基于HMM-FNN模型的复杂动态手势识别

复杂动态手势识别是利用视频手势进行人机交互的关键问题.提出一种HMM-FNN模型结构.它整合了隐马尔可夫模型对时序数据的建模能力与模糊神经网络的模糊规则构建与推理能力,并将其应用到复杂动态手势的识别中.复杂动态手势具备两大特点:运动特征的可分解性与定义描述的模糊性.针对这两种特性,复杂手势被分解为手形变化、2D平面运动与Z轴方向运动3个子部分,分别利用HMM进行建模,HMM模型对观察子序列的似然概率被作为FNN的模糊隶属度,通过模糊规则推理,最终得到手势的分类类别.HMM-FNN方法将高维手势特征分解为低维子特征序列,降低了模型的复杂度.此外,它还可以充分利用人的经验辅助模型结构的创建与优化.实验表明,该方法是一种有效的复杂动态手势识别方法,并且优于传统的HMM模型方法.     

Personalized gesture interactions for cyber-physical smart-home environments

A gesture-based interaction system for smart homes is a part of a complex cyber-physical environment, for which researchers and developers need to address major challenges in providing personalized gesture interactions. However, current research efforts have not tackled the problem of personalized gesture recognition that often involves user identification. To address this problem, we propose in this work a new event-driven service-oriented framework called gesture services for cyber-physical environments (GS-CPE) that extends the architecture of our previous work gesture profile for web services (GPWS). To provide user identification functionality, GS-CPE introduces a two-phase cascading gesture password recognition algorithm for gesture-based user identification using a two-phase cascading classifier with the hidden Markov model and the Golden Section Search, which achieves an accuracy rate of 96.2% with a small training dataset. To support personalized gesture interaction, an enhanced version of the Dynamic Time Warping algorithm with multiple gestural input sources and dynamic template adaptation support is implemented. Our experimental results demonstrate the performance of the algorithm can achieve an average accuracy rate of 98.5% in practical scenarios. Comparison results reveal that GS-CPE has faster response time and higher accuracy rate than other gesture interaction systems designed for smart-home environments.     

Adaptive visual gesture recognition for human–robot interaction using a knowledge-based software platform

In human–human communication we can adapt or learn new gestures or new users using intelligence and contextual information. Achieving natural gesture-based interaction between humans and robots, the system should be adaptable to new users, gestures and robot behaviors. This paper presents an adaptive visual gesture recognition method for human–robot interaction using a knowledge-based software platform. The system is capable of recognizing users, static gestures comprised of the face and hand poses, and dynamic gestures of face in motion. The system learns new users, poses using multi-cluster approach, and combines computer vision and knowledge-based approaches in order to adapt to new users, gestures and robot behaviors. In the proposed method, a frame-based knowledge model is defined for the person-centric gesture interpretation and human–robot interaction. It is implemented using the frame-based Software Platform for Agent and Knowledge Management (SPAK). The effectiveness of this method has been demonstrated by an experimental human–robot interaction system using a humanoid robot ‘Robovie’.     

Head gestures for perceptual interfaces: The role of context in improving recognition

Head pose and gesture offer several conversational grounding cues and are used extensively in face-to-face interaction among people. To accurately recognize visual feedback, humans often use contextual knowledge from previous and current events to anticipate when feedback is most likely to occur. In this paper we describe how contextual information can be used to predict visual feedback and improve recognition of head gestures in human–computer interfaces. Lexical, prosodic, timing, and gesture features can be used to predict a user's visual feedback during conversational dialog with a robotic or virtual agent. In non-conversational interfaces, context features based on user–interface system events can improve detection of head gestures for dialog box confirmation or document browsing. Our user study with prototype gesture-based components indicate quantitative and qualitative benefits of gesture-based confirmation over conventional alternatives. Using a discriminative approach to contextual prediction and multi-modal integration, performance of head gesture detection was improved with context features even when the topic of the test set was significantly different than the training set.     

姿态情绪识别研究综述

从姿态信息采集、姿态情绪特征提取、姿态情绪识别算法和姿态情绪数据库几个方面对国内外姿态情绪识别研究进行了全面的总结,分析了姿态情绪识别研究存在的难点和挑战,提出姿态情绪识别的关键是姿态情绪特征提取和姿态情绪数据库的建立,最后探讨了姿态情绪识别研究的发展方向.     

面向虚拟现实的层次化交互手势建模与理解方法

虚拟现实中的交互手势包括多种不同类型,层次化建模方法避免了采用单一模型导致效率不高的问题.识别是一个由粗到精的过程,通过滑动窗技术实时提取手势的统计特征,实现手势类别的粗略划分,然后采用不同方法对各类手势进行分析.交互环境及上下文信息用以辅助手势的类别划分,提高了识别效率.最后通过虚拟家居系统对该方法进行了验证.     

Adaptive mixture-of-experts models for data glove interface with multiple users

Hand gestures have great potential to act as a computer interface in the entertainment environment. However, there are two major problems when implementing the hand gesture-based interface for multiple users, the complexity problem and the personalization problem. In order to solve these problems and implement multi-user data glove interface successfully, we propose an adaptive mixture-of-experts model for data-glove based hand gesture recognition models which can solve both the problems.The proposed model consists of the mixture-of-experts used to recognize the gestures of an individual user, and a teacher network trained with the gesture data from multiple users. The mixture-of-experts model is trained with an expectation-maximization (EM) algorithm and an on-line learning rule. The model parameters are adjusted based on the feedback received from the real-time recognition of the teacher network.The model is applied to a musical performance game with the data glove (5DT Inc.) as a practical example. Comparison experiments using several representative classifiers showed both outstanding performance and adaptability of the proposed method. Usability assessment completed by the users while playing the musical performance game revealed the usefulness of the data glove interface system with the proposed method.     

基于特征包支持向量机的手势识别

针对类肤色信息或复杂背景的影响,难以通过手势分割得到精确手势轮廓而对后期手势识别率与实时交互的影响,提出了一种基于特征包支持向量机(BOF-SVM)的手势识别方法。采用SIFT算法提取手势图像局部不变性特征点,将手势局部特征向量(尺度不变特征变换(SIFT)描述子)进行K-means聚类生成视觉码书,并通过视觉码书量化每一幅手势图像的视觉码字集合,以此获得手势图像的固定维数的表征向量来训练支持向量机(SVM)多类分类器。该方法只需框定手势所在区域,无需精确地分割人手。实验表明,该方法对9种交互手势的平均识别率达到92.1%,并具有很好的鲁棒性及实时性,能适应环境的变化。     

Seeking common ground while reserving differences in gesture elicitation studies

Gesture elicitation studies have been frequently conducted in recent years for gesture design. However, most elicitation studies adopted the frequency ratio approach to assign top gestures derived from end-users to the corresponding target tasks, which may cause the results get caught in local minima, i.e., the gestures discovered in an elicitation study are not the best ones. In this paper, we propose a novel approach of seeking common ground while reserving differences in gesture elicitation research. To verify this point, we conducted a four-stage case study on the derivation of a user-defined mouse gesture vocabulary for web navigation and then provide new empirical evidences on our proposed method, including 1) gesture disagreement is a serious problem in elicitation studies, e.g., the chance for participants to produce the same mouse gesture for a given target task without any restriction is very low, below 0.26 on average; 2) offering a set of gesture candidates can improve consistency; and 3) benefited from the hindsight effect, some unique but highly teachable gestures produced in the elicitation study may also have a chance to be chosen as the top gestures. Finally, we discuss how these findings can be applied to inform all gesture-based interaction design.

     

多尺度卷积特征融合的SSD手势识别算法

为了提高对中小占比手势识别的准确性与稳定性,提出了一种多尺度卷积特征融合的SSD(single shot multibox detector)手势识别方法。该方法突出表现在两大方面,其一,在原始的SSD算法的多尺度卷积检测方法基础上,引入了不同卷积层的特征融合思想,经过空洞卷积下采样操作与反卷积上采样操作,实现网络结构中的浅层视觉卷积层与深层语义卷积层的融合,代替原有的卷积层用于手势识别,以提高模型对中小目标手势的识别精度;其二,为了解决正负样本不均衡导致分类性能差的问题,提出一种改进的损失函数,以提升模型对目标手势的分类能力。在手势识别公开的数据集上的实验结果表明,与SSD和Faster R-CNN等识别方法相比,能够在保持较高的手势检测精度的同时,又具有较好的鲁棒性与检测速度。     

基于光流的动态手势识别

手势识别是人机交互中的重要组成部分，文章针对基于光流PCA（主分量分析）和DTW（动态时间规整）进行命令手势识别。利用块相关算法计算光流，并通过主分量分析得到降维的投影系数，以及手掌区域的质心作为混合特征向量。针对该混合特征向量定义了新的加权距离测度，并用DTW对手势进行匹配。针对9个手势训练和识别，识别率达到92％。     

一种基于深度图像的静态手势神经网络识别方法

静态手势识别是以手势驱动的人机交互系统的核心技术。针对静态手势识别问题,提出了一种基于深度图像进行静态手势识别的方法。为了消除静态手势识别过程中的平移、旋转和缩放不变性,提取手势轮廓的Hu不变矩,并以Hu不变矩作为特征构建静态手势深度感知神经网络模型,以此实现对静态手势进行分类识别。在VisualStudio的开发环境下实现了对该方法的验证,取得了良好的效果,并与传统的模板匹配法与基于卷积神经网络的深度学习方法作比较,静态手势识别准确率总体可达95%,识别效率高,能满足实时性要求。     

基于Leap Motion的动态手势识别方法

伴随虚拟现实（Virtual Reality,VR）技术的发展,以及人们对人机交互性能和体验感的要求提高,手势识别作为影响虚拟现实中交互操作的重要技术之一,其精确度急需提升^[1].针对当前手势识别方法在一些动作类似的手势识别中表现欠佳的问题,提出了一种多特征动态手势识别方法.该方法首先使用体感控制器Leap Motion追踪动态手势获取数据,然后在特征提取过程中增加对位移向量角度和拐点判定计数的提取,接着进行动态手势隐马尔科夫模型（Hidden Markov Model,HMM）的训练,最后根据待测手势与模型的匹配率进行识别.从实验结果中得出,该多特征识别方法能够提升相似手势的识别率.     

Human–computer interaction using vision-based hand gesture recognition systems: a survey

Considerable effort has been put toward the development of intelligent and natural interfaces between users and computer systems. In line with this endeavor, several modes of information (e.g., visual, audio, and pen) that are used either individually or in combination have been proposed. The use of gestures to convey information is an important part of human communication. Hand gesture recognition is widely used in many applications, such as in computer games, machinery control (e.g., crane), and thorough mouse replacement. Computer recognition of hand gestures may provide a natural computer interface that allows people to point at or to rotate a computer-aided design model by rotating their hands. Hand gestures can be classified into two categories: static and dynamic. The use of hand gestures as a natural interface serves as a motivating force for research on gesture taxonomy, its representations, and recognition techniques. This paper summarizes the surveys carried out in human--computer interaction (HCI) studies and focuses on different application domains that use hand gestures for efficient interaction. This exploratory survey aims to provide a progress report on static and dynamic hand gesture recognition (i.e., gesture taxonomies, representations, and recognition techniques) in HCI and to identify future directions on this topic.     

自拍相机运动手势交互界面的设计与实现

随着智能移动终端的发展及摄像镜头的小型化,自拍变得越来越流行。如何设计新型自拍交互方法使得用户在自拍过程中能够自由、实时地控制相机是自拍相机交互界面的关键问题。提出利用基于视觉的运动手势交互界面的新方法,使自拍过程中用户只要挥一挥手臂就可以实现与自拍相机的交互功能。使用手势交互的方法,用户可以把相机放在任意的平台上,自由地摆出各种自拍姿态,增加了自拍的丰富性,提高了用户体验。主要提出挥手及画圈两种交互手势,通过组合应用可以实现丰富高效的自拍交互控制功能,如快门控制、白平衡,曝光度等。手势的识别利用相机摄像的实时图像进行处理,采用稀疏光流算法来识别运动手势。用户评估实验表明,所提出运动手势自拍交互界面具有较好的交互效率以及良好的用户满意度,两种手势的识别效率约为85%。     

基于自适应子空间在线PCA的手势识别

基于视觉的手势识别系统的学习一般是离线的,导致系统对新手势的正确识别需要重新离线学习,因此系统实时性、可扩展性和鲁棒性较差,不适合认知发育的智能框架。文中提出了基于自适应子空间在线PCA的手势识别方法。该方法通过计算样本投影系数向量的PCA来实现子空间在线更新,并根据新样本与已学习样本的差异程度,调整子空间更新策略,使算法自适应于不同情况,减少计算和存储开销,实现增量的在线学习和识别手势的目的。实验表明,本文方法能处理未知手势问题,实现手势在线积累和更新,逐渐增强系统识别能力。     

Static hand gesture recognition using neural networks

This paper presents a novel technique for hand gesture recognition through human–computer interaction based on shape analysis. The main objective of this effort is to explore the utility of a neural network-based approach to the recognition of the hand gestures. A unique multi-layer perception of neural network is built for classification by using back-propagation learning algorithm. The goal of static hand gesture recognition is to classify the given hand gesture data represented by some features into some predefined finite number of gesture classes. The proposed system presents a recognition algorithm to recognize a set of six specific static hand gestures, namely: Open, Close, Cut, Paste, Maximize, and Minimize. The hand gesture image is passed through three stages, preprocessing, feature extraction, and classification. In preprocessing stage some operations are applied to extract the hand gesture from its background and prepare the hand gesture image for the feature extraction stage. In the first method, the hand contour is used as a feature which treats scaling and translation of problems (in some cases). The complex moment algorithm is, however, used to describe the hand gesture and treat the rotation problem in addition to the scaling and translation. The algorithm used in a multi-layer neural network classifier which uses back-propagation learning algorithm. The results show that the first method has a performance of 70.83% recognition, while the second method, proposed in this article, has a better performance of 86.38% recognition rate.     

沉浸式所触即所得网络可视分析方法

沉浸式网络可视化在空间沉浸、用户参与、多维感知等方面具有天然的优势。受用户与日常物体交互方式所启发,基于所触即所得(WYTIWYG)的理念提出一种沉浸式网络可视分析方法来挖掘网络特征和关联模式。首先提出手势舒适度评估模型来指导手势动作设计,并引入窗口状态模型来优化手势识别稳定性。此外,将网络分析交互需求与手势动作语义绑定,定义沉浸式网络手势交互范式。与真实世界中抓取交互类似,用户可利用自然交互手势在沉浸式环境下执行移动、高亮、布局维度变换、边绑定等操作。最后,案例研究验证了方法的有效性。