Gaussian process inference approximation for indoor pedestrian localisation


Clutter has a complex effect on radio propagation, and limits the effectiveness of deterministic methods in wireless indoor positioning. In contrast, a Gaussian process (𝒢𝒫) can be used to learn the spatially correlated measurement error directly from training samples, and build a representation from which a position can be inferred. A method of exploiting 𝒢ℬ inference to obtain measurement predictions from within a pose graph optimisation framework is presented. However, 𝒢𝒫 inference has a run-time complexity of 𝒪(N3) in the number of training samples N, which precludes it from being called in each optimiser iteration. The novel contributions of this work are a method for building an approximate 𝒢𝒫 inference map and an 𝒪(1) bi-cubic interpolation strategy for sampling this map during optimisation. Using inertial, magnetic, signal strength and time-of-flight measurements between four anchors and a single mobile sensor, it is shown empirically that the presented approach leads to decimetre precision indoor pedestrian localisation.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE :Maximum Likelihood Decoding for Gaussian Noise Channels With Gain or Offset Mismatch - 2018ABSTRACT:Besides the omnipresent noise, different important inconveniences in communication and storage systems are shaped
PROJECT TITLE :Rectified Gaussian Scale Mixtures and the Sparse Non-Negative Least Squares Problem - 2018ABSTRACT:In this Project, we develop a Bayesian evidence maximization framework to unravel the sparse non-negative least
PROJECT TITLE :Particle Smoothing for Conditionally Linear Gaussian Models as Message Passing Over Factor Graphs - 2018ABSTRACT:During this Project, the fixed-lag smoothing problem for conditionally linear Gaussian state-space
PROJECT TITLE :Fast Low-Rank Bayesian Matrix Completion With Hierarchical Gaussian Prior Models - 2018ABSTRACT:The problem of low-rank matrix completion is taken into account in this Project. To use the underlying low-rank structure
PROJECT TITLE :Beyond A Gaussian Denoiser: Residual Learning Of Deep Cnn For Image Denoising - 2017ABSTRACT:The discriminative model learning for image denoising has been recently attracting considerable attentions due to its

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry