基于智能手机的实时跌倒检测系统研究

为减少跌倒对老年人造成的伤害,并对跌倒进行实时检测,提出了一种基于Android智能手机的人体跌倒检测系统,手机安置于腰上采集手机加速度传感器数据,利用了姿态识别和跌倒检测相结合的算法,区分出跌倒行为和人体日正常常活动。当检测到异常跌倒时,报警信息以及从手机中GPS获取的位置被发送。仿真及实验表明：系统能够有效地识别出跌倒和日常行为,算法具有较高实时性、具有较高灵敏度和特异度。     

Differentiating slip-induced falls from normal walking and successful recovery after slips using kinematic measures

Slip-induced falls are prevalent and serious in occupational settings. Fall detection can minimise the adverse consequences caused by falls. However, a limitation in the existing fall detection research is that the fall indicators were predetermined without any theoretical and experimental basis. This study aimed to determine the optimal fall indicators for fall detection research by experimentally examining a comprehensive set of kinematic measures. The body kinematic measures were compared among normal walking, successful recovery after slips and slip-induced falls. We identified the kinematic measures that differ between falls and the selected non-fall activities (i.e. successful recovery and normal walking), especially at the early stage of loss-of-balance due to slips. Findings obtained from this study can enhance the understanding of kinematic differences between slip-induced falls and non-fall activities, and such knowledge is particularly useful for developing fall detection models.

Practitioner Summary: Slips have been reported to be a major cause of accidental falls. Findings from this study can help determine the kinematic measures that can effectively and efficiently differentiate slip-induced falls from successful recovery and normal walking. Such knowledge can help develop effective strategies to prevent slip-induced falls.     

可穿戴式跌倒检测智能系统设计

为提高对老年人跌倒检测的正确率,设计一种可穿戴式跌倒检测系统.研制基于三轴加速度计的跌倒检测设备,给出系统硬件和软件的实现方案;提出基于反向传播(BP)神经网络的跌倒检测算法,将训练好的网络参数植入研制的可穿戴式跌倒检测设备,实现对跌倒的实时检测.实验结果表明:所研制的跌倒检测智能系统能够有效地区分跌倒与非跌倒,正确率达97.37％.     

基于ZigBee的定位和人体跌倒检测系统

提出了一个具有跌倒定位和远程报警功能的无线跌倒监控系统。跌倒监测是基于人体跌倒过程中加速度曲线的变化特性,由三轴加速度传感器和ARM处理器实现;同时介绍了一种新颖的基于ZigBee的定位方法,当监测到人体跌倒时,一个带有跌倒位置的报警信息将立即发送到医护人员的移动手机上。实验结果表明,本系统可以100%监测到人体跌倒,提供精度为1 m的精确定位,使医护人员在5 s内收到跌倒报警信息。     

Deep learning for vision‐based fall detection system: Enhanced optical dynamic flow

Accurate fall detection for the assistance of older people is crucial to reduce incidents of deaths or injuries due to falls. Meanwhile, vision‐based fall detection system has shown some significant results to detect falls. Still, numerous challenges need to be resolved. The impact of deep learning has changed the landscape of the vision‐based system, such as action recognition. The deep learning technique has not been successfully implemented in vision‐based fall detection system due to the requirement of a large amount of computation power and requirement of a large amount of sample training data. This research aims to propose a vision‐based fall detection system that improves the accuracy of fall detection in some complex environments such as the change of light condition in the room. Also, this research aims to increase the performance of the pre‐processing of video images. The proposed system consists of Enhanced Dynamic Optical Flow technique that encodes the temporal data of optical flow videos by the method of rank pooling, which thereby improves the processing time of fall detection and improves the classification accuracy in dynamic lighting condition. The experimental results showed that the classification accuracy of the fall detection improved by around 3% and the processing time by 40–50 ms. The proposed system concentrates on decreasing the processing time of fall detection and improving the classification accuracy. Meanwhile, it provides a mechanism for summarizing a video into a single image by using dynamic optical flow technique, which helps to increase the performance of image preprocessing steps.     

基于递归神经网络的跌倒检测系统

针对现有跌倒检测方法存在适应性差和功能较单一等问题，引入递归神经网络，通过发掘位置传感器数据之间的内在联系提高检测跌倒行为的效果。首先，设计了传感器、训练与检测输入数据的序列化表示方法，为发掘其中与跌倒和接近跌倒行为相关的内在关联提供了基础；接着，给出了用于跌倒检测的RNN训练算法以及基于RNN的跌倒检测算法，将跌倒检测转换为输入序列的分类问题；最后，在前期实现的基于分布式神经元大规模RNN系统的基础上，在Spark平台上实现了基于RNN的跌倒检测系统，使用Fall_adl_data数据集进行了测试与分析，验证了其能有效提高跌倒检测的准确率和召回率，F值相比现有跌倒检测系统提高12%和7%，同时能有效检测出接近跌倒的行为，有助于及时采取保护措施减少伤害。     

A supervised approach to automatically extract a set of rules to support fall detection in an mHealth system

Automatic fall detection is a major issue in the health care of elderly people. In this task the ability to discriminate in real time between falls and normal daily activities is crucial. Several methods already exist to perform this task, but approaches able to provide explicit formalized knowledge and high classification accuracy have not yet been developed and would be highly desirable. To achieve this aim, this paper proposes an innovative and complete approach to fall detection based both on the automatic extraction of knowledge expressed as a set of IF-THEN rules from a database of fall recordings, and on its use in a mobile health monitoring system. Whenever a fall is detected by this latter, the system can take immediate actions, e.g. alerting medical personnel. Our method can easily overcome the limitations of other approaches to fall detection. In fact, thanks to the knowledge gathering, it overcomes both the difficulty faced by a human being dealing with many parameters and trying to find out which are the most suitable, and also the need to apply a laborious trial-and-error procedure to find the values of the related thresholds. In addition, in our approach the extracted knowledge is processed in real time by a reasoner embedded in a mobile device, without any need for connection to a remote server. This proposed approach has been compared against four other classifiers on a database of falls simulated by volunteers, and its discrimination ability has been shown to be higher with an average accuracy of 91.88%. We have also carried out a very preliminary experimental phase. The best set of rules found by using the previous database has allowed us to achieve satisfactory performance in these experiments as well. Namely, on these real-world falls the obtained results in terms of accuracy, sensitivity, and specificity are of about 92%, 86%, and 96%, respectively.     

基于双摄像头的摔倒检测技术

随着人口老龄化趋势的加快, 老人独居现象增多, 为了减少老人摔倒所带来的伤害, 本文对基于双摄像头的摔倒检测技术进行研究. 针对Vibe算法在运动目标检测过程中存在的鬼影问题, 结合了帧间差分法进行鬼影区域的判断, 加快了鬼影的消除, 避免了其干扰. 利用人体外接矩形对检测到的人体进行标记, 求取出人体运动过程中高度、外接矩形高宽比、质心、Hu矩特征, 通过基于阈值分析法和支持向量机(SVM)的摔倒检测算法判断是否摔倒. 为了提高摔倒行为的检测率, 提出采用双摄像头进行联合判断. 实验结果表明, 系统能有效识别摔倒与其他日常行为, 算法准确度高、实时性好.     

Optimal fall indicators for slip induced falls on a cross-slope

Slip-induced falls are among the most common cause of major occupational injuries in the UK as well as being a major public health concern in the elderly population. This study aimed to determine the optimal fall indicators for fall detection models which could be used to reduce the detrimental consequences of falls. A total of 264 kinematic variables covering three-dimensional full body model translation and rotational measures were analysed during normal walking, successful recovery from slips and falls on a cross-slope. Large effect sizes were found for three kinematic variables which were able to distinguish falls from normal walking and successful recovery. Further work should consider other types of daily living activities as results show that the optimal kinematic fall indicators can vary considerably between movement types.

Practitioner Summary: Fall detection models are used to minimise the adverse consequences of slip-induced falls, a major public health concern. Optimal fall indicators were derived from a comprehensive set of kinematic variables for slips on a cross-slope. Results suggest robust detection of falls is possible on a cross-slope but may be more difficult than level walking.     

A system for ubiquitous fall monitoring at home via a wireless sensor network and a wearable mote

Accidental falls of our elderly, and physical injuries resulting, represent a major health and economic problem. Falls are the most common cause of serious injuries and are a major health threat in the stratum of older population. Early detection of a fall is a key factor when trying to provide adequate care to elderly person who has suffered an accident at home. Therefore, the detection of falls in the elderly remains a major challenge in the field of public health. Specific actions aimed at the fall detection can provide urgent care which allows, on the other hand, drastically reduce the cost of medical care, and improve primary care service. In this paper, we present a support system for detecting falls of an elder person by the combination of a wearable wireless sensor node based on an accelerometer and a static wireless non-intrusive sensory infrastructure based on heterogeneous sensor nodes. This previous infrastructure called DIA (Dispositivo Inteligente de Alarma, in Spanish) is an AAL (Ambient Assisted Living) system that allows to infer a potential fall. This inference is reinforced for prompt attention by a specific sensorisation at portable node sensor in order to help distinguish between falls and daily activities of assisted person. The wearable node will not determine a falling situation, it will advice the reasoner layer about specific acceleration patterns that could, eventually, imply a falling. Is at the higher layer where the falling is determined from the whole context produced by mesh of fixed nodes. Experimental results have shown that the proposed system obtains high reliability and sensitivity in the detection of the fall.     

A framework for the elderly first aid system by integrating vision-based fall detection and BIM-based indoor rescue routing

The occurrence of falls among older adults may result in life-threatening injuries and accidental deaths due to their vulnerability. As such, an advanced first aid system is significantly necessary to accurately detect falls and provide prompt assistance. However, current research primarily focused on fall prevention, fall detection, and first aid services after falling, thus lacking studies dealing with a systematic solution. To address this issue, the present research proposes an integrated framework for the elderly first aid system in an indoor environment using computer vision and building information model (BIM) techniques, which consists of three primary components: a vision-based module for fall detection, a cloud server (internet), and a BIM-based module for rescue routing. The experimental results showed that the proposed method could achieve 94.1% precision in identifying the fall status of older adults (i.e., falling or non-falling). Also, the proposed method enabled to automatically generate a rescue route in consideration of the routing accessibility for first aid in a BIM environment. The framework proposed in this study will improve the efficiency of the elderly first aid when falls occur, with shortening the rescue time to mitigate injury severity.     

一种防跌倒预警系统的研究与实现

跌倒是造成世界上意外伤害死亡的第二大原因,如何预防跌倒已成为保障老人生命的关键。目前常见 “跌倒报警器”的传感模块一般采用单一的三轴加速度计,测量精度受限,仅能实现人体跌倒后的报警功能而不 能实现跌倒前的预警。文章设计并实现了一种基于 MEMS 惯性传感单元的防跌倒预警器,率先设计了含“三轴 加速度计+三轴陀螺仪+三轴磁力计”的高精度多模态传感模块,内嵌跌倒预警算法,并通过蜂鸣器和振动器警 示。对九名健康年轻实验对象进行了总计 81 次的跌倒实验,系统结合基于阈值的跌倒预警算法,结果表明,其 检测灵敏度可达 98.61% 且特异度为 98.61%,平均预警时间为 300 ms。未来研究将嵌入全球移动通信系统(Global System For Mobile, GSM)、全球定位系统(Global Positioning System, GPS)等电路模块功能及配备穿戴式安全气 囊,有望在易跌人群中实现实时防护和及时救治。     

基于穿戴式平台的老人摔倒监测系统设计

针对老年人跌倒伤害预防问题,基于人体躯域网络可穿戴检测平台,设计了一种人体摔倒生理状态检测系统.系统主要包括摔倒状态检测模块,人体生理状态检测模块,GPS定位模块以及远程监护模块等.当老年人摔倒发生时,摔倒状态检测模块通过三轴加速度传感器检测,确认摔倒后立刻与远程监护平台通信,告知监护人,并通过穿戴式生理状态检测模块实时监测其心率信息,利用GPS定位,通过无线通信的方式将摔倒位置以及生理信息实时反馈给监护人.实验结果表明:该系统可以有效监测老人摔倒状态和生理状态,对及时救助有很大的帮助,具有良好的社会意义.     

基于特征自动提取的跌倒检测算法

跌倒是导致老年人受伤甚至死亡的主要原因。准确及时的跌倒检测系统可以帮助跌倒者获得紧急救援。 目前基于传感器的跌倒检测方法主要利用人工设计提取的信号特征来区分跌倒和非跌倒运动,但人工提取的特征往往会限制算法的精确度,增大算法时延。为提高跌倒检测的精确度和实时性,本文提出了一种基于深度学习的跌倒检测算法。该算法可以自动提取数据特征,实现从原始数据到检测结果的端到端的处理。算法模型主要由两层级联的长短期记忆（Long Short-Term Memory, LSTM）循环神经网络组成,通过神经网络提取加速度计和陀螺仪数据内部的特征,并判断是否有跌倒状况发生。我们使用两个公开数据集MobiAct和SisFall对算法性能进行评估。 实验结果显示,算法在两个数据集都达到了较高的精确度（99.58%以上）和较低的时延（2.2毫秒以内）。     

基于视频和人体姿态估计的老年人摔倒监测研究

人口老龄化所带来的养老服务问题是现代社会面临的严重问题。例如在很多国家跌倒是造成老年人因伤致死的最大原因,因此如何对老年人进行自动摔倒监测就成为养老服务亟待解决的问题。目前,在室内摔倒监测领域中,基于可穿戴设备和基于环境传感器等主流摔倒监测方法面临着设备复杂、成本较高等问题。鉴于此,将人体姿态估计引入摔倒监测领域,提出了一种基于2D视频的摔倒监测算法。首先利用OpenPose数据集提取原始数据中人体关节的位置;其次利用这些具有增强特征的数据构建静态分类模型和动态分类模型;最后,在3个公共摔倒数据集上进行模型训练和摔倒监测的测试,取得了较好的效果,可以为摔倒监测相关研究提供一定的参考。     

Detecting unseen falls from wearable devices using channel-wise ensemble of autoencoders

A fall is an abnormal activity that occurs rarely, so it is hard to collect real data for falls. It is, therefore, difficult to use supervised learning methods to automatically detect falls. Another challenge in automatically detecting falls is the choice of engineered features. In this paper, we formulate fall detection as an anomaly detection problem and propose to use an ensemble of autoencoders to learn features from different channels of wearable sensor data trained only on normal activities. We show that the traditional approach of choosing a threshold as the maximum of the reconstruction error on the training normal data is not the right way to identify unseen falls. We propose two methods for automatic tightening of reconstruction error from only the normal activities for better identification of unseen falls. We present our results on two activity recognition datasets and show the efficacy of our proposed method against traditional autoencoder models and two standard one-class classification methods.     

老年人运动状态监测和跌倒报警系统

体育锻炼是促进老年人健康长寿的有效手段之一。为了对老年人的运动状态进行实时监测,掌握运动状态参数,并能够对老年人不慎意外踏空或者某种疾病突发导致的跌倒及时报警,设计一种能够实时监测老年人跌倒动作发生并发送定位及报警信息给远程接收端的便携式监测系统。系统采用腰部三轴加速度传感器实时采集人体运动姿态数据;使用嵌入式处理器和无线网络实现数据处理、无线传输和远程报警;通过三级阈值的人体跌倒检测算法,实现人体跌倒姿态变化的加速度特征提取,对人体运动状态进行分级,预测严重的跌倒行为。实验结果表明：该系统具有性能稳定、正确率高和轻巧方便等特点,非常适合老年人穿戴使用,可保障老年人运动安全,应用前景广阔。     

Introducing the use of depth data for fall detection

Current emergency systems for elderly contain at least one sensor (button or accelerometer), which has to be worn or pressed in case of emergency. If elderly fall and loose their consciousness, they are not able to press the button anymore. Therefore, autonomous systems to detect falls without wearing any devices are needed. This paper presents three different non-invasive technologies: the use of audio, 2D sensors (cameras) and introduces a new technology for fall detection: the Kinect as 3D depth sensor. Our fall detection algorithms using the Kinect are evaluated on 72 video sequences, containing 40 falls and 32 activities of daily living. The evaluation results are compared with State-of-the-Art approaches using 2D sensors or microphones.     

基于内距离形状上下文的跌倒检测方法

在全球社会老龄化的大背景下,老年人的身体健康状况和晚年生活质量需要更多的关注。跌倒在老年人群中发生率高并且带来的后果比较严重。文中提出一种应用于家庭场景的基于Inner-Distance形状上下文（ Inner-Distance Shape Context,IDSC）的跌倒检测方法。该方法通过Inner-Distance形状上下文获得视频帧前景形状的描述信息,使用形状匹配方法对视频序列中人体形状变化进行量化。对形变量化信息使用动态时间规整（ Dynamic Time Warping,DTW）方法实现跌倒行为的判定。实验结果表明该方法可有效、快速地判断跌倒,提取结果具有较好的查准率和查全率。     

基于Kinect体感传感器的老年人跌倒自动检测

跌倒是独居老人最主要的意外风险之一,为快速有效获取跌倒信息,使老年人得到及时救助,提出一种基于Kinect体感传感器的人体跌倒自动检测方法,利用Kinect深度图像技术获取人体深度图像前景图,建立前景图三维包围盒,通过实时计算的三维包围盒的长、宽、高数值以及该数值的变化速度,判断人体跌倒是否发生。利用遮挡融合算法,解决了人体躯干被障碍物部分遮挡时,跌倒事件的检测和判定。在室内居家环境下进行了26种测试场景实验,检测误报率为2.0%~6.0%,漏报率为0~4.0%。该方法可以较为准确地实现人体跌倒自动检测。