Dragana Carevic

Learn More
This paper considers the problem of the estimation of the motion parameters of multiple targets moving linearly in a three-dimensional (3-D) observation area contaminated by clutter. The measurements are limited to time differences of arrival (TDOAs) of short-duration acoustic emissions, or transients, generated by the targets. This problem can arise in(More)
A modified deterministic annealing expectation maximization (MDAEM) algorithm has been proposed [D. Carevic, ldquoAutomatic estimation of multiple target positions and velocities using passive TDOA measurements of transients,rdquo IEEE Transactions on Signal Processing, vol. 55, no. 2, pp. 424-436, 2007] for the estimation of the motion parameters of(More)
is coded separately using some standard technique that In this paper we consider a number of extensions to current exploits the spatial correlation between pixels, such as dif-adaptive compression methods for color images. One, we use ferential pulse code modulation (DPCM) [25], transform clustering or segmentation procedures to determine self-similar(More)
  • D. Carevic
  • 2007
The PLM-MDAEM algorithm is proposed for multitarget detection and tracking in cluttered three dimensional (3-D) underwater environments. The measurements are time delays of arrival (TDOA) of passive transient signals. The (underwater) observer platform is modelled as consisting of a number of 3-D ideal geometric bodies. The receiving sensors used to derive(More)
We consider a problem of modelling and tracking dynamic time-frequency spectra where the number of spectral components is allowed to vary in time. The proposed approach involves representing spectral densities as mixtures of normal distributions with an unknown number of components using a time-varying non-parametric Bayesian method. A multi-target tracking(More)
This paper considers track-before-detect algorithms that can be applied to modeling and tracking of dynamic time-frequency spectra where the number of spectral components is allowed to vary in time. The algorithms are the adaptive Dirichlet process mixture model-based Rao-Blackwellised particle filter (ADPM-RBPF) and the histogram probabilistic(More)
  • 1