A probabilistic nearest neighbor filter algorithm for tracking in a clutter environment

Authors:
Taek Lyul Song;Dong Gwan Lee;Jonha Ryu
Affiliations:
Department of Control and Instrumentation Engineering, Hanyang University, Sangnok-Gu, Ansan-Si, Gyeonggi-Do, Republic of Korea;Department of Control and Instrumentation Engineering, Hanyang University, Sangnok-Gu, Ansan-Si, Gyeonggi-Do, Republic of Korea;Agency for Defense Development, Korea
Venue:
Signal Processing
Year:
2005

Citing 2
Cited 5

Tracking and data association

Tracking and data association
Target perceivability and its applications

IEEE Transactions on Signal Processing

The SAFEE on-board threat detection system

ICVS'08 Proceedings of the 6th international conference on Computer vision systems
Unified cardinalized probability hypothesis density filters for extended targets and unresolved targets

Signal Processing
Spatio-temporal target-measure association using an adaptive geometrical approach

Pattern Recognition Letters
A global difference measure for the reduction of Gaussian inverse Wishart mixtures

Signal Processing
A novel fast partitioning algorithm for extended target tracking using a Gaussian mixture PHD filter

Signal Processing

Quantified Score

Hi-index	0.08

Visualization

Abstract

A new probabilistic nearest neighbor (NN) filter algorithm which accounts for the probability that the NN measurement is a false one is proposed to improve the performance of the NN filter. The NN filter is the most popular and widely used algorithm for target tracking in clutter due to its computational simplicity. The proposed algorithm is derived from establishing probability density functions conditioned on all the possible events related to the NN measurement. The resulting algorithm is different from the existing probabilistic nearest neighbor filter (PNNF) algorithm. The performance of the proposed algorithm is analyzed and compared with that of the NNF. The proposed algorithm for aerial target tracking in a clutter environment is tested by a series of Monte Carlo simulation runs. Simulation results are also compared with the off-line performance prediction algorithm developed in this paper.