Walking Direction Research Articles

A Grassmannian Approach to Address View Change Problem in Gait Recognition.

Gait recognition appears to be a valuable asset when conventional biometrics cannot be employed. Nonetheless, recognizing human by gait is not a trivial task due to the complex human kinematic structure and other external factors affecting human locomotion. A major challenge in gait recognition is view variation. A large difference between the views in the query and reference sets often leads to performance deterioration. In this paper, we show how to generate virtual views to compensate the view difference in the query and reference sets, making it possible to match the query and reference sets using standardized views. The proposed method, which combines multiview matrix representation and a novel randomized kernel extreme learning machine, is an end-to-end solution for view change problem under Grassmann manifold treatment. Under the right condition, the view-tagging problem can be eliminated. Since the recording angle and walking direction of the subject are not always available, this is particularly valuable for a practical gait recognition system. We present several working scenarios for multiview recognition that have not be considered before. Rigorous experiments have been conducted on two challenging benchmark databases containing multiview gait datasets. Experiments show that the proposed approach outperforms several state-of-the-arts methods.

Local form interference in biological motion perception.

Replacing the local dots of point-light walkers with complex images leads to significant detriments to performance in biological motion detection and discrimination tasks. This detriment has previously been shown to be larger when the local elements match the global shape in object category and facing direction. In contrast, studies using Navon stimuli have demonstrated that local interference on global processing primarily occurs when local elements are dissimilar to the global form. In 3 experiments, we investigated this contradiction by replacing the local dots of a point-light walker with human images or stick figures. Participants were significantly faster and more accurate at discriminating the facing and walking direction of a walker when the local images were facing in the same direction as the global walker than when they were facing in the opposite direction. These results provide support for the idea that organization of biological motion depends on allocation of limited processing resources to the global motion information when the local elements are complex. However, there is more disruption to global form processing when the local elements and global form conflict in task-related properties.

Walking to singular points of fingerprints

Singular point is an essential global feature in fingerprint images. Existing methods for singular points’ detection generally visit each pixel or each small image block to determine the singular point. That is to say, existing methods require scanning the image to compute a quantity at each pixel or block, and hence they are inevitably time-consuming. We propose a fast algorithm for detecting singular points by walking directly to them instead of scanning the image. Walking Directional Fields (WDFs) are established from the orientation field. Then following the walking directions on WDFs, we can rapidly walk to the singular points. The walking algorithm is extremely fast and easily implemented with acceptable accuracy. Further more, its accuracy can also be improved by combining with state-of-the-art methods: we can rapidly walk to a candidate singular point, then refine its location using existing more accurate method in the local area. Experimental results on datasets of SPD2010 and FVC validate the high efficiency and satisfactory accuracy of the proposed algorithm.

Anticipatory control and spatial cognition in locomotion and navigation through typical development and in cerebral palsy.

Behavioural evidence, summarized in this narrative review, supports a developmental model of locomotor control based on increasing neural integration of spatial reference frames. Two consistent adult locomotor behaviours are head stabilization and head anticipation: the head is stabilized to gravity and leads walking direction. This cephalocaudal orienting organization aligns gaze and vestibula with a reference frame centred on the upcoming walking direction, allowing anticipatory control on body kinematics, but is not fully developed until adolescence. Walking trajectories and those of hand movements share many aspects, including power laws coupling velocity to curvature, and minimized spatial variability. In fact, the adult brain can code trajectory geometry in an allocentric reference frame, irrespective of the end effector, regulating body kinematics thereafter. Locomotor trajectory formation, like head anticipation, matures in early adolescence, indicating common neurocomputational substrates. These late-developing control mechanisms can be distinguished from biomechanical problems in children with cerebral palsy (CP). Children's performance on a novel navigation test, the Magic Carpet, indicates that typical navigation development consists of the increasing integration of egocentric and allocentric reference frames. In CP, right-brain impairment seems to reduce navigation performance due to a maladaptive left-brain sequential egocentric strategy. Spatial integration should be considered more in rehabilitation.

Invariant Heel Strike Detection using Gait Motion

In visual surveillance and biomedical field, the detecting heel strike position is a basic step for analyzing human behaviors, condition, and gait since due to its capabilities to provide gait stride, step length, walking speed/direction, and walking pattern. This paper presents a novel method for estimating the heel strike position based on analyzing the gait motion regardless of the walking speed and direction. Generally, when a person walks there is known torso movement in the vertical direction. This gait trajectory is a cue to calculate the gait period and the heel strike position. The trajectory can be analyzed by Wavelet decomposition to detect the gait periodicity and the moment of heel strike. Using the above information and known prior knowledge of the gait, a 3D gait trajectory model is constructed to estimate the accurate heel strike event. We evaluate our new approach using the different type of databases and show that we can indeed determine the heel strike position to good effect, including analysis of the scene of crime data. The contributions of this research are that we develop a new gait period detection method by wavelet decomposition and a new strategy which detects the heel strike position based on the human gait movement.

Detecting Boundary Nodes and Coverage Holes in Wireless Sensor Networks

The emergence of coverage holes in wireless sensor networks (WSNs) means that some special events have broken out and the function of WSNs will be seriously influenced. Therefore, the issues of coverage holes have attracted considerable attention. In this paper, we focus on the identification of boundary nodes and coverage holes, which is crucially important to preventing the enlargement of coverage holes and ensuring the transmission of data. We define the problem of coverage holes and propose two novel algorithms to identify the coverage holes in WSNs. The first algorithm, Distributed Sector Cover Scanning (DSCS), can be used to identify the nodes on hole borders and the outer boundary of WSNs. The second scheme, Directional Walk (DW), can locate the coverage holes based on the boundary nodes identified with DSCS. We implement the algorithms in various scenarios and fully evaluate their performance. The simulation results show that the boundary nodes can be accurately detected by DSCS and the holes enclosed by the detected boundary nodes can be identified by DW. The comparisons confirm that the proposed algorithms outperform the existing ones.

ジャイロ効果による歩行時の進行方向誘導

In this paper, we propose a method that unconsciously makes people walk slightly different direction by using gyro moment. We use rotational disks mounted on user’s feet to control their direction intentionally. Two rotational axes: one is rotational motion of foot while walking and the other one is the rotating disks of the proposed device, induces gyro moment. Then the landing angle of their foot is controlled depending on the rotational direction of the disks. Walking direction is assumed to follow the toe directions. As an application, a user can walk in a large VR space in a limited real space by the support of this device.

Pulling a Fire Hose by a Humanoid Robot While Walking

This paper discusses a strategy for a humanoid robot to pull a fire hose while walking. A hybrid controller on the robot's wrist holding the fire hose is implemented for pulling it. Through simulation analysis it is shown that when the robot walks while pulling the fire hose a drift in the walking direction is generated. To cope with this drift and to direct the robot to a desired position and orientation, a walking task is introduced. Using a motion capture system, the robot's chest position and orientation is monitored and feed to the robot's walking pattern generator to correct the orientation drift and to determine where to walk and when to stop walking. Through experimental results the validity of the proposed strategy was confirmed. It is shown that the proposed hybrid controller contributes to the improvement of the robot's balance when walking.

焦電型赤外線センサを用いた１人用ゲートにおける通行判定

安全・快適・便利・省エネな空間を提供するスマートビルシステムでは，ビル利用者の行動を抽出し，その行動情報に基づきサービスを実施することが有効である．行動情報抽出の一つのアプローチとして，多数の小型・低消費電力・安価な人検知センサから構成されるセンサネットワークにより，人流や人口分布を計測する研究が行われており，費用やプライバシーの問題を解消する方式として期待される．本研究では，センサノードとして焦電型赤外線センサを用い，小さな衝立やキャビネットにより作られた１人用ゲートを通行する人数と方向を判定する方式を提案する．デュアル型センサを天井に設置し，フレネルレンズにより一組の検知エリアを設定する．床面と人の温度差を変化させ，種々の通行動作を行う予備実験により得られた出力信号データから，信号ピークの符号パターンと振幅比を用いた判定アルゴリズムを考案する．判定対象とする通行動作は，異なる速度で通行（ゆっくり～走る），短時間立ち止まる，複数人が縦列に接近して通行，１人が通過した直後にもう１人が逆の方向に通行である．センサ基板とマイコンボードから構成される通行判定装置にアルゴリズムを実装して種々の通行実験を行い，実際の通行で頻度の高い１人の通過（ゆっくり～小走り）と２人の近接縦列（間隔３０cm以上）の通行に対し，１００％の精度で判定できることを確認した．講義室やパネル展示会場での検証実験では，１人通過は１００％正しく判定され，平均でも通行動作の回数では９０％以上，人数計数では８８％以上の正解率が得られた．

Assessment of an Adaptive Driving Beam Headlighting System: Visibility and Glare

Recent developments in solid-state lighting, sensor, and control technologies make new configurations for vehicle forward lighting feasible. Adaptive driving beam (ADB) systems build on systems that automatically switch from high- to low-beam headlights in the presence of oncoming vehicles. ADB systems can detect oncoming headlights and preceding taillights and reduce their intensity only in the direction of the other lights, while they maintain higher levels of illumination throughout the remainder of the field of view. The nominal benefit of ADB systems is the provision of high-beam levels of illumination in the forward scene, while glare is reduced to oncoming and preceding drivers, who perceive low-beam illumination levels. In this study, two dynamic field experiments were conducted: one experiment measured the ability of observers to identify the walking direction of roadside pedestrian targets with and without the use of the ADB system; the other experiment evaluated the discomfort glare elicited by the ADB system compared with the glare from conventional low- and high-beam headlights. The findings from both experiments were consistent with previous analytical and static field tests and suggested that ADB systems can offer safety benefits beyond those offered by conventional headlight systems.

ロコモティブシンドローム対策のための簡易な歩行診断システムの開発

The two-step test to measure stride length is one of locomotive syndrome risk test. By it the balance ability of lower limbs can be also assessed. In this study, quantitative measurement method of stride length and the balance ability is proposed. This adopts only one initial sensor, so the signal processing by adding the characteristics of walking is used. An inertial sensor is mounted on the waist of the subject and acceleration of walking direction is integrated twice to estimate the stride length. In order to suppress the integration error, the acceleration is modified to satisfy that velocity of the waist is zero at the rest. Horizontal displacement meaning the balance ability is estimated by applying Fourier integral in the acceleration of the horizontal direction utilizing the periodicity of the walking. Walking experiments are carried out and the results clearly show validity of the proposal method.

歩幅と進行方向の能動的支援を目的とした片側装着形歩行運動創成機構の開発

This paper discusses a development of an exoskeleton-type walking assist machine having essentially minimum number of joints in order to guarantee the intrinsic safety, simple and inexpensive structure, and can be divided into two pieces so that a part of the apparatus can be detached, when that part becomes unnecessary due to a recovery of body function. Since the obtained mechanism was designed to achieve target human gaits obtained by a number of motion capture experiments, including changings of step lengths and turnings of walking directions. In the determination of the mechanism composition, at first, a most practical composition was chosen among four candidates that were found by taking different selections of possible attachment locations between the device and a human's lower limb into account. Subsequently, the number of joints of the determined composition was synthesized by using only revolute joints so that the device could establish the required DOF for generating the motion of human gait. After that, dimensions of the obtained mechanism were determined through an optimization process considering a minimization of required driving torque which was calculated by a static analysis of the mechanism.

2F2-3 歩行者の進行方向が自転車の回避行動に与える影響

2F2-3 歩行者の進行方向が自転車の回避行動に与える影響

Neural model for multi-stability in visual action recognition

The visual perception of body movements shows interesting dynamical properties. Biological motion perception can show perceptual multi-stability with respect to the perceived walking direction [1]. In addition, body motion perception is subject to adaptation, as is demonstrated by the existence of high-level after-effects and of fMRI repetition suppression in relevant areas. Existing neural models for action recognition do not account for these phenomena. We present neurodynamical model that reproduces these phenomena, and which allows to study the interplay between multi-stability, adaptation and intrinsic fluctuations in body motion perception.

Neuronal control of walking: studies on insects

Abstract The control of walking in insects is to a substantial amount a function of neuronal networks in the thoracic ganglia. While descending signals from head ganglia provide general commands such as for walking direction and velocity, it is the thoracic central nervous system that controls movements of individual joints and legs. The coordination pattern of legs is velocity dependent. However, a clear stereotypic coordination pattern appears only at high velocities. In accordance with the unit burst oscillator concept, oscillatory networks (central pattern generators (CPGs)) interlocked with movement and load sensors control the timing and amplitude of joint movements. For a leg’s movements different joint CPGs of a leg are mainly coupled by proprioceptors. Differential processing of proprioceptive signals allows a task specific modulation of leg movements, for example, for changing movement direction. A switch between walking and searching movements of a leg is under local control. When stepping into a gap missing sensory input and the activation of a local command neuron evokes stereotypic searching movements of the leg.

Heritage Education and Heritagization Processes: SHEO Metodology for Educational Programs Evaluation

The cultural approach that is developed at the beginning of this article about “heritagization” processes, allows profiling three different agencies involved in these processes, therefore, an institutional agency, an individual agency, and a community agency are drawn; the last three agencies also determine the characteristics of their own processes, finding different approaches and aspects in the economic meanings and even in the evaluation assets themselves. Approaching this phenomenon through heritage education, and more specifically from the OEPE (Spanish Heritage Education Observatory), we find a starting point for the procedural route designed by Fontal (La educacion patrimonial: teoria y practica para el aula, el museo e internet, 2003) and extended by Gomez-Redondo (Gomez- Redondo (Identizacion: La construccion discursiva del individuo. Arte, Individuo y Sociedad, 23(2), 19–28, 2012), it serves us here as a measure for the evaluation of several educational programs. This and other parameters have been used to classify educational projects undertaken in Spain, and this is the environment where one realizes the magnitude and consistency of the process for creating a database. The next step, therefore, is to evaluate the educational programs that have been catalogued. In this article we propose some examples of qualitative evaluation of various educative designs that we analysed and which will provide information about the walking direction of heritage education in Spain, even they will allow us to detect and to infer characteristics of heritage education models, serving agencies to design models similar to the ones proposed in this article.

Experimental Study on Modifiable Walking Pattern Generation for Handling Infeasible Navigational Commands

To accommodate various navigational commands, a humanoid should be able to change its walking motion in real time. Using the modifiable walking pattern generation (MWPG) algorithm, a humanoid can handle dynamic walking commands by changing its walking period, step length, and direction independently. If the humanoid is given a command to perform an infeasible movement, the algorithm substitutes the infeasible command with a feasible one using binary search. The feasible navigational command is subsequently translated into the desired center-of-mass (CM) state. Every sample time CM reference is generated using a zero-moment-point (ZMP) variation scheme. Based on this algorithm, various complex walking patterns can be generated, including backward and sideways walking, without detailed consideration of the feasibility of the navigational commands. In a previous study, the effectiveness of the MWPG algorithm was verified by dynamic simulation. This paper presents experimental results obtained using the small-sized humanoid robot platform DARwIn-OP.

Neuroethology: Unweaving the Senses of Direction

Three recent studies have significantly advanced our understanding of the highly conserved central complex of the insect brain, showing how it provides an internal representation of body orientation, encodes behaviorally relevant sensory cues, and at the same time controls motor actions.

Muscle contributions to centre of mass acceleration during turning gait in typically developing children: A simulation study

Turning while walking requires substantial joint kinematic and kinetic adaptations compared to straight walking in order to redirect the body centre of mass (COM) towards the new walking direction. The role of muscles and external forces in controlling and redirecting the COM during turning remains unclear. The aim of this study was to compare the contributors to COM medio-lateral acceleration during 90° pre-planned turns about the inside limb (spin) and straight walking in typically developing children. Simulations of straight walking and turning gait based on experimental motion data were implemented in OpenSim. The contributors to COM global medio-lateral acceleration during the approach (outside limb) and turn (inside limb) stance phase were quantified via an induced acceleration analysis. Changes in medio-lateral COM acceleration occurred during both turning phases, compared to straight walking (p<0.001). During the approach, outside limb plantarflexors (soleus and medial gastrocnemius) contribution to lateral (away from the turn side) COM acceleration was reduced (p<0.001), whereas during the turn, inside limb plantarflexors (soleus and gastrocnemii) contribution to lateral acceleration (towards the turn side) increased (p≤0.013) and abductor (gluteus medius and minimus) contribution medially decreased (p<0.001), compared to straight walking, together helping accelerate the COM towards the new walking direction. Knowledge of the changes in muscle contributions required to modulate the COM position during turning improves our understanding of the control mechanisms of gait and may be used clinically to guide the management of gait disorders in populations with restricted gait ability.

Neuronal control of walking: studies on insects

The control of walking in insects is to a substantial amount a function of neuronal networks in the thoracic ganglia. While descending signals from head ganglia provide general commands such as for walking direction and velocity, it is the thoracic central nervous system that controls movements of individual joints and legs. The coordination pattern of legs is velocity dependent. However, a clear stereotypic coordination pattern appears only at high velocities. In accordance with the unit burst oscillator concept, oscillatory networks (central pattern generators (CPGs)) interlocked with movement and load sensors control the timing and amplitude of joint movements. For a leg’s movements different joint CPGs of a leg are mainly coupled by proprioceptors. Differential processing of proprioceptive signals allows a task specific modulation of leg movements, for example, for changing movement direction. A switch between walking and searching movements of a leg is under local control. When stepping into a gap missing sensory input and the activation of a local command neuron evokes stereotypic searching movements of the leg.