Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/366552
Title: | Adaptive Marginalized Particle Filter for Target Tracking Applications |
Researcher: | Sanil J. |
Guide(s): | N. Santhi |
Keywords: | Engineering Engineering and Technology Engineering Electrical and Electronic |
University: | Noorul Islam Centre for Higher Education |
Completed Date: | 2021 |
Abstract: | Target tracking is considered as a critical element in many applications including guidance system, collision avoidance, surveillance, missile tracking, aircraft tracking. An effective solution of target tracking is achieved by considering it as a state estimation problem. The thesis contributes to the development of a state estimation filter known as the Adaptive Marginalized Particle Filter (AMPF) which can replace some of the existing estimation techniques in solving target tracking problems such as Particle Filter (PF) and Marginalized Particle Filter (MPF). The thesis is bifurcated into the simulation of existing techniques, the algorithmic formulation of AMPF and the testing using several aircraft tracking simulations. newlineThe study of various existing estimation techniques in solving target tracking problems in the former part of the thesis done using simulations reveals the research gap of the thesis. The ability of MPF in withstanding the varying noise conditions is clearly noticed in the simulations, making it a possible candidate for modification by incorporating the varying noise condition which usually prevails in real world target tracking problems. This varying nature of the noise is not considered in the development of estimation techniques as per the literature review. The noise tolerance property of MPF along with the varying nature of noise affecting the system has been the backbone of the proposed state estimation filter. newlineThe central portion of the thesis includes all the relevant explanations regarding the algorithmic formulation of AMPF. AMPF can be applied to all the target tracking problems in which a linear Gaussian substructure is present in the model. The algorithmic modification in comparison with MPF is that, AMPF adapts itself in accordance with noise in terms of the number of particles thereby resulting in better execution speed as well as accuracy. The later part of the thesis involves the testing of AMPF in solving a typical target tracking example using several simulation scenarios i |
Pagination: | 8845Kb |
URI: | http://hdl.handle.net/10603/366552 |
Appears in Departments: | Department of Electronics and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
80_recommendation.pdf | Attached File | 136.06 kB | Adobe PDF | View/Open |
certificate.pdf | 65.72 kB | Adobe PDF | View/Open | |
chapter 1.pdf | 66.83 kB | Adobe PDF | View/Open | |
chapter 2.pdf | 74.86 kB | Adobe PDF | View/Open | |
chapter 3.pdf | 8.13 MB | Adobe PDF | View/Open | |
chapter 4.pdf | 1.2 MB | Adobe PDF | View/Open | |
chapter 5.pdf | 6.67 MB | Adobe PDF | View/Open | |
chapter 6.pdf | 822.86 kB | Adobe PDF | View/Open | |
chapter 7.pdf | 33.5 kB | Adobe PDF | View/Open | |
list of publications based on thesis.pdf | 22.09 kB | Adobe PDF | View/Open | |
preliminary pages.pdf | 60.47 kB | Adobe PDF | View/Open | |
references.pdf | 72.88 kB | Adobe PDF | View/Open | |
title page.pdf | 35.8 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: