Walking Direction Research Articles

Local Dynamic Stability of the Locomotion of Lower Extremity Joints and Trunk During Backward Upslope Walking

Backward slope walking was considered as a practical rehabilitation and training skill. However, its gait stability has been hardly studied, resulting in its limited application as a rehabilitation tool. In this study, the effect of walking direction and slope grade were investigated on the local dynamic stability of the motion of lower extremity joints and trunk segment during backward and forward upslope walking (BUW/FUW). The local divergence exponents (λS) of 16 adults were calculated during their BUW and FUW at grades of 0%, 5%, 10%, and 15%. Mean standard deviation over strides (MeanSD) was analyzed as their gait variability. Backward walking showed larger λS for the abduction-adduction and rotational angles of knee and ankle on inclined surface than forward walking, while λS for hip flexion-extension angle at steeper grades was opposite. No grade effect for any joint existed during BUW, while λS increased with the increasing grade during FUW. As to the trunk, walking direction did little impact on λS. Still, significant larger λS for its medial-lateral and vertical motion were found at the steeper grades during both FUW and BUW. Results indicate that during BUW, the backward direction may influence the stability of joint motions, while the trunk stability was challenged by the increasing grades. Therefore, BUW may be a training tool for the stability of both upper and lower body motion during gait.

Robust gait identification using Kinect dynamic skeleton data

Gait has been recently proposed as a biometric feature that, with respect to other human characteristics, can be captured at a distance without requiring the collaboration of the observed subject. Therefore, it turns out to be a promising approach for people identification in several scenarios, e.g. access control and forensic applications. In this paper, we propose an automatic gait recognition system based on a set of features acquired using the 3D skeletal tracking provided by the popular Kinect sensor. Gait features are defined in terms of distances between selected sets of joints and their vertical and lateral sway with respect to walking direction. Moreover we do not rely on any geometrical assumptions on the position of the sensor. The effectiveness of the defined gait features is shown in the case of person identification based on supervised classification, using the principal component analysis and the support vector machine. A rich set of experiments is provided in two scenarios: a controlled identification setup and a classical video-surveillance setting, respectively. Moreover, we investigate if gait can be considered invariant over time for an individual, at least in a time interval of few years, by comparing gait samples of several subjects three years apart. Our experimental analysis shows that the proposed method is robust to acquisition settings and achieves very competitive identification accuracy with respect to the state of the art.

Groups at a glance: Perceivers infer social belonging in a group based on perceptual summaries of sex ratio.

Human observers extract perceptual summaries for sets of items after brief visual exposure, accurately judging the average size of geometric shapes (Ariely, 2001), walking direction of a crowd (Sweeny, Haroz, & Whitney, 2013), and the eye gaze of groups of faces (Sweeny & Whitney, 2014). In addition to such actuarial summaries, we hypothesize that observers also extract social information about groups that may influence downstream judgments and behavior. In four studies, we first show that humans quickly and accurately perceive the sex ratio of a group after only 500 ms of visual exposure. We then test whether these percepts bias judgments about the group's social attitudes and affect the perceiver's sense of belonging. As the ratio of men to women increased, both male and female perceivers judged the group to harbor more sexist norms, and judgments of belonging changed concomitantly, albeit in opposite directions for men and women. Thus, observers judge a group's sex ratio from a mere glimpse and use it to infer social attitudes and interpersonal affordances. We discuss the implication of these findings for a heretofore overlooked hurtle facing women in male-dominated fields (e.g., science, technology, engineering, or mathematics): how the ratio of men to women provides an early visible cue that signals an individual's potential fit. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

Gait representation and recognition from temporal co-occurrence of flow fields

This paper proposes a new gait representation that encodes the dynamics of a gait period through a 2D array of 17-bin histograms. Every histogram models the co-occurrence of optical flow states at every pixel of the normalized template that bounds the silhouette of a target subject. Five flow states (up, down, left, right, null) are considered. The first histogram bin counts the number of frames over the gait period in which the optical flow for the corresponding pixel is null. In turn, each of the remaining 16 bins represents a pair of flow states and counts the number of frames in which the optical flow vector has changed from one state to the other during the gait period. Experimental results show that this representation is significantly more discriminant than previous proposals that only consider the magnitude and instantaneous direction of optical flow, especially as the walking direction gets closer to the viewing direction, which is where state-of-the-art gait recognition methods yield the lowest performance. The dimensionality of that gait representation is reduced through principal component analysis. Finally, gait recognition is performed through supervised classification by means of support vector machines. Experimental results using the public CMU MoBo and AVAMVG datasets show that the proposed approach is advantageous over state-of-the-art gait representation methods.

Personal Identification Through Pedestrians’ Behavior

This article focuses on a new approach for personal identification by exploring the features of pedestrian behavior. The recent progress of a motion capture sensor system enables personal identification using human behavioral data observed from the sensor. Kinect is a motion sensing input device developed by Microsoft for Xbox 360 and Xbox One. Personal identification using the Microsoft Kinect sensor (hereafter referred to as Kinect) is presented in this study. Kinect is used to estimate body sizes and the walking behaviors of pedestrians. Body sizes such as height and width, and walking behavior such as joint angles and stride lengths, for example, are used as explanatory variables for personal identification. An algorithm for the personal identification of pedestrians is defined by a traditional neural network and by a support vector machine. In the numerical experiments, pictures of body sizes and the walking behaviors are captured from fifteen examinees through Kinect. The walking direction of pedestrians was specified as 0°, 90°, 180°, and 225°, and then the accuracies were compared. The results indicate that identification accuracy was best when the walking direction was 180°. In addition, the accuracy of the vector machine was better than that of the neural network.

A Gait Recognition Method for Human Following in Service Robots

In this paper, we propose a gait recognition method for service robots to conduct human following tasks. A walking sequence segmentation method is designed to extract the consecutive gait cycles from an arbitrary walking sequence. Based on the segmentation results, a novel hybrid gait feature is proposed to capture the static, dynamic, and trajectory features for each segmented key and supplementary gait cycles. A dataset of 25 human subjects is collected to evaluate the proposed method in three different walking paths with various walking directions. Experimental results show that the proposed method achieves satisfactory performance in terms of identification accuracy and ${F} _{\text {comb}}$ indexes on our dataset. Compared with five state-of-the-art gait recognition methods, the proposed method achieves the best performance on human gait recognition based on the walking sequences defined in our proposed dataset.

Fundamental diagrams for pedestrian flows in a channel via an extended social force model

In this paper, an extended social force model was applied to investigate fundamental diagrams of pedestrian flows. In the presented model, both the static floor field and the view field were taken into account. Then each pedestrian can determine his/her desired walking directions according to both global and local information. The fundamental diagrams were obtained numerically under periodic boundary condition. It was found that the fundamental diagrams show good agreement with the measured data in the case of unidirectional flow, especially in the medium density range. However, the fundamental diagram for the case of bidirectional flow gave larger values than the measured data. Furthermore, the bidirectional flux is larger than the unidirectional flux in a certain density range. It is indicated that the bidirectional flow may be more efficient than the unidirectional flow in some cases. The process of lane formation is quite quick in the model. Typical flow patterns in three scenarios were given to show some realistic applications.

Approach toward footstep planning considering the walking period: Optimization-based fast footstep planning for humanoid robots

This paper proposes the necessity of a walking period in footstep planning and details situations in which it should be considered. An optimization-based fast footstep planner that takes the walking period into consideration is also presented. This footstep planner comprises three stages. A binary search is first used to determine the walking period. The front stride, side stride, and walking direction are then determined using the modified rapidly-exploring random tree algorithm. Finally, particle swarm optimization (PSO) is performed to ensure feasibility without departing significantly from the results determined in the two stages. The parameters determined in the previous two stages are optimized together through the PSO. Fast footstep planning is essential for coping with dynamic obstacle environments; however, optimization techniques may require a large computation time. The two stages play an important role in limiting the search space in the PSO. This framework enables fast footstep planning without compromising on the benefits of a continuous optimization approach.

Intelligent robotic walker with actively controlled human interaction

In this study, we developed a robotic walker that actively controls its speed and direction of movement according to the user's gait intention. Sensor fusion between a low-cost light detection and ranging (LiDAR) sensor and inertia measurement units (IMUs) helps determine the user's gait intention. The LiDAR determines the walking direction by detecting both knees, and the IMUs attached on each foot obtain the angular rate of the gait. The user's gait intention is given as the directional angle and the speed of movement. The two motors in the robotic walker are controlled with these two variables, which represent the user's gait intention. The estimated direction angle is verified by comparison with a Kinect sensor that detects the centroid trajectory of both the user's feet. We validated the robotic walker with an experiment by controlling it using the estimated gait intention.

A dose-finding study of oxytocin using neurophysiological measures of social processing.

Recent interest has focused on oxytocin (OT), a neurotransmitter that promotes social processing, to improve social functioning in people with schizophrenia. However, little information is available regarding the doses of OT that are effective for influencing social processing in the brain (i.e., target engagement). In this study, we conducted a double-blind, placebo-controlled, cross-over dose ranging study of OT. In total 47 patients with schizophrenia were randomly assigned to one of eight doses of OT (8, 12, 24, 36, 48, 60, 72, or 84 IU). Patients completed two social processing tasks: one electroencephalography (EEG) task, a biological motion Mu-suppression task (i.e., identifying the gender, emotion, or direction of walking of point-light animations of human movement); and one pupillometry task, pupil dilation in response to viewing affective faces. Participants completed these tasks twice, one week apart, and were randomly administered drug or placebo intranasally 30 min prior to each session. Mu-suppression, i.e., suppression of oscillations in the 8-12 Hz range over central electrodes in response to social stimuli, was significantly enhanced at doses of 36 and 48 IU in comparison to placebo, but not at other doses. Significant pupil dilation was observed in response to faces vs. non-face stimuli, though there were no drug effects at any dose. Results suggest that OT affects central measures of social information processing in patients with schizophrenia and is optimal at a mid-range dose (36-48 IU). These results provide dosing guidance for future studies of OT to be used to enhance social processing in people with schizophrenia.

Biomechanical evaluation of virtual reality-based turning on a self-paced linear treadmill

BackgroundPatients with brain injuries such as Parkinson’s disease or stroke exhibit abnormal gait characteristics especially during gait transitions such as step initiation and turning. Since such transitions could precipitate falls and resultant injuries, evaluation and rehabilitation of non-steady state gait in those patients are important. Whereas body weight supported treadmill training (BWSTT) provides a safe and controlled environment for gait training, it is unable to adequately train for gait transitions since the typical linear treadmill does not allow for changes in walking direction and natural fluctuations in speed. Research questionThis paper verifies if the suggested virtual reality (VR) based walking interface combined with the unidirectional treadmill can stimulate the user to initiate turning gait. MethodsTo validate whether initiation of turning was successfully achieved with the proposed walking system, we developed the VR-based walking interface combined with the self-paced treadmill and compared kinematics, kinetics, and muscle activation levels during the VR-based turning and overground (OG) turning as well as between straight walking and turning within conditions. ResultsDespite walking on a linear treadmill, subjects showed significant increases in head rotation, pelvic rotation, right hip abduction, left hip adduction, foot progression, medial-lateral ground reaction forces, right medial hamstring activation level, and changes in step width during the VR turn compared to straight walking. SignificanceThe developed VR-based turning interface can provide a safe and controlled environment for assessment of turning in healthy controls and may have a potential for assessment and training in patients with neurological disorders.

Mind the gaps: Edge-based monitoring for continuous room-level location tracking

Abstract In-home monitoring applications often need strong and reliable contextual information to be of value. Indoor location tracking can play an important role in providing this context. However, most current indoor tracking solutions require extensive, application-specific knowledge and pre-deployment preparation, often including detailed information about floorplans and RF signal strength calibration, which is not practical in many deployments. This paper introduces an edge-based location monitoring technique that uses doorway sensors to detect doorway crossing events with walking directions. The approach is designed to provides room-level tracking. Users movement from a wearable device is used in conjunction with the edge-monitored approach to track multiple people. This method also enables the tracked location and doorway crossing events to be transformed into states and state transitions, respectively. This provides an opportunity to implement stochastic models to the edge-based location tracking to correct tracking errors and improve its accuracy, as demonstrated in simulation. This location tracking method has been implemented and deployed in a health monitoring study on dementia-related agitation.

Optimal human navigation in steep terrain: a Hamilton–Jacobi–Bellman approach

Author(s): Parkinson, Christian; Arnold, David; Bertozzi, Andrea L; Chow, Yat Tin; Osher, Stanley | Abstract: We present a method for determining optimal walking paths in steep terrain using the level set method and an optimal control formulation. By viewing the walking direction as a control variable, we can determine the optimal control by solving a Hamilton-Jacobi-Bellman equation. We then calculate the optimal walking path by solving an ordinary differential equation. We demonstrate the effectiveness of our method by computing optimal paths which travel throughout mountainous regions of Yosemite National Park. We include details regarding the numerical implementation of our model and address a specific application of a law enforcement agency patrolling a nationally protected area.

Operator Dermal Exposure to Pesticides in Tomato and Strawberry Greenhouses from Hand-Held Sprayers

Protection of greenhouse crops in southern Italy usually requires 15–20 phytosanitary treatments per year, with volume rates in the range of 1000–2000 L ha−1, depending on the plant growth stage. The most widespread sprayers are hand-held, high-pressure devices, which may expose operators to high levels of pesticides. This paper, also with the aim to lead toward a more sustainable use of greenhouses in agricultural productions, including some aspects of workers’ safety, reports the results of experimental tests aimed at measuring the amount of the mixture deposited on the worker’s body (potential dermal exposure, PDE) during pesticide applications to tomato and strawberry plants in a protected environment. Experimental tests on tomatoes were carried out taking into account two plant growth stages (flowering and senescence), two types of spray lance, two working pressures (1 and 2 MPa), and two walking directions (forwards and backwards). Those on the strawberries were carried out at the maturity of the fruit growth stage, comparing two hand-held sprayers (a standard spray gun and a short hand-held spray boom equipped with two nozzles) and working according to the common practice: forwards movement of the operator and high pressure (2 MPa). The results showed that with the tomato plants, the most important factor in reducing the deposit on the operator was the walking direction: on average, the PDE was 718 mL per 1000 L of the sprayed mixture (0.72‰) while walking forwards and 133 mL (0.13‰) while walking backwards. The reduction factor ranged from 3.0 at the flowering growth stage to 7.2 at the senescence growth stage. With respect to the strawberry plants, the PDE was significantly higher when the operator used the short hand-held spray boom (887 mL per 1000 L of the sprayed mixture, equivalent to 0.89‰), rather than the spray gun (344 mL, 0.34‰). In both cases, the most exposed body parts were the lower limbs, which accounted for 89–94% of the total PDE.

Effect of magnetic components on the smoothness of linear motion for a pedrailed wall-climbing robot

This paper presents the effect of the adhesion force achieved from magnetic components that are about to adhere to (off) the wall on the smoothness of linear motion for a magnetically pedrailed wall-climbing robot. This adhesion force is a kind of disturbing force, which affects the movement of the robot by affecting the torque of the sprockets. Therefore, on the basis of analyzing the limit adhesion force that ensures the robot to be adhered safely on the wall, the minimum adhesion force is determined. To calculate the adhesion force and obtain variation curve of adhesion force with the rotational angle of the sprocket, the software, Maxwell, is used to simulate the magnetic field of the magnetic components at different working positions relative to the wall, and then calculate the driving moment and resisting moment caused by magnetic components. The total moment is obtained by combing the driving moment and resisting moment by using Excel software. This total moment or torque will influence the acceleration of the robot’s centroid in the walking direction. On the basis of this disturbing acceleration, the linear motion smoothness of the robot is analyzed.

A machine learning approach to targeted balance rehabilitation in people with Parkinson's disease using a sparse sensor set.

Clinical Balance Assessments Often Rely On Functional Tasks As A Proxy For Balance (E.G., Timed Up And Go). In Contrast, Analyses Of Balance In Research Settings Incorporate Quantitative Biomechanical Measurements (E.G., Whole-Body Angular Momentum, H) Using Motion Capture Techniques. Fully Instrumenting Patients In The Clinic Is Not Feasible, And Thus It Is Desirable To Estimate Biomechanical Quantities Related To Balance From Measurements Taken From A Subset Of The Body Segments. Machine Learning Algorithms Are Well-Suited For This Type Of Low- To High-Dimensional Mapping. Thus, Our Objective Was To Develop And Validate An Artificial Neural Network For Estimating Contributions To H From 12 Body Segments Using Only Five Inertial Measurement Units. The Network Was Trained, Tested And Validated On Data From Five Able-Bodied Individuals Performing Forty Trials Each Of A Circuit Involving Complex Walking Tasks, Including Stairs, Ramp, And Direction Changes. The Network Was Also Separately Tested On Four Trials Of An Individual With Parkinson'S Disease Walking On The Circuit. The Output Of The Network Was Strongly Correlated With The Segment Contributions To H In Both Able-Bodied (R= 0.997) And Parkinson'S Disease (R= (0.998) Subjects. The Estimated Values Also Had Low Error Relative To The Signal Magnitude, With The Largest Mean ± SD Rootmean-Squared Errors Of 8.04 ± 1.76% Peak Signal Magnitude In Able-Bodied Individuals And 7.96 ± 0.91% In The Individual With Parkinson'S Disease. These Promising Results Establish The Feasibility Of Using A Sparse Set Of Inertial Measurement Units To Provide Quantitative Data To Clinicians For Targeted Balance Rehabilitation Across Different Patients.

Effectiveness of backward walking training on spatial-temporal gait characteristics: A systematic review and meta-analysis

BackgroundBackward walking training (BWT) is thought to affect gait biomechanics, but relevant evidence has been sparse and inconclusive. ObjectiveThis study systematically reviewed and quantified the effectiveness of BWT on spatial–temporal gait characteristics (STGC). MethodsA keyword and reference search of interventions on BWT was conducted in five bibliographic databases: PubMed, Web of Science, SPORTDiscus, CINAHL, and Cochrane Library for articles published until November, 2017. Two reviewers independently screened titles, abstracts, and full texts of all articles and jointly decided the final pool. A standardized form was used to extract data from each included article. Meta-analysis was conducted to estimate the pooled effect of BWT on STGC. ResultsEleven studies met the eligibility criteria and were included in the review. All studies reported some positive influences of BWT on STGC relative to forward walking training (FWT) and/or control. Compared to FWT, BWT was associated with an increase in forward gait speed by 0.69 (95% confidence interval [CI] = 0.12, 1.25) m/s and stride length by 0.51 (95% CI = 0.22, 0.80) cm. Compared to control, BWT was associated with an increase in forward gait speed by 1.00 (95% CI = 0.36, 1.64) m/s. ConclusionsBWT could improve participants’ STGC and be potentially useful in neurological rehabilitation. However, current evidence remains preliminary. The effects found could merely be due to differences in training intensity between the FWT and BWT, and thus, may not reflect actual differences between training in different walking directions. Future studies are warranted to elucidate the pathways linking BWT to gait biomechanics.

Beyond estimating discrete directions of walk: a fuzzy approach

Direction of walk of a pedestrian is vital information in various applications like visual surveillance, traffic monitoring and control, assisted living systems and automated car assistance system. Existing methods of direction of walk estimation exploit inter-frame and intra-frame features of a pedestrian frame sequence to classify the motion among predefined discrete direction classes. However, in order to achieve a robust method to estimate direction of walk, a strong analogy to justify an evident stationary or motion pattern as potential feature for direction estimation is essential. Discrete results of walk direction are famously used as it can be estimated in less time and are preferable for less precision sensitive scenario. However, the intra-frame feature that yields per-frame orientation is underutilized when the walk directions are subjected to discrete classes and hence there is a stringent need to go beyond discrete levels of direction and comment on specific walk direction angles at the same time maintaining a strong analogy to justify the potential of proposed features for direction of walk estimation. With this motivation, the article proposes a type-1 fuzzy approach over apposite inter-frame as well as intra-frame locomotion feature of pedestrian to yield precise direction of walk in terms of fuzzy directions beyond discrete levels of pedestrian walk directions. The method identifies eight directions as potential membership functions. Identified features are subjected to rule-based table for identification and removal of noisy orientation results, decision on membership function and their membership grade generation. The defuzzified result yields crisp direction of walk estimates beyond discrete levels of direction. The enhanced direction of walk estimation results is evident from qualitative comparison from existing research works and is also supported by the simulation performed over different datasets. The proposed method achieves 98.33%, 98.79%, and 100% Rank-2 balanced accuracy while applied on CASIA Dataset A, B, and NITR Conscious Walk Dataset respectively, which clearly points out its better performance than state of the art.

Gait recognition in the wild using shadow silhouettes

Gait recognition systems allow identification of users relying on features acquired from their body movement while walking. This paper discusses the main factors affecting the gait features that can be acquired from a 2D video sequence, proposing a taxonomy to classify them across four dimensions. It also explores the possibility of obtaining users' gait features from the shadow silhouettes by proposing a novel gait recognition system. The system includes novel methods for: (i) shadow segmentation, (ii) walking direction identification, and (iii) shadow silhouette rectification.The shadow segmentation is performed by fitting a line through the feet positions of the user obtained from the gait texture image (GTI). The direction of the fitted line is then used to identify the walking direction of the user. Finally, the shadow silhouettes thus obtained are rectified to compensate for the distortions and deformations resulting from the acquisition setup, using the proposed four-point correspondence method. The paper additionally presents a new database, consisting of 21 users moving along two walking directions, to test the proposed gait recognition system. Results show that the performance of the proposed system is equivalent to that of the state-of-the-art in a constrained setting, but performing equivalently well in the wild, where most state-of-the-art methods fail. The results also highlight the advantages of using rectified shadow silhouettes over body silhouettes under certain conditions.

Gait symmetry measurement method based on a single camera

Changes in gait symmetry may indicate health deterioration of seniors, such as inefficiency and loss of balance control. Measuring symmetry of seniors’ daily gaits can provide essential information on health status and functional abilities of the seniors, and therefore has attracted increasing attention in the field of elderly health care. Current gait symmetry measurement using a single camera is usually restricted to walking directions, because most studies require subjects to walk perpendicularly to the camera’s optical axis. This limits the application of single-camera-based systems in daily-life gait measurement. In this paper, we propose a gait symmetry measurement method using a single camera, unconstrained by walking directions. We first establish mathematical relationship between projections of step length and body’s height on the image plane in three consecutive steps, and then utilize the mathematical relations to generate a formula for symmetry ratio of lengths of two adjacent steps, and meanwhile eliminate impacts of the walking directions. For a monocular monitoring video, the proposed method segments the sequence of human silhouettes into multiple steps after detecting a moving human, and then makes use of information of these steps to compute the symmetry ratio according to the derived formula, and finally provides gait symmetry measurement irrespective of walking directions. Experimental results indicate that our method can achieve accurate gait symmetry measurement, in good agreement with actual measured data, in unconstrained environments where subjects’ walking directions are not strictly restricted.