一种新的实时彩色目标分割方法

为实现对视频序列图象中彩色目标的识别与跟踪,提出了一种鲁棒的实时分割方法。它分为象素分类与区域特征提取两过程。在象素分类阶段,把每一个目标象素建模成一个二维高斯模型,定义相应的决策函数,将图象中所有象素点分类成为目标和背景,同时对高斯模型的参数进行在线动态修改,使之对变化的光照条件所引起的彩色畸变具有自适应性。在区域特征提取阶段,对象素分类所形成的二值图象实现行程编码,产生行程编码映射图,在此基础上,采用一种基于树的区域搜索算法计算出区域特征量。文中提出的方法已成功地应用于足球机器人视觉子系统中,取得了良好的效果。     

A 2D/3D model-based object tracking framework

This paper presents a robust framework for tracking complex objects in video sequences. Multiple hypothesis tracking (MHT) algorithm reported in (IEEE Trans. Pattern Anal. Mach. Intell. 18(2) (1996)) is modified to accommodate a high level representations (2D edge map, 3D models) of objects for tracking. The framework exploits the advantages of MHT algorithm which is capable of resolving data association/uncertainty and integrates it with object matching techniques to provide a robust behavior while tracking complex objects. To track objects in 2D, a 4D feature is used to represent edge/line segments and are tracked using MHT. In many practical applications 3D models provide more information about the object's pose (i.e., rotation information in the transformation space) which cannot be recovered using 2D edge information. Hence, a 3D model-based object tracking algorithm is also presented. A probabilistic Hausdorff image matching algorithm is incorporated into the framework in order to determine the geometric transformation that best maps the model features onto their corresponding ones in the image plane. 3D model of the object is used to constrain the tracker to operate in a consistent manner. Experimental results on real and synthetic image sequences are presented to demonstrate the efficacy of the proposed framework.     

结合背景差分和闭合轮廓拟合的运动人体检测

假定图像序列的背景图像已经获得,提出一种结合时空背景差和闭合轮廓拟合的运动人体目标检测算法。算法以较小的阈值获得当前帧的背景差分图像,并搜寻最大连通域为初始前景目标;构造加权高斯滤波器,提取初始前景目标边缘;拟合前景目标轮廓,提出2 bit区域选择法提取不连续弧段的端点,根据类间最小距离准则构造闭合轮廓,结合帧间差分提取最终前景轮廓,标注运动目标位置。仿真实验表明,该算法能准确提取出运动目标,并标注目标位置,在背景环境发生变化时同样可以准确检测到运动目标,具有较好的鲁棒性。     

基于人体行为3D模型的2D行为识别

针对行为识别中行为者朝向变化带来的问题, 提出了一种基于人体行为3D模型的2D行为识别算法. 在学习行为分类器时, 以3D占据网格表示行为样本, 提取人体3D关节点作为描述行为的特征, 为每一类行为训练一个基于范例的隐马尔可夫模型(Exemplar-based hidden Markov model, EHMM), 同时从3D行为样本中选取若干帧作为3D关键姿势集, 这个集合是连接2D观测样本和人体3D关节点特征的桥梁. 在识别2D行为时, 2D观测样本序列可以由一个或多个非标定的摄像机采集. 首先在3D关键姿势集中为每一帧2D观测样本寻找与之最匹配的3D关键姿势帧, 之后由行为分类器对2D观测样本序列对应的3D关键姿势序列进行识别. 该算法在训练行为分类器时要进行行为者的3D重构和人体3D关节点的提取, 而在识别2D行为时不再需要进行3D重构. 通过在3个数据库上的实验, 证明该算法可以有效识别行为者在任意朝向下的行为, 并可以适应不同的行为采集环境.     

三维形体的形态学运算及应用

本文首先讨论了边界表示的物体的形态学运算问题。文中讨论了任意形状的物体，包括凸物体和非凸物体；引入了负形体的概念；并提出了２Ｄ和３Ｄ连续物体的Ｍｉｎｋｏｗｓｋｉ运算的统一算法。利用这一算法，提出了３Ｄ任意形体间的变形新算法，把边界表示的物体的形态学运算的概念扩展到任意曲线和任意曲面上，并且介绍了３Ｄ物空间中曲线的概念和３Ｄ物空间双参数曲面的概念。文中任意形体的３Ｄ变形算法能很好地解决具有不同拓扑结构的３Ｄ边界表示的物体之间的变形问题。     

A single solution method for converting 2D assembly drawings to 3D part drawings

Although solid models play a central role in modern CAD systems, 2D CAD systems are still commonly used for designing products without complex curved faces. Therefore, an important task is to convert 2D drawings to solid models, and this is usually carried out manually even in present CAD systems. Many methods have been proposed to automatically convert orthographic part drawings of solid objects to solid models. Unfortunately, products are usually drawn as 2D assembly drawings, and therefore, these methods cannot be applied. A further problem is the difficult and time-consuming task of decomposing 2D assembly drawings into 2D part drawings. In previous work, the authors proposed a method to automatically decompose 2D assembly drawings into 3D part drawings, from which 2D part drawings can be easily generated. However, one problem with the proposed method was that the number of solutions could easily explode if the 2D assembly drawings became complex. Building on this work, here we describe a new method to automatically convert 2D assembly drawings to 3D part drawings, generating a unique solution for designers regardless of the complexity of the original 2D assembly drawings. The only requirement for the approach is that the assembly drawings consist of standard parts such as bars and plates. In 2D assembly drawings, the dimensions, part numbers and parts lists are usually drawn, and the proposed method utilizes these to obtain a unique solution.     

A new and fast contour-filling algorithm

Contour filling is one of the most common problems in image and graphics processing. The executing speed of the contour filling is vital, especially for a real-time system. This paper studies the advantages and disadvantages of the conventional filling algorithms, analyzes their original ideas, and proposes a new filling algorithm. The new algorithm presents a very simple idea for finding seeds automatically, and limits the scan within the filling regions. Repeated experiments have proven that with the new algorithm, any complex inner and outer contours can be filled with higher speed.     

3D video components generation using object tracking technique

2D-to-3D conversion that would be a solution of the lack of 3D contents has been a worthy and challenging research field. In this paper, we propose a computer interactive conversion method to capture components which is used to generate 3D sequences. First, we divide the key frame into foreground and background, and then label the objects by convenient computer interactive operation. Depth information of objects is labeled after segmentation. Second, we use object tracking technique which synthesizes the advantages of kernel-based mean shift tracker and contour tracker to accomplish object depth capture for non-key frame. Finally, all the 3D information is prepared to render 3D sequences. After all, we propose our future work direction: a 2D-to-3D system which can generate 3D sequence interactively.     

CubeALS:新的三维协同过滤推荐算法

随着互联网的快速发展,人们对个性化网页搜索、个性化广告投放、个性化社会标注等三维推荐服务的需求越来越紧迫。这些三维立方体数据高度稀疏,且与二维推荐系统相比三维推荐系统中对象之间的关系更加复杂。为了更好地模拟三维对象之间的关系并解决三维数据高度稀疏的问题,提出了一种新的三维协同过滤推荐算法CubeALS(cube alternating least squares)。该算法对三维协同过滤推荐算法CubeSVD(cube singular value decomposition)进行了改进,尝试使用不同于SVD的算法进行矩阵分解。在真实的个性化社会标注数据集上的实验结果表明,与CubeSVD算法相比,CubeALS的性能得到了显著提高。     

一种将羽毛球比赛的2D视频转换到3D视频的算法

文中提出一种羽毛球比赛的2D视频转换到3D视频的算法。在这类视频中,前景是最受关注的部分,准确地从背景中提取出前景对象是获取深度图的关键。文中采用一种改进的图割算法来获取前景,并根据场景结构构建背景深度模型,获取背景深度图;在背景深度图的基础上,根据前景与镜头之间的距离关系为前景对象进行深度赋值,从而得到前景深度图。然后,融合背景深度图和前景深度图,得到完整的深度图。最后,通过基于深度图像的虚拟视点绘制技术DIBR来获取用于3D显示的立体图像对。实验结果表明,最终生成的立体图像对具有较好的3D效果。     

CurveNet: Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition

In computer vision fields, 3D object recognition is one of the most important tasks for many real-world applications. Three-dimensional convolutional neural networks (CNNs) have demonstrated their advantages in 3D object recognition. In this paper, we propose to use the principal curvature directions of 3D objects (using a CAD model) to represent the geometric features as inputs for the 3D CNN. Our framework, namely CurveNet, learns perceptually relevant salient features and predicts object class labels. Curvature directions incorporate complex surface information of a 3D object, which helps our framework to produce more precise and discriminative features for object recognition. Multitask learning is inspired by sharing features between two related tasks, where we consider pose classification as an auxiliary task to enable our CurveNet to better generalize object label classification. Experimental results show that our proposed framework using curvature vectors performs better than voxels as an input for 3D object classification. We further improved the performance of CurveNet by combining two networks with both curvature direction and voxels of a 3D object as the inputs. A Cross-Stitch module was adopted to learn effective shared features across multiple representations. We evaluated our methods using three publicly available datasets and achieved competitive performance in the 3D object recognition task.      

统计特征和Markov模型在三维模型分类中的应用

针对三维模型的分类问题,提出了一种基于统计特征量和Markov模型的分类算法。该算法对预处理后的三维模型进行几何切分,并提取切分后每块的统计特征。对三维模型各分块进行一定顺序的观测,可以获得由各分块的统计特征量构成的Markov模型的伪时间序列。再对不同类模型进行训练并得到各类模型对应的Markov模型参数。最后定义模型间的相似度度量,获得三维模型的分类结果。实验表明该算法在绝大多数类别的模型上分类效果较好,准确率达到90%以上。     

Reconstruction of 3D Objects from Orthographic Projections

An algorithm for automatic reconstruction of 3D objects from their orthographic projections is presented in this paper. It makes some improvements to, and complements the, Wesley-Markowsky algorithm, which is a typical hierarchical reconstruction algorithm limited to polyhedral objects, and extracts the idea of pattern recognition expressed in the Aldefeld algorithm. It is shown in theory by analysis and in practice by implementation that the proposed algorithm successfully rejected pathological cases and found all solutions with the same set of orthographic views. Compared with the existing algorithms presented in references, this algorithm covers some more complex cases of objects incorporating cylinders.     

Integrative 3D modelling of complex carving surface

Modelling of a complex carving surface is the most important process for digitization of art carving such as Chinese classical furniture carving, and it is difficult to be fulfilled. However, a complex 2D curve flower pattern can be easily acquired or drawn by handcraft or a drawing software. This paper presents a quick integrative 3D modeling method of complex carving surface based on a 2D curve flower pattern. The proposed method uses a scanning analysis algorithm, a normal distribution function and a distance function to model and create carving tracks. In this paper, the delamination, combination and interpolation of modelling process are described as well. The provided research method will make the modelling of complex carving surface more intelligent, agile, and will meet the requirement of integrative 3D modelling of digital art carving. Experimental results show that this method is of quick modelling and multi-model effective characteristics with realizable interactive designing and excellent practicability.     

Tomographic Reconstruction of 3D Objects Using Marked Point Process Framework

For reconstructing sparse volumes of 3D objects from projection images taken from different viewing directions, several volumetric reconstruction techniques are available. Most popular volume reconstruction methods are algebraic algorithms (e.g. the multiplicative algebraic reconstruction technique, MART). These methods which belong to voxel-oriented class allow volume to be reconstructed by computing each voxel intensity. A new class of tomographic reconstruction methods, called “object-oriented” approach, has recently emerged and was used in the Tomographic Particle Image Velocimetry technique (Tomo-PIV). In this paper, we propose an object-oriented approach, called Iterative Object Detection—Object Volume Reconstruction based on Marked Point Process (IOD-OVRMPP), to reconstruct the volume of 3D objects from projection images of 2D objects. Our approach allows the problem to be solved in a parsimonious way by minimizing an energy function based on a least squares criterion. Each object belonging to 2D or 3D space is identified by its continuous position and a set of features (marks). In order to optimize the population of objects, we use a simulated annealing algorithm which provides a “Maximum A Posteriori” estimation. To test our approach, we apply it to the field of Tomo-PIV where the volume reconstruction process is one of the most important steps in the analysis of volumetric flow. Finally, using synthetic data, we show that the proposed approach is able to reconstruct densely seeded flows.     

3D street art illusions: embedding chalk stylized rendering of 3D objects into a pavement photo

Three dimensional street art illusions have become more popular in recent years. Many of them are drawn on pavement such as streets, sidewalks, and town squares. It is often known as 3D chalk art, where a 2D artwork is drawn on the street, giving the viewer a 3D optical illusion from a certain perspective. This paper supplies chalk stylized renderings for 3D models and synthesizes 3D objects into a realistic photograph. Users can input one photo for the 3D model. First, a camera position is achieved by using a camera calibration algorithm. Second, a chalk stylized rendering was applied to create an artistic image of the 3D models using the same camera position. Then, the non‐photorealistic rendering image is composited into a source photograph using a modified Poisson approach. All of the enhanced pavement texture details are also blended into the object's image. The major contribution of this paper is providing a user to create any interesting and attractive 3D illusionary art without physically drawing pictures on the pavement. Finally, the proposed method is demonstrated using various experimental 3D street art illusion images. Copyright © 2014 John Wiley & Sons, Ltd.     

Markov-Miml: A Markov chain-based multi-instance multi-label learning algorithm

The main aim of this paper is to propose an efficient and novel Markov chain-based multi-instance multi-label (Markov-Miml) learning algorithm to evaluate the importance of a set of labels associated with objects of multiple instances. The algorithm computes ranking of labels to indicate the importance of a set of labels to an object. Our approach is to exploit the relationships between instances and labels of objects. The rank of a class label to an object depends on (i) the affinity metric between the bag of instances of this object and the bag of instances of the other objects, and (ii) the rank of a class label of similar objects. An object, which contains a bag of instances that are highly similar to bags of instances of the other objects with a high rank of a particular class label, receives a high rank of this class label. Experimental results on benchmark data have shown that the proposed algorithm is computationally efficient and effective in label ranking for MIML data. In the comparison, we find that the classification performance of the Markov-Miml algorithm is competitive with those of the three popular MIML algorithms based on boosting, support vector machine, and regularization, but the computational time required by the proposed algorithm is less than those by the other three algorithms.     

三维虚拟空间移动物三维坐标的二视映射算法

在接受三维坐标输入装置的三维虚拟空间中 ,移动物在三维坐标输入装置的控制下在屏幕上移动、改变大小以实现虚拟空间。为满足真实性 ,提出了从移动物的三维坐标映射屏幕二视坐标的算法。     

Gamma/X-ray linear pushbroom stereo for 3D cargo inspection

For evaluating the contents of trucks, containers, cargo, and passenger vehicles by a non-intrusive gamma-ray or X-ray imaging system to determine the possible presence of contraband, three-dimensional (3D) measurements could provide more information than just 2D measurements. In this paper, a linear pushbroom scanning model is built for such a commonly used gamma-ray or X-ray cargo inspection system. Three-dimensional (3D) measurements of the objects inside a cargo can be obtained by effectively constructing a pushbroom stereo system using two such scanning systems with different scanning angles. A simple but robust calibration method is proposed to find the important parameters of the linear pushbroom sensors. Then, a fast stereo matching algorithm is developed to obtain 3D measurements of the objects under inspection. This algorithm is fully automatic based on free-form deformable registration. An interactive user interface is designed for 3D visualization of the objects of interest. Using the interactive tool, the automatic algorithm is also compared with a very simple semi-automatic algorithm based on point correlation. Experimental results of sensor calibration, stereo matching, 3D measurements and visualization of a 3D cargo container, and the objects inside, are presented.