RECOGNIZING SIMPLE HUMAN ACTIONS USING 3D HEAD MOVEMENT

Recognizing human actions from video has been a challenging problem in computer vision. Although human actions can be inferred from a wide range of data, it has been demonstrated that simple human actions can be inferred by tracking the movement of the head in 2D. This is a promising idea as detecting and tracking the head is expected to be simpler and faster because the head has lower shape variability and higher visibility than other body parts (e.g., hands and/or feet). Although tracking the movement of the head alone does not provide sufficient information for distinguishing among complex human actions, it could serve as a complimentary component of a more sophisticated action recognition system. In this article, we extend this idea by developing a more general, viewpoint invariant, action recognition system by detecting and tracking the 3D position of the head using multiple cameras. The proposed approach employs Principal Component Analysis (PCA) to register the 3D trajectories in a common coordinate system and Dynamic Time Warping (DTW) to align them in time for matching. We present experimental results to demonstrate the potential of using 3D head trajectory information to distinguish among simple but common human actions independently of viewpoint.     

Human action recognition using hull convexity defect features with multi-modality setups

We consider developing a taxonomic shape driven algorithm to solve the problem of human action recognition and develop a new feature extraction technique using hull convexity defects. To test and validate this approach, we use silhouettes of subjects performing ten actions from a commonly used video database by action recognition researchers. A morphological algorithm is used to filter noise from the silhouette. A convex hull is then created around the silhouette frame, from which convex defects will be used as the features for analysis. A complete feature consists of thirty individual values which represent the five largest convex hull defects areas. A consecutive sequence of these features form a complete action. Action frame sequences are preprocessed to separate the data into two sets based on perspective planes and bilateral symmetry. Features are then normalized to create a final set of action sequences. We then formulate and investigate three methods to classify ten actions from the database. Testing and training of the nine test subjects is performed using a leave one out methodology. Classification utilizes both PCA and minimally encoded neural networks. Performance evaluation results show that the Hull Convexity Defect Algorithm provides comparable results with less computational complexity. This research can lead to a real time performance application that can be incorporated to include distinguishing more complex actions and multiple person interaction.     

Human activity recognition using multi-features and multiple kernel learning

This paper presents two sets of features, shape representation and kinematic structure, for human activity recognition using a sequence of RGB-D images. The shape features are extracted using the depth information in the frequency domain via spherical harmonics representation. The other features include the motion of the 3D joint positions (i.e. the end points of the distal limb segments) in the human body. Both sets of features are fused using the Multiple Kernel Learning (MKL) technique at the kernel level for human activity recognition. Our experiments on three publicly available datasets demonstrate that the proposed features are robust for human activity recognition and particularly when there are similarities among the actions.     

人机任务仿真中虚拟人行为建模及仿真实现

提出一种采用高级智能对象(ASO)的建模方法,实现虚拟人的行为建模。首先, 引入 ASO 的概念,对交互特征中的交互元素、交互部位及对象动作进行定义,并对交互动作进 行分类;其次,提出了对象驱动方法,解决由虚拟对象作为主动体动作而导致的虚拟人作为被 动体的运动计算问题,实现对象以交互特征为主的建模;最后,根据人机任务需要对虚拟人的 基本行为动作进行分析,选择常用的 4 种基本动作,对其进行定义并进行动作组合,给出以交 互元素为主的位姿、手型的计算方法,实现了行为建模并进行仿真实现,解决了任务仿真中的 交互量大问题,使仿真结果具有重用性。并以飞机装配的手工铆接仿真为例对方法进行验证。     

Discovering common outcomes of agents’ communicative actions in various domains

We explore the common patterns of human behavior, expressed via communicative actions, and displayed in various domains of human activities associated with conflicts. We build the generic methodology based on machine learning and reasoning to predict specific communicative actions of human agents, given previous sequence of communicative actions of themselves and their opponents. This methodology is applied to textual as well as structured data on inter-human conflicts of diverse modalities. Scenarios are represented by directed graphs with labeled vertices (for communicative actions) and arcs (for temporal and causal relationships between subjects of these actions). Scenario representation and learning techniques are firstly developed in the domain of textual customer complaints, and then applied to such problems as predicting an outcome of international conflicts, assessment of an attitude of a security clearance candidate, mining emails for suspicious emotional profiles, and recognizing suspicious behavior of cell phone users. We present an evaluation of the proposed methodology in the domain of customer complaint and conduct some comparative evaluation in the other domains mentioned above. Successful use of the proposed methodology in rather distinct domains shows its adequacy for mining human attitude-related data in a wide range of applications.     

3D model retrieval using principal plane analysis and dynamic programming

Three dimensional models play an important role in many applications; the problem is how to select the appropriate models from a 3D database rapidly and accurately. In recent years, a variety of shape representations, statistical methods, and geometric algorithms have been proposed for matching 3D shapes or models. In this paper, we propose a 3D shape representation scheme based on a combination of principal plane analysis and dynamic programming. The proposed 3D shape representation scheme consists of three steps. First, a 3D model is transformed into a 2D image by projecting the vertices of the model onto its principal plane. Second, the convex hall of the 2D shape of the model is further segmented into multiple disjoint triangles using dynamic programming. Finally, for each triangle, a projection score histogram and moments are extracted as the feature vectors for similarity searching. Experimental results showed the robustness of the proposed scheme, which resists translation, rotation, scaling, noise, and destructive attacks. The proposed 3D model retrieval method performs fairly well in retrieving models having similar characteristics from a database of 3D models.     

线性动态系统反演模型在人体行为识别的应用

目的 人体行为识别在视频监控、环境辅助生活、人机交互和智能驾驶等领域展现出了极其广泛的应用前景。由于目标物体遮挡、视频背景阴影、光照变化、视角变化、多尺度变化、人的衣服和外观变化等问题,使得对视频的处理与分析变得非常困难。为此,本文利用时间序列正反演构造基于张量的线性动态模型,估计模型的参数作为动作序列描述符,构造更加完备的观测矩阵。方法 首先从深度图像提取人体关节点,建立张量形式的人体骨骼正反向序列。然后利用基于张量的线性动态系统和Tucker分解学习参数元组（A_F,A_I,C）,其中C表示人体骨架信息的空间信息,A_F和A_I分别描述正向和反向时间序列的动态性。通过参数元组构造观测矩阵,一个动作就可以表示为观测矩阵的子空间,对应着格拉斯曼流形上的一点。最后通过在格拉斯曼流形上进行字典学习和稀疏编码完成动作识别。结果 实验结果表明,在MSR-Action 3D数据集上,该算法比Eigenjoints算法高13.55%,比局部切从支持向量机（LTBSVM）算法高2.79%,比基于张量的线性动态系统（tLDS）算法高1%。在UT-Kinect数据集上,该算法的行为识别率比LTBSVM算法高5.8%,比tLDS算法高1.3%。结论 通过大量实验评估,验证了基于时间序列正反演构造出来的tLDS模型很好地解决了上述问题,提高了人体动作识别率。     

Human action learning via hidden Markov model

To successfully interact with and learn from humans in cooperative modes, robots need a mechanism for recognizing, characterizing, and emulating human skills. In particular, it is our interest to develop the mechanism for recognizing and emulating simple human actions, i.e., a simple activity in a manual operation where no sensory feedback is available. To this end, we have developed a method to model such actions using a hidden Markov model (HMM) representation. We proposed an approach to address two critical problems in action modeling: classifying human action-intent, and learning human skill, for which we elaborated on the method, procedure, and implementation issues in this paper. This work provides a framework for modeling and learning human actions from observations. The approach can be applied to intelligent recognition of manual actions and high-level programming of control input within a supervisory control paradigm, as well as automatic transfer of human skills to robotic systems     

A discrete methodology for controlling the sign of curvature and torsion for NURBS

This paper develops a discrete methodology for approximating the so-called convex domain of a NURBS curve, namely the domain in the ambient space, where a user-specified control point is free to move so that the curvature and torsion retains its sign along the NURBS parametric domain of definition. The methodology provides a monotonic sequence of convex polyhedra, converging from the interior to the convex domain. If the latter is non-empty, a simple algorithm is proposed, that yields a sequence of polytopes converging uniformly to the restriction of the convex domain to any user-specified bounding box. The algorithm is illustrated for a pair of planar and a spatial Bézier configuration.     

基于深度数据的人体动作识别方法

本文提出了一个基于流形学习的动作识别框架,用来识别深度图像序列中的人体行为。本文从Kinect设备获得的深度信息中评估出人体的关节点信息,并用相对关节点位置差作为人体特征表达。在训练阶段,本文利用Lapacian eigenmaps(LE)流形学习对高维空间下的训练集进行降维,得到低维隐空间下的运动模型。在识别阶段,本文用最近邻差值方法将测试序列映射到低维流形空间中去,然后进行匹配计算。在匹配过程中,通过使用改进的Hausdorff距离对低维空间下测试序列和训练运动集的吻合度和相似度进行度量。本文用Kinect设备捕获的数据进行了实验,取得了良好的效果;同时本文也在MSR Action3D数据库上进行了测试,结果表明在训练样本较多情况下,本文识别效果优于以往方法。实验结果表明本文所提的方法适用于基于深度图像序列的人体动作识别。     

Action categorization by structural probabilistic latent semantic analysis

Temporal dependency is a very important cue for modeling human actions. However, approaches using latent topics models, e.g., probabilistic latent semantic analysis (pLSA), employ the bag of words assumption therefore word dependencies are usually ignored. In this work, we propose a new approach structural pLSA (SpLSA) to model explicitly word orders by introducing latent variables. More specifically, we develop an action categorization approach that learns action representations as the distribution of latent topics in an unsupervised way, where each action frame is characterized by a codebook representation of local shape context. The effectiveness of this approach is evaluated using both the WEIZMANN dataset and the MIT dataset. Results show that the proposed approach outperforms the standard pLSA. Additionally, our approach is compared favorably with six existing models including GMM, logistic regression, HMM, SVM, CRF, and HCRF given the same feature representation. These comparative results show that our approach achieves higher categorization accuracy than the five existing models and is comparable to the state-of-the-art hidden conditional random field based model using the same feature set.     

基于L1/2正则化的三维人体姿态重构

针对从给定2D特征点的单目图像中重构对象的3D形状问题,本文在形状空间模型的基础上,结合L_1/2正则化和谱范数的性质提出一种基于L_1/2正则化的凸松弛方法,将形状空间模型的非凸求解问题通过凸松弛方法转化为凸规划问题;在采用ADMM算法对凸规划问题进行优化求解过程中,提出谱范数近端梯度算法保证解的正交性与稀疏性.利用所提的优化方法,基于形状空间模型和3D可变形状模型在卡内基梅隆大学运动捕获数据库上进行3D人体姿态重构,定性和定量对比实验结果表明本文方法均优于现有的优化方法,验证了所提方法的有效性.     

Tracking in object action space

In this paper we focus on the joint problem of tracking humans and recognizing human action in scenarios such as a kitchen scenario or a scenario where a robot cooperates with a human, e.g., for a manufacturing task. In these scenarios, the human directly interacts with objects physically by using/manipulating them or by, e.g., pointing at them such as in “Give me that…”. To recognize these types of human actions is difficult because (a) they ought to be recognized independent of scene parameters such as viewing direction and (b) the actions are parametric, where the parameters are either object-dependent or as, e.g., in the case of a pointing direction convey important information. One common way to achieve recognition is by using 3D human body tracking followed by action recognition based on the captured tracking data. For the kind of scenarios considered here we would like to argue that 3D body tracking and action recognition should be seen as an intertwined problem that is primed by the objects on which the actions are applied. In this paper, we are looking at human body tracking and action recognition from a object-driven perspective. Instead of the space of human body poses we consider the space of the object affordances, i.e., the space of possible actions that are applied on a given object. This way, 3D body tracking reduces to action tracking in the object (and context) primed parameter space of the object affordances. This reduces the high-dimensional joint-space to a low-dimensional action space. In our approach, we use parametric hidden Markov models to represent parametric movements; particle filtering is used to track in the space of action parameters. We demonstrate its effectiveness on synthetic and on real image sequences using human-upper body single arm actions that involve objects.