Search

Foot-mounted positioning devices are becoming more and more popular in the different application field. For example, inertial sensors are now embedded in safety shoes to monitor security. They allow positioning with zero velocity update to bound the error growth of foot-mounted inertial sensors. High positioning accuracy depends on robust zero velocity detector (ZVD). Existing Artificial Intelligent (AI)-based methods classify the pedestrian dynamics to adjust ZVD at the cost of high computation costs and error propagation from miss-classification. We propose a machine learning model to detect zero velocity moments without any pre-classification step, named Uniform AI Model for All pedestrian Motions (UMAM). Performance is evaluated by benchmarking on two new subjects of opposite gender and different size, not included in the training data set, over complex indoor/outdoor paths of 2 km for subject 1 and 2.1 km for subject 2. We obtain an average 2D loop closure error of less than 0.37%. [ABSTRACT FROM AUTHOR]

Pedestrian navigation with handheld sensors is still particularly complex. Pedestrian Dead Reckoning method is generally used, but the estimation of the walking direction remains problematic because the device's pointing direction does not always correspond to the walking direction. To overcome this difficulty, it is possible to use gait modeling based approaches. But, these methods suffer from sporadic erroneous estimates and their accumulation over time. The HEAD (smootH Estimation of wAlking Direction) filter uses WAISS and MAGYQ angular estimates as observations to correct the walking direction and to obtain more robust and smooth results. TDCP updates are applied to constrain the walking direction estimation error while pseudo‐ranges directly update the position. HEAD is tested by 5 subjects over 21 indoor/outdoor acquisitions (between 720 m and 1.3 km). A 54% improvement is achieved thanks to the fusion in texting mode. The median obtained angular error is 5.5∘ in texting mode and 12∘ in pocket mode. [ABSTRACT FROM AUTHOR]

Zero velocity update is a common and efficient approach to bound the accumulated error growth for foot-mounted inertial navigation system. Thus a robust zero velocity detector (ZVD) for all kinds of locomotion is needed for high accuracy pedestrian navigation systems. In this paper, we investigate two machine learning-based ZVDs: Histogram-based Gradient Boosting (HGB) and Random Forest (RF), aiming at adapting to different motion types while reducing the computation costs compared to the deep learning-based detectors. A complete data pre-processing procedure, including a feature engineering study and data augmentation techniques, is proposed. A motion classifier based on HGB is used to distinguish “single support” and “double float” motions. This concept is different from the traditional locomotion classification (walking, running, stair climbing) since it merges similar motions into the same class. The proposed ZVDs are evaluated with inertial data collected by two subjects over a 1.8 km indoor/outdoor path with different motions and speeds. The results show that without huge training dataset, these two machine learning-based ZVDs achieve better performances (55 cm positioning accuracy) and lower computational costs than the two deep learning-based Long Short-Term Memory methods (1.21 m positioning accuracy). [ABSTRACT FROM AUTHOR]

Pedestrian Dead Reckoning algorithms are commonly used to assist pedestrian navigation with handheld sensors. The estimation of the walking direction remains an important source of positioning error of mobile phone users since this direction may be different from the device’s pointing direction. A better understanding of human walking gait has enabled to produce new algorithms to mitigate the impact of the way the device is held in hand. WAISS algorithm is one of them. It is based on the study of horizontal hand accelerations and their modeling using Gaussian Mixture Models (GMM). However, ongoing search for universal modeling of handheld device carrying mode defeats the varying nature of human gait. This paper investigates the impact of individual gait characteristics and their modeling to improve the estimation of the walking direction. Different models are learned for curved and straight lines and varying GMM are proposed to account for inter-individual gait variations. This results in a reduced walking direction error with a 8.1° mean error to the 90th percentile computed for 3 subjects over a 1.5 km indoor/outdoor walk. [ABSTRACT FROM AUTHOR]

Contrary to Global Navigation Satellite System or Wi-Fi based navigation, pedestrian dead reckoning (PDR) method with handheld inertial and magnetic sensors gives the opportunity to achieve indoor/outdoor ubiquitous pedestrian localization. A remaining PDR critical issue is the estimation of the walking direction. Existing methods are principally searching for the energy main axis, but they do not consider the variability of hand movements introducing robustness issues. A new method, based on statistical models and likelihood maximization adjusted to the person and his/her activity, is proposed in this paper. Performance is assessed with experiments in a motion capture room and a shopping mall. The new statistical approach gives globally better results than state of the art methods. A 1.4° to 15.3° error on the walking direction estimates is found over several “1-km walk” tests indoors. [ABSTRACT FROM PUBLISHER]

To complement traditional clinical fall risk assessments, research is oriented towards adding real-life gait-related fall risk parameters (FRP) using inertial sensors fixed to a specific body position. While fixing the sensor position can facilitate data processing, it can reduce user compliance. A newly proposed step detection method, Smartstep, has been proven to be robust against sensor position and real-life challenges. Moreover, FRP based on step variability calculated from stride times (Standard deviation (SD), Coefficient of Variance (Cov), fractal exponent, and sample entropy of stride duration) proved to be useful to prospectively predict the fall risk. To evaluate whether Smartstep is convenient for calculating FRP from different sensor placements. 29 elderly performed a 6-minute walking test with IMU placed on the waist and the wrist. FRP were computed from step-time estimated from Smartstep and compared to those obtained from foot-mounted inertial sensors: precision and recall of the step detection, Root mean square error (RMSE) and Intraclass Correlation Coefficient (ICC) of stride durations, and limits of agreement of FRP. The step detection precision and recall were respectively 99.5% and 95.9% for the waist position, and 99.4% and 95.7% for the wrist position. The ICC and RMSE of stride duration were 0.91 and 54 ms respectively for both the waist and the hand position. The limits of agreement of Cov, SD, fractal exponent, and sample entropy of stride duration are respectively 2.15%, 25 ms, 0.3, 0.5 for the waist and 1.6%, 16 ms, 0.23, 0.4 for the hand. Robust against the elderly's gait and different body locations, especially the wrist, this method can open doors toward ambulatory measurements of steps, and calculation of different discrete stride-related falling risk indicators. • Fall risk parameters (FRP) estimated independently of sensor positions. • Fall risk parameters based on discrete stride time series. • Foot-mounted compared to wrist and waist inertial sensors. • Precision and recall of step detection were 99% and 96% respectively. • Encouraging results for usage in real-life fall risk monitoring. [ABSTRACT FROM AUTHOR]