Dim target tracking base on GM-PHD filter

Authors:
Lei Li;Jinqiu Sun;Yu Zhu;Haisen Li
Affiliations:
Shaanxi Province Key Laboratory of Speech & Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China;Institute of Precision Guidance and Control, Northwestern Polytechnical University, Xi'an, China;Shaanxi Province Key Laboratory of Speech & Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China;Shaanxi Province Key Laboratory of Speech & Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China
Venue:
IScIDE'11 Proceedings of the Second Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2011

Citing 5
Cited 0

Statistical Multisource-Multitarget Information Fusion

Statistical Multisource-Multitarget Information Fusion
A New Starry Images Matching Method in Dim and Small Space Target Detection

ICIG '09 Proceedings of the 2009 Fifth International Conference on Image and Graphics
Relative entropy rate based multiple hidden Markov model approximation

IEEE Transactions on Signal Processing
The Gaussian Mixture Probability Hypothesis Density Filter

IEEE Transactions on Signal Processing
Tracking an unknown time-varying number of speakers using TDOA measurements: a random finite set approach

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a real time method for detecting and tracking multiple dim targets in deep space background is presented. We matched the stars in tow continuous images to get their speed at first and found moving targets through speed in both images. Using the targets in the common frame data association is achieved. The Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter is used to track targets to solve the problem of targets disappearance. To initialize of the birth random finite sets (RFSs) the targets sequences are built to find new targets. Extensive experiments on real images sequences show that the proposed approach could effectively meet the requirements of the real-time detection with a low false alarm rate and a high detection probability.