基于骨架树描述符匹配的物体相似性度量方法

提出了通过匹配骨架树来度量物体相似度的新方法.该方法用一种新的物体特征-树描述符来表示一个骨架树,用搜索树描述符中最长公共子串的方法获得最大同构子树;用新的模型度量骨架枝的形状相似性,并把形状特征和拓扑特征的有机的结合起来.最后,对骨架有环和骨架上有噪声的情况进行了讨论.实验结果表明,本方法计算的相似度具有物体的旋转、大小、平移不变性,算法时间复杂度为o（n^3）,n为物体骨架枝数,对多种物体取得了令人满意的结果.     

基于Reeb图的三维网格模型骨架提取算法

针对目前骨架提取算法存在计算复杂度高、骨架结构不够精确等问题,本文基于Reeb思想提出一种改进的三角网格模型骨架提取算法。首先对三角网格模型进行有效简化,计算简化后的模型特征点,以特征点为聚合点,测地距离函数为映射函数,根据不同顶点的函数值进行特征区域划分,然后利用不同分支的顶点信息进行拓扑分析,连接拓扑构造出的骨架点,并对多余骨架点做删除操作。实验结果表明,可得到较好的骨架提取结果。     

基于距离场细化的骨架提取算法

骨架保存了要处理对象的拓扑信息,是图像分析的重要研究内容之一.传统的骨架细化算法不能保证结果的准确性,而距离场的方法无法保证结果的连续性.为此提出一种快速有效的骨架提取算法,将经典的距离变换法和细化方法结合,克服二者之间存在的缺陷,实现算法的互补.经过大量实验验证,此方法能够得到连续、准确的骨架,可以很好地满足实际应用的需求.     

基于形状分解的书法字骨架提取新方法

针对传统骨架提取算法产生的骨架毛刺较多、交叉处易产生畸变的问题,文章提出一种书法字骨架提取新方法。在基于形状分解思想的基础上,将书法字骨架提取转化成一个分步的问题:由于点云模型能够充分利用现有汉字的底层信息,因此文章采用K-均值聚类算法分割书法字图像;并提出一种适用于书法字特征的以四邻域像素点距离为聚类中心的增量聚类算法提取书法字的部件骨架;最后基于字的拓扑结构连接部件骨架形成完整的骨架。实验结果表明,该方法在骨架提取中表现出了极大的优势,获得了质量较好的骨架,为骨架提取提供了新的思路。     

基于骨架的人体识别

本文采用了人体骨架模型的方法,通过距离变换的算法对人体进行了骨架特征提取,同时用腐蚀和还原的算法对骨架的细小分支进行剔除,保留了骨架的主要特征,取得了较好的效果。     

基于距离变换的多尺度连通骨架算法

传统的基于距离变换的骨架算法不能保证骨架的连通性，需要引入鞍点解决连通问题．该类算法复杂，且不够准确，同时鞍点的定义很难推广到三维，限制了传统算法的发展．本文提出一种新型骨架算法，在图形内根据距离变换的约束，由骨架种子点开始以单像素宽度逐点生长出各骨架分支，逐点生长保证了连通性．实验证明该算法的骨架生长过程是骨架由粗到精的演变过程，能够方便地实现骨架的多尺度控制．     

基于稀疏方位超图匹配的图像配准算法

为提高超图匹配的正确匹配率并降低其计算复杂度,提出了一种基于稀疏方位超图匹配的图像配准算法。提取图像的结构特征点为图节点,采用最小生成树算法获取节点间的主要连接关系,并用包含邻近的节点与边的三元组结构定义超边,计算超边的方位角度信息,由此构建稀疏方位超图;利用方位信息构建亲近矩阵,并采用全局最优匹配方法实现匹配。实验表明,对于实际图像的配准,该算法既具有较低的计算复杂度,又有良好的匹配效果。     

一种快速的目标骨架提取算法

提出了一种已知骨架点邻域骨架点的判别准则,首先确定邻域骨架点的大致位置,根据图像离散化的特性在大致位置附近进行骨架点的精确判断,据此可以直接判别初始骨架点邻域的骨架点,以此生成目标的整个骨架结构.同时利用曲线演化与最大圆弦长的方法进行骨架的多尺度控制.算例研究表明:该算法保证了目标骨架的连通性与单像素性,而对骨架的多尺度控制能较好地表示图像中的视觉重要成分,且算法的运算复杂度是骨架点数级的,大大提高了运算速度,为将目标骨架应用于实时目标识别提供了支持.     

基于多维动态拓扑学习图卷积的骨架动作识别

图卷积由于其对图数据的强大表示能力被广泛应用于基于骨架的动作识别任务中.但是现有的图卷积方法在所有帧或通道上都使用共享的图拓扑进行特征聚合,这极大限制了图卷积网络的表示能力.为了解决这些问题,本文提出多维动态拓扑学习图卷积用于动态建模具有时序与通道特异性的拓扑结构.多维动态拓扑学习图卷积主要包含三个组成部分：纯粹节点拓扑学习图卷积（pure Joint topology learning Graph Convolution, J-GC）、动态时序特异性拓扑学习图卷积（Dynamic Temporal-Wise topology learning Graph Convolution, DTW-GC）和通道特异性拓扑学习图卷积（Channel-Wise topology learning Graph Convolution, CW-GC）.特别地,在DTW-GC中使用了动态骨架拓扑建模方法（Dynamic Skeleton Topology Learning, DSTL）,以高效地建模富含全局时空拓扑特征的动态骨架拓扑.将多维动态拓扑学习图卷积与多尺度时间卷积（Multi-Scale Te...     

基于向量内积的新型骨架提取方法

为了提高骨架提取的准确性和连通性,提出了一种基于向量内积的新型骨架提取方法。对二值图像进行欧氏距离变换,获得了由内部像素点指向边界点的边界向量,通过比较内部像素点8-邻域范围内对应边界向量内积值符号在4个方向上的变化情况确定了边界向量方向发生重大变化的次数,并据此选取候选骨架点;采用基于回归分析的方法确定延伸方向,并完成连接操作生成完整的骨架线。实验结果表明,该算法能够保证骨架的连通性和完整性,且骨架定位准确,平均正确率达到92.27%,同时可以克服边界扰动,是一种有效的骨架提取算法。     

Adaptive lossless compression of skeleton sequences

The increasing importance of skeleton information in surveillance big data feature analysis demands significant storage space. The development of an effective and efficient solution for storage is still a challenging task. In this paper, we propose a new framework for the lossless compression of skeleton sequences by exploiting both spatial and temporal prediction and coding redundancies. Firstly, we propose a set of skeleton prediction modes, namely, spatial differential-based, motion vector-based, relative motion vector-based, and trajectory-based skeleton prediction mode. These modes can effectively handle both spatial and temporal redundancies present in the skeleton sequences. Secondly, we further enhance performance by introducing a novel approach to handle coding redundancy. Our proposed scheme is able to significantly reduce the size of skeleton data while maintaining exactly the same skeleton quality due to lossless compression approach. Experiments are conducted on standard surveillance and Posetrack action datasets containing challenging test skeleton sequences. Our method obviously outperforms the traditional direct coding methods by providing an average of 73% and 66% bit-savings on the two datasets.     

基于骨架约束的人体轮廓图像变形算法

经典的基于控制点的移动最小二乘变形方法,没有考虑到图像变形过程中图像的拓扑结构,导致变形效果脱离现实人体轮廓结构,变得夸张且不符合常理.而骨架刚好能完整地保留图像轮廓的拓扑结构.提出一种在变形过程中加入骨架约束的变形算法,通过推导计算得到一个约束系数,使每一个像素点的移动相对于骨架存在一个约束,从而达到真实有效的变形....     

基于骨架特征的机场主跑道识别

基于骨架对跑道区域进行表示,从骨架图中检测骨架分支基元,计算分支基元的显著性度量并建立分支基元之间的邻接关系。针对机场跑道区域具有的几何特征,采用脊柱基元表示条状区域,将脊柱基元的宽度、长度和方向信息作为脊柱基元的显著性度量,借助先验知识,检测得到主跑道的脊柱基元,识别主跑道。选取一幅某机场遥感图像作为实验分析,验证了算法的可行性。     

Analysis and implementation of morphological skeleton transforms

This paper presents the analysis and the implementation algorithms of the morphological skeleton transform (MST) of binary images. A general MST algorithm is provided from which different subclasses of MSTs can be derived by choosing different structuring elements. Three subclasses of MSTs are discussed in this paper: the uniform-step-distance MST (USDMST), the periodically-uniform-step-distance MST (PUSDMST) and the pseudo-Euclidean MST (PEMST). A general discrete distance called morphological distance relates distance measures to the definitions of structuring elements. The PEMST is proposed which uses isotropic discrete structuring elements called quasi-circular structuring elements (QCSE). The QCSEs of all integer sizes are composed by a dilation interpolation method so that they can be decomposed into simplest elements in order to reduce computation. The PEMST has better performance in terms of rotation-invariance than any existing MSTs. The algorithm has an approximately linear computational complexity. Finally, the implementation of the three MSTs are discussed.     

Boundary-free skeleton extraction and its evaluation in sensor networks

Wireless Networks - In sensor networks community, the skeleton (or medial axis), as an important infrastructure which can correctly capture the topological and geometrical features of the...     

People tracking in an environment with multiple depth cameras: A skeleton-based pairwise trajectory matching scheme

This paper proposes a pairwise trajectory matching scheme from multiple cameras for people tracking, handling the mistracking situations caused by occlusion events occurred in one of the cameras. In a multiple cameras environment, a geometric calibration process is necessary for the co-plane of the overlapping field of views from different cameras as the initial step. Once the geometry is calibrated, according to the 2D positions of the analyzed foot joints from the depth cameras. Homography transformation is applied to project the detected foot points from different views into a synergistic virtual bird’s eye view for people tracking. At the virtual bird’s eye view, the people tracking results from each of the cameras based on Kalman filter are fused according to the proposed pairwise trajectory matching scheme. The contribution of this paper is trifold: (1) The proposed hand-gesture-triggered calibration process with temporally synchronization capability can effectively build and calibrate the geometry in a region of interest. (2) The proposed interleaving-based skeleton obtaining and moving average based valid skeleton determination can extend the skeleton tracking capability to track more people. (3) The proposed pairwise trajectory matching scheme effectively manages occlusion situations happened in one of the depth cameras. In addition, in the extensive experimental results, the proposed method can track up to six simultaneously freely moving persons in the field of view, with affordable complexity for real-time applications. Furthermore, the infrared-based depth cameras track people satisfactorily from bright to extremely dark environments.     

Attributed skeleton graphs using mathematical morphology

The aim of the work described is to use the potential strength of the skeleton of discrete objects in computer vision and pattern recognition where features of objects are needed for classification. Algorithms are introduced for detecting skeleton characteristic points (end points, junction points and curve points) and creating an attributed graph, that can then be used as an input to graph matching algorithms, based on a morphological approach