan Xu
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

This paper presents a novel approach to tracking a large number of closely spaced objects (CSO) in image sequences that is based on the particle probability hypothesis density (PHD) filter and multiassignment data association. First, the particle PHD filter is adopted to eliminate most of the clutters and to estimate multitarget states. In the particle PHD filter, a noniterative multitarget estimation technique is introduced to reliably estimate multitarget states, and an improved birth particle sampling scheme is present to effectively acquire targets among clutters. Then, an integrated track management method is proposed to realize multitarget track continuity. The core of the track management is the track-to-estimation multiassignment association, which relaxes the traditional one-to-one data association restriction due to the unresolved focal plane CSO measurements. Meanwhile, a unified technique of multiple consecutive misses for track deletion is used jointly to cope with the sensitivity of the PHD filter to the missed detections and to eliminate false alarms further, as well as to initiate tracks of large numbers of CSO. Finally, results of two simulations and one experiment show that the proposed approach is feasible and efficient.

Paper Details

Date Published: 1 November 2011
PDF: 12 pages
Opt. Eng. 50(11) 116401 doi: 10.1117/1.3651798
Published in: Optical Engineering Volume 50, Issue 11
Show Author Affiliations
Liangkui Lin, National Univ. of Defense Technology (China)
Hui Xu, National Univ. of Defense Technology (China)
Wei An, National Univ. of Defense Technology (China)
Weidong Sheng, National Univ. of Defense Technology (China)
Dan Xu, National Univ. of Defense Technology (China)


© SPIE. Terms of Use
Back to Top