scholarly journals Pedestrian Stride Length Estimation from IMU Measurements and ANN Based Algorithm

2017 ◽  
Vol 2017 ◽  
pp. 1-10 ◽  
Author(s):  
Haifeng Xing ◽  
Jinglong Li ◽  
Bo Hou ◽  
Yongjian Zhang ◽  
Meifeng Guo
Keyword(s):  
Stride Length ◽  
Nonlinear Models ◽  
Back Propagation ◽  
Dead Reckoning ◽  
Estimation Algorithm ◽  
Position Estimation ◽  
Superior Performance ◽  
Measurement Unit ◽  
Neural Net ◽  
Length Estimation

Pedestrian dead reckoning (PDR) can be used for continuous position estimation when satellite or other radio signals are not available, and the accuracy of the stride length measurement is important. Current stride length estimation algorithms, including linear and nonlinear models, consider a few variable factors, and some rely on high precision and high cost equipment. This paper puts forward a stride length estimation algorithm based on a back propagation artificial neural network (BP-ANN), using a consumer-grade inertial measurement unit (IMU); it then discusses various factors in the algorithm. The experimental results indicate that the error of the proposed algorithm in estimating the stride length is approximately 2%, which is smaller than that of the frequency and nonlinear models. Compared with the latter two models, the proposed algorithm does not need to determine individual parameters in advance if the trained neural net is effective. It can, thus, be concluded that this algorithm shows superior performance in estimating pedestrian stride length.

Continuous Learning Framework for Freeway Incident Detection

1998 ◽  
Vol 1644 (1) ◽  
pp. 124-131 ◽  
Author(s):  
Srinivas Peeta ◽  
Debjit Das
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Superior Performance ◽  
Incident Detection ◽  
Neural Net ◽  
Continuous Learning ◽  
Back Propagation Algorithm ◽  
Learning Capability ◽  
Detection Algorithms ◽  
On Line

Existing freeway incident detection algorithms predominantly require extensive off-line training and calibration precluding transferability to new sites. Also, they are insensitive to demand and supply changes in the current site without recalibration. We propose two neural network-based approaches that incorporate an on-line learning capability, thereby ensuring transferability, and adaptability to changes at the current site. The least-squares technique and the error back propagation algorithm are used to develop on-line neural network-trained versions of the popular California algorithm and the more recent McMaster algorithm. Simulated data from the integrated traffic simulation model is used to analyze performance of the neural network-based versions of the California and McMaster algorithms over a broad spectrum of operational scenarios. The results illustrate the superior performance of the neural net implementations in terms of detection rate, false alarm rate, and time to detection. Of implications to current practice, they suggest that just introducing a continuous learning capability to commonly used detection algorithms in practice such as the California algorithm enhances their performance with time in service, allows transferability, and ensures adaptability to changes at the current site. An added advantage of this strategy is that existing traffic measures used (such as volume, occupancy, and so forth.) in those algorithms are sufficient, circumventing the need for new traffic measures, new threshold parameters, and variables that require subjective decisions.

scholarly journals Pedestrian Stride-Length Estimation Based on LSTM and Denoising Autoencoders

Sensors ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 840 ◽  
Author(s):  
Qu Wang ◽  
Langlang Ye ◽  
Haiyong Luo ◽  
Aidong Men ◽  
Fang Zhao ◽  
...  
Keyword(s):  
Error Rate ◽  
Stride Length ◽  
Inertial Sensor ◽  
Dead Reckoning ◽  
Training Data ◽  
Sensor Data ◽  
Walking Distance ◽  
Estimation Accuracy ◽  
Length Estimation ◽  
Pedestrian Dead Reckoning

Accurate stride-length estimation is a fundamental component in numerous applications, such as pedestrian dead reckoning, gait analysis, and human activity recognition. The existing stride-length estimation algorithms work relatively well in cases of walking a straight line at normal speed, but their error overgrows in complex scenes. Inaccurate walking-distance estimation leads to huge accumulative positioning errors of pedestrian dead reckoning. This paper proposes TapeLine, an adaptive stride-length estimation algorithm that automatically estimates a pedestrian’s stride-length and walking-distance using the low-cost inertial-sensor embedded in a smartphone. TapeLine consists of a Long Short-Term Memory module and Denoising Autoencoders that aim to sanitize the noise in raw inertial-sensor data. In addition to accelerometer and gyroscope readings during stride interval, extracted higher-level features based on excellent early studies were also fed to proposed network model for stride-length estimation. To train the model and evaluate its performance, we designed a platform to collect inertial-sensor measurements from a smartphone as training data, pedestrian step events, actual stride-length, and cumulative walking-distance from a foot-mounted inertial navigation system module as training labels at the same time. We conducted elaborate experiments to verify the performance of the proposed algorithm and compared it with the state-of-the-art SLE algorithms. The experimental results demonstrated that the proposed algorithm outperformed the existing methods and achieves good estimation accuracy, with a stride-length error rate of 4.63% and a walking-distance error rate of 1.43% using inertial-sensor embedded in smartphone without depending on any additional infrastructure or pre-collected database when a pedestrian is walking in both indoor and outdoor complex environments (stairs, spiral stairs, escalators and elevators) with natural motion patterns (fast walking, normal walking, slow walking, running, jumping).

Evaluation of a New Method of Heading Estimation for Pedestrian Dead Reckoning Using Shoe Mounted Sensors

2005 ◽  
Vol 58 (1) ◽  
pp. 31-45 ◽  
Author(s):  
Ross Stirling ◽  
Ken Fyfe ◽  
Gérard Lachapelle
Keyword(s):  
Urban Areas ◽  
Stride Length ◽  
Performance Metrics ◽  
Dead Reckoning ◽  
Tall Buildings ◽  
Global Navigation Satellite Systems ◽  
Measurement Technology ◽  
Reference Trajectory ◽  
Length Estimation ◽  
Pedestrian Dead Reckoning

In this paper, a novel method of sensor based pedestrian dead reckoning is presented using sensors mounted on a shoe. Sensor based systems are a practical alternative to global navigation satellite systems when positioning accuracy is degraded such as in thick forest, urban areas with tall buildings and indoors. Using miniature, inexpensive sensors it is possible to create self-contained systems using sensor-only navigation techniques optimised for pedestrian motion. The systems developed extend existing foot based stride measurement technology by adding the capability to sense direction, making it possible to determine the path and displacement of the user. The proposed dead-reckoning navigation system applies an array of accelerometers and magneto-resistive sensors worn on the subject's shoe. Measurement of the foot's acceleration allows the precise identification of separate stride segments, thus providing improved stride length estimation. The system relies on identifying the stance phase to resolve the sensor attitude and determine the step heading. Field trials were carried out in forested conditions. Performance metrics include position, stride length estimation and heading with respect to a high accuracy reference trajectory.

A Robust Step Detection and Stride Length Estimation for Pedestrian Dead Reckoning Using a Smartphone

2020 ◽  
Vol 20 (17) ◽  
pp. 9685-9697
Author(s):  
Yingbiao Yao ◽  
Lei Pan ◽  
Wei Fen ◽  
Xiaorong Xu ◽  
Xuesong Liang ◽  
...  
Keyword(s):  
Stride Length ◽  
Dead Reckoning ◽  
Step Detection ◽  
Length Estimation ◽  
Pedestrian Dead Reckoning

scholarly journals Comparison of Different Algorithms for Calculating Velocity and Stride Length in Running Using Inertial Measurement Units

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4194 ◽  
Author(s):  
Markus Zrenner ◽  
Stefan Gradl ◽  
Ulf Jensen ◽  
Martin Ullrich ◽  
Bjoern Eskofier
Keyword(s):  
Motion Tracking ◽  
Stride Length ◽  
Positive Impact ◽  
Estimation Algorithm ◽  
Velocity Estimation ◽  
Measurement Unit ◽  
Trajectory Estimation ◽  
Inertial Measurement ◽  
Using Data ◽  
Foot Trajectory

Running has a positive impact on human health and is an accessible sport for most people. There is high demand for tracking running performance and progress for amateurs and professionals alike. The parameters velocity and distance are thereby of main interest. In this work, we evaluate the accuracy of four algorithms, which calculate the stride velocity and stride length during running using data of an inertial measurement unit (IMU) placed in the midsole of a running shoe. The four algorithms are based on stride time, foot acceleration, foot trajectory estimation, and deep learning, respectively. They are compared using two studies: a laboratory-based study comprising 2377 strides from 27 subjects with 3D motion tracking as a reference and a field study comprising 12 subjects performing a 3.2-km run in a real-world setup. The results show that the foot trajectory estimation algorithm performs best, achieving a mean error of 0.032 ± 0.274 m/s for the velocity estimation and 0.022 ± 0.157 m for the stride length. An interesting alternative for systems with a low energy budget is the acceleration-based approach. Our results support the implementation decision for running velocity and distance tracking using IMUs embedded in the sole of a running shoe.

scholarly journals Pedestrian Walking Distance Estimation Based on Smartphone Mode Recognition

2019 ◽  
Vol 11 (9) ◽  
pp. 1140 ◽  
Author(s):  
Qu Wang ◽  
Langlang Ye ◽  
Haiyong Luo ◽  
Aidong Men ◽  
Fang Zhao ◽  
...  
Keyword(s):  
Stride Length ◽  
Estimation Method ◽  
Distance Estimation ◽  
Dead Reckoning ◽  
Walking Distance ◽  
Estimation Model ◽  
Length Estimation ◽  
Mode Recognition ◽  
Stride Interval ◽  
Normal Speed

Stride length and walking distance estimation are becoming a key aspect of many applications. One of the methods of enhancing the accuracy of pedestrian dead reckoning is to accurately estimate the stride length of pedestrians. Existing stride length estimation (SLE) algorithms present good performance in the cases of walking at normal speed and the fixed smartphone mode (handheld). The mode represents a specific state of the carried smartphone. The error of existing SLE algorithms increases in complex scenes with many mode changes. Considering that stride length estimation is very sensitive to smartphone modes, this paper focused on combining smartphone mode recognition and stride length estimation to provide an accurate walking distance estimation. We combined multiple classification models to recognize five smartphone modes (calling, handheld, pocket, armband, swing). In addition to using a combination of time-domain and frequency-domain features of smartphone built-in accelerometers and gyroscopes during the stride interval, we constructed higher-order features based on the acknowledged studies (Kim, Scarlett, and Weinberg) to model stride length using the regression model of machine learning. In the offline phase, we trained the corresponding stride length estimation model for each mode. In the online prediction stage, we called the corresponding stride length estimation model according to the smartphone mode of a pedestrian. To train and evaluate the performance of our SLE, a dataset with smartphone mode, actual stride length, and total walking distance were collected. We conducted extensive and elaborate experiments to verify the performance of the proposed algorithm and compare it with the state-of-the-art SLE algorithms. Experimental results demonstrated that the proposed walking distance estimation method achieved significant accuracy improvement over existing individual approaches when a pedestrian was walking in both indoor and outdoor complex environments with multiple mode changes.

scholarly journals An Embedded Platform for Positioning and Obstacle Detection for Small Unmanned Aerial Vehicles

Electronics ◽  
2020 ◽  
Vol 9 (7) ◽  
pp. 1175
Author(s):  
Salvatore Ponte ◽  
Gennaro Ariante ◽  
Umberto Papa ◽  
Giuseppe Del Core
Keyword(s):  
Unmanned Aerial Vehicles ◽  
Degrees Of Freedom ◽  
Estimation Algorithm ◽  
General Purpose ◽  
Obstacle Detection ◽  
Position Estimation ◽  
Unmanned Aircraft ◽  
Measurement Unit ◽  
Accelerometer Data ◽  
Aerial Vehicles

Unmanned Aerial Vehicles (UAV) with on-board augmentation systems (UAS, Unmanned Aircraft System) have penetrated into civil and general-purpose applications, due to advances in battery technology, control components, avionics and rapidly falling prices. This paper describes the conceptual design and the validation campaigns performed for an embedded precision Positioning, field mapping, Obstacle Detection and Avoiding (PODA) platform, which uses commercial-off-the-shelf sensors, i.e., a 10-Degrees-of-Freedom Inertial Measurement Unit (10-DoF IMU) and a Light Detection and Ranging (LiDAR), managed by an Arduino Mega 2560 microcontroller with Wi-Fi capabilities. The PODA system, designed and tested for a commercial small quadcopter (Parrot Drones SAS Ar.Drone 2.0, Paris, France), estimates position, attitude and distance of the rotorcraft from an obstacle or a landing area, sending data to a PC-based ground station. The main design issues are presented, such as the necessary corrections of the IMU data (i.e., biases and measurement noise), and Kalman filtering techniques for attitude estimation, data fusion and position estimation from accelerometer data. The real-time multiple-sensor optimal state estimation algorithm, developed for the PODA platform and implemented on the Arduino, has been tested in typical aerospace application scenarios, such as General Visual Inspection (GVI), automatic landing and obstacle detection. Experimental results and simulations of various missions show the effectiveness of the approach.

A Waist-Attached PNS Algorithm Based on MIMU

2012 ◽  
Vol 562-564 ◽  
pp. 1272-1278
Author(s):  
Qi Fan Zhou ◽  
Hai Zhang ◽  
You Ze Mao ◽  
Yan Hong Chang
Keyword(s):  
Stride Length ◽  
Model Identification ◽  
Dead Reckoning ◽  
Position Estimation ◽  
Detection Model ◽  
Pedestrian Navigation ◽  
Heading Direction ◽  
Current Location ◽  
Walking Speeds ◽  
Mems Imu

Pedestrian Navigation System (PNS) is a system aims at determining the current location of person, recording the walking trajectory. This paper presents an algorithm of PNS based on lowperformance MEMS-IMU attaching to the waist of people. The algorithm consists of step detection, model identification, stride, heading determination and position estimation. A method to identify a user’s status, calibrate the length coefficient K by Least-Squares and update K online according to different models and acceleration is presented, which adaptively adjusts the calculation of stride length in case of different walking speeds and manners. The integration of INS and magnetic azimuth for heading direction is put forward and the walking trajectory is calculated by Dead Reckoning (DR). Several tests have been conducted and the algorithm performed well.

Sign in / Sign up

Export Citation Format

Share Document