In recent years there has been a considerable research on the development of indoor positioning systems. Several kinds of technologies such as ultrasonic, UWB, WLAN, optical waves and hybrid solutions were utilized already. However, using these technologies many difficulties arise in indoor environments due to none line of sight (NLoS) and multipath errors. In this paper, the realization and the evaluation of a 3D indoor localization system, which is robust for harsh and NLoS environments is presented. The positioning system is Direct Current (DC) magnetic based, shows no multipath effects and has excellent characteristics for penetrating various obstacles. To elim inate additional interference fields (e.g. earth's magnetic field, electrical disturbances) a differential measurement principle and adaptive noise suppression algorithms are used.In the case of the deployment in smaller areas, even smart phones equipped with embedded low cost sensors can be utilized as mobile station. A real time 3D position estimation with an accuracy up to 50 cm is achievable by setting up only three magnetic coils inside or around the building. In order to analyze existing systematic errors, a simple calibration procedure has been implemented.The calibration routine reduces the systematic errors, which leads to improved system's positioning accuracy up to 10 cm.
Decentralized magnetic indoor localization is a sophisticated method for processing sampled magnetic data directly on a mobile station (MS), thereby decreasing or even avoiding the need for communication with the base station. In contrast to central-oriented positioning systems, which transmit raw data to a base station, decentralized indoor localization pushes application-level knowledge into the MS. A decentralized position solution has thus a strong feasibility to increase energy efficiency and to prolong the lifetime of the MS. In this article, we present a complete architecture and an implementation for a decentralized positioning system. Furthermore, we introduce a technique for the synchronization of the observed magnetic field on the MS with the artificially-generated magnetic field from the coils. Based on real-time clocks (RTCs) and a preemptive operating system, this method allows a stand-alone control of the coils and a proper assignment of the measured magnetic fields on the MS. A stand-alone control and synchronization of the coils and the MS have an exceptional potential to implement a positioning system without the need for wired or wireless communication and enable a deployment of applications for rescue scenarios, like localization of miners or firefighters.
Location-based services (LBS) have gained increasing importance in our everyday lives and serve as the foundation for many smartphone applications. Whereas Global Navigation Satellite Systems (GNSS) enable reliable position estimation outdoors, there does not exist any comparable gold standard for indoor localization yet. Wireless local area network (WLAN) fingerprinting is still a promising and widely adopted approach to indoor localization, since it does not rely on preinstalled hardware but uses the existing WLAN infrastructure typically present in buildings. The accuracy of the method is, however, limited due to unstable fingerprints, etc. Deep learning has recently gained attention in the field of indoor localization and is also utilized to increase the performance of fingerprinting-based approaches. Current solutions can be grouped into models that either estimate the exact position of the user (regression) or classify the area (pre-segmented floor plan) or a reference location. We propose a model, DeepLocBox (DLB), that offers reliable area localization in multi-building/multi-floor environments without the prerequisite of a pre-segmented floor plan. Instead, the model predicts a bounding box that contains the user’s position while minimizing the required prediction space (size of the box). We compare the performance of DLB with the standard approach of neural network-based position estimation and demonstrate that DLB achieves a gain in success probability by 9.48% on a self-collected dataset at RWTH Aachen University, Germany; by 5.48% for a dataset provided by Tampere University of Technology (TUT), Finland; and by 3.71% for the UJIIndoorLoc dataset collected at Jaume I University (UJI) campus, Spain.
Geospatial information modelling (GIM) is used for decades to document phenomena of the real world. Visualizing and analysing GIM data are usually accomplished by geographic information system tools. The construction industry, on the other hand, uses usually computer-aided design (CAD) tools to plan buildings. With the introduction of building information modelling (BIM), modelling in CAD was enhanced to the entire life cycle of constructions. BIM and GIM are not independent of each other, e.g. BIM uses geospatial data for planning purposes. However, integrating both is challenging since the modelling methods differ. The paper describes approaches to establish interoperability between models of both domains. A literature review reveals the problems and challenges different researchers tackled to achieve interoperability.
The accuracy of fingerprinting-based indoor localization correlates with the quality and up-to-dateness of collected training data. Perpetual crowdsourced data collection reduces manual labeling effort and provides a fresh data base. However, the decentralized collection comes with the cost of heterogeneous data that causes performance degradation. In settings with imperfect data, area localization can provide higher positioning guarantees than exact position estimation. Existing area localization solutions employ a static segmentation into areas that is independent of the available training data. This approach is not applicable for crowdsoucred data collection, which features an unbalanced spatial training data distribution that evolves over time. A segmentation is required that utilizes the existing training data distribution and adapts once new data is accumulated. We propose an algorithm for data-aware floor plan segmentation and a selection metric that balances expressiveness (information gain) and performance (correctly classified examples) of area classifiers. We utilize supervised machine learning, in particular, deep learning, to train the area classifiers. We demonstrate how to regularly provide an area localization model that adapts its prediction space to the accumulating training data. The resulting models are shown to provide higher reliability compared to models that pinpoint the exact position.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.