A hand gesture recognition technique for human–computer interaction

We propose an approach to recognize trajectory-based dynamic hand gestures in real time for human–computer interaction (HCI). We also introduce a fast learning mechanism that does not require extensive training data to teach gestures to the system. We use a six-degrees-of-freedom position tracker to collect trajectory data and represent gestures as an ordered sequence of directional movements in 2D. In the learning phase, sample gesture data is filtered and processed to create gesture recognizers, which are basically finite-state machine sequence recognizers. We achieve online gesture recognition by these recognizers without needing to specify gesture start and end positions. The results of the conducted user study show that the proposed method is very promising in terms of gesture detection and recognition performance (73% accuracy) in a stream of motion. Additionally, the assessment of the user attitude survey denotes that the gestural interface is very useful and satisfactory. One of the novel parts of the proposed approach is that it gives users the freedom to create gesture commands according to their preferences for selected tasks. Thus, the presented gesture recognition approach makes the HCI process more intuitive and user specific.     

基于卷积神经网络优化TLD运动手势跟踪算法

针对TLD（Tracking-Learning-Detection）算法在光照变化不均、遮挡严重、跟踪目标模糊等情况下会出现跟踪失败的问题，提出一种基于卷积神经网络优化TLD运动手势跟踪算法。选取手势特征作正样本，其背景作负样本，获取手势HOG特征并投入到卷积神经网络中加以训练，得到手势检测分类器，从而确定目标手势区域，实现手势的自动识别；再利用TLD算法对手势进行跟踪与学习，对正负样本进行估计检测并实时校正，同时运用SURF特征匹配更新跟踪器。实验结果验证，该算法对比TLD经典算法跟踪精度提高了4.24%，增强了运动手势的跟踪效果，相比经典跟踪算法拥有更高鲁棒性。     

Dance performance evaluation using hidden Markov models

We present in this paper a hidden Markov model‐based system for real‐time gesture recognition and performance evaluation. The system decodes performed gestures and outputs at the end of a recognized gesture, a likelihood value that is transformed into a score. This score is used to evaluate a performance comparing to a reference one. For the learning procedure, a set of relational features has been extracted from high‐precision motion capture system and used to train hidden Markov models. At runtime, a low‐cost sensor (Microsoft Kinect) is used to capture a learner's movements. An intermediate step of model adaptation was hence requested to allow recognizing gestures captured by this low‐cost sensor. We present one application of this gesture evaluation system in the context of traditional dance basics learning. The estimation of the log‐likelihood allows giving a feedback to the learner as a score related to his performance. Copyright © 2016 John Wiley & Sons, Ltd.     

一种基于平面约束的偏瘫恢复运动评价方法

偏瘫是一种常见的脑卒中后遗症,偏瘫患者在患有肢体运动障碍的同时,常常伴有轻微的感觉、语言、认知等方面的障碍。提出一种基于惯性传感器的偏瘫患者运动恢复过程的跟踪与评价的新方法,主要应用于痉挛减轻阶段偏瘫患者的自主恢复过程的姿态跟踪及运动能力的评定。该方法融合了惯性传感器信号和偏瘫上肢恢复动作的生物力学约束,根据运动过程中前一时刻前臂和后臂的运动姿态,构建约束平面,对加速度信息进行约束。基于该方法,通过对偏瘫病人上肢的运动恢复过程的跟踪,测量人体上肢不同部位(前臂、后臂)的动作完成的完整程度。实验表明,该方法有效地降低了传感器噪声所引起的漂移,有效地提高了角度测量的准确度和稳定性。     

基于手势的自然用户界面(NUI)在会议中的应用

自然用户界面NUI的清晰、简洁、智能化的方式让用户体验更加直观,更为人性化。基于自然用户界面的应用设备层出不穷,手势识别这种操作技术占据了重要的位置。随着虚拟现实技术快速发展,人们的办公方式也发生了很大的变化。在幻灯片演示方面,传统的方式显得呆板,不能让人们自由使用动作。因此,文中提出一种使用手势来代替鼠标输入的方法,使用Leap Motion控制器。经过试验,计算机的反应速度快,并能准确地辨别出有效手势,能够对幻灯片进行操作。     

基于动态贝叶斯网络的手势识别

研究了动态手势的识别技术,实现人机交互。采用HSV空间的肤色模型实现手势定位,光流场算法进行手势追踪,具有较好的快速性、准确性和鲁棒性。提出应用链码描述手势运动矢量,双手相对位置标量以及双手与脸的相对位置标量,将多条链码作为动态手势的特征进行提取。建立了一个动态手势识别的动态贝叶斯网络模型,将一部分手势链码作为训练样本,通过对DBNs的推理学习实现手势识别。实验构建动态手势识别系统,可应用于多媒体、智能电器或幻灯片控制之中。     

基于深度预分割结合Camshift跟踪算法的动态手势识别方法

针对现有改进的Camshift手势跟踪算法没有考虑光照变化影响下的鲁棒性,进而降低了动态手势的识别率,提出一种基于深度预分割结合Camshift跟踪算法的动态手势识别法.通过在Camshift手势跟踪的基础上引入深度信息,对手势搜索区域进行深度预分割,改进手势目标匹配概率,去除非手势肤色区域及光照变化的影响,最后用隐马尔可夫模型(HMM)进行识别.实验结果表明,提出的方法在光照变化及肤色干扰的环境下有很好的鲁棒性,数字0～9的平均识别率可达97.7％.     

基于Leap Motion的动态手势识别

动态手势识别作为人机交互的一个重要方向，在各个领域具有广泛的需求。相较于静态手势，动态手势的变化更为复杂，对其特征的充分提取与描述是准确识别动态手势的关键。为了解决对动态手势特征描述不充分的问题，利用高精度的Leap Motion传感器对手部三维坐标信息进行采集，提出了一种包含手指姿势和手掌位移的特征在内的、能够充分描述复杂动态手势的特征序列，并结合长短期记忆网络模型进行动态手势识别。实验结果表明，提出的方法在包含16种动态手势的数据集上的识别准确率为98.50%；与其他特征序列的对比实验表明，提出的特征序列，能更充分准确地描述动态手势特征。     

Hand gesture recognition using valley circle feature and Hu’s moments technique for robot movement control

Hand gesture recognition is a simpler and more natural way of human computer interaction. The goal of this paper is to detect the continuous gestures and use them to convey information for the robot movement control. So the hand gesture recognition requires fast and extremely robust. In this paper, three strategies were used to realize the hand gesture recognition: (1) the valley circle (VC) was created for the first stage of 6 fingertip numbers classification; (2) the hybrid feature vector of Hu’s moments, convexity and compactness (HCC) were constructed for the second stage of gesture recognition of the remainder unknown gesture classes; (3) a new template matching recognition (NTMR) algorithm was proposed to realize 10 gesture classes recognition. To test the hand gesture recognition method, the robot movement control system was built. It is experimental proved that the NTMR algorithm is effective and corrective for the hand gesture recognition. It increased the recognition accuracy by 4% and decreased the recognition duration by 112 ms compared with Hu’s moment method. It had good performances of the real-time hand gesture acquisition and information conveyance, and it had the invariant properties when the gesture was rotated and shifted and scaled.