基于核聚类的H .264压缩域的运动对象分割方法

提出了一种基于核聚类的H.264压缩域的运动对象分割的方法。首先对运动矢量进行归一化处理,其次又引入了平均欧式距离的中值滤波的方法对运动矢量进行滤波去噪,再次利用减法聚类初始化聚类中心并且使用引入了核函数的模糊聚类进行聚类,最后将有效函数的判断结果作为分割条件,从而达到自适应分割出压缩域中的运动对象的目的。本方法对Hall视频序列进行了实验。实验证明,通过该方法可以较好地分割出视频序列中的运动对象。     

基于核聚类的H.264压缩域的运动对象分割方法

提出了一种基于核聚类的H.264压缩域的运动对象分割的方法。首先对运动矢量进行归一化处理,其次用引入了平均欧式距离的中值滤波的方法对运动矢量进行滤波去噪,再次利用减法聚类初始化聚类中心并且使用引入了核函数的模糊聚类进行聚类,最后将有效函数的判断结果作为分割条件,从而达到自适应分割出压缩域中的运动对象的目的。本方法对Hall视频序列进行了实验,实验证明,通过该方法可以获得较好的分割出视频序列中的运动对象。     

基于EM聚类的H.264压缩域视频对象实时分割算法

从压缩域直接分割视频对象比传统的像素域分割具有快速高效的特点,目前已有不少从MPEG域分割的方法,但从H.264压缩域分割的甚少。为此提出一种基于H.264域的实时分割运动对象方法,该算法先对当前视频帧进行全局运动估计和补偿,然后对4×4的运动矢量场进行分类处理,最后对非零运动矢量使用改进的EM聚类分割算法。本文算法对多个视频序列进行了实验,结果表明,该算法针对静止背景和运动背景的视频序列都能达到较精确的实时分割。     

基于模糊聚类的H.264压缩域视频对象分割

鉴于压缩域视频运动分割方法在分割速度上的优越性,提出一种基于H.264的压缩域视频运动对象分割方法,对初始的运动矢量场进行去噪、中值滤波、校正和累积处理,得到更可靠的运动矢量场,用改进的模糊C-均值聚类算法分割出视频序列中的运动对象。实验结果表明,该方法可以快速准确地提取出视频序列中的运动对象。     

基于边界搜索的运动对象快速凸壳分割算法

目前在H.264/AVC压缩域分割领域中常用方法造成局部运动矢量(MV)缺失,而通过全局运动补偿来还原运动矢量导致其时间复杂度提高。为解决此问题,提出一种基于边界聚类的快速凸壳分割(BS-CHSTF)算法。该方法主要利用码流中的运动矢量场信息进行分割,首先,对MV利用时空域滤波(STF)对运动矢量进行预处理,采用八方向自适应搜索算法进行边界搜索确定运动连通域;然后根据每个连通域边界求解凸壳并对其进行连通域填充,之后利用运动矢量与距离信息设定聚类规则,对多个连通域进行聚类;最后,对其进行优化掩膜达到分割运动对象的效果。实验结果表明,与混合高斯模型(GMM)分割算法和压缩域蚁群算法(ACA)比较,在分割准确率上平均提高了近3%,甚至在运动矢量场严重缺失的情况下,提高了近20%;而在分割速度上平均提高了近25%。该方法着重于求得运动对象的完整性与快速性,在运动对象不完整的情况下,能够获得较好分割精准度。     

视频监控中的行为序列分割与识别

智能监控系统中的行为分析与识别是当前计算机视觉领域的研究热点,而行为序列分割则是行为分析与识别的基础.提出了一种无监督的行为序列分割算法,并对分割结果进行识别.首先,采用鲁棒的形状编码方案得到人体轮廓的紧凑表示,提取轮廓点集特征描述运动人体;然后,基于奇异值分解(SVD)估计行为序列数据的本征维数,确定数据对应的低维流形,并通过检测特征数据在该流形上的投影误差的突变实现行为序列分割;最后,采用隐马尔可夫模型(HMM)对分割结果进行识别.在公共数据库上的实验结果表明了此分割和识别算法的有效性.     

基于扩展C型HMM人脸表情识别

隐马尔科夫模型(HMM)能够很好地对时间和空间建模,在对动态的表情序列进行识别时HMM取得了很好的识别效果。但是传统的HMM训练算法基于最大似然准则,在该准则下训练的HMM表情序列模型识别能力有限。针对这一不足,通过增加状态中心参数C对HMM模型进行了扩展,然后在此基础上使用状态空间上隐射算法来建立模型。试验结果表明所建立的扩展C型HMM模型和相应的算法提高了识别能力。     

基于HMM2的时间序列凝聚聚类算法

为弥补传统的基于隐M arkov模型在前提假设上的不足,提出了二阶隐马尔可夫模型。在研究二阶隐马尔可夫模型和凝聚算法在时空序列分析的基础上,提出了一种新的基于 HMM2的时间序列凝聚算法。该算法应用 HMM2对时间序列进行建模,合理考虑了概率和模型历史状态的关联性,按照相异度原则将序列聚成几个类,每个类用模型代表,进而对这些模型训练、合并及迭代得到聚类结果。实验比较了该算法与基于HMM算法的聚类质量,研究了聚类正确率与聚类数、距离正确率与模型距离的关系。结果表明,该算法比传统的基于HMM的聚类算法具有更好的性能。     

基于层次HMM的运动目标分割

提出对差分图像用三层统计模型表示的思想：前景运动汽车层、背景运动汽车层和运动阴影层,并分别建立了各层的统计模型,应用HMM对运动图像序列进行模型参数估计,通过模型进行运动汽车分割。HMM利用图像序列帧之间的图像像素空间相关性和时间相关性,从而完成模型参数的识别。通过MAP算法完成模型参数具体化,不但用模型完成图像前景目标的分割,同时在分割中自然区别了背景运动目标和阴影,实现了复杂背景图像的运动汽车分割。实验结果表明方法能够有效地完成分割目的。     

基于小波多尺度聚类水平集的医学图像分割

针对医学图像低对比度、灰度不均匀等特点,提出了一种小波多尺度聚类水平集的图像分割方法,能够很好地解决医学图像灰度不均匀的问题。首先,利用小波多尺度分析的良好信噪分离能力提取各尺度下图像的有效边缘信息,将边缘信息添加到水平集模型的能量函数中从而提高模型的局部控制能力。然后,基于灰度不均匀的图像模型,派生出对于感兴趣区域的局部灰度聚类,在每个点的邻域内定义基于灰度的局部聚类准则函数。将局部聚类准则函数转化为全局准则函数。在水平集框架中,该准则根据水平集函数定义了代表图像域划分的能量项和引起图像强度不均匀的偏置域。最后,从小波变换的顶层低频子带图像开始逐层采用改进的聚类水平集方法分割图像,并将分割结果通过插值方式传递至下一层作为分割的初始轮廓,最终实现灰度不均匀医学图像的分割。实验结果表明,该方法能够有效地分割医学图像,具有计算更加鲁棒稳定、效率更高和更加准确的优点。     

具有不同数目状态结点的HMMs在中国手语识别中的应用

中国手语是中国聋人使用的语言,主要通过手势动作来表达一定的含义。因而,手语识别问题是动态连续信号的识别问题。目前大部分手语识别系统采用HMMs(hidden Markov models)作为系统的识别系统。由于各个词包含的基本手势数不同,若所有模型都由同样数目的状态结点构成会影响识别率。而由人为每个词设置状态数又很难达到完全准确,所述系统使用一种基于动态规划的估计状态结点数的办法,并实现了基于具有不同状态数目的HMM的训练及识别过程,实验结果表明,该系统在手语的识别速度和识别精度方面都有所提高。     

Analysis of 3D Hand Trajectory Gestures Using Stroke-Based Composite Hidden Markov Models

We present a glove-based hand gesture recognition system using hidden Markov models (HMMs) for recognizing the unconstrained 3D trajectory gestures of operators in a remote work environment. A Polhemus sensor attached to a PinchGlove is employed to obtain a sequence of 3D positions of a hand trajectory. The direct use of 3D data provides more naturalness in generating gestures, thereby avoiding some of the constraints usually imposed to prevent performance degradation when trajectory data are projected into a specific 2D plane. We use two kinds of HMMs according to the basic units to be modeled: gesture-based HMM and stroke-based HMM. The decomposition of gestures into more primitive strokes is quite attractive, since reversely concatenating stroke-based HMMs makes it possible to construct a new set of gesture-based HMMs. Any deterioration in performance and reliability arising from decomposition can be remedied by a fine-tuned relearning process for such composite HMMs. We also propose an efficient method of estimating a variable threshold of reliability for an HMM, which is found to be useful in rejecting unreliable patterns. In recognition experiments on 16 types of gestures defined for remote work, the fine-tuned composite HMM achieves the best performance of 96.88% recognition rate and also the highest reliability.     

Airwriting: a wearable handwriting recognition system

We present a wearable input system which enables interaction through 3D handwriting recognition. Users can write text in the air as if they were using an imaginary blackboard. The handwriting gestures are captured wirelessly by motion sensors applying accelerometers and gyroscopes which are attached to the back of the hand. We propose a two-stage approach for spotting and recognition of handwriting gestures. The spotting stage uses a support vector machine to identify those data segments which contain handwriting. The recognition stage uses hidden Markov models (HMMs) to generate a text representation from the motion sensor data. Individual characters are modeled by HMMs and concatenated to word models. Our system can continuously recognize arbitrary sentences, based on a freely definable vocabulary. A statistical language model is used to enhance recognition performance and to restrict the search space. We show that continuous gesture recognition with inertial sensors is feasible for gesture vocabularies that are several orders of magnitude larger than traditional vocabularies for known systems. In a first experiment, we evaluate the spotting algorithm on a realistic data set including everyday activities. In a second experiment, we report the results from a nine-user experiment on handwritten sentence recognition. Finally, we evaluate the end-to-end system on a small but realistic data set.     

Most discriminating segment – Longest common subsequence (MDSLCS) algorithm for dynamic hand gesture classification

In this work, we consider the recognition of dynamic gestures based on representative sub-segments of a gesture, which are denoted as most discriminating segments (MDSs). The automatic extraction and recognition of such small representative segments, rather than extracting and recognizing the full gestures themselves, allows for a more discriminative classifier. A MDS is a sub-segment of a gesture that is most dissimilar to all other gesture sub-segments. Gestures are classified using a MDSLCS algorithm, which recognizes the MDSs using a modified longest common subsequence (LCS) measure. The extraction of MDSs from a data stream uses adaptive window parameters, which are driven by the successive results of multiple calls to the LCS classifier. In a preprocessing stage, gestures that have large motion variations are replaced by several forms of lesser variation. We learn these forms by adaptive clustering of a training set of gestures, where we reemploy the LCS to determine similarity between gesture trajectories. The MDSLCS classifier achieved a gesture recognition rate of 92.6% when tested using a set of pre-cut free hand digit (0–9) gestures, while hidden Markov models (HMMs) achieved an accuracy of 89.5%. When the MDSLCS was tested against a set of streamed digit gestures, an accuracy of 89.6% was obtained. At present the HMMs method is considered the state-of-the-art method for classifying motion trajectories. The MDSLCS algorithm had a higher accuracy rate for pre-cut gestures, and is also more suitable for streamed gestures. MDSLCS provides a significant advantage over HMMs by not requiring data re-sampling during run-time and performing well with small training sets.     

Compression and recognition of dance gestures using a deformable model

In this paper, we aim for the recognition of a set of dance gestures from contemporary ballet. Our input data are motion trajectories followed by the joints of a dancing body provided by a motion-capture system. It is obvious that direct use of the original signals is unreliable and expensive. Therefore, we propose a suitable tool for non-uniform sub-sampling of spatiotemporal signals. The key to our approach is the use of a deformable model to provide a compact and efficient representation of motion trajectories. Our dance gesture recognition method involves a set of hidden Markov models (HMMs), each of them being related to a motion trajectory followed by the joints. The recognition of such movements is then achieved by matching the resulting gesture models with the input data via HMMs. We have validated our recognition system on 12 fundamental movements from contemporary ballet performed by four dancers. This revised version was published online in November 2004 with corrections to the section numbers. Ballet Atlantique Régine Chopinot.     

An adaptive visual attentive tracker for human communicational behaviors using HMM-based TD learning with new State distinction capability

To develop a nonverbal communication channel between an operator and a system, we built a tracking system called the Adaptive Visual Attentive Tracker (AVAT) to track and zoom in to the operator's behavioral sequence which represents his/her intention. In our system, hidden Markov models (HMMs) first roughly model the gesture pattern. Then, the state transition probabilities in HMMs are used to assign as the rewards in temporal difference (TD) learning. Later, the TD learning method is utilized to adjust the action model of the tracker for its situated behaviors in the tracking task. Identification of the hand sign gesture context through wavelet analysis autonomously provides a reward value for optimizing AVAT's action patterns. Experimental results of tracking the operator's hand sign action sequences during her natural walking motion with higher accuracy are shown which demonstrate the effectiveness of the proposed HMM-based TD learning algorithm of AVAT. During TD learning experiments, the exploring randomly chosen actions sometimes exceed the predefined state area, and thus involuntarily enlarge the domain of states. We describe a method utilizing HMMs with continuous observation distribution to detect whether the state would be split to make a new state. The generation of new states brings the ability of enlarging the predefined area of states.     

Sequence classification via large margin hidden Markov models

We address the sequence classification problem using a probabilistic model based on hidden Markov models (HMMs). In contrast to commonly-used likelihood-based learning methods such as the joint/conditional maximum likelihood estimator, we introduce a discriminative learning algorithm that focuses on class margin maximization. Our approach has two main advantages: (i) As an extension of support vector machines (SVMs) to sequential, non-Euclidean data, the approach inherits benefits of margin-based classifiers, such as the provable generalization error bounds. (ii) Unlike many algorithms based on non-parametric estimation of similarity measures that enforce weak constraints on the data domain, our approach utilizes the HMM’s latent Markov structure to regularize the model in the high-dimensional sequence space. We demonstrate significant improvements in classification performance of the proposed method in an extensive set of evaluations on time-series sequence data that frequently appear in data mining and computer vision domains.     

Online human moves recognition through discriminative key poses and speed-aware action graphs

Recognizing user-defined moves serves a large number of applications including sport monitoring, virtual reality or natural user interfaces (NUI). However, many of the efficient human move recognition methods are still limited to specific situations, such as straightforward NUI gestures or everyday human actions. In particular, most methods depend on a prior segmentation of recordings to both train and recognize moves. This segmentation step is generally performed manually or based on heuristics such as neutral poses or short pauses, limiting the range of applications. Besides, speed is generally not considered as a criterion to distinguish moves. We present an approach composed of a simplified move training phase that requires minimal user intervention, together with a novel online method to robustly recognize moves online from unsegmented data without requiring any transitional pauses or neutral poses, and additionally considering human move speed. Trained gestures are automatically segmented in real time by a curvature-based method that detects small pauses during a training session. A set of most discriminant key poses between different moves is also extracted in real time, optimizing the number of key poses. All together, this semi-supervised learning approach only requires continuous move performances from the user with small pauses. Key pose transitions and moves execution speeds are used as input to a novel human move recognition algorithm that recognizes unsegmented moves online, achieving high robustness and very low latency in our experiments, while also effective in distinguishing moves that differ only in speed.     

Real-time Unsupervised Segmentation of human whole-body motion and its application to humanoid robot acquisition of motion symbols

An interactive loop between motion recognition and motion generation is a fundamental mechanism for humans and humanoid robots. We have been developing an intelligent framework for motion recognition and generation based on symbolizing motion primitives. The motion primitives are encoded into Hidden Markov Models (HMMs), which we call “motion symbols”. However, to determine the motion primitives to use as training data for the HMMs, this framework requires a manual segmentation of human motions. Essentially, a humanoid robot is expected to participate in daily life and must learn many motion symbols to adapt to various situations. For this use, manual segmentation is cumbersome and impractical for humanoid robots. In this study, we propose a novel approach to segmentation, the Real-time Unsupervised Segmentation (RUS) method, which comprises three phases. In the first phase, short human movements are encoded into feature HMMs. Seamless human motion can be converted to a sequence of these feature HMMs. In the second phase, the causality between the feature HMMs is extracted. The causality data make it possible to predict movement from observation. In the third phase, movements having a large prediction uncertainty are designated as the boundaries of motion primitives. In this way, human whole-body motion can be segmented into a sequence of motion primitives. This paper also describes an application of RUS to AUtonomous Symbolization of motion primitives (AUS). Each derived motion primitive is classified into an HMM for a motion symbol, and parameters of the HMMs are optimized by using the motion primitives as training data in competitive learning. The HMMs are gradually optimized in such a way that the HMMs can abstract similar motion primitives. We tested the RUS and AUS frameworks on captured human whole-body motions and demonstrated the validity of the proposed framework.