Improvement of the Laplace-based Particle Filter for Track-before-detect

摘要

Track-before-detect (TBD) is an efficient approach for tracking a target with low signal-to-noise-ratio. Unlike classic detection methods, TBD does not require thresholding. TBD integrates the signal of the target over space and time. This paper follows the one we published last year. A new particle filter has been proposed where the proposal density is constructed thanks to local Laplace approximations at the modes of the posterior density. An improved and fast version of this filter is proposed which includes also a sequential target detection test. Some results on simulated and experimental infrared images are presented.