面向智能家居的挥手识别算法

目的 用手势控制家电是智能家居发展的趋势之一,传统的静态手势识别算法难以适应复杂的居家环境,特别当使用广角相机或环境干扰大时,为此提出一种动态的挥手识别算法,可以对视频序列中的挥手动作做出响应,以达到控制家电的目的。方法 挥手动作具有周期性且频率相对稳定,算法首先调整长滤波器和短滤波器使其检测到视频内周期性运动的区域,然后利用人手识别算法对周期性运动区域进行验证并确认人手。结果 通过与主流的手势识别算法的对比,在复杂环境下,本文算法将成功次数提高了3%,误触发次数降低了44%,响应时间也降低了近0.4 s。结论 实验结果表明,算法能够满足实际应用需求。此外,算法不基于运动目标检测,运算量极低,可以在较高的图像分辨率下实时运行,并能被移植到嵌入式平台下。     

Combining discriminative spatiotemporal features for daily life activity recognition using wearable motion sensing suit

Motion sensing plays an important role in the study of human movements, motivated by a wide range of applications in different fields, such as sports, health care, daily activity, action recognition for surveillance, assisted living and the entertainment industry. In this paper, we describe how to classify a set of human movements comprising daily activities using a wearable motion capture suit, denoted as FatoXtract. A probabilistic integration of different classifiers recently proposed is employed herein, considering several spatiotemporal features, in order to classify daily activities. The classification model relies on the computed confidence belief from base classifiers, combining multiple likelihoods from three different classifiers, namely Naïve Bayes, artificial neural networks and support vector machines, into a single form, by assigning weights from an uncertainty measure to counterbalance the posterior probability. In order to attain an improved performance on the overall classification accuracy, multiple features in time domain (e.g., velocity) and frequency domain (e.g., fast Fourier transform), combined with geometrical features (joint rotations), were considered. A dataset from five daily activities performed by six participants was acquired using FatoXtract. The dataset provided in this work was designed to be extremely challenging since there are high intra-class variations, the duration of the action clips varies dramatically, and some of the actions are quite similar (e.g., brushing teeth and waving, or walking and step). Reported results, in terms of both precision and recall, remained around 85 %, showing that the proposed framework is able to successfully classify different human activities.     

基于语音识别的智能家居系统研究

针对智能家居系统中信息不能随时随地进行控制及其交流方式不流畅的问题,融合电话公用网和家庭网络设计了一个基于ARM9和语音识别技术的智能家居系统.该系统采用RASTA滤波方法去除语音信号中夹杂的卷积信道噪声,采用改进的动态时间规正(DTW)算法对语音命令进行识别.     

Situation-centered goal reinforcement of activities of daily living in smart home environments

Older adults with early-stage dementia (ED) can experience confusion or lack clarity when performing routine activities of daily living (ADLs). These circumstances predispose the older adult to safety-critical and often risky situations. A safety-critical risky situation is one that constitutes a hazard. To support independent living, a sensor-laden smart environment can be employed to mitigate such hazards. In this paper, we propose a situation-centered goal reinforcement framework that supports older adults with ED in their decision making, and guides them through their ADL in order to fulfill their goal or intention and avoid hazards. First, we employ an LSTM (Long Short-Term Memory) model to infer the current goal of the resident, using their previously observed normal ADL patterns. Secondly, we identify potentially risky situations in their currently observed goal path. We then incorporate a situ-learning agent (SLA) that helps an inhabitant to make the right decision, thus preventing adverse events while guiding her through the task sequence that leads to her goal state. In addition, we use a naïve agent to simulate episodes of confusion similar to those that might be experienced by older adults with ED. We validated our method against an open-source dementia dataset (Quesada et al., 2015) by considering four types of ADLs as case studies. We achieved an accuracy of 90.1% for our goal inference model, higher than the accuracies reported by related studies. We also reported other metrics including precision, recall and f1-score for goal inference model. Finally, SLA's action recommendations relevance was evaluated accordingly.     

Integration of discriminative and generative models for activity recognition in smart homes

Activity recognition in smart homes enables the remote monitoring of elderly and patients. In healthcare systems, reliability of a recognition model is of high importance. Limited amount of training data and imbalanced number of activity instances result in over-fitting thus making recognition models inconsistent. In this paper, we propose an activity recognition approach that integrates the distance minimization (DM) and probability estimation (PE) approaches to improve the reliability of recognitions. DM uses distances of instances from the mean representation of each activity class for label assignment. DM is useful in avoiding decision biasing towards the activity class with majority instances; however, DM can result in over-fitting. PE on the other hand has good generalization abilities. PE measures the probability of correct assignments from the obtained distances, while it requires a large amount of data for training. We apply data oversampling to improve the representation of classes with less number of instances. Support vector machine (SVM) is applied to combine the outputs of both DM and PE, since SVM performs better with imbalanced data and further improves the generalization ability of the approach. The proposed approach is evaluated using five publicly available smart home datasets. The results demonstrate better performance of the proposed approach compared to the state-of-the-art activity recognition approaches.     

Evidential fusion of sensor data for activity recognition in smart homes

Advances in technology have provided the ability to equip the home environment with a layer of technology to provide a truly ‘Smart Home’. These homes offer improved living conditions and levels of independence for the population who require support with both physical and cognitive functions. At the core of the Smart Home is a collection of sensing technology which is used to monitor the behaviour of the inhabitant and their interactions with the environment. A variety of different sensors measuring light, sound, contact and motion provide sufficient multi-dimensional information about the inhabitant to support the inference of activity determination. A problem which impinges upon the success of any information analysis is the fact that sensors may not always provide reliable information due to either faults, operational tolerance levels or corrupted data. In this paper we address the fusion process of contextual information derived from uncertain sensor data. Based on a series of information handling techniques, most notably the Dempster–Shafer theory of evidence and the Equally Weighted Sum operator, evidential contextual information is represented, analysed and merged to achieve a consensus in automatically inferring activities of daily living for inhabitants in Smart Homes. Within the paper we introduce the framework within which uncertainty can be managed and demonstrate the effects that the number of sensors in conjunction with the reliability level of each sensor can have on the overall decision making process.     

基于本体的智能空间用户活动识别方法

为提高智能空间中用户活动识别的准确率,提出一种基于本体的活动识别方法.通过分析智能家居中的上下文语义及实体间的关联,建立了明确的活动领域本体,结合上下文知识和用户模型,定义相关用户活动状态,进而采用语义推理实现了用户活动的识别.实验验证了该方法的有效性和可扩展性,并将识别的时间效率与HMM识别法进行了比较,表明了该方法的识别时间低于HMM识别法.     

基于智能手机传感器的人体活动识别

人体活动识别是上下文感知系统及其应用中一个具有挑战性的研究问题。目前,关于人体活动识别的研究主要使用一些基于监督学习或半监督学习的统计方法来构建识别模型。然而,考虑到识别活动类型本身具有的复杂性和多样性,当前的人体活动识别系统不能取得较好的识别效果。针对这一问题,通过智能手机的三维加速度和陀螺仪传感器信息来提取人体活动的特征向量,选择四种典型的统计学习方法（分别是K-近邻算法、支持向量机、朴素贝叶斯网络以及基于朴素贝叶斯网络的AdaBoost算法）分别创建人体活动的识别模型,最后通过模型决策得到最优的人体活动识别模型。实验结果表明,通过模型决策选择的识别模型对人体活动识别准确率达到92%,取得很好的识别效果。     

Advanced issues in artificial intelligence and pattern recognition for intelligent surveillance system in smart home environment

During the last decades, many researchers in image processing and AI community have been focused on developing image and video analysis and understanding. However, despite their extensive efforts on these, there are still several significant challenges such as robust object segmentation and tracking, motion feature extraction, context modeling, and machine learning algorithms. Therefore, more advanced related issues should be taken into account. We have selected nine research papers whose topics are strongly related to the intelligent surveillance system in smart home environment.     

A ubiquitous smart home for elderly

One major challenge to successful aging is the capability to preserve health, or from another perspective to avoid disease. Unfortunately, a large percentage of the elderly people are living with chronic diseases or disabilities. Home care technologies and other emerging technologies have the potential to play a major role in home-based health care approach. The advent of sensor technology, in addition to telecom industry has made this possible. The main goal of the presented research in this paper is to develop a cost-effective user-friendly telehealth system to serve the elderly and disabled people in the community. The research also aims at utilizing the state-of-the-art advances in medical instrumentation technology to establish a continuous communication link between patients and caregivers and allow physicians to offer help when needed. Hence, we are presenting here an integrated user-friendly model of a smart home which provides telemedicine for elderly at home. The general problem addressed in this paper is that of offering a smart environment which monitors the elderly continuously as he moves around at home, and sends an emergency call for help in case of an occurrence of an accident or a severe health problem. The paper focuses on implementation details and practical considerations of integrating the diverse technologies into a working system.     

Face recognition for smart environments

Smart environments, wearable computers, and ubiquitous computing in general are the coming “fourth generation” of computing and information technology. But that technology will be a stillbirth without new interfaces for interaction, minus a keyboard or mouse. To win wide consumer acceptance, these interactions must be friendly and personalized; the next generation interfaces must recognize people in their immediate environment and, at a minimum, know who they are. In this article, the authors discuss face recognition technology, how it works, problems to be overcome, current technologies, and future developments and possible applications. Twenty years ago, the problem of face recognition was considered among the most difficult in artificial intelligence and computer vision. Today, however, there are several companies that sell commercial face recognition software that is capable of high-accuracy recognition with databases of more than 1,000 people. The authors describe the face recognition technology used, explaining the algorithms for face recognition as well as novel applications, such as behavior monitoring that assesses emotions based on facial expressions     

面向结构化数据集的敏感属性识别与分级算法

如何对生产环境中经代码混淆的结构化数据集的敏感属性（字段）进行自动化识别、分类分级,已成为对结构化数据隐私保护的瓶颈。提出一种面向结构化数据集的敏感属性自动化识别与分级算法,利用信息熵定义了属性敏感度,通过对敏感度聚类和属性间关联规则挖掘,将任意结构化数据集的敏感属性进行识别和敏感度量化;通过对敏感属性簇中属性间的互信息相关性和关联规则分析,对敏感属性进行分组并量化其平均敏感度,实现敏感属性的分类分级。实验表明,该算法可识别、分类、分级任意结构化数据集的敏感属性,效率和精确率更高;对比分析表明,该算法可同时实现敏感属性的识别与分级,无须预知属性特征、敏感特征字典,兼顾了属性间的相关性和关联关系。     

Latent feature learning for activity recognition using simple sensors in smart homes

Multimedia Tools and Applications - Activity recognition is an important step towards monitoring and evaluating the functional health of an individual, and it potentially promotes human-centric...     

Combining ontological and temporal formalisms for composite activity modelling and recognition in smart homes

Activity recognition is essential in providing activity assistance for users in smart homes. While significant progress has been made for single-user single-activity recognition, it still remains a challenge to carry out real-time progressive composite activity recognition. This paper introduces a hybrid ontological and temporal approach to composite activity modelling and recognition by extending existing ontology-based knowledge-driven approach. The compelling feature of the approach is that it combines ontological and temporal knowledge representation formalisms to provide powerful representation capabilities for activity modelling. The paper describes in detail ontological activity modelling which establishes relationships between activities and their involved entities, and temporal activity modelling which defines relationships between constituent activities of a composite activity. As an essential part of the model, the paper also presents methods for developing temporal entailment rules to support the interpretation and inference of composite activities. In addition, this paper outlines an integrated architecture for composite activity recognition and elaborated a unified activity recognition algorithm which can support the recognition of simple and composite activities. The approach has been implemented in a feature-rich prototype system upon which testing and evaluation have been conducted. Initial experimental results have shown average recognition accuracy of 100% and 88.26% for simple and composite activities, respectively.     

Mutual authentication scheme for smart devices in IoT-enabled smart home systems

The emergence of Internet of Things (IoT) technology has yielded a firm technical basis for the construction of a smart home. A smart home system offers occupants the convenience of remote control and automation of household systems. However, there are also potential security risks associated with smart home technologies. The security of users in a smart home environment is related to their life and possessions. A significant amount of research has been devoted to studying the security risks associated with IoT-enabled smart home systems. The increasing intelligence of devices has led to a trend of independent authentication between devices in smart homes. Therefore, mutual authentication for smart devices is essential in smart home systems. In this paper, a mutual authentication scheme is proposed for smart devices in IoT-enabled smart home systems. Signature updates are provided for each device. In addition, with the assistance of a home gateway, the proposed scheme can enable devices to verify the identity of each other. According to the analysis, the proposed scheme is secure against a forged SD or a semi-trusted HG. The computational cost of the proposed scheme in the simulation is acceptable for the application in smart home systems.     

面向灵巧操作的视觉目标识别

为了能够实现灵巧手对目标物体进行精准操作,研究了一种利用Kinect检测出目标物体,在帧差法的基础上对获取的深度进行背景相减,获取出目标物体的运动点,在此基础上利用获取的目标物体的特征采用T-S模糊逻辑判断出目标物体的方法,以BH8-280对目标物体进行抓取实验为例,在实验中,Kinect在帧差法的基础上检测出目标物体的位姿,大小,形状,以此为基础建立起T-S模糊逻辑系统,判断出目标物体的属性和类别,通过实验结果进一步说明了利用本文研究的方法显著地提高了判断物体的准确率和效率,为灵巧手的精细控制抓取奠定了基础。     

智能家居虚拟场景设计与实现

面向智能家居应用,以Unity 3D为虚拟现实开发平台,给出了用虚拟智能化家庭场景实现虚拟场景家电设备及环境监测设备的模型设计。平台中的虚拟人可以在虚拟场景中自由漫游,并且通过虚拟人手中的终端设备,实时家电控制并获得环境监测设备的实时数据,使得家庭控制更加生动形象,实现虚拟与现实的融合。虚拟场景的设计有助于智能家居的宣传、培训和展示,同时让用户通过远程操作,也可以体验到真实的智能家居系统,零距离展示智能家居实验室的科研成果。     

Emotion-relevant activity recognition based on smart cushion using multi-sensor fusion

More and more common activities are leading to a sedentary lifestyle forcing us to sit several hours every day. In-seat actions contain significant hidden information, which not only reflects the current physical health status but also can report mental states. Considering this, we design a system, based on body-worn inertial sensors (attached to user’s wrists) combined with a pressure detection module (deployed on the seat), to recognise and monitor in-seat activities through sensor- and feature-level fusion techniques. Specifically, we focus on four common basic emotion-relevant activities (i.e. interest-, frustration-, sadness- and happiness-related). Our results show that the proposed method, by fusion of time- and frequency-domain feature sets from all the different deployed sensors, can achieve high accuracy in recognising the considered activities.