Multi-Floor Indoor Pedestrian Dead Reckoning with a Backtracking Particle Filter and Viterbi-Based Floor Number Detection

Cock, Cedric De; Joseph, Wout; Martens, Luc; Trogh, Jens; David, Paul A.

doi:10.3390/s21134565

Cited by 16 publications

(12 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This EKF-based fusion model obtains a mean accuracy of 1.25 m, which is better than that of the MP/PDR fusion approaches using GPF in [22] and IPF in [35]. Different from the popular WiFi/PDR fusion in [2], [13], PDR/Bluetooth fusion in [14], WiFi/magnetic/PDR/scene recognition fusion in [15], our method is infrastructure-free and obtains promising results. From the perspective of real-time localization, Tab.VI shows that the proposed method has a shorter localization query time than that of the IPF/GPF-based models.…”

Section: E Discussionmentioning

confidence: 89%

See 1 more Smart Citation

Indoor Localization Using Mind Evolutionary Algorithm-Based Geomagnetic Positioning and Smartphone IMU Sensors

et al. 2022

Self Cite

View full text Add to dashboard Cite

With the pervasiveness and ubiquitous distribution of the magnetic field in indoor environments, indoor localization using magnetic positioning (MP) has attracted considerable attention. This work concentrates on the MP and pedestrian dead reckoning (PDR) method, and constructs a fusion system for smartphones using MP and PDR based on the extended Kalman filter (EKF). The mind evolutionary algorithm (MEA) is introduced to search for the optimal magnetic position based on a heuristic searching strategy, which uses the similartaxis and dissimilation for the evolutionary operation. In the PDR module, the acceleration characteristics of different walking patterns are analyzed and the corresponding features are extracted. The enhanced genetic algorithm-based extreme learning machine (EGA-ELM) is adopted to train these features and address the gait recognition problem of different walking patterns. Finally, to obtain a lightweight and high-precision fusion method, MEA-based MP is integrated with PDR based on the EKF. Extensive experiments are conducted to evaluate the proposed methods. The testing results showed that MEA-based MP can obtain a location error within 2.3 m and steps can be recognized with a mean accuracy of 95% when different users participate in testing. The positioning results after fusion with PDR reveal that the mean location error and root-mean-square error (RMSE) are 1.25 m and 1.53 m respectively, which outperforms the MP, PDR, MP and PDR fusion methods using improved particle filter (IPF) and genetic particle filter (GPF).

show abstract

Section: E Discussionmentioning

confidence: 89%

“…Only using PDR may not deliver precise results. Researchers usually integrate PDR with other technologies to reduce errors, like combining Wi-Fi in [13], Bluetooth in [14], and WiFi/scene recognition in [15]. Compared with the above methods, PDR is consequent, infrastructure-free, and it is the preferred solution for fusion positioning.…”

Section: Introductionmentioning

confidence: 99%

Indoor Localization Using Mind Evolutionary Algorithm-Based Geomagnetic Positioning and Smartphone IMU Sensors

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the contrary, the empirical Weinberg model estimates the stride length according to the dynamic movement state, which is closer to reality [ 43 ]. The model is given by:

where

is the dynamic value concerned with the acceleration of each step and

are the maximum and minimum accelerations for each step [ 44 ].…”

Section: Methodsmentioning

confidence: 99%

“…The current magnetometer heading signals, current gyroscope readings, and previously fused headings are weight-averaged to form the fused heading. The weighting factor is adaptive and is based on the magnetometer’s stability as well as the correlation between the magnetometer and the gyroscope [ 44 ]. As they are already fused in the rotation vector achieved from the rotation sensor in the smartphone, the heading change can be calculated by a rotation matrix transformed from the rotation vector [ 45 ].…”

Section: Methodsmentioning

confidence: 99%

Indoor Spatiotemporal Contact Analytics Using Landmark-Aided Pedestrian Dead Reckoning on Smartphones

Gao

Konomi

2022

Sensors

View full text Add to dashboard Cite

Due to the prevalence of COVID-19, providing safe environments and reducing the risks of virus exposure play pivotal roles in our daily lives. Contact tracing is a well-established and widely-used approach to track and suppress the spread of viruses. Most digital contact tracing systems can detect direct face-to-face contact based on estimated proximity, without quantifying the exposed virus concentration. In particular, they rarely allow for quantitative analysis of indirect environmental exposure due to virus survival time in the air and constant airborne transmission. In this work, we propose an indoor spatiotemporal contact awareness framework (iSTCA), which explicitly considers the self-containing quantitative contact analytics approach with spatiotemporal information to provide accurate awareness of the virus quanta concentration in different origins at various times. Smartphone-based pedestrian dead reckoning (PDR) is employed to precisely detect the locations and trajectories for distance estimation and time assessment without the need to deploy extra infrastructure. The PDR technique we employ calibrates the accumulative error by identifying spatial landmarks automatically. We utilized a custom deep learning model composed of bidirectional long short-term memory (Bi-LSTM) and multi-head convolutional neural networks (CNNs) for extracting the local correlation and long-term dependency to recognize landmarks. By considering the spatial distance and time difference in an integrated manner, we can quantify the virus quanta concentration of the entire indoor environment at any time with all contributed virus particles. We conducted an extensive experiment based on practical scenarios to evaluate the performance of the proposed system, showing that the average positioning error is reduced to less than 0.7 with high confidence and demonstrating the validity of our system for the virus quanta concentration quantification involving virus movement in a complex indoor environment.

show abstract

“…Khedr and El-Sheimy [59] mentioned that PDR systems that suffer from the inherited errors are reliable for a limited period, and in order to correct and compensate those errors, an aid by other technologies is required. Within multiple floors building, it is very difficult for pedestrian to be tracked using PDR only, since this technology has challenge in detecting floor transitions and identifying the correct floor number [60].…”

Section: Dead Reckoning Technologymentioning

confidence: 99%

A Hybrid Indoor Positioning Model for Critical Situations Based on Localization Technologies

Mahdi

Chalechale

AbdelRaouf

2022

Mobile Information Systems

View full text Add to dashboard Cite

The domains of positioning and tracking have undergone substantial evolution and advancements recently, especially within the concept of the Internet of Things (IoT) and in health care. Unfortunately, neither the current satellite positioning systems nor the standalone cellular systems remain useful for successfully localizing and tracking inside buildings. This paper proposes a new model that could improve the accuracy of localization in indoor environments. In addition, a broad review is conducted to discover the state-of-the-art indoor localization technologies appropriate for disasters and rescue situations. After a comprehensive study, three important technologies that need to be deeply reviewed are identified, which are wireless local area network (WLAN), dead reckoning (DR), and hybrid approaches. Based on these, a novel architecture is introduced that is more convenient to meet the operation of rescuing injured or older people in critical situations, where other technologies might be unavailable or require some extra infrastructures. The proposed model has two modes and selects one of these modes automatically. The first mode assumes the existence of both WLAN signals and smartphone sensors to be used for identifying the position of the object; otherwise, only smartphone sensors will be employed to achieve positioning. Significantly, the designated components and the flow control depicted provide a proper and suitable horizon for the next researchers who desire to develop a new indoor positioning system in this discipline with a low positioning root-mean-squared error on the centimeter scale that can later be incorporated in numerous applications relating to the IoT, health care, and evacuation plans.

show abstract

Multi-Floor Indoor Pedestrian Dead Reckoning with a Backtracking Particle Filter and Viterbi-Based Floor Number Detection

Cited by 16 publications

References 63 publications

Indoor Localization Using Mind Evolutionary Algorithm-Based Geomagnetic Positioning and Smartphone IMU Sensors

Indoor Localization Using Mind Evolutionary Algorithm-Based Geomagnetic Positioning and Smartphone IMU Sensors

Indoor Spatiotemporal Contact Analytics Using Landmark-Aided Pedestrian Dead Reckoning on Smartphones

A Hybrid Indoor Positioning Model for Critical Situations Based on Localization Technologies

Contact Info

Product

Resources

About