Step Length Estimation Research Articles

StepNet—Deep Learning Approaches for Step Length Estimation

The case of a user walking with a smartphone in an indoor environment is considered. Instead of using traditional pedestrian dead reckoning approaches to estimate the user step-length, we define a deep learning based framework with an activity recognition model to regress the user change in distance and step-length. We propose StepNet - a family of deep-learning based approaches to regress the step-length or change in distance. In addition, we propose regressing a time-varying gain instead of a constant one used for traditional step-length estimation. A comparison is made between the proposed approaches and different network architectures. Experimental results show that the proposed deep-learning approaches outperform traditional ones for the examined trajectories.

Smartphone Location Recognition: A Deep Learning-Based Approach.

One of the approaches for indoor positioning using smartphones is pedestrian dead reckoning. There, the user step length is estimated using empirical or biomechanical formulas. Such calculation was shown to be very sensitive to the smartphone location on the user. In addition, knowledge of the smartphone location can also help for direct step-length estimation and heading determination. In a wider point of view, smartphone location recognition is part of human activity recognition employed in many fields and applications, such as health monitoring. In this paper, we propose to use deep learning approaches to classify the smartphone location on the user, while walking, and require robustness in terms of the ability to cope with recordings that differ (in sampling rate, user dynamics, sensor type, and more) from those available in the train dataset. The contributions of the paper are: (1) Definition of the smartphone location recognition framework using accelerometers, gyroscopes, and deep learning; (2) examine the proposed approach on 107 people and 31 h of recorded data obtained from eight different datasets; and (3) enhanced algorithms for using only accelerometers for the classification process. The experimental results show that the smartphone location can be classified with high accuracy using only the smartphone’s accelerometers.

Performance Analysis of Sensor Fusion Techniques for Heading Estimation Using Smartphone Sensors

Efficient indoor positioning requires accurate heading and step length estimation algorithms. Therefore, in order to improve the indoor position accuracy, it is necessary to estimate both the user heading and step length with minimal error. These include errors from the accelerometer, magnetometer and gyroscope of smartphone sensors. Fusing different sensor data has a high impact on improving heading accuracy. In this paper, we present a comparative analysis of different sensor fusion techniques for heading estimation using smartphone sensors. The performance of different sensor fusion techniques is discussed in terms of root mean square error and cumulative distribution functions of heading errors. The experimental results show the effects of different sensor fusion techniques for heading estimation. The performance of five sensor fusion techniques such as a linear Kalman filter (LKF), extended Kalman filter (EKF), unscented Kalman filter (UKF), particle filters (PF) and complementary filters (CF) were analyzed. The UKF fusion algorithm shows better results compared to EKF and LKF fusion algorithms. The EKF approach is better than LKF and CF approaches. The experimental results show that the PF fusion technique has poor performance for heading estimation.

Research on Improved Pedestrian Dead Reckoning Algorithms

In view of user's requirements of high performance, easy operation and low cost with indoor location, data acquisition software based on Android platform utilize sensors built-in cellphone is used to study the pedestrian dead reckoning (PDR). Step detection and step length estimation are carried out by collecting leg swing angle while walking, and the classical step length estimation algorithm is improved. At the same time, the improved heuristic drift elimination algorithm is used to calculate the direction. Finally, the experiment results show that the PDR technology can better satisfy the requirements of indoor pedestrian positioning, and as for the low-cost multi-sensor. compared with the existing algorithm, the improved algorithm with higher positional accuracy.

Heading Drift Reduction for Foot-Mounted Inertial Navigation System via Multi-Sensor Fusion and Dual-Gait Analysis

Foot-mounted inertial navigation is an important issue in areas such as pedestrian localization, gait analysis, and sport training. However, low-cost inertial sensors suffer from several errors that make the navigation results less convincing. In this paper, a multi-sensor approach with one sensor on each foot is presented to reduce the system heading drift. Through dual-gait analysis, gait parameters between two feet are employed to make the non-collocated and uncoupled subsystems be related to each other. A step length estimator based on an inverted pendulum model is developed to derive a relative position vector between the two foot-mounted sensors rather than a distance scalar. A Kalman-type filter with one time update and two measurement updates is developed to fuse the velocity and position observations at foot and person levels, respectively. Experiments were conducted by four healthy subjects, and experimental results show that the proposed sensor fusion method can effectively reduce the heading drift of inertial navigation and make the captured dual-foot motion closer to its actual process.

Research of step-length estimation methods for full waveform inversion in time domain

ABSTRACTFull waveform inversion (FWI) is a powerful tool for reconstructing high-resolution subsurface parameters estimated by iteratively minimising the difference between calculated and observed data. Step-length estimation is a key step in the successful implementation of the FWI algorithm. An optimal step-length value rapidly causes the FWI algorithm to reach the global minimum with reduced iterations and fewer extra forward modelling simulations during each iteration. Step-length can typically be calculated using an inexact or an exact line-search method. The backtracking line-search method (BLSM) is a typical inexact method. Initial methods of guessing the step-length and evaluation conditions determine the efficiency of a BLSM scheme. Here, we propose a quadratic extrapolation value as the initial guess in a BLSM scheme, and then compare it with other initial-guess approaches by using the first Wolfe condition to evaluate step-length values. Exact line-search methods include a parabolic fitting search method through three points (PFSM-3), a parabolic fitting search method through two points (PFSM-2) and the analytical step-length method (ASLM). To find optimal and stable step-length estimation methods for FWI, we compare four step-length estimation methods: BLSM, PFSM-3, PFSM-2 and ASLM. Numerical examples using synthetic data demonstrate that quadratic extrapolation values perform better than first-order change and adaptive values in the BLSM scheme, in terms of resolution of the reconstructed model and computational costs. Of the four step-length estimation methods, ASLM and BLSM are both efficient for noise-free data, and robust ASLM is more efficient for noisy data. However, PFSM-2 and PFSM-3 are less efficient because of low accuracy and high computational cost.

Stride and Step Length Obtained with Inertial Measurement Units during Maximal Sprint Acceleration.

During sprint acceleration, step length, step rate, ground contact, and airtime are key variables for coaches to guide the training process and technical development of their athletes. In the field, three of these variables are easily obtained with inertial measurement units (IMUs), but, unfortunately, valid estimates of step length with IMUs currently are limited to low speeds (<50% max). A simple method is proposed here to derive step length during maximal sprint acceleration, using IMUs on both feet and two timing gates only. Mono-exponential velocity-time functions are fitted to the 30-m (split) and 60-m times, which in combination with IMU-derived step durations yield estimates of step length. To validate this approach, sixteen well-trained athletes with IMUs on the insteps of both feet executed two 60-m maximal sprints, starting from a three-point position. As a reference, step lengths were determined from video data. The reference step lengths combined with IMU-derived step durations yielded a time series of step velocity that confirmed the appropriateness of a mono-exponential increase of step velocity (R2 ≥ 0.96). The comparison of estimated step lengths to reference measurements showed no significant difference (p > 0.05) and acceptable agreement (root mean square error, RMSE = 8.0 cm, bias ± Limits of Agreement = −0.15 ± 16 cm). Step length estimations further improved (RMSE = 5.7 cm, −0.16 ± 11 cm) after smoothing the original estimated step lengths with a third order polynomial function (R2 = 0.94 ± 0.04). In conclusion, during maximal sprint acceleration, acceptable estimates of stride and step length were obtained from IMU-derived step times and 30-m (split) and 60-m sprint times.

Accurate Step Length Estimation for Pedestrian Dead Reckoning Localization Using Stacked Autoencoders

Pedestrian dead reckoning (PDR) is a popular indoor localization method due to its independence of additional infrastructures and the wide availability of smart devices. Step length estimation is a key component of PDR, which has an important influence on the performance of PDR. Existing step length estimation models suffer from various limitations such as requiring knowledge of user’s height, lack of consideration of varying phone carrying ways, and dependence on spatial constraints. To solve these problems, we propose a deep learning-based step length estimation model, which can adapt to different phone carrying ways and does not require individual stature information and spatial constraints. Experimental results show that the proposed method outperforms existing popular step length estimation methods.

Estimation of the walking speed of individuals with transfemoral amputation from a single prosthetic shank-mounted IMU.

Microprocessor prosthetic knees, able to restore the gait of people with transfemoral amputation, are now often equipped with sensors embedded in the prosthetic shank, which could be used to assess some gait characteristics during real-life activities. In particular, an estimation of the walking speed during the locomotion of those subjects would be a relevant indicator of the performance. However, if methods have already been proposed in the literature to compute this walking speed, none are directly usable in this context and with this population. For these reasons, the current study proposed to estimate the instantaneous walking speed with a shank-embedded Inertial Measurement Units based on a biomechanical model of the prosthetic lower limb. Averaged walking speed estimation has been quantified for nine individuals with transfemoral amputation walking on a treadmill at different speeds and slopes when wearing an instrumented knee ankle prosthesis. Experimental results demonstrated the ability of the model to estimate the walking speed with an accuracy of 9% (normalized root mean squared errors over all the patients), which is consistent with previous reported walking speed estimation errors. In addition, as the walking speed estimation is instantaneous, the proposed method can provide the estimation by the end of the stance phase, which is an originality compared to other methods based on step length estimation. The present method is relevant for the estimation of walking speed during real-life activities of above-knee amputees opening the way to direct activity monitoring from the prosthesis.

Do Older People Accurately Estimate the Length of Their First Step during Gait Initiation?

ABSTRACTBackground/Study Context: Advancing age is associated with a decrease in step length. In line with previous studies showing that older adults often overestimate their motor abilities, we investigate whether older adults overestimate the length of their first step during gait initiation. The underlying effect could be a failure to update the internal model of motor action as a function of age-related motor decline.Methods: Without taking a step, community-dwelling older women (n = 22, age range: 68–87 years) and younger women (n = 19, age range: 19–33 years) estimated the length of their first step for both preferred step length and largest step length, which were performed without endangerment. Thereafter, the participants performed real gait initiation for both types of steps. The estimated step lengths were compared to the actual step lengths.Results: Older adults judged their first step as larger than it was (mean error: 30% for the preferred step and 9% for the largest step). A fine-grained analysis showed that this effect mainly concerned those for whom an increased risk of falling was suspected. These older adults were also among those who performed the shortest steps, and they presented with a slight decrease in cognitive functioning. Younger participants underestimated their preferred step length. Overall, the estimates were more accurate for the largest steps than for the preferred-length steps.Conclusion: Step length estimation revealed powerful evidence for overestimation in older adults. Those who overestimated step length presented with more signs of motor decline. While this result sustains the idea of an insufficient actualization of the motor-action model, the explanation also refers to more global appraisal processes. Further research should explore the relevance of this task as a clinical laboratory tool for assessing gait capacity and the risk of falling.

Pedestrian Tracking by Acoustic Doppler Effects

Localization is the foundation of location-based services and has received considerable attention recently. Pedestrian dead-reckoning (PDR) systems are widely used to infer user positions. However, a main problem is that the errors may easily accumulate during multiple integrations. In this research, we exploit the frequency shift of a wave caused by relative movement, i.e., the Doppler effect, of feet to infer user movement for locating user’s location. Specifically, when the two feet of a person move, the relative movements exhibit self-Doppler effect. This observation allows us to implement a PDR system by mounting two speakers and one microphone on shoes. The advantage is that the displacement can be inferred by integration once, as opposed to twice for accelerometers. To investigate the performance of our system, we evaluate its capability in measuring step event, step length, and step direction. Field trial results are presented, which show that our approach performs very well in step detection with 99.6% accuracy and step length estimation with error $\approx 0.0073$ m. However, its direction estimation is still not accurate enough and, thus, needs the help of other sensors.

적분 접근법과 파라메트릭 접근법을 융합한 허리 장착 보행항법시스템

In this paper, we proposed a pedestrian dead reckoning (PDR) system consisting of an integration approach and a parametric approach. The integration approach is used for obtaining the position by integrating the inertial sensor signal, and the parametric approach is for estimating the stride through the gait characteristic and estimating the position through the estimated step length and walking direction. If the inertial sensor is attached to the shoe, the position can be estimated by the integration approach with a zero velocity update. The integration approach has a disadvantage that the position error increases very quickly if periodic position or velocity correction is not possible. Therefore, when the inertial sensor is mounted at another part, the position is generally estimated through the parametric approach. In the case of the parametric approach, because the step length is estimated through the parameter, there is a disadvantage that the step length estimation error becomes large when the walking motion is not normal. To overcome these drawbacks, we proposed a waist-mounted PDR system combining the integration approach and parametric approach. The performance of the proposed algorithm was verified by experiments.

A Pedestrian Dead-Reckoning System for Walking and Marking Time Mixed Movement Using an SHSs Scheme and a Foot-Mounted IMU

A pedestrian dead-reckoning (PDR) system based on micro-inertial technology usually uses a sensor integrated with a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer and is attached to the person’s body (usually on the foot) to acquire the trajectory of the pedestrian. Although a variety of PDR system solutions have been proposed, the PDR solution for marking time and walking hybrid motions has not been formally proposed and solved. Therefore, in this paper, we propose the PDR system using a step-and-heading system scheme for marking time and walking hybrid motion. The main contributions include: 1) an adaptive gait partitioning method for walking and marking time hybrid motions is proposed; 2) a motion classification algorithm that uses a multi-layer perceptron to classify whether each step is walking or marking time is proposed; and 3) a new step length estimator based on several currently proposed models is proposed. Finally, an extended Kalman filtering algorithm combining heuristic heading reduction, flat-ground hypothesis, and cardinal heading aided inertial navigation techniques is used for heading estimation. We evaluate the effectiveness of the proposed algorithm through experiments, and the experimental results show that the average position error of the two groups of test experiments based on marking time and walking hybrid motion is 0.42% and 0.6%, respectively.

A Novel Pedestrian Dead Reckoning Algorithm for Multi-Mode Recognition Based on Smartphones

With the rapid development of smartphone technology, pedestrian navigation based on built-in inertial sensors in smartphones shows great application prospects. Currently, most smartphone-based pedestrian dead reckoning (PDR) algorithms normally require a user to hold the phone in a fixed mode and, thus, need to correct the gyroscope heading with inputs from other sensors, which restricts the viability of pedestrian navigation significantly. In this paper, in order to improve the accuracy of the traditional step detection and step length estimation method for different users, a state transition-based step detection method and a step length estimation method using a neural network are proposed. In order to decrease the heading errors and inertial sensor errors in multi-mode system, a multi-mode intelligent recognition method based on a neural network was constructed. On this basis, we propose a heading correction method based on zero angular velocity and an overall correction method based on lateral velocity limitation (LV). Experimental results show that the maximum positioning errors obtained by the proposed algorithm are about 0.9% of the total path length. The proposed novel PDR algorithm dramatically enhances the user experience and, thus, has high value in real applications.

Average Step Length Estimation Models’ Evaluation Using Inertial Sensors: A Review

Inertial sensors of smartphones and other Internet-of-Things devices present a very promising tool to monitor users’ activity including their step length. In this review paper, we deal with an in-depth analysis and comparison of 13 representative step length estimation models using smartphone inertial sensors: step-frequency-based, acceleration-based, angle-based, and multiparameter. Hereby, we have studied the influence of different walking speeds and four typical sensor positions on the models’ performance. Results indicate that smartphone position affected the performance of most acceleration-based models derived from a gait model. Their performance deteriorated if smartphone was carried in hand or pocket. Walking speed affected the performance of models that include step frequency when tuned with personalized sets of constants. Most of them performed better for fast and normal walking speeds. During this research, we also established an open-source dataset that contains over 22 km of gait measurements obtained from a group of 15 healthy adults.

Behaviors classification based distance measuring system for pedestrians via a foot‐mounted inertial sensor

AbstractIn this paper, we develop a foot‐mounted pedestrian navigation system prototype with the emphasis on distance measuring with an inertial measurement unit (IMU) which implies the characteristics of pedestrian gait cycle and thus can be used as a crucial step indicator for distance calculation. Conventional methods for step detection and step length estimation cannot adapt well to the general pedestrian applications since the parameters in these methods may vary for different persons and motions. In this paper, an adaptive time‐ and frequency‐domains joint distance measuring method is proposed by utilizing the means of behaviors classification. Two key issues are studied: step detection and step length determination. For the step detection part, first behavior classification along with state transition strategy is designed to identify typical pedestrian behaviors including standing still, walking, running and irregular swing. Then a four‐stage step detection method is proposed to adaptively determine both step frequency and threshold in a flexible window. Based on the behavior classification results, a two‐segment functional based step length model is established to adapt the walking and running behaviors. Finally, real experiments are carried out to verify our proposed step detection method and step length model. The results show that the proposed method outperforms the existing representative methods and it exhibits the merits of accuracy and adaptability for different persons in real time and significantly improves the accuracy of distance measuring.

A Novel Step Length Estimator Based on Foot-Mounted MEMS Sensors.

Pedestrian Dead Reckoning (PDR)-based pedestrian navigation technology is an important part of indoor and outdoor seamless positioning services. To improve the performance of PDR, we have conducted research on a step length estimator. Firstly, based on the basic theory of inertial navigation, we analyze in detail the errors in traditional Strapdown Inertial Navigation Systems (SINSs) caused by the unique motion state of pedestrians. Then, according to the fact that the inertial data from the foot can directly reflect the gait characteristics, we conduct a step length estimator that does not rely on SINS. The experimental results show that accuracy of the proposed method is between 0.6% and 1.4% with a standard deviation of 0.25%.

Pedestrian Dead Reckoning With Smartphone Mode Recognition

Smartphone mode recognition is becoming a key aspect of many applications, such as daily life monitoring, health care, and indoor positioning. In the later, two approaches exist to perform positioning using smartphone inertial sensors: traditional inertial navigation algorithms and pedestrian dead reckoning (PDR). Usually, PDR is preferred since it requires less integrations on the noisy sensory data. Step length estimation is a critical stage in PDR. It requires a calibration phase to determine appropriate gains, prior to PDR application. Using an incorrect gain will result in a position error. Such gains are very sensitive to different smartphone modes, such as talking, texting, swing, or pocket. Therefore, each smartphone mode requires a different gain. In this paper, the effect of the smartphone mode on PDR positioning accuracy is highlighted. To circumvent this error source, we employ machine learning classification algorithms to recognize the smartphone modes and thereby enabling the choice of a proper gain value to improve PDR positioning accuracy. To that end, a methodology of training on a single user and testing on multiple users, as well as unique features for the classification process, is implemented. Experimental results obtained using 13 participates walking in different indoor conditions and smartphone modes, show successes of more than 95% in classifying the smartphone modes and as a consequence may improve PDR positioning performance.

Step Length Estimation Methods Based on Inertial Sensors: A Review

Inertial sensors are included in most of the current smart devices and many researchers have identified their ability to be used for analyzing different parameters of human behavior. Among them, the pedestrian’s step length provides very useful information for different applications, such as pedestrian dead reckoning positioning or gait analysis. During the last three decades, many step length estimation methods using inertial sensors have been proposed; however, there is no specific review work that reflects the current state of the art. In this paper, we will conduct a systematic and complete review that covers the whole workflow of tasks involved in the design, test, and evaluation of step length estimation methods based on inertial sensors. The main conclusion drawn from this review is that the lack of public data sets and standard methodologies to guide testing and evaluation makes it difficult to compare the different methods in a fair and robust way. Some reflections on how to move forward on this direction have been presented.

허리 장착 기반의 IMU 센서를 이용한 3D 보행자 위치 추정 알고리즘 연구

This paper proposes a three-dimensional pedestrian position estimation algorithm using a waist-mounted Inertial Measurement Unit (IMU) sensor. A Pedestrian Dead Reckoning (PDR) system has been implemented using a single IMU sensor to locate a pedestrian who is carrying the PDR system on his waist in a building in which GPS signals are too weak to be utilized for localization. The position estimation system using IMU data suffers from degraded accuracy caused by the bias drift of gyroscope values. This approach adopts the quaternion to reduce the bias drift and obtain the precise Euler angles to localize the pedestrian in two-dimensional space with the step length estimation. To extend the localization into three-dimensional space to incorporate situations in which the pedestrian is ascending or descending the stairs, Zero-Velocity UpdaTe (ZUPT) scheme has been applied for processing gyroscope data from the IMU sensor. Real experiments have been performed to show the proposed algorithm’s effectiveness in both two- and three-dimensional spaces.