Information Fusion for Industrial Mobile Platform Safety via Track-Before-Detect Labeled Multi-Bernoulli Filter

Rathnayake, T, Tennakoon, R, Khodadadian Gostar, A, Bab-Hadiashar, A and Hoseinnezhad, R 2019, 'Information Fusion for Industrial Mobile Platform Safety via Track-Before-Detect Labeled Multi-Bernoulli Filter', Sensors, vol. 19, no. 9, pp. 1-20.


Document type: Journal Article
Collection: Journal Articles

Title Information Fusion for Industrial Mobile Platform Safety via Track-Before-Detect Labeled Multi-Bernoulli Filter
Author(s) Rathnayake, T
Tennakoon, R
Khodadadian Gostar, A
Bab-Hadiashar, A
Hoseinnezhad, R
Year 2019
Journal name Sensors
Volume number 19
Issue number 9
Start page 1
End page 20
Total pages 20
Publisher MDPIAG
Abstract This paper presents a novel Track-Before-Detect (TBD) Labeled Multi-Bernoulli (LMB) filter tailored for industrial mobile platform safety applications. At the core of the developed solution is two techniques for fusion of color and edge information in visual tracking. We derive an application specific separable likelihood function that captures the geometric shape of the human targets wearing safety vests. We use a novel geometric shape likelihood along with a color likelihood to devise two Bayesian updates steps which fuse shape and color related information. One approach is sequential and the other is based on weighted Kullback-Leibler average (KLA). Experimental results show that the KLA based fusion variant of the proposed algorithm outperforms both the sequential update based variant and a state-of-art method in terms of the performance metrics commonly used in computer vision literature.
Subject Computer Vision
Image Processing
Keyword(s) Bayesian
Kullback-Leibler divergence
labeled multi bernoulli
multi-target tracking
random finite sets
track-before-detect
DOI - identifier 10.3390/s19092016
Copyright notice © 2019 by the authors. Licensee MDPI, Basel, Switzerland. Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
ISSN 1424-8220
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 3 Abstract Views  -  Detailed Statistics
Created: Fri, 05 Jul 2019, 12:33:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us