Robust Multi-Object Tracking: A Labeled Random Finite Set Approach
Access Status
Open access
Authors
Gardiyawasam Punchihewa, Yuthika Samanmali
Date
2018Supervisor
Ba-Ngu Vo
Type
Thesis
Award
PhD
Metadata
Show full item recordFaculty
Science and Engineering
School
School of Electrical Engineering, Computing and Mathematical Sciences
Collection
Abstract
The labeled random finite set based generalized multi-Bernoulli filter is a tractable analytic solution for the multi-object tracking problem. The robustness of this filter is dependent on certain knowledge regarding the multi-object system being available to the filter. This dissertation presents techniques for robust tracking, constructed upon the labeled random finite set framework, where complete information regarding the system is unavailable.
Related items
Showing items related by title, author, creator and subject.
-
Arora, Balwinder Singh (2012)The precise positioning applications have long been carried out using dual frequency carrier phase and code observables from the Global Positioning System (GPS). The carrier phase observables are very precise in comparison ...
-
Amiri, Amirpiran (2013)The alumina industry provides the feedstock for aluminium metal production and contributes to around A$6 billion of Australian exports annually. One of the most energy-intensive parts of alumina production, with a strong ...
-
Reuter, S.; Vo, Ba Tuong; Vo, Ba-Ngu; Dietmayer, K. (2014)In this paper, we propose the labeled multi-Bernoulli filter which explicitly estimates target tracks and provides a more accurate approximation of the multi-object Bayes update than the multi-Bernoulli filter. In particular, ...