基于混合运动估计方法的视觉里程计

由于RGB-D相机深度信息范围有限且易受噪声影响,为了提高其视觉里程计的精度,提出一种基于混合3D-3D和3D-2D运动估计方法的视觉里程计。使用基于RICP算法（RANSAC-ICP）的3D-3D模型,并结合3D-2D运动模型,将深度信息缺失的二维特征点添加到估计方法中,充分利用了图像信息,提高了匹配准确率。综合考虑了关键帧和前一帧的地图信息进行迭代估计,增加了匹配点对数量,提供了更多约束信息。在该混合运动估计方法的基础上,结合稀疏光束平差法SBA对位姿估计结果进行优化,达到定位精度高、积累误差小的效果。在基于Kinect相机的移动平台上进行了验证,结合离线和在线实验表明,该方法满足实时性同时有效地提高了定位精度。     

基于几何约束及0-1规划的视频帧间线段特征匹配算法

针对线段因遮挡、断裂以及端点提取不准确等原因造成的线段特征匹配困难问题,特别是现有匹配算法在匹配过程中出现"多配多"时直接采取"最相似匹配"而导致丢失大量真实匹配的问题,提出了一种基于多重几何约束及0-1规划的线段特征匹配算法。首先,基于校正后视频帧间线段特征的空间相邻性计算线段匹配的初始候选集;然后,基于极线约束、单应矩阵模型约束以及点-线相邻性约束等多重几何约束,对候选集进行筛选从而剔除部分错误匹配;其次,将线段匹配问题建模为一个大规模0-1规划问题;最后,设计了一种基于分组策略的两阶段求解算法对该问题进行求解,从而实现线段特征的"一配一"精确匹配。实验结果表明,该算法与LS（Line Sigature）、LJL（Line-Junction-Line）方法相比,匹配正确率接近,但匹配线段数量分别提高了60%和11%。所提算法可以实现视频帧间的线段特征匹配,为基于线特征的视觉SLAM（Simultaneously Localization and Mapping）奠定基础。     

室内环境下基于平面与线段特征的RGB-D视觉里程计

针对室内环境的结构特点,提出一种使用平面与线段特征的RGB-D视觉里程计算法．首先根据RGB-D扫描点的法向量对3D点云进行聚类,并使用随机抽样一致（RANSAC）算法对每簇3D点集进行平面拟合,抽取出环境中的平面特征;随后利用边缘点检测算法分割出环境中的边缘点集,并提取出环境中的线段特征;然后提出一种基于平面与线段几何约束的特征匹配算法,完成特征之间的匹配．在平面与线段特征匹配结果能提供充足的位姿约束的条件下,利用特征之间的匹配关系直接求解RGB-D相机的位姿;若不能,则利用匹配线段的端点以及线段点集来实现RGB-D相机位姿的估计．在TUM公开数据集中的实验证明了选择平面与线段作为环境特征可以提升视觉里程计估计和环境建图的精度．特别是在fr3/cabinet数据集中,本文算法的旋转、平移的均方根误差分别为2.046°/s、0.034m/s,要显著优于其他经典的视觉里程计算法．最终将本文系统应用到实际的移动机器人室内建图中,系统可以建立准确的环境地图,且系统运行速度可以达到3帧/s,满足实时处理的要求．     

一种基于帧间差探测函数模型的运动估计算法

针对基于匹配搜索的运动估计快速算法中,匹配环节在运动估计算法中耗费大量的处理时间,使得块匹配法运动估计实时性差的问题,提出了一种基于帧间差探测函数模型的运动估计新算法,该算法将"虚拟边缘"引入目标运动事件中,建立了帧间差探测函数模型,并确定了实际的帧间差探测函数模型中参数的选择策略.实验结果及分析表明,该算法不仅能够很好地完成较复杂背景下运动小目标的跟踪,而且能够获得相对于块匹配法更好的实时性能.     

位平面匹配的电子稳像算法的改进

针对位平面匹配算法很难对视频图像中存在的旋转运动进行估计的缺陷,提出了一种改进的电子稳像算法。该算法采用钻石搜索策略的位平面法来估计并补偿视频图像序列间的平移运动,对参考帧图像进行拉普拉斯变换,在靠近图像边缘处选取若干个特征小块与当前帧进行块匹配,进一步计算并补偿其可能存在的旋转运动。通过理论分析和实验仿真表明：在处理存在旋转运动的视频图像时,改进后的算法在满足实时性的同时提高了稳像精度。     

平行线段对应的运动估计线性算法

针对图像序列特征的运动估计问题,提出一种基于平行线段对应的运动估计线性算法(parallel linesegments,PLS).线段采用点、线两要素表述模型,利用平行性,由像线段逐步恢复场景中的空间线段,再根据螺旋理论四元数法建立并求解基于空间线段两要素的线性运动约束方程,进一步建立粒子群优化算法(PSO)优化算法优...     

基于有向模板和颜色加权SVD的图像匹配算法

为快速稳定地匹配视频序列,并考虑SVD算法的高效性,根据视频序列的特点,对SVD匹配算法进行改进,提出了一种适合视频序列的匹配算法。该算法使用Harris角点检测算子检测兴趣点,使用有向模板提取具有旋转不变性的特征,并通过引入颜色加权法改进SVD算法中的相似性度量函数。同时,又提出一种基于运动一致性约束的误配点剔除方法,首先拟合匹配点间的运动模型,然后自适应地调整参数将错误的匹配点剔除。该算法使用有向模板消除图像间旋转变换的影响,使用颜色特征降低兴趣点匹配时的不确定性,通过运动一致性约束降低误配点数量。实验结果表明,该算法在图像间存在旋转变换关系和不同的光照条件时都可以获得很好的匹配结果,特别是在图像间基线距离较大时仍能得到大量的匹配点并具有很高的正确匹配率,能很好满足实际需要。     

采用自适应缩放系数优化的块匹配运动估计

尽管基于平移模型的快速块匹配运动估计算法在一定程度上解决了高计算量的问题,但却是以牺牲运动补偿质量为代价的,而高阶运动模型尚存在计算量高、收敛不稳定的不足.通过实验统计发现,视频中约有56.21%的块包含缩放运动,进而得出缩放运动是除平移运动外最主要的视频运动形式的结论.进而借助双线性插值,在传统的块平移模型中引进一个缩放系数,将运动补偿误差表示为该缩放系数的一元二次函数,利用韦达定理推导出1D缩放运动下最佳缩放系数的计算方法,并将其进一步推广到2D等比例缩放运动的情况下.在此基础上,提出了一种采用自适应缩放系数优化的快速块匹配运动估计算法.该算法以菱形搜索计算平移矢量,再用自适应缩放系数确定待预测块的最佳匹配块.在33个标准测试视频上的实验结果表明,与基于平移模型的块匹配全搜索和快速菱形搜索相比,该算法的平均运动补偿峰值信噪比（peak signal-to-noise ratio,简称PSNR）分别提高了0.11dB和0.64dB,计算量比全搜索下降了96.02%,略高于菱形搜索;与基于缩放模型的运动估计相比,该算法的平均峰值信噪比较之3D全搜索下降了0.62dB,但是比快速3D菱形搜索提高了0.008dB,而计算量仅分别为两者的0.11%和3.86%,并且无需向解码端传输缩放矢量,能够实现编、解码端的自同步,不会增加边信息的码流开销.此外,该自适应缩放系数计算方法还可与菱形搜索以外的其他快速块匹配运动估计相结合,提高其运动补偿质量.     

基于BPOF特征与深度图像的人体姿态估计研究

人体姿态估计是一个有着非常广泛应用前景的研究课题,并且在计算机视觉领域中,该课题已经成为了重要研究热点之一。针对人体姿态估计中的特征表达提出了一种基于二元纯位相匹配滤波器（BPOF）的特征提取算法,首先对图像中每一个像素点都从8个方向去计算扫描线段长度值,然后再将得到的8个值引入到BPOF算法中进行计算以便得到该像素点的特征值,同时针对随机森林分类器进行优化,最终对图像中的人体姿态做出估计。该改进方法在识别率以及鲁棒性方面有了很大提高,同时优化的随机森林分类器使得算法系统时间开销有所降低。     

一种基于仿射变换模型的目标跟踪算法

在图像目标跟踪的应用中,传统方法多采用基于平移运动模型和相关（correlation）类型匹配准则的跟踪算法。该类算法以目标仅发生平移运动为假设前提,难以有效适应目标在图像中通常会发生的缩放、旋转和错切等变化。本文应用了一种基于仿射变换模型的目标跟踪算法。该算法建立起包含六个参数的仿射变换模型,以其描述目标在序列图像中的变化,然后构造适当的匹配误差目标函数,并采用牛顿迭代法求解得到最优的仿射参数。实验结果表明,该算法具有较强的鲁棒性,能够得到较好的跟踪效果。     

Motor Algebra for 3D Kinematics: The Case of the Hand-Eye Calibration

In this paper we apply the Clifford geometric algebra for solving problems of visually guided robotics. In particular, using the algebra of motors we model the 3D rigid motion transformation of points, lines and planes useful for computer vision and robotics. The effectiveness of the Clifford algebra representation is illustrated by the example of the hand-eye calibration. It is shown that the problem of the hand-eye calibration is equivalent to the estimation of motion of lines. The authors developed a new linear algorithm which estimates simultaneously translation and rotation as components of rigid motion.     

The Motor Extended Kalman Filter: A Geometric Approach for Rigid Motion Estimation

In this paper the motor algebra for linearizing the 3D Euclidean motion of lines is used as the oretical basis for the development of a novel extended Kalman filter called the motor extended Kalman filter (MEKF). Due to its nature the MEKF can be used as online approach as opposed to batch SVD methods. The MEKF does not encounter singularities when computing the Kalman gain and it can estimate simultaneously the translation and rotation transformations. Many algorithms in the literature compute the translation and rotation transformations separately. The experimental part demonstrates that the motor extended Kalman filter is an useful approach for estimation of dynamic motion problems. We compare the MEKF with an analytical method using simulated data. We present also an application using real images of a visual guided robot manipulator; the aim of this experiment is to demonstrate how we can use the online MEKF algorithm. After the system has been calibrated, the MEKF estimates accurately the relative position of the end-effector and a 3D reference line. We believe that future vision systems being reliably calibrated will certainly make great use of the MEKF algorithm.     

New Geometric Methods for Computer Vision: An Application to Structure and Motion Estimation

We discuss a coordinate-free approach to the geometry of computer vision problems. The technique we use to analyse the three-dimensional transformations involved will be that of geometric algebra: a framework based on the algebras of Clifford and Grassmann. This is not a system designed specifically for the task in hand, but rather a framework for all mathematical physics. Central to the power of this approach is the way in which the formalism deals with rotations; for example, if we have two arbitrary sets of vectors, known to be related via a 3D rotation, the rotation is easily recoverable if the vectors are given. Extracting the rotation by conventional means is not as straightforward. The calculus associated with geometric algebra is particularly powerful, enabling one, in a very natural way, to take derivatives with respect to any multivector (general element of the algebra). What this means in practice is that we can minimize with respect to rotors representing rotations, vectors representing translations, or any other relevant geometric quantity. This has important implications for many of the least-squares problems in computer vision where one attempts to find optimal rotations, translations etc., given observed vector quantities. We will illustrate this by analysing the problem of estimating motion from a pair of images, looking particularly at the more difficult case in which we have available only 2D information and no information on range. While this problem has already been much discussed in the literature, we believe the present formulation to be the only one in which least-squares estimates of the motion and structure are derived simultaneously using analytic derivatives.     

图形变换和运动的共形几何代数表示方法*

共形几何代数是一种新的几何表示和几何计算工具,它具有直观、简洁、高效、统一、雅致等特性。在简单介绍外积、内积和几何积等基本概念之后,重点论述了共形几何代数在图形反射、旋转、平移等变换和刚体运动、螺旋运动等方面的描述和计算方法,并给出了实验示例。共形几何代数在计算机图形学、计算机视觉和机器人学等领域将有广泛应用。     

Pose Estimation in Conformal Geometric Algebra Part II: Real-Time Pose Estimation Using Extended Feature Concepts

Part II uses the foundations of Part I [35] to define constraint equations for 2D-3D pose estimation of different corresponding entities. Most articles on pose estimation concentrate on specific types of correspondences, mostly between points, and only rarely use line correspondences. The first aim of this part is to extend pose estimation scenarios to correspondences of an extended set of geometric entities. In this context we are interested to relate the following (2D) image and (3D) model types: 2D point/3D point, 2D line/3D point, 2D line/3D line, 2D conic/3D circle, 2D conic/3D sphere. Furthermore, to handle articulated objects, we describe kinematic chains in this context in a similar manner. We ensure that all constraint equations end up in a distance measure in the Euclidean space, which is well posed in the context of noisy data. We also discuss the numerical estimation of the pose. We propose to use linearized twist transformations which result in well conditioned and fast solvable systems of equations. The key idea is not to search for the representation of the Lie group, describing the rigid body motion, but for the representation of their generating Lie algebra. This leads to real-time capable algorithms.Bodo Rosenhahn gained his diploma degree in Computer Science in 1999. Since then he has been pursuing his Ph.D. at the Cognitive Systems Group, Institute of Computer Science, Christian-Albrechts University Kiel, Germany. He is working on geometric applications of Clifford algebras in computer vision.Prof. Dr. Gerald Sommer received a diploma degree in physics from the Friedrich-Schiller-Universität Jena, Germany, in 1969, a Ph.D. degree in physics from the same university in 1975, and a habilitation degree in engineering from the Technical University Ilmenau, Germany, in 1988. Since 1993 he is leading the research group Cognitive Systems at the Christian-Albrechts-Universität Kiel, Germany. Currently he is also the scientific coordinator of the VISATEC project.     

Algorithms for matching 3D line sets

Matching two sets of lines is a basic tool that has applications in many computer vision problems such as scene registration, object recognition, motion estimation, and others. Line sets may be composed of infinitely long lines or finite length line segments. Depending on line lengths, three basic cases arise in matching sets of lines: 1) finite-finite, 2) finite-infinite, and 3) infinite-infinite. Case 2 has not been treated in the literature. For Cases 1 and 3, existing algorithms for matching 3D line sets are not completely satisfactory in that they either solve special situations, or give approximate solutions, or may not converge, or are not invariant with respect to coordinate system transforms. In this paper, we present new algorithms that solve exactly all three cases for the general situation. The algorithms are provably convergent and invariant to coordinate transforms. Experiments with synthetic and real 3D image data are reported.     

Lie Algebra and System Identification Techniques for 3D Rigid Motion Estimation and Monocular Tracking

This paper addresses the parameters’ estimation of 2D and 3D transformations. For the estimation we present a method based on system identification theory, we named it the “A-method”. The transformations are considered as elements of the Lie group GL(n) or one of its subgroups. We represent the transformations in terms of their Lie Algebra elements. The Lie algebra approach assures to follow the shortest path or geodesic in the involved Lie group. To prove the potencial of our method, two experiments are presented. The first one is a monocular estimation of 3D rigid motion of an object in the visual space. With this aim, the six parameters of the rigid motion are estimated based on measurements of the six parameters of the affine transformation in the image. Secondly, we present the estimation of the affine or projective transformations involved in monocular region tracking. Jaime Ortegón-Aguilar received his degree in computer sciences at the Universidad Autonoma de Yucatan in Merida, Mexico in 2000. He earned his M.Sc. degree at the Cinvestav in Guadalajara, Mexico in 2002. He received his PhD degree from Cinvestav in 2006. His research interests include image processing, computer vision, robotics and applications of geometric algebra. Eduardo Jose Bayro-Corrochano gained his Ph.D. in Cognitive Computer Science in 1993 from the University of Wales at Cardiff. From 1995 to 1999 he has been Researcher and Lecturer at the Institute for Computer Science, Christian Albrechts University, Kiel, Germany, working on applications of geometric Clifford algebra to cognitive systems. At present is a full professor at CINVESTAV Unidad Guadalajara, México, Department of Electrical Engineering and Computer Science. His current research interest focuses on geometric methods for artificial perception and action systems. It includes geometric neural networks, visually guided robotics, humanoids, color image processing, Lie bivector algebras for early vision and robot maneuvering. He developed the quaternion wavelet transform for quaternion multi-resolution analysis using the phase concept. He is associate editor of Robotics and Journal of Advanced Robotic Systems and member of the editorial board of Journal of Pattern Recognition, Journal of Mathematical Imaging and Vision, Iberoamerican Journal of Computer and Systems and Journal of Theoretical and Numerical Approximation. He is editor and author of the following books: Geometric Computing for Perception Action Systems, E. Bayro-Corrochano, Springer Verlag, 2001; Geometric Algebra with Applications in Science and Engineering, E. Bayro-Corrochano and G. Sobczyk (Eds.), Birkhauser 2001; Handbook of Geometric Computing for Pattern Recognition, Computer Vision, Neurocomputing and Robotics, E. Bayro-Corrochano, Springer Verlag, 2005. He has published over 120 refereed journal, book chapters and conference papers. He is fellow of the IAPR society.     

基于SIFT特征描述子的立体匹配算法

目前,立体匹配是计算机视觉领域最活跃的研究课题之一。为了克服传统的局部特征匹配算法对噪声和图像灰度的非线性变换敏感的缺点,本文提出了一种新的基于SIFT(Scale Invariant Feature Transform)特征描述子的立体匹配算法。该算法利用图像梯度信息,构造基于三维梯度方向直方图的SIFT特征描述子作为区域特征描述符,通过立体视觉理论中的极线约束将匹配特征的搜索空间从二维降到一维,最后以基于特征描述子欧氏距离的最近邻匹配得到匹配结果。实验结果表明,该方法匹配精度高,对图像灰度的非线性变换比较鲁棒,可以应用于对匹配算法鲁棒性要求比较高的立体视觉系统中。     

A pixel-based outlier-free motion estimation algorithm for scalable video quality enhancement

Scalable video quality enhancement refers to the process of enhancing low quality frames using high quality ones in scalable video bitstreams with time-varying qualities. A key problem in the enhancement is how to search for correspondence between high quality and low quality frames. Previous algorithms usually use block-based motion estimation to search for correspondences. Such an approach can hardly estimate scale and rotation transforms and always introduces outliers to the motion estimation results. In this paper, we propose a pixel-based outlier-free motion estimation algorithm to solve this problem. In our algorithm, the motion vector for each pixel is calculated with respect to estimate translation, scale, and rotation transforms. The motion relationships between neighboring pixels are considered via the Markov random field model to improve the motion estimation accuracy. Outliers are detected and avoided by taking both blocking effects and matching percentage in scaleinvariant feature transform field into consideration. Experiments are conducted in two scenarios that exhibit spatial scalability and quality scalability, respectively. Experimental results demonstrate that, in comparison with previous algorithms, the proposed algorithm achieves better correspondence and avoids the simultaneous introduction of outliers, especially for videos with scale and rotation transforms.     

Optic flow field segmentation and motion estimation using a robustgenetic partitioning algorithm

Optic flow motion analysis represents an important family of visual information processing techniques in computer vision. Segmenting an optic flow field into coherent motion groups and estimating each underlying motion is a very challenging task when the optic flow field is projected from a scene of several independently moving objects. The problem is further complicated if the optic flow data are noisy and partially incorrect. In this paper, the authors present a novel framework for determining such optic flow fields by combining the conventional robust estimation with a modified genetic algorithm. The baseline model used in the development is a linear optic flow motion algorithm due to its computational simplicity. The statistical properties of the generalized linear regression (GLR) model are thoroughly explored and the sensitivity of the motion estimates toward data noise is quantitatively established. Conventional robust estimators are then incorporated into the linear regression model to suppress a small percentage of gross data errors or outliers. However, segmenting an optic flow field consisting of a large portion of incorrect data or multiple motion groups requires a very high robustness that is unattainable by the conventional robust estimators. To solve this problem, the authors propose a genetic partitioning algorithm that elegantly combines the robust estimation with the genetic algorithm by a bridging genetic operator called self-adaptation