RNN-Aided Human Velocity Estimation from a Single IMU

Feigl, Tobias; Kram, Sebastian; Woller, P; Siddiqui, Ramiz H.; Philippsen, Michæl; Mutschler, Christopher

doi:10.3390/s20133656

Cited by 24 publications

(16 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They achieve an improvement in the accuracy of at least of 50% and the processing is 10 times faster than conventional PDR systems. The authors in [141] use a combination of CNN with Binary LSTM for a hybrid estimation of the pedestrian's velocity, obtaining an accuracy greater than similar works and with lower computational cost. They train the Binary SLTM with two IMUs and implement the localization with only one IMU.…”

Section: Machine Learning In Inertial Navigation Systemsmentioning

confidence: 99%

A Survey of Machine Learning in Pedestrian Localization Systems: Applications, Open Issues and Challenges

et al. 2021

View full text Add to dashboard Cite

With the popularization of machine learning (ML) techniques and the increased chipset's performance, the application of ML to pedestrian localization systems has received significant attention in the last years. Several survey papers have attempted to provide a state-of-the-art overview, but they usually limit their scope to a particular type of positioning system or technology. In addition, they are written from the point of view of ML techniques and their practice, not from the point of view of the localization system and the specific problems that ML techniques can help to solve. This article is intended to offer a comprehensive state-of-the-art survey of the ML techniques that have been adopted over the last ten years to improve the performance of pedestrian localization systems, addressing the applicability of ML techniques in this domain, along with the main localization strategies. It concludes by indicating the underlying open issues and challenges associated with the existing systems, and possible future directions in which ML techniques could improve the performance of pedestrian localization systems. Among other open issues, most previous authors have focused their attention on position estimation accuracy, which wastes the potential of ML techniques to improve other performance parameters (e.g., response time, computational complexity, robustness, scalability or energy efficiency). This study shows that there is a strong trend towards the application of supervised learning. Consequently, there are many potential research opportunities in the use of other learning types, such as unsupervised and reinforcement learning, to improve the performance of pedestrian localization systems.

show abstract

Section: Machine Learning In Inertial Navigation Systemsmentioning

confidence: 99%

A Survey of Machine Learning in Pedestrian Localization Systems: Applications, Open Issues and Challenges

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This means that tracking is unaffected by any possible repositioning of the phone (e.g., if the user moves the phone to a different pocket). A number of other learning-based algorithms for computing the walker's velocity, or for detecting steps and measuring stride lengths, have been recently proposed [33,34,[54][55][56][57][58][59][60][61].…”

Section: Learning-based Odometrymentioning

confidence: 99%

Smartphone-Based Inertial Odometry for Blind Walkers

Ren

Elyasi

Manduchi

2021

Sensors

View full text Add to dashboard Cite

Pedestrian tracking systems implemented in regular smartphones may provide a convenient mechanism for wayfinding and backtracking for people who are blind. However, virtually all existing studies only considered sighted participants, whose gait pattern may be different from that of blind walkers using a long cane or a dog guide. In this contribution, we present a comparative assessment of several algorithms using inertial sensors for pedestrian tracking, as applied to data from WeAllWalk, the only published inertial sensor dataset collected indoors from blind walkers. We consider two situations of interest. In the first situation, a map of the building is not available, in which case we assume that users walk in a network of corridors intersecting at 45° or 90°. We propose a new two-stage turn detector that, combined with an LSTM-based step counter, can robustly reconstruct the path traversed. We compare this with RoNIN, a state-of-the-art algorithm based on deep learning. In the second situation, a map is available, which provides a strong prior on the possible trajectories. For these situations, we experiment with particle filtering, with an additional clustering stage based on mean shift. Our results highlight the importance of training and testing inertial odometry systems for assisted navigation with data from blind walkers.

show abstract

“…It measures acceleration, angular velocity, and magnetic field experienced by the pen, which helps create a deadreckoning system based on the pen's motion vectors. Despite wide use of IMUs in localization [17,25,38,56], applying IMU in high-precision tracking tasks is not sufficiently explored-the drifting nature of IMU makes it extremely hard to provide stable low-error position measurement over a long period. Therefore, to effectively use IMU, we must first understand the merits and demerits of IMU, and then explore how it can assist in our case.…”

Section: Augmenting Location Tracking With Imumentioning

confidence: 99%

ITrackU

Cao

Dhekne

Ammar

2021

Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services

View full text Add to dashboard Cite

High-precision tracking of a pen-like instrument's movements is desirable in a wide range of fields spanning education, robotics, and art, to name a few. The key challenge in doing so stems from the impracticality of embedding electronics in the tip of such instruments (a pen, marker, scalpel, etc.) as well as the difficulties in instrumenting the surface that it works on. In this paper, we present ITrackU, a movement digitization system that does not require modifications to the surface or the tracked instrument's tip. ITrackU fuses locations obtained using ultra-wideband radios (UWB), with an inertial and magnetic unit (IMU) and a pressure sensor, yielding multidimensional improvements in accuracy, range, cost, and robustness, over existing works. ITrackU embeds a micro-transmitter at the base of a pen which creates a trackable beacon, that is localized from the corners of a writing surface. Fused with inertial motion sensor and a pressure sensor, ITrackU enables accurate tracking. Our prototype of ITrackU covers a large 2.5 × 2 area, while obtaining around 2.9 median error. We demonstrate the accuracy of our system by drawing numerous shapes and characters on a whiteboard, and compare them against a touchscreen and a camera-based ground-truthing system. Finally, the produced stream of digitized data is minuscule in volume, when compared with a video of the whiteboard, which saves both network bandwidth and storage space. CCS CONCEPTS• Computer systems organization → Sensors and actuators; • Human-centered computing → Ubiquitous and mobile devices.

show abstract

RNN-Aided Human Velocity Estimation from a Single IMU

Cited by 24 publications

References 75 publications

A Survey of Machine Learning in Pedestrian Localization Systems: Applications, Open Issues and Challenges

A Survey of Machine Learning in Pedestrian Localization Systems: Applications, Open Issues and Challenges

Smartphone-Based Inertial Odometry for Blind Walkers

ITrackU

Contact Info

Product

Resources

About