Rao-Blackwellised Particle Filter for Star-Convex Extended Target Tracking Models

Date

2016-07-08

Author

Özkan, Emre
Godsill, Simon J.

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

57
views

0
downloads

In this paper, we explore the potential gains in using Sequential Monte Carlo (SMC) methods for extended target tracking (ETT) models based on Gaussian processes (GP). The existing random hypersurface based ETT models use Extended/Unscented Kalman filter for inference, which may lead to poor performance under high uncertainty. Particle filters (PFs) are known to provide robust performance in the cases where the non-linear Kalman filtering solutions fail. We design a Rao-Blackwellised particle filter (RBPF) where we exploit the conditional linear Gaussian structure of the GP parameters. We illustrate the gain in the performance with simulations.

URI

https://hdl.handle.net/11511/55669

Conference Name

19th International Conference on Information Fusion (FUSION)

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

A CMOS visible image sensor array using current mirroring integration readout circuitry Akbay, Selim Sermet; Bircan, A.; Akın, Tayfun (null; 2000-08-30) This paper reports the development of a CMOS visible sensor array using a high performance readout circuit called Current Mirroring Integration (CMI). The sensor element is a photodiode implemented using n-well and p+ -active layers available in any CMOS process. The current generated by optical excitation is mirrored and integrated in an off-pixel capacitor using the CMI readout circuit, which provides high injection efficiency, low input impedance, almost-zero and stable detector bias, and a high dynamic ...
Efficient Bayesian track-before-detect Tekinalp, Serhat; Alatan, Abdullah Aydın (2006-10-11) This paper presents a novel Bayesian recursive track-before-detect (TBD) algorithm for detection and tracking of dim targets in optical image sequences. The algorithm eliminates the need for storing past observations by recursively incorporating new data acquired through sensor to the existing information. It calculates the likelihood ratio for optimal detection and estimates target state simultaneously. The technique does not require velocity-matched filtering and hence, it is capable of detecting any targ...
Reliable Low Resolution 01-4DM Receivers via Deep Learning Balevi, Eren; Andrews, Jeffrey G. (2018-01-01) This paper develops novel deep learning-based architectures and design methodologies for an orthogonal frequency division multiplexing (OFDM) receiver under the constraint of one-bit complex quantization. Single bit quantization greatly reduces complexity and power consumption, but makes accurate data detection difficult. This is particularly true for multicarrier waveforms, which have high peak-to-average ratio in the time domain and fragile subcarrier orthogonality in the frequency domain. The severe dist...
Optimization of a Self-organized Collective Motion in a Robotic Swarm Bahaidarah, Mazen; Bana, Fatemeh Rekabi; Turgut, Ali Emre; Marjanovic, Ognjen; Arvin, Farshad (2022-01-01) A novel collective organization method is proposed in this paper to improve the performance of the former Active Elastic Sheet (AES) algorithm by applying the Particle Swarm Optimization technique. Replacing the manual parameters tuning of the AES model with an evolutionary-based method leads the swarm to remain stable meanwhile the agents make a perfect alignment exploiting less energy. The proposed algorithm utilizes a hybrid cost function including the alignment error, interaction force, and time to cons...
Multiple Model Adaptive Estimation Algorithm for Systems with Parameter Change Söken, Halil Ersin (2016-01-01) This paper presents an autonomous multiple model (AMM) estimation algorithm for systems with sudden parameter changes. Estimates of a bank of Kalman filters (KFs) are merged based on a newly defined likelihood function. The function is composed of two measures, one for weighting the filters during the steady state mode and the other for weighting when there is a change in the parameters. Compared to the interacting multiple model (IMM) method, the KFs do not interact but compete on the basis of the likeliho...

Citation Formats

E. Özkan and S. J. Godsill, “Rao-Blackwellised Particle Filter for Star-Convex Extended Target Tracking Models,” presented at the 19th International Conference on Information Fusion (FUSION), Heidelberg, GERMANY, 2016, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/55669.