Representing arbitrary sensor observations for target tracking in wireless sensor networks. (November 2017)

• Record Type: Journal Article
• Authors: Sleep, Scott Ryan; Dadej, Arek; Lee, Ivan
• Is Part Of: Computers & electrical engineering. Volume 64(2017)
• Page Start: 354
• Page End: 364
• Publication Date: 2017-11
• Subjects: Wireless sensor network -- Target tracking -- Heterogeneous sensors -- Adaptive state space -- Nonparametric representation -- Occupancy grid; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2016.11.033
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Framework for distributed target tracking algorithm with a priori unknown sensor types. Representing location and non-location observations together using a joint belief distribution. Found 38% average reduction in location error in a simulation of simple sensors, compared to conventional representation. Graphical abstract: Abstract: Conventional object tracking in wireless sensor networks requires the use of predefined sensor types, which presents challenges when faced with adaptability and scalability constraints. This paper considers heterogeneous sensors and proposes a sensor-independent tracking framework. The Adaptive Grid Representation of belief Distribution (Adaptive GRiD) provides a common data format to allow heterogeneous sensors to be treated homogeneously. The proposed framework has been evaluated by simulation, and the results demonstrate that the Adaptive GRiD technique yields improved location estimation over a conventional occupancy grid approach.