Lightweight map matching for indoor localisation using conditional random fields

Abstract

Indoor tracking and navigation is a fundamental need for pervasive and context-aware smartphone applications. Although indoor maps are becoming increasingly available, there is no practical and reliable indoor map matching solution available at present. We present MapCraft, a novel, robust and responsive technique that is extremely computationally efficient (running in under 10 ms on an Android smartphone), does not require training in different sites, and tracks well even when presented with very noisy sensor data. Key to our approach is expressing the tracking problem as a conditional random field (CRF), a technique which has had great success in areas such as natural language processing, but has yet to be considered for indoor tracking. Unlike directed graphical models like Hidden Markov Models, CRFs capture arbitrary constraints that express how well observations support state transitions, given map constraints. Extensive experiments in multiple sites show how MapCraft outperforms state-of-the art approaches, demonstrating excellent tracking error and accurate reconstruction of tortuous trajectories with zero training effort. As proof of its robustness, we also demonstrate how it is able to accurately track the position of a user from accelerometer and magnetometer measurements only (i.e. gyro-and WiFi-free). We believe that such an energy-efficient approach will enable alwayson background localisation, enabling a new era of location-aware applications to be developed.978-1-4799-3146-0/14/$31.00 ©2014 IEEE

Efficient Indoor Positioning with Visual Experiences via Lifelong Learning

“…On the other hand, if the graph can be embedded to a consistent frame of reference, e.g. by map matching [6], localisation against the graph is equivalent to positioning within the global map (see Fig. 4(b)).…”

“…Comparing to the traditional solutions which seek to compute the global coordinates of the users [4], [5], [6], those teach-repeat systems require much less bootstrapping and training effort. For instance, the Escort system [1] navigates a user towards another by combining her previously recorded inertial trajectories with encounters from audio beacons.…”

A Joint Indoor WLAN Localization and Outlier Detection Scheme Using LASSO and Elastic-Net Optimization Techniques

“…The estimated position is a weighted average of the selected points, where these weights are obtained using an inner product between the online and radio map fingerprints using a Kernel equivalent function. More sophisticated probabilistic techniques have been recently investigated including Kullback-Leibler (KL) divergence [55], Principal Component Analysis (PCA) [56], Conditional Random Fields (CRF) [57] and Bayesian Networks [58].…”

Multifrequency Phase Difference of Arrival Range Measurement: Principle, Implementation, and Evaluation

“…What is more, the phase delay is a periodic function with 2 radians while the measured phase value by the reader is mod (2 ). If the tag-to-reader distance is larger than max = /2 , which is referred as the maximum unambiguous range, the phase difference exceeds 2 and brings phase warping.…”