基于下肢轮廓角度距离和步幅变化的步态识别算法研究

在视频监控系统中进行实时步态识别,不仅需要保证高识别率,同时需要尽量缩短识别时间。因此,提出一种基于下肢轮廓角度距离和步幅变化的步态识别算法。该算法对提取的轮廓图像按其最小外接矩形进行裁剪,并在保持宽高比不变的情况下,按照所有图像的最大高度进行图像缩放;提取一个周期内所有图像帧的质心高度、步幅,以及以骨盆关节点为依据的相邻两帧图像之间的下肢轮廓角度距离变化率作为步态特征;通过动态时间规整(DTW)算法和K近邻算法分别完成相似性度量和分类识别。实验结果表明,该算法能够较好地平衡识别率和时间代价之间的关系,以较短的时间实现用户身份高识别率,同时对衣着和背包状态具有较好的鲁棒性。     

基于改进时空步态图的步态识别

基于图像步态识别因缺乏有效动态、时序特征,导致跨视角识别时准确率较低,而基于模型步态识别特征维度不足,容易造成步态识别平均准确率不高。故提出一种改进时空步态图(Improved Chrono-Gait Image,ICGI)及特征融合策略的解决方法,将时序信息与人体下肢关节间角度的规律变化相结合,突出步态运动时下肢的周期性变化。在引入时序信息的基础上,融合下肢关节点间动态特征,建立一个更加丰富、有效的特征集。结合最近邻算法(KNN)建立步态识别模型,在CASIA-B数据集上进行对比实验,证实所提方法能有效提高复杂环境下步态识别精度。     

姿态特征结合2维傅里叶变换的步态识别

目的 针对现有步态识别方法易受携带物品、衣服变化等影响的问题,提出了将无肩姿态能量图、步态参数等姿态特征与步态参数的2维傅里叶变换相结合的步态识别算法。方法 基于姿态关节点序列提出忽略肩膀宽度信息的无肩姿态能量图,用以减弱衣服变化的影响;由于下肢受衣物及背包影响较小,提取3个或3个以上的下肢关节点局部结构参数,即提取中臀点与左右膝关节点、中臀点与左右踝关节点构成的两个三角形面积以及所有下肢关节点构成的多边形面积作为步态参数,增强下肢参数在步态识别中的作用;人在行走时,单肢体的运动具有一定的周期性,且肢体之间运动具有一定的协调性,用步态参数的2维幅度谱来表示单肢体运动的周期性与肢体之间运动的协调性,以提高步态参数的可区别性;在现有典型步态特征的基础上,融合本文提出的无肩姿态能量图、步态参数及其2维傅里叶变换幅度谱,采用多特征表示步态的方法,充分利用各特征的优点,提出加权平均与最大池化相结合的两层分数融合策略进行步态识别,提高了步态识别算法在携带物品、衣服变化和跨视角等条件下的正确率。结果 实验结果表明,在中国科学院自动化研究所发布的步态数据集CASIA-B上,本文方法在相同视角条件下,正常状态、背包状态和穿大衣状态的平均识别率分别为99.56%、99.23%和94.25%;在跨视角条件下,正常状态、背包状态和穿大衣状态的平均识别率分别为91.32%、85.34%和69.51%。与典型算法相比,穿大衣状态的识别率有显著提升。结论 本文方法采用加权平均与最大池化相结合的两层分数融合策略,综合利用各特征的优点及其适用场景,有效提高了步态识别的准确率,特别是减弱了衣服厚度、样式等变化对步态识别的影响。     

基于下肢轮廓特征的步态周期算法

步态周期是步态的一个重要特征,步态识别是建立在准确的步态周期分割之上的。本文提出了一个基于下肢轮廓的步态周期检测方法,首先对步态序列图像进行灰度化,然后计算各像素点在步态图像序列中的中值,获取整个步态序列图像的背景,提取人体目标后,利用数学形态学方法和区域跟踪算法填补二值化图像中的空洞;采用轮廓跟踪算法获得人体下肢轮廓,并将其转换为对应距离向量,在一个步态系列中利用距离向量范数研究步态周期。本算法计复杂度低,鲁棒性好,精确度高。     

基于Radon变换特征提取的步态识别

提出了一种基于Radon变换特征提取的步态识别算法.该算法根据步态轮廓图下肢的宽度信息确定步态运动准周期性,对二进制准周期步态轮廓序列进行Radon变换构造特征向量模板.对特征向量进行主成分分析,并采用k-近邻法进行步态特征分类.在CASIA步态数据库上和CAS识别算法进行了详细的比较,实验结果表明,该算法在性能上有较大程度的提高,是一种有效的步态识别方法.     

一种基于模型的步态识别方法

该文提出了一种简单有效的基于人体骨骼化模型的步态识别方法。首先,对输入的步态序列自动进行背景初始化;然后分割图像中运动人体的侧面影像,并进一步细化为人体的骨骼化模型;从模型中提取人体的静态参数(如身高、步幅)以及动态参数(如运动过程中关节点的位置、肢体角度);最后,应用标准的模式分类技术对个体的身份做出识别。实验结果表明,此方法通过提取可靠的步态特征,降低了数据处理的代价,而且得到了较为良好的识别性能。     

基于特征融合的步态识别算法研究*

提出一种融合步态运动中的人体形状信息特征和下肢运动信息特征的步态识别算法：利用边界跟踪算法获取人体轮廓边界线,并采用傅里叶描述子表达人体轮廓特征;依据人体解剖学的知识定位下肢关节点,并提取下肢角度特征;分别对两种特征进行匹配,然后采用特征融合的方法对匹配结果进行处理。实验结果表明,本算法的性能较基于单个特征的步态识别算法有明显的改善。     

基于sEMG的行走步态非均匀特性及其对识别的影响

人体生理特性和运动特性是影响步态识别的重要因素。利用实验采集的下肢表面肌电信号,首先对肌电信号进行小波消噪及特征提取,然后构造支持向量机分类器进行分类与识别,并针对步态周期数据的非均匀性（非等时性）特性进行了详细讨论。结果表明,即使在匀速行走条件下,人体步态周期仍然存在一定的非均匀特性,且这一特点会影响步态识别的准确性。这对于进一步研究步态稳定性和步态识别率等具有一定的参考价值。     

基于堆叠深度卷积沙漏网络的步态识别

提出了一种基于堆叠深度卷积沙漏网络的步态识别方法。为了解决人体建模中关节点准确定位的问题，采用基于深度卷积的沙漏网络来提取步态图上的关节点坐标，并计算肘关节与膝关节的角度作为运动特征。为了解决行走速度变化带来的影响，采用动态时间规整（Dynamic Time Warping）对特征序列进行距离计算。通过最近邻分类器对结果进行准确分类。该方法在公共CASIA-B数据集与TUM-GAID数据集上进行了验证并与其他方法进行比较，结果表明该方法有较高的识别率。     

基于图像处理的人体步态信息采集与处理

为了获取健康人体的正常步态信息, 提出了一种快捷有效的获取方法. 通过在下肢关节点处粘贴标记点, 利用摄像机获取正常人行走的图像, 对图像进行二值化处理, 提取出标记点坐标. 经过最小二乘拟合分析可得到人体脚心在一个步态周期内的运动轨迹及运动速度. 最后对下肢康复机器人进行步态规划, 得到下肢康复机器人的步态轨迹及其速度,并对不同年龄人群的步态速度曲线进行了分析. 实验结果表明, 该系统可行性好, 工作稳定, 为下肢康复机器人的运动学分析与控制提供有力的理论依据和验证方法.     

理疗师交互下的下肢康复训练机器人个性化步态规划方法

针对偏瘫患者的个体差异及病况差异,提出了一种理疗师交互下的下肢康复训练机器人步态规划方法,在理疗师-减重悬吊式康复训练机器人-患者三者共存的复杂环境中,理疗师穿戴主控外骨骼直接行走实现步态时空参数规划,并融入理疗师的医学经验及对患者的评估.首先,基于旋量理论建立运动学模型,实现理疗师空间与机器人空间的运动映射;然后,统一规划机器人关节运动轨迹、减重机构重心调整轨迹及跑步机步速.最后,通过理疗师步态参数的实时采集、运动映射实验及机器人轨迹跟踪实验,验证了步态时空规划方法的有效性.结果表明,髋、膝关节规划角度在人体关节活动范围内,速度变化平稳,关节轨迹规划和重心调整规划均符合人体行走的生理特性.理疗师的参与实现了渐进康复训练中的个性化步态规划.     

Changes in gait kinematics and posture with the use of a front pack

The objective of this study was to determine if posture during gait can be affected by position of the load. It was hypothesized that the front pack would result in postural changes in the gait cycle, compared to a similarly loaded backpack. Thirteen healthy adults, free of any injury, volunteered to participate in this study. Two dimensional video data were collected at 50 Hz using a MacReflex video system. A backpack and a front pack were compared using loads of 10 and 15% of body weight. Markers were placed on the ear, acromion, greater trochanter and lateral joint line of the knee, lateral malleolus and fifth metatarsophalangeal joint. Data were collected while the participants walked at 0.75 stride/s. The data were used to calculate joint angles and displacements during each gait cycle. There was a significant difference noted in angles of the hip flexion, with the backpack condition demonstrating a greater flexion in each stride than either the control or front pack. Both backpack and front pack conditions demonstrated a significant change in neck motion compared to the control condition. The results of the position analysis over time also revealed an increase in the forward head position when participants were wearing the backpack compared to either the control or the front pack condition. It was concluded that the use of a front pack results in a more upright posture in gait, when compared to a backpack carrying the same load.     

Changes in gait kinematics and posture with the use of a front pack

The objective of this study was to determine if posture during gait can be affected by position of the load. It was hypothesized that the front pack would result in postural changes in the gait cycle, compared to a similarly loaded backpack. Thirteen healthy adults, free of any injury, volunteered to participate in this study. Two dimensional video data were collected at 50 Hz using a MacReflex video system. A backpack and a front pack were compared using loads of 10 and 15% of body weight. Markers were placed on the ear, acromion, greater trochanter and lateral joint line of the knee, lateral malleolus and fifth metatarsophalangeal joint. Data were collected while the participants walked at 0.75 stride/s. The data were used to calculate joint angles and displacements during each gait cycle. There was a significant difference noted in angles of the hip flexion, with the backpack condition demonstrating a greater flexion in each stride than either the control or front pack. Both backpack and front pack conditions demonstrated a significant change in neck motion compared to the control condition. The results of the position analysis over time also revealed an increase in the forward head position when participants were wearing the backpack compared to either the control or the front pack condition. It was concluded that the use of a front pack results in a more upright posture in gait, when compared to a backpack carrying the same load.     

A review of current state-of-the-art control methods for lower-limb powered prostheses

Lower-limb prostheses aim to restore ambulatory function for individuals with lower-limb amputations. While the design of lower-limb prostheses is important, this paper focuses on the complementary challenge—the control of lower-limb prostheses. Specifically, we focus on powered prostheses, a subset of lower-limb prostheses, which utilize actuators to inject mechanical power into the walking gait of a human user.In this paper, we present a review of existing control strategies for lower-limb powered prostheses, including the control objectives, sensing capabilities, and control methodologies. We separate the various control methods into three main tiers of prosthesis control: High-level control for task and gait phase estimation, mid-level control for desired torque computation (both with and without the use of reference trajectories), and low-level control for enforcing the computed torque commands on the prosthesis. In particular, we focus on the high- and mid-level control approaches in this review. Additionally, we outline existing methods for customizing the prosthetic behavior for individual human users. Finally, we conclude with a discussion on future research directions for powered lower-limb prostheses based on the potential of current control methods and open problems in the field.     

Effect of backpack load on the head,cervical spine and shoulder postures in children during gait termination

Twelve boys with an average age of 9.9 years were instructed to carry backpacks that weighed 0%, 10% and 15% of their body weights (BWs) to complete planned and unplanned gait termination experiments. The craniohorizontal, craniovertebral and sagittal shoulder posture angles at the sagittal plane as well as the anterior head alignment and coronal shoulder posture angles at the coronal plane were analysed. Results revealed significantly smaller craniohorizontal and sagittal shoulder posture angles during planned gait termination and a significantly smaller sagittal shoulder posture angle during unplanned gait termination under loaded conditions compared with those at 0% BW backpacks. Furthermore, the coronal shoulder posture angles at 10% and 15% BW during planned and unplanned gait terminations were significantly larger than those at 0% BW. Therefore, subjects were more likely to have a forward head posture, rounded shoulder posture and increased lateral tilting of the shoulders during gait termination as backpack loads were increased. However, gait termination, whether planned or unplanned, did not elicit a remarkable effect on posture.     

基于Tsfresh-RF特征提取的人体步态识别算法

惯性传感器(IMU)由于尺寸小、价格低、精度高以及信息实时性强等优点, 在人体运动信息的获取与控制等方面得到广泛应用, 但在步态识别的时间序列特征提取和步态环境数据等方面还存在着明显的局限. 本文针对人体下肢步态识别特征提取的复杂性及适用性差等问题, 提出基于Tsfresh-RF特征提取的人体步态识别新方法. 首先, 利用IMU获取的人体步态数据集, 构建基于Tsfresh时间序列特征提取和随机森林(RF)的人体步态识别算法模型. 其次, 采用该算法对人体不同传感器位置进行实验, 完成爬梯、行走、转弯等9种人体运动步态的识别. 最后, 实验结果表明所提方法平均分类准确率达到91.0％, 显著高于传统的支持向量机(SVM)与朴素贝叶斯(NB)等方法的识别结果. 此外, 本文所提基于Tsfresh-RF特征提取的人体步态识别算法具有很好的鲁棒性, 将为后续下肢外骨骼机器人的控制提供有利依据.     

基于特征融合的步态识别算法

步态运动中包含人体形状信息和运动信息,目前步态识别算法多数基于单一信息,不能取得满意的识别结果。利用特征融合的思想,提出一种融合人体轮廓特征和下肢角度特征的步态识别算法。采用傅立叶描述子描述人体轮廓特征;区别于基于模型的运动特征提取方法,依据人体解剖学的知识获取下肢角度,计算代价较小;采用加权融合规则实现两类特征的融合。仿真结果表明,本算法的性能较基于单个特征的算法有明显的提高。     

基于列质量向量和SVM的步态识别

步态识别是根据人行走的方式来识别其身份,以其特有的优势作为一种身份识别手段。为了提高步态的识别率,提出了一种新方法,使用人体轮廓列质量向量表征特征信息,并使用支持向量机进行识别。根据人体轮廓的高度和宽度计算出步态周期,提取每个步态轮廓列质量向量,最后采用支持向量机进行分类识别。为了验证所提出方法的有效性,在CASIA步态数据库上进行了充足的实验,验证了该方法具有较高的识别率。     

Gait event detection based on inter-joint coordination using only angular information

The detection of gait events with wearable sensors is necessary for a robotic system interacting with walking people. Conventional gait phase detection methods are based on machine learning. However, this method cannot detect a gait event every gait cycle because it is difficult to extract characteristic points. Additionally, using only angular information for detection is beneficial because angular information is needed for the control and evaluation of the robots. This paper proposes a novel algorithm for the detection of heel contact and toe-off using the inter-joint coordination of the hip, knee, and ankle joints that has a lower-dimensional structure. The proposed algorithm derives the four planes in the angular space and finds the switching points of the planes. Seven participants walked on force plates that measured the force of the foot against the floor. The error was less than 0.035 s when the gait events were detected after calculating planes using the first gait datum. The change in the patterns of the inter-joint coordination reflected the change in gait phases. Although the data were calculated offline, the results show that the heel contact and toe-off could be detected as soon as the angles were sensed once the planes were derived.     

Mechanical design of powered prosthetic leg and walking pattern generation based on motion capture data

In this paper, we describe the design procedure of an above-knee powered prosthetic leg and an algorithm to generate appropriate gait patterns that are synchronized with the movement of the user. The developed prosthetic leg has powered knee and ankle joints for transfemoral amputees, and its weight and dimensions were determined on the basis of human body data. In particular, two degrees of freedom (roll and pitch axes) were adopted in the ankle joint to achieve dynamic balance control on uneven ground, and passive toe joints using a crank-rocker mechanism and torsional springs were attached at the foot to increase the walking stability. In addition, we developed a walking pattern simulator that is able to test the walking patterns of the powered prosthetic leg in the air. By attaching two inertial sensors on both thighs of the user and measuring both thigh motions, the per cent of gait cycle is suitably calculated from the proposed algorithm, and smooth gait motions are generated according to the gait cycle percent. Finally, walking patterns of the powered prosthetic leg were successfully generated by synchronizing to the human gait, and the generated gaits were analyzed by comparing them to the human gait.