基于人体轮廓宽度特征的步态识别

基于人体轮廓宽度特征提出了一种步态识别算法。首先对每个序列进行运动轮廓抽取,将这些时变的二维轮廓形状转换为对应的一维横向宽度信号,通过主元分析法(PCA)来提取低维步态特征,在此基础上采用线性判决分析(LDA),以获取最佳投影方向,达到提高数据分类能力的目的。在NLPR、CMU和UMF步态数据库中进行实验,结果表明算法具备快速、稳健特征,在实际应用中具备较大的价值。     

GCA-Net: Gait contour automatic segmentation model for video gait recognition

Multimedia Tools and Applications - Gait recognition from videos is a very important task for surveillance video analysis. Although a number of studies have explored gait recognition models, they...     

基于列质量向量和SVM的步态识别

步态识别是根据人行走的方式来识别其身份,以其特有的优势作为一种身份识别手段。为了提高步态的识别率,提出了一种新方法,使用人体轮廓列质量向量表征特征信息,并使用支持向量机进行识别。根据人体轮廓的高度和宽度计算出步态周期,提取每个步态轮廓列质量向量,最后采用支持向量机进行分类识别。为了验证所提出方法的有效性,在CASIA步态数据库上进行了充足的实验,验证了该方法具有较高的识别率。     

Gait recognition using linear time normalization

We present a novel system for gait recognition. Identity recognition and verification are based on the matching of linearly time-normalized gait walking cycles. A novel feature extraction process is also proposed for the transformation of human silhouettes into low-dimensional feature vectors consisting of average pixel distances from the center of the silhouette. By using the best-performing of the proposed methodologies, improvements of 8-20% in recognition and verification performance are seen in comparison to other known methodologies on the “Gait Challenge” database.     

一种基于联合轮廓特征矢量的目标识别方法

针对基于形状特征进行目标识别的方法存在的不足,提出一种联合轮廓不变矩特征和轮廓几何特征的识别方法;针对不同的待识别目标,采集足够数量的训练样本,统计每一个轮廓特征的均值、标准差和变异系数;并据此对这些轮廓特征进行动态筛选和加权,建立起待识别目标的联合轮廓特征矢量模型.在线识别时,提取场景目标的联合轮廓特征矢量,对其进行...     

基于帧差能量图行质量向量的步态识别算法

为了有效地捕捉步态的连续性动态信息,快速进行身份认证和识别,提出一种以帧差能量图（FDEI）的行质量向量作为步态特征的步态识别方法。该算法通过目标检测、二值化、形态学处理、连通性分析等预处理后得到步态轮廓图像,并利用其序列的宽度进行准周期性分析,再用连续隐马尔可夫模型(CHMM)对所提取的步态帧差能量图行质量向量进行模型参数训练和识别。在CASIA数据库上进行了仿真实验,结果表明该算法具有特征提取简单、特征维数低、识别速度快和识别率高的优点,可以满足实时识别的需要。     

应用核独立成分分析进行弱周期性步态识别研究

提出一种基于时空能量图和核独立成分分析的步态特征表达和步态识别方法,利用步态序列图像的非线性特征和高维统计信息,并消除识别算法对时间配准和步态周期定位的依赖,时空能量图集成了步行运动信息中时间与空间变化的特点,并极大地减少了特征的数据量。针对10人值班的涉密场所进行步态识别正确率达到93.9%。实验结果表明该算法具有较好的识别性能和相当低的空间需求和计算量。     

用轮廓的点分布特征分析和识别步态

提出了一种轮廓点分布特征匹配方法来分析和识别行人步态。首先通过设计一种轮廓采样点区域分布直方图分析了步态的周期性特征,提取了一个步态周期的帧图像轮廓;继而采用一种局部轮廓描述子得到帧图像轮廓的点分布直方图阵列作为轮廓特征、用轮廓点集间的Hausdorff距离结合动态时间规整技术求取测试序列和参考序列间的匹配相似度;最后通过分类实现了人体步态识别。在Soton步态数据库进行了实验,正确分类识别率最高达到90.27%。相关文献的对比分析表明：该方法的识别率有较大的提高,是有效的。     

基于轮廓特征的HMM手写数字识别

在手写数字识别中,边界链码和环构成了对字符轮廓的完整描述。针对手写数字的特点,建了24种笔划。首先将样本边界链码转化成由24个笔划组成的特征值,再加上环特征,构成整个特征值。然后利用隐马尔可夫模型（HMM）对提取的特征值进行分类识别。首次将字符轮廓特征应用在基于HMM的手写数字识别中,在识别MNIST字库上,取得了92.2%的识别率。     

姿态特征结合2维傅里叶变换的步态识别

目的 针对现有步态识别方法易受携带物品、衣服变化等影响的问题,提出了将无肩姿态能量图、步态参数等姿态特征与步态参数的2维傅里叶变换相结合的步态识别算法。方法 基于姿态关节点序列提出忽略肩膀宽度信息的无肩姿态能量图,用以减弱衣服变化的影响;由于下肢受衣物及背包影响较小,提取3个或3个以上的下肢关节点局部结构参数,即提取中臀点与左右膝关节点、中臀点与左右踝关节点构成的两个三角形面积以及所有下肢关节点构成的多边形面积作为步态参数,增强下肢参数在步态识别中的作用;人在行走时,单肢体的运动具有一定的周期性,且肢体之间运动具有一定的协调性,用步态参数的2维幅度谱来表示单肢体运动的周期性与肢体之间运动的协调性,以提高步态参数的可区别性;在现有典型步态特征的基础上,融合本文提出的无肩姿态能量图、步态参数及其2维傅里叶变换幅度谱,采用多特征表示步态的方法,充分利用各特征的优点,提出加权平均与最大池化相结合的两层分数融合策略进行步态识别,提高了步态识别算法在携带物品、衣服变化和跨视角等条件下的正确率。结果 实验结果表明,在中国科学院自动化研究所发布的步态数据集CASIA-B上,本文方法在相同视角条件下,正常状态、背包状态和穿大衣状态的平均识别率分别为99.56%、99.23%和94.25%;在跨视角条件下,正常状态、背包状态和穿大衣状态的平均识别率分别为91.32%、85.34%和69.51%。与典型算法相比,穿大衣状态的识别率有显著提升。结论 本文方法采用加权平均与最大池化相结合的两层分数融合策略,综合利用各特征的优点及其适用场景,有效提高了步态识别的准确率,特别是减弱了衣服厚度、样式等变化对步态识别的影响。     

基于改进蛇模型的步态轮廓提取

提出了一种基于Snake模型的改进算法，不仅能够精确地搜索到图像轮廓，且程序运行速度较快。该算法在CMU数据库上进行了实验，结果表明提取出的步态轮廓完整且封闭，能有效地提高识别率。     

Face recognition using difference vector plus KPCA

In this paper, a novel approach for face recognition based on the difference vector plus kernel PCA is proposed. Difference vector is the difference between the original image and the common vector which is obtained by the images processed by the Gram-Schmidt orthogonalization and represents the common invariant properties of the class. The optimal feature vectors are obtained by KPCA procedure for the difference vectors. Recognition result is derived from finding the minimum distance between the test difference feature vectors and the training difference feature vectors. To test and evaluate the proposed approach performance, a series of experiments are performed on four face databases: ORL, Yale, FERET and AR face databases and the experimental results show that the proposed method is encouraging.     

Human motion recognition using support vector machines

We propose a motion recognition strategy that represents each videoclip by a set of filtered images, each of which corresponds to a frame. Using a filtered-image classifier based on support vector machines, we classify a videoclip by applying majority voting over the predicted labels of its filtered images and, for online classification, we identify the most likely type of action at any moment by applying majority voting over the predicted labels of the filtered images within a sliding window. We also define a classification confidence and the associated threshold in both cases, which enable us to identify the existence of an unknown type of motion and, together with the proposed recognition strategy, make it possible to build a real-time motion recognition system that cannot only make classifications in real-time, but also learn new types of motions and recognize them in the future. The proposed strategy is demonstrated on real datasets.     

Extracting eyebrow contour and chin contour for face recognition

This paper proposes a novel method for extraction of eyebrow contour and chin contour. We first segment rough eyebrow regions using spatial constrained sub-area K-means clustering. Then eyebrow contours are extracted by Snake method with effective image force. For chin contour extraction, we first estimate several possible chin locations which are used to build a number of curves as chin contour candidates. Based on the chin like edges extracted by proposed chin edge detector, the curve with the largest likeliness to be the actual chin contour is selected. Finally, the credible extracted eyebrow contour and the estimated chin contours are used as geometric features for face recognition. Experimental results show that the proposed algorithms can extract eyebrow contours and chin contours with good accuracy and the extracted features are effective for improving face recognition rates.     

Gait recognition for person re-identification

The Journal of Supercomputing - Person re-identification across multiple cameras is an essential task in computer vision applications, particularly tracking the same person in different scenes....     

基于不变矩的步态识别

提出了一种利用不变矩进行步态识别的方法。该方法把二维人体空间轮廓信号变换为一维不变矩信号,把人体的步态序列变换为不变矩矢量,对不变矩矢量进行规格化,然后根据规格化不变矩矢量进行步态识别。实验中,本文的方法取得很好的效果。     

基于不变矩特征和神经网络的步态识别

步态识别是利用人体步行的方式来识别人的身份.近年来,步态作为一种生物特征识别技术已引起越来越多人们的兴趣.本文提出了一种简单有效的步态识别算法,首先通过背景差方法得到运动人体轮廓,然后利用不变矩描述轮廓特征,最后用BP神经网络方法来进行模板匹配,实现人的身份识别.