Conference Proceedings


Chris Bleakley
Nagesh Yadav


Computer Science

observers control theory location three dimensional imaging fusion kalman filter sensor data fusion hybrid bayesian statistical decision theory

Hybrid Bayesian fusion of range-based and sourceless location estimates under varying observability (2012)

Abstract The paper proposes a hybrid Bayesian approachfor multi-sensor data fusion for 3D localization. The approachaddresses the problem of fusing range-based and sourcelesslocalization estimates under conditions of varying observability inthe range-based sub-system. The proposed localization approachuses a mixture of Single-Hypothesis-Tracking (e.g. Kalman filter)and Multi-Hypothesis-Tracking (MHT) (e.g. Particle Filters)Bayesian filtering to improve tracking accuracy under conditionsof varying observability. Under conditions of sufficient (or no)range measurements a single hypothesis approach is used. Underthe condition of insufficient range measurements (i.e, 1 or 2ranges), MHT is used, since it more accurately models thedistribution of real error in the estimated positions by means ofGaussian mixtures rather that a single Gaussian. The results showup to 10% improvement in 3D position estimation as comparedto Single-Constraint-at-a-Time (SCAAT) approach and upto 24%improvement compared to an Extended Kalman Filter approachfor intermittent 3 second partial range occlusions when trackinghuman arm movements.
Collections Ireland -> University College Dublin -> College of Science
Ireland -> University College Dublin -> School of Computer Science
Ireland -> University College Dublin -> Computer Science Research Collection

Full list of authors on original publication

Chris Bleakley, Nagesh Yadav

Experts in our system

Chris Bleakley
University College Dublin
Total Publications: 105