You can view the full text of this article for free using the link below.

Title: State estimation-based target tracking and applications of multi sensor data fusion

Authors: David Kondru; Mehmet Celenk; Xiaoping A. Shen

Addresses: School of EECS, Ohio University, Athens, OH, 45701, USA ' School of EECS, Ohio University, Athens, OH, 45701, USA ' Department of Mathematics, Ohio University, Athens, OH, 45701, USA

Abstract: Detection, discrimination and tracking of a target under a given dynamic environment is one of the main challenges of an integrated sensory system. A combination of two or more sensors will always provide a better position estimate rather than a single sensor. The advantages of multi-sensor data fusion over a conventional single sensor tracking are presented in this paper. Using state estimators from simple linear rustic filters to a complex nonlinear filter, the tracking of target performing three different motions with sensor noises are presented in this paper. RADAR and the infrared search and track (IRST) are the two sensors considered based on which a complete mathematical modelling and simulation of the sensor measurements and tracking methodologies are utilised. The extension of the paper also presents the image fusion techniques using a widely known technique known as principle component analysis method. The RMS errors in position as well as image error measurements are performed that shows the superiority of the multi sensor data fusion process.

Keywords: Kalman filter; particle filter; measurement fusion; state vector fusion; SVF; image fusion; principle component analysis.

DOI: 10.1504/IJFSE.2019.104718

International Journal of Forensic Software Engineering, 2019 Vol.1 No.1, pp.32 - 46

Received: 27 Nov 2018
Accepted: 31 Jan 2019

Published online: 28 Jan 2020 *

Full-text access for editors Access for subscribers Free access Comment on this article