A generalized registration method for augmented reality systems

In augmented reality systems, registration is one of the most difficult problems currently limiting their applications. In this paper, we propose a generalized registration method using projective reconstruction technique in computer vision. This registration method is composed of embedding and tracking. Embedding involves specifying four points to build the world coordinate system on which a virtual object will be superimposed. In this stage, any arbitrary two unrelated images or any 3×4 projective matrices with rank 3 can be used to calculate the 3D pseudo-projective coordinates of the four specified points. In the tracking process, these 3D pseudo-projective coordinates are used to track the four specified points to compute the registration matrix for augmentation. The proposed method is simple, as only four points need to be specified at the embedding stage, and the virtual object can then be easily augmented onto a real scene from a video sequence. One advantage is that the virtual objects can still be superimposed on the specified regions even when the regions are occluded in the video sequence. Another advantage of the proposed method is that the registration errors can be adjusted in real-time to ensure that they are less than certain thresholds that have been specified at the initial embedding stage. Several experiments have been conducted to validate the performance of the proposed generalized method.     

Registration using natural features for augmented reality systems

Registration is one of the most difficult problems in augmented reality (AR) systems. In this paper, a simple registration method using natural features based on the projective reconstruction technique is proposed. This method consists of two steps: embedding and rendering. Embedding involves specifying four points to build the world coordinate system on which a virtual object will be superimposed. In rendering, the Kanade-Lucas-Tomasi (KLT) feature tracker is used to track the natural feature correspondences in the live video. The natural features that have been tracked are used to estimate the corresponding projective matrix in the image sequence. Next, the projective reconstruction technique is used to transfer the four specified points to compute the registration matrix for augmentation. This paper also proposes a robust method for estimating the projective matrix, where the natural features that have been tracked are normalized (translation and scaling) and used as the input data. The estimated projective matrix will be used as an initial estimate for a nonlinear optimization method that minimizes the actual residual errors based on the Levenberg-Marquardt (LM) minimization method, thus making the results more robust and stable. The proposed registration method has three major advantages: 1) It is simple, as no predefined fiducials or markers are used for registration for either indoor and outdoor AR applications. 2) It is robust, because it remains effective as long as at least six natural features are tracked during the entire augmentation, and the existence of the corresponding projective matrices in the live video is guaranteed. Meanwhile, the robust method to estimate the projective matrix can obtain stable results even when there are some outliers during the tracking process. 3) Virtual objects can still be superimposed on the specified areas, even if some parts of the areas are occluded during the entire process. Some indoor and outdoor experiments have been conducted to validate the performance of this proposed method.     

基于投影技术的增强现实注册方法

注册技术是实现增强现实应用系统的关键问题之一。实现了一种利用投影技术改进了的注册方法。这种注册方法主要包含4个步骤：（1）检测标识和特征点的位置;（2）利用投影技术跟踪摄像机;（3）计算模型视图矩阵;（4）绘制虚拟物体。在初始阶段,指定4个点建立世界坐标系,虚拟物体将会被叠加到这个坐标系上;在注册过程中,利用投影技术跟踪特征点的位置,并计算用于增强的模型视图转换。这种注册方法可以为一般的室内增强现实系统提供所需的精确度和实时性。     

改进TLD与ORB的AR系统长时跟踪注册方法

针对增强现实系统长时跟踪注册需求以及三维跟踪注册时待注册区域尺度变化、光照变化、内外旋转等复杂环境易导致注册失败问题,提出改进TLD跟踪及ORB特征检测的增强现实长时三维注册方法。通过采用TLD长时鲁棒跟踪算法对待注册区域跟踪,并利用待注册位置自适应动态检测策略对TLD算法跟踪-学习-检测的结构机制的实时性和精确度进行优化;利用ORB算法对待注册位置进行特征检测及三维注册矩阵计算;将虚拟信息叠加至待注册位置。选取长时视频序列进行跟踪、检测及注册仿真实验。实验结果表明,改进TLD长时跟踪算法相比TLD算法在OPE精确度方面提升约5%,对待注册位置的跟踪速率提升约2倍,使得AR系统在复杂环境下的长时跟踪注册具有更好的稳定性和鲁棒性。     

一种基于视沉的增强现实三维注册算法

为了提高增强现实系统三维注册的精度和效率，提出了一种基于计算机视觉的增强现实三维注射算法，并已将其用于采用透射式头盔显示器的增强现实系统中，该算法有如下特点：（1）构架简单，实用性强，一般情况下只需4个平面标志物就可实现三维注册；（2）工作范围大，甚至可以应用到室外的增强现实系统中；（30数值求解过程最线性过程，误差小，可以满足增强现实系统高精度三维注册的要求，另外，应用这种算法所需要作的图象处理计算量很小，其典型系统包括一个彩色CCD和几个不同颜色的标志点，由于很容易获得标志点的对应像面位置，而且不需要计算图象对，因此实时性好，是一般图形工作站和PC机上的增强现实系统进行实时注册的算法基础。     

融合目标检测和空间投影的增强现实方法

实现对固定目标物的注册跟踪方法中, 目前最常使用预制标识物的方法, 或者需要使用集成深度摄像头等配件的专业AR设备, 成本较高. 针对现有方法的缺陷, 提出一种融合目标检测和空间投影算法的简单协作式混合跟踪注册技术, 先通过深度学习算法进行目标检测得到目标物类型, 再利用传感器位姿信息通过空间投影算法确定目标物ID, 从而提高了虚拟信息叠加在真实场景中的匹配度和准确性. 基于此算法实现了智慧物联基础设施维护的增强现实应用, 并对灯杆、垃圾桶等目标物进行了实验. 实验结果表明, 本方法可以在普通智能手机及AR眼镜上运行, 取得了预期效果, 也避免了预制标识物, 降低了对硬件资源的要求.     

A 3D GIS-based interactive registration mechanism for outdoor augmented reality system

Registering virtual objects with reference to their corresponding real-world objects plays a key role in augmented reality (AR) system. Although there have been a lot of work on using vision-based method to perform registration for indoor AR system, it is very difficult to apply such registration method for outdoor AR system due to the inability to modify the objects in outdoor environment and the huge range of working area. 3D Geographic Information System (GIS) is capable of providing an outdoor virtual geographic environment where users are located at, which may provide users with a corresponding virtual object for the one in the physical world. In this study, a 3D GIS-based registration mechanism is proposed for outdoor AR system. Specifically, an easy-use interactive method for precise registration was developed to improve the performance of the registration. To implement the registration mechanism, an outdoor AR system built upon 3D GIS was developed, named Augmented Reality Geographical Information System (ARGIS). ARGIS has the capability of performing precise registration in outdoor environment without using traditional vision tracking method, which thus enables users to arbitrarily manipulate the system. A prototype was developed to conduct experiment on the campus of Peking University, Beijing, China to test the proposed registration mechanism. The experiment shows that the developed registration mechanism is feasible and efficient in the outdoor environment. The ARGIS is expected to enrich the applications of outdoor AR system, including but not limited to underground facility mapping, emergency rescue and urban planning.     

Tangible authoring of 3D virtual scenes in dynamic augmented reality environment

This paper proposes tangible interfaces and interactions for authoring 3D virtual and immersive scenes easily and intuitively in tangible augmented reality (AR) environment. It provides tangible interfaces for manipulating virtual objects in a natural and intuitive manner and supports adaptive and accurate vision-based tracking in AR environments. In particular, RFID is used to directly integrate physical objects with virtual objects and to systematically support the tangible query of the relation between physical objects and virtual ones, which can provide more intuitive tangibility and a new way of virtual object manipulation. Moreover, the proposed approach offers an easy and intuitive switching mechanism between tangible environment and virtual environment. This paper also proposes a context-adaptive marker tracking method which can remove an inconsistent problem while embedding virtual objects into physical ones in tangible AR environments. The context-adaptive tracking method not only adjusts the locations of invisible markers by interpolating the locations of existing reference markers and those of previous ones, but also removes a jumping effect of movable virtual objects when their references are changed from one marker to another. Several case studies for generating tangible virtual scenes and comparison with previous work are given to show the effectiveness and novelty of the proposed approach.     

利用2D射影变换求解空间复杂结构的3D不变量

3D不变量作为不随姿态、视点等成像条件变化而变化的特征参量，可以广泛应用于计算机视觉的多重领域．通过分析2D射影变换矩阵求解的多种可能性，由单纯基于点集对应的思路扩展到利用点集、线集、点、线组合等其它方法，从而拓宽了建立两射影平面对应关系的应用条件．由此提出了一种基于多种点线组合构造虚元素的方法，结合实元素和虚元素可以巧妙提取空间复杂结构下的多种3D不变量，以用于目标识别和描述当中．实验结果验证了方法的有效性。     

A performance study for camera pose estimation using visual marker based tracking

Vision-based tracking systems are widely used for augmented reality (AR) applications. Their registration can be very accurate and there is no delay between real and virtual scene. However, vision-based tracking often suffers from limited range, errors, heavy processing time and present erroneous behavior due to numerical instability. To address these shortcomings, robust method are required to overcome these problems. In this paper, we survey classic vision-based pose computations and present a method that offers increased robustness and accuracy in the context of real-time AR tracking. In this work, we aim to determine the performance of four pose estimation methods in term of errors and execution time. We developed a hybrid approach that mixes an iterative method based on the extended Kalman filter (EKF) and an analytical method with direct resolution of pose parameters computation. The direct method initializes the pose parameters of the EKF algorithm which performs an optimization of these parameters thereafter. An evaluation of the pose estimation methods was obtained using a series of tests and an experimental protocol. The analysis of results shows that our hybrid algorithm improves stability, convergence and accuracy of the pose parameters.     

Calibration of an HMPD-Based Augmented Reality System

In augmented reality (AR) applications, accurately registering a virtual object with its real counterpart is a challenging problem. The size, depth, and geometry, as well as the physical attributes of the virtual object, have to be rendered precisely relative to a physical reference. This paper presents a systematic calibration process to address the registration challenge in a custom-designed AR system, which is based upon recent head-mounted projective display (HMPD) technology. Following a concise review of the HMPD concept and our system configuration, we first present a computational model of the HMPD viewing system and requirements for the system calibration. Then, we describe, in detail, the calibration procedures to obtain estimates of unknown transformations, summarize the application of the estimates in a customized graphics rendering toolkit, and discuss the evaluation experiments and observations. Finally, the implementation of a testbed to demonstrate a successful registration is briefly described, and experimental results are presented     

基于SURF与光流法的增强现实跟踪注册

提出一种基于SURF与光流法相结合的增强现实局部跟踪注册方法。采用光流法对移动对象区域进行跟踪,利用SURF算法仿射、尺度不变性及运算速度快的优点对该区域进行特征提取与匹配,利用相邻帧之间特征点的匹配关系求得三维注册矩阵,在保持注册精确性的同时降低了系统运算时间。实验结果表明该方法达到了实时跟踪与准确注册的效果,并且在环境变化时保持了较好的鲁棒性。     

基于遗传算法的射影重构

在实现分层重构的过程中，射影重构是关键的第1步。目前，大多已有算法对模拟数值是非常有效的，但对于真实图象效果并不理想。为了寻求更为鲁棒的算法，提出了一种基于遗传算法的射影重构算法。该算法对于射影深度采用十进制编码，并以测量矩阵的秩为4作为约束，来定义适应度函数，然后利用遗传算法，并结合奇异值分解（SVD）技术来迭代估计射影深度，进而实现射影重构，该算法是行之有效的，且鲁棒性较好。     

面向建筑物重建的相机标定方法研究

由于灭点具有很多独特的几何属性且大量地存在于建筑物场景中,因此针 对建筑物重建,提出了一种基于灭点的相机标定方法。首先通过构造各种几何约束关系,如 灭点与相机矩阵间的关系、世界坐标原点和相机矩阵间的关系,逐步实现相机矩阵的度量重 建和欧氏重建,获得相机矩阵的值,然后通过分解相机矩阵得到相机的内外部参数。该方法 在标定过程中无须借助任何标定物,求解过程简单,标定速度快。实验结果表明,该方法可 以满足虚拟现实中建筑物场景重建的需要。     

一种半自动的三维欧氏重建方法

从二维图像得到场景的三维模型是计算机视觉和虚拟现实的重要研究内容。本文通过用户的简单交互,利用平面型场景的同形关系自动进行两幅大差异图像之间的角点匹配,将这些匹配结果作为初始点,再利用RANSAC鲁棒算法估计基本矩阵。以此结果进行仿射重建,然后在简化相机模型的基础上通过给出的约束条件直接实现欧氏重建,真实数据的实验结果表明了该算法的有效性。     

MEEM跟踪和改进ORB特征检测的三维注册方法

针对增强现实系统三维注册在线跟踪模型漂移问题,以及特征检测算法耗时问题导致的注册失败。提出一种基于MEEM跟踪和改进ORB特征检测的三维注册方法。通过MEEM算法对移动对象区域跟踪。对跟踪的目标位置采用ORB算法检测特征点时,采用多尺度空间理论提取稳定特征点,并且采用改进决策树的递归调整方式,同时对特征检测参数设置。利用相邻帧之间特征点的匹配关系求得三维注册矩阵;将跟踪数据集与OpenGL生成的立方体模型进行跟踪注册仿真实验。仿真结果表明,改进ORB特征检测算法对待注册区域的检测具有尺度不变性、更高稳定性以及特征分布均匀,误差相比ORB算法降低约42%,该注册方法在运行过程中基本能够保证误差在7 mm以内;使得AR系统具有较好的实时性、精确性和鲁棒性。     

基于SURF的增强现实标识物跟踪注册

针对基于标识物的增强现实跟踪注册方法对复杂环境的适应能力和鲁棒性的不足,提出一种用SURF实现标识物跟踪注册的改进算法。用SURF对平面标识物的特征点进行检测与描述,采用K-means算法对检测出的标识物特征点集合进行聚类分析得到其聚类中心,结合对视频图像中标识物的阈值分割与连通域分析,以聚类中心构建标识物的SURF特征点坐标系,通过矩阵变换实现标识物的跟踪注册。实验结果表明,该算法的增强现实系统具备较好的鲁棒性、稳定性和实时性。     

Binocular mobile augmented reality based on stereo camera tracking

Mobile augmented reality (AR) applications have become feasible with the evolution of mobile hardware. For example, the advent of the smartphone allowed implementing real-time mobile AR, which triggered the release of various applications. Recently, rapid development of display technology, especially for stereoscopic displays, has encouraged researches to implement more immersive and realistic AR. In this paper, we present a framework of binocular augmented reality based on stereo camera tracking. Our framework was implemented on a smartphone and supports autostereoscopic display and video see-through display in which a smartphone can be docked. We modified edge-based 3-D object tracking in order to estimate poses of left and right cameras jointly; this guarantees consistent registration across left and right views. Then, virtual contents were overlaid onto camera images using estimated poses, and the augmented stereo images were distorted to be shown through a video see-through display. The feasibility of the proposed framework is shown by experiments and demonstrations.     

基于模板跟踪的实时无标志点注册算法

为了解决不依赖于标志点的增强现实系统的环境注册问题,提出了一种基于选定模板跟踪的无标志点注册算法。该算法使用已标定的单目摄像机进行场景捕捉,通过对运动目标上的选定模板进行实时跟踪,获得每帧场景图像中的对应特征,利用透射投影变换计算运动区域的单应性约束后,再结合摄像机内参数,完成对目标的3维姿态估计,从而得到场景的3维环境注册信息。实现了一种基于该算法的无标志点的增强现实系统。介绍了系统结构和工作流程,试验结果验证了理论的正确性和系统的鲁棒性。     

基于特征点动态选择的三维人脸点云模型重建

针对典型的点云配准方法中伪特征点过多导致配准效率低和配准结果不精确的问题,提出一种基于特征点动态选择的三维人脸点云模型重建方法。该方法在粗配准阶段,采用动态特征矩阵求解法获取粗匹配特征变换矩阵以避免伪特征点的干扰。在精配准过程中,采用二次加权法向量垂直距离法在人脸流形表面选择更有效的特征点以减少伪特征点的数量,并采用基于特征融合与局部特征一致性的迭代最近点方法进行精配准。经过对比实验验证了算法的可行性,实验结果表明,提出算法能够实现高精度且快速的三维人脸点云模型重建,且均方根误差达到1.816 5 mm,相较于其他算法,在模型重建精度和效率方面都有所提升,具有良好的应用前景。