Action Recognition with Multiple Relative Descriptors of Trajectories

Neural Processing Letters - Dense trajectory has become one of the most successful hand-crafted features for action recognition. However, most of the existing dense trajectories based methods...     

傅里叶描述子和Hough变换检测封闭边界运动

运动检测广泛的应用于机器视觉和基于对象的视频编码以及生物医学的运动功能分析等领域。文章分析了平面封闭边界运动和傅里叶描述系数的变化关系,提出了基于边界傅里叶描述子和Hough变换检测平面封闭边界的运动,并通过计算机仿真证明该方法的可行性。     

基于时空权重姿态运动特征的人体骨架行为识别研究

人体行为识别在视觉领域的广泛应用使得它在过去的几十年里一直都是备受关注的研究热点.近些年来,深度传感器的普及以及基于深度图像实时骨架估测算法的提出,使得基于骨架序列的人体行为识别研究越来越吸引人们的注意.已有的研究工作大部分提取帧内骨架不同关节点的空间域信息和帧间骨架关节点的时间域信息来表征行为序列,但没有考虑到不同关节点和姿态对判定行为类别所起作用是不同的.因此本文提出了一种基于时空权重姿态运动特征的行为识别方法,采用双线性分类器迭代计算得到关节点和静止姿态相对于该类别动作的权重,确定那些信息量大的关节点和姿态;同时,为了对行为特征进行更好的时序分析,本文引入了动态时间规整和傅里叶时间金字塔算法进行时序建模,最后采用支持向量机完成行为分类.在多个数据集上的实验结果表明,该方法与其它一些方法相比,表现出了相当大的竞争力,甚至更好的识别效果.     

基于运动轨迹聚类的运动分割

文中提出了一种基于子空间聚类的运动分割算法。针对基于因式分解的运动分割方法对噪声敏感的问题,引入一个基于形状相关矩阵的相似矩阵,然后将特征点映射到一个由相似矩阵决定的低维子空间中。在这个子空间中,可以通过光谱图聚类方法对特征点进行聚类。为提高光谱图聚类方法的分段常数特征向量条件,文中计算了一个相关的概率矩阵的较大特征值相对于边权重变化的敏感度,来切断类之间的连接。通过实验,可以看到文中的方法有较好的鲁棒性。     

基于运动区域差分与卷积神经网络的动作识别

针对视频动作识别中数据处理效率不高的问题,建立一种基于视频帧间差分序列的动作识别模型。利用帧间差分检测视频帧中的运动区域,以该区域为中心进行相应的图像剪切和增强处理。整个识别模型采用双流架构,在数据样本制作时通过适当的隔帧差分来扩大样本的时间跨度。采用分阶段逐步增加训练样本量的方法,以提升模型识别性能并解决训练过程中易出现的过拟合问题。实验结果表明,该模型可以在CPU级配置的电脑中完成快速动作识别,且在UCF11和UCF25数据集中的识别准确率均高于85%。     

基于傅立叶描述子的步态识别

提出了基于傅立叶描述子的步识别方法。用背景差方法得到运动人体的轮廊,通过步态周期分析提取步态序列的关键帧。利用傅立叶描述子处理关键帧的轮廊线序列,并进行数据维数压缩,得到匹配模板。用最近邻近法进行分类和识别。应用上述方法在Soton步态数据库上进行了实验,结果表明所提的步态识别方法具有罗高的识别性能。     

Simultaneous Facial Action Tracking and Expression Recognition in the Presence of Head Motion

The recognition of facial gestures and expressions in image sequences is an important and challenging problem. Most of the existing methods adopt the following paradigm. First, facial actions/features are retrieved from the images, then the facial expression is recognized based on the retrieved temporal parameters. In contrast to this mainstream approach, this paper introduces a new approach allowing the simultaneous retrieval of facial actions and expression using a particle filter adopting multi-class dynamics that are conditioned on the expression. For each frame in the video sequence, our approach is split into two consecutive stages. In the first stage, the 3D head pose is retrieved using a deterministic registration technique based on Online Appearance Models. In the second stage, the facial actions as well as the facial expression are simultaneously retrieved using a stochastic framework based on second-order Markov chains. The proposed fast scheme is either as robust as, or more robust than existing ones in a number of respects. We describe extensive experiments and provide evaluations of performance to show the feasibility and robustness of the proposed approach.     

仿射高斯描绘子及其在模式识别中的应用

在不同位置、从不同角度拍摄同一个二维景物,得到的图像几何形状是不同的,这种几何变形通常可用仿射变换来描述.因此,寻找一组关于仿射变换不变的特征是识别这类图像的关键.本文构造一组仿射不变的特征,即仿射高斯描绘子.构造过程主要是,先计算图像的协方差矩阵,再由该矩阵的特征值和特征向量生成一组同心椭圆,进而利用二维高斯函数构造出仿射高斯描绘子.将这些仿射不变量用于模式识别,以获得较高的识别率.     

Hierarchical Estimation and Segmentation of Dense Motion Fields

In this paper we present a comprehensive energy-based framework for the estimation and the segmentation of the apparent motion in image sequences. The robust cost functions and the associated hierarchical minimization techniques that we propose mix efficiently non-parametric (dense) representations, local interacting parametric representations, and global non-interacting parametric representations related to a partition into regions. Experimental comparisons, both on synthetic and real images, demonstrate the merit of the approach on different types of photometric and kinematic contents ranging from moving rigid objects to moving fluids.     

轨迹分布模式学习的层次自组织神经网络方法

提出一个层次自组织神经网络模型,并将其应用于基于事件识别的轨迹分布模式学习中。该文利用神经元的侧向连接将神经元连成若干条线,每条线对应一个“内部网”。对应于层次神经网络模型,建立了两个领域,即神经元领域和“内部网”领域,两个领域内的神经元都要不同程度地改变权值,从而完成运动轨迹分布模式的学习。还给出了利用轨迹分布模式检测出局部可能的异常现象、检测整个运动轨迹所表示的事件是否为异常事件和目标行为预测的方法。实验进一步说明了该方法的可行性和有效性。     

Second-order Temporal Pooling for Action Recognition

International Journal of Computer Vision - Deep learning models for video-based action recognition usually generate features for short clips (consisting of a few frames); such clip-level features...     

基于傅里叶的卡通动画形状上下文动作捕捉

对已有二维卡通角色进行动作捕捉,然后重新利用的传统方法效率很低。本文提出的方法可以在过滤掉源卡通角色中的冗余信息提高计算效率之后,捕捉更多角色信息以供重用。首先用基于YUV双阈值的方法得到角色的姿态序列(包含角色轮廓和内部线条信息),然后由傅里叶描绘子过滤冗余信息的同时保留所需要的角色动作信息(局部和全局形变),最后用形状上下文捕捉角色轮廓和关键点信息。实验结果表明,此方法可以高效实时地从源卡通角色中捕捉动作和形变信息以供重新利用。     

View Invariance for Human Action Recognition

This paper presents an approach for viewpoint invariant human action recognition, an area that has received scant attention so far, relative to the overall body of work in human action recognition. It has been established previously that there exist no invariants for 3D to 2D projection. However, there exist a wealth of techniques in 2D invariance that can be used to advantage in 3D to 2D projection. We exploit these techniques and model actions in terms of view-invariant canonical body poses and trajectories in 2D invariance space, leading to a simple and effective way to represent and recognize human actions from a general viewpoint. We first evaluate the approach theoretically and show why a straightforward application of the 2D invariance idea will not work. We describe strategies designed to overcome inherent problems in the straightforward approach and outline the recognition algorithm. We then present results on 2D projections of publicly available human motion capture data as well on manually segmented real image sequences. In addition to robustness to viewpoint change, the approach is robust enough to handle different people, minor variabilities in a given action, and the speed of aciton (and hence, frame-rate) while encoding sufficient distinction among actions. This work was done when the author was a graduate student in the Department of Computer Science and was partially supported by the NSF Grant ECS-02-5475. The author is curently with Siemens Corporate Research, Princeton, NJ. Dr. Chellappa is with the Department of Electrical and Computer Engineering.     

A Feature-based Approach for Dense Segmentation and Estimation of Large Disparity Motion

We present a novel framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation. We estimate the initial correspondences by comparing vectors of filter outputs at interest points, from which we compute candidate scene relations via random sampling of minimal subsets of correspondences. We achieve a dense, piecewise smooth assignment of pixels to motion layers using a fast approximate graphcut algorithm based on a Markov random field formulation. We demonstrate our approach on image pairs containing large inter-frame motion and partial occlusion. The approach is efficient and it successfully segments scenes with inter-frame disparities previously beyond the scope of layer-based motion segmentation methods. We also present an extension that accounts for the case of non-planar motion, in which we use our planar motion segmentation results as an initialization for a regularized Thin Plate Spline fit. In addition, we present applications of our method to automatic object removal and to structure from motion.     

基于小波描述子和神经网络的形状识别

提出一种把小波描述子和神经网络相结合的形状识别方法。通过小波描述子提取待识别物体的形状特征,所提取的特征值不受物体位移、缩放和旋转的影响,接着用多层分类器网络对物体的形状进行识别分类,并采用BP算法对神经网络进行学习和训练。最后得出令人满意的实验结果。     

基于小波描述子和神经网络的形状识别

提出一种把小波描述子和神经网络相结合的形状识别方法。通过小波描述子提取待识别物体的形状特征，所提取的特征值不受物体位移、缩放和旋转的影响，接着用多层分类器网络对物体的形状进行识别分类，并采用BP算法对神经网络进行学习和训练。最后得出令人满意的实验结果。