基于单应矩阵的相对位姿改进算法

从单应矩阵恢复相对位姿在视觉导航、视觉伺服应用中具有重要价值,证明了单应矩阵的新性质,并利用该性质改进了基于单应矩阵分解的相对位姿估计算法。与已有算法相比,该算法的候选解个数减半,并扩大了适用范围。理论分析、合成数据和真实数据测试均表明,改进方法使从候选解中筛选出唯一解的运算时间减少了50%,提高了位姿估计的总体运算效率。     

基于平面单应性的单目视觉里程计设计

针对如何准确获取位姿信息来实现移动机器人的避障问题,提出一种可用于实时获取移动机器人位姿的单目视觉里程计算法。该算法利用单目摄像机获取连续帧间图像路面SURF（Speeded Up Robust Features）特征点;并结合极线几何约束来解决路面特征点匹配较难的问题,通过计算平面单应性矩阵获取移动机器人的位姿变化。实验结果表明该算法具有较高的精度和实时性。     

基于正交平面的摄像机自定标

提出了一种基于正交平面摄像机定标的新算法。它利用场景中的正交平面,摄像机作五次以上的平移运动,根据每次运动关于平面的单应矩阵建立内参数的线性约束方程组,从而线性地确定内参数。与以往的定标方法相比,文章对摄像机的运动不苛刻,只需控制摄像机作平移运动,这在一般的实验平台上可以很容易地实现,并且线性地确定摄像机所有的五个内参数。模拟实验和真实图象实验表明,文章给出的方法在机器人视觉中具有一定的实用价值。     

Infinitesimal Plane-Based Pose Estimation

Estimating the pose of a plane given a set of point correspondences is a core problem in computer vision with many applications including Augmented Reality (AR), camera calibration and 3D scene reconstruction and interpretation. Despite much progress over recent years there is still the need for a more efficient and more accurate solution, particularly in mobile applications where the run-time budget is critical. We present a new analytic solution to the problem which is far faster than current methods based on solving Pose from \(n\) Points (PnP) and is in most cases more accurate. Our approach involves a new way to exploit redundancy in the homography coefficients. This uses the fact that when the homography is noisy it will estimate the true transform between the model plane and the image better at some regions on the plane than at others. Our method is based on locating a point where the transform is best estimated, and using only the local transformation at that point to constrain pose. This involves solving pose with a local non-redundant 1st-order PDE. We call this framework Infinitesimal Plane-based Pose Estimation (IPPE), because one can think of it as solving pose using the transform about an infinitesimally small region on the surface. We show experimentally that IPPE leads to very accurate pose estimates. Because IPPE is analytic it is both extremely fast and allows us to fully characterise the method in terms of degeneracies, number of returned solutions, and the geometric relationship of these solutions. This characterisation is not possible with state-of-the-art PnP methods.     

局部特征描述改进的LK跟踪注册方法

针对KLT跟踪方法抗光照变化和抗遮挡较差的问题,提出一种使用局部特征描述改进的LK跟踪注册方法(DF-LK)。使用ORB特征点求解初始位姿,通过自适应非极大值抑制重新划分特征点,选择均匀分布的特征点作为LK方法跟踪的控制点集。相邻帧图像之间的单应性矩阵通过在DF描述后的图像上使用LK方法进行求解,跟踪的结果由向前向后错误检测进行评估,由单应性矩阵和初始位姿求解出当前帧的摄像机位姿,并叠加虚拟信息。实验结果表明,该方法在光照变化、部分遮挡和透视变化时均有较好的稳定性和鲁棒性。     

基于改进RANSAC算法的单应矩阵鲁棒估计方法

单应矩阵的鲁棒性和精度直接决定了其应用效果,如何利用RANSAC算法估计出鲁棒、精确的单应矩阵,仍是一个有待研究的热点问题。针对传统RANSAC算法迭代次数多、运行时间长、单应矩阵估计精度较低的问题,在SIFT特征匹配算法的基础上,从剔除样本集中不符合图像几何特性的部分外点、快速舍弃不合理单应矩阵和迭代精炼单应矩阵等方面对RANSAC算法进行改进,提出一种基于改进RANSAC算法的单应矩阵估计方法,提高了单应矩阵估计的精度和效率。实验结果表明,该方法有效解决了传统RANSAC算法存在的问题,能够快速、精确估计单应矩阵。另外,对于不同视角和大小的图像,该方法均具有较好的鲁棒性。     

基于线对应的单应矩阵估计及其在视觉测量中的应用

单应矩阵估计在视觉测量、摄像机标定、三维重建等领域有重要的应用价值, 但是在具体应用中如何鲁棒、精确地估计单应矩阵仍是一个没有很好解决的问题. 在研究和实际应用中我们发现,直接线性方法在基于线对应的单应矩阵估计中会出现在某些特殊的摄像机姿态下误差较大的情况. 针对这一情况, 我们提出了一种基于线对应的归一化单应矩阵估计方法并将其应用到视觉测量中,即通过简单的归一化操作使测量矩阵元素的大小分布尽量均匀, 从而降低了测量矩阵的条件数, 提高了算法的鲁棒性, 同时又保持了直接线性方法简单、快速、易实现等优点. 模拟实验和真实图像实验均验证了该方法的有效性.     

基于ORB-SLAM2系统的快速误匹配剔除算法与地图构建

针对ORB-SLAM2系统中随机抽样一致（RANSAC）算法在误匹配剔除时因其算法本身的随机性而导致效率较低的问题和在ORB-SLAM2系统里未能构建稠密点云地图的问题，采用渐进一致采样（PROSAC）算法来改进ORB-SLAM2系统中的误匹配剔除，并在系统中添加稠密点云地图和八叉树地图构建线程。首先，与RANSAC算法相比，PROSAC算法依据评价函数对特征点进行预排序，并选取评价质量较高的特征点求解单应性矩阵，根据单应性矩阵的解与匹配误差阈值进行误匹配剔除；然后，根据ORB-SLAM2系统进行相机的位姿估计与重定位；最后，根据所选关键帧进行稠密点云地图与八叉树地图的构建。根据TUM数据集上的实验结果，PROSAC算法在进行相同图像的误匹配剔除时所用时间是RANSAC算法的50%左右，并且所提系统的绝对轨迹误差与相对位姿误差与ORB-SLAM2系统基本一致，表现出良好的鲁棒性；另外，与稀疏点云地图相比，提出的新构建地图可以直接用于机器人的导航与路径规划。     

基于ORB-SLAM2系统的快速误匹配剔除算法与地图构建

针对ORB-SLAM2系统中随机抽样一致（RANSAC）算法在误匹配剔除时因其算法本身的随机性而导致效率较低的问题和在ORB-SLAM2系统里未能构建稠密点云地图的问题,采用渐进一致采样（PROSAC）算法来改进ORB-SLAM2系统中的误匹配剔除,并在系统中添加稠密点云地图和八叉树地图构建线程。首先,与RANSAC算法相比,PROSAC算法依据评价函数对特征点进行预排序,并选取评价质量较高的特征点求解单应性矩阵,根据单应性矩阵的解与匹配误差阈值进行误匹配剔除;然后,根据ORB-SLAM2系统进行相机的位姿估计与重定位;最后,根据所选关键帧进行稠密点云地图与八叉树地图的构建。根据TUM数据集上的实验结果,PROSAC算法在进行相同图像的误匹配剔除时所用时间是RANSAC算法的50%左右,并且所提系统的绝对轨迹误差与相对位姿误差与ORB-SLAM2系统基本一致,表现出良好的鲁棒性;另外,与稀疏点云地图相比,提出的新构建地图可以直接用于机器人的导航与路径规划。     

基于机器学习的自然特征匹配方法

针对增强现实中的三维注册问题,提出一种基于机器学习的图像自然特征点识别方法。基于高斯混合模型进行样本选择,利用模式识别中的分类方法替代特征向量的最近邻匹配,将计算负担从实时阶段转移到训练阶段,利用各匹配点对之间的相似度计算核密度估计的权值,实现相关平面目标的跟踪。实验结果表明,该方法实时性好、相机位姿估计精确,对光照、遮挡、透视等变化具有较强的鲁棒性。     

Study on Visual Positioning Based on Homography for Indoor Mobile Robot

Monocular visual positioning for indoor mobile robot is concerned in this paper.A new visual positioning method based on homography matrix in Euclidean space is proposed.It can calculate the position and pose of the mobile robot according to the intrinsic parameters of camera and two position-known points in a plane.It is very simple and low cost in computation.The experimental results show its effectiveness.     

基于单应性矩阵的室内移动机器人视觉定位研究

Monocular visual positioning for indoor mobile robot is concerned in this paper. A new visual positioning method based on homography matrix in Euclidean space is proposed. It can calculate the position and pose of the mobile robot according to the intrinsic parameters of camera and two position-known points in a plane. It is very simple and low cost in computation. The experimental results show its effectiveness.     

Analysis of head pose accuracy in augmented reality

A method is developed to analyze the accuracy of the relative head-to-object position and orientation (pose) in augmented reality systems with head-mounted displays. From probabilistic estimates of the errors in optical tracking sensors, the uncertainty in head-to-object pose can be computed in the form of a covariance matrix. The positional uncertainty can be visualized as a 3D ellipsoid. One useful benefit of having an explicit representation of uncertainty is that we can fuse sensor data from a combination of fixed and head-mounted sensors in order to improve the overall registration accuracy. The method was applied to the analysis of an experimental augmented reality system, incorporating an optical see-through head-mounted display, a head-mounted CCD camera, and a fixed optical tracking sensor. The uncertainty of the pose of a movable object with respect to the head-mounted display was analyzed. By using both fixed and head mounted sensors, we produced a pose estimate that is significantly more accurate than that produced by either sensor acting alone     

基于三维模型的人脸姿态估计方法

提出一种三维人脸姿态估计方法。该方法通过估计三维平面人脸模型到图像平面的单应矩阵来获得人脸相对于摄像机坐标系的旋转矩阵,并利用M-估计优化方法迭代求精。其主要特点是：实施简单,不需要对透视摄像机参数预先进行标定,能够在较大范围内较精确地估计人脸姿态。对模拟数据及真实人脸图像的实验均验证了该方法的有效性。     

Line Geometry and Camera Autocalibration

We provide a completely new rigorous matrix formulation of the absolute quadratic complex (AQC), given by the set of lines intersecting the absolute conic. The new results include closed-form expressions for the camera intrinsic parameters in terms of the AQC, an algorithm to obtain the dual absolute quadric from the AQC using straightforward matrix operations, and an equally direct computation of a Euclidean-upgrading homography from the AQC. We also completely characterize the 6×6 matrices acting on lines which are induced by a spatial homography. Several algorithmic possibilities arising from the AQC are systematically explored and analyzed in terms of efficiency and computational cost. Experiments include 3D reconstruction from real images. This work has been partly supported by the Spanish Administration agencies CDTI and CICYT under projects CENIT-VISION 2007-1007 and TEC2007-67764 respectively.     

A vision-based fast base frame calibration method for coordinated mobile manipulators

The mobile manipulators (MMs) have been increasingly adopted for machining large and complex components. In order to ensure the machining efficiency and quality, the MMs usually need to cooperate with each other. However, due to the low motion accuracy of the mobile platform, the relative pose accuracy between the coordinated MMs are difficult to guarantee, so an effective calibration method is needed to on-line obtain the relative pose of the MMs. For this purpose, a vision-based fast base frame calibration method is proposed in this paper, which can quickly and accurately obtain the relative pose between the coordinated MMs. The method only needs to add a camera and a marker, and then a frame network of the calibration system can be generated by installing the marker at three different positions. Based on the Perspective-n-Points principle and the robot forward kinematics, the transformation matrix of the marker frame with respect to the camera frame and the robot base frame can be determined by simply obtaining the images of the marker at different positions and corresponding robot joint angles. Then, the relative pose between the base frames of coordinated MMs can be determined by the calibration equation established based on a frame closed chains. In addition, the calibration method is capable of real-time calculation by dividing the calibration process into off-line and on-line stages. Simulation and experimental results have verified the effectiveness of the proposed method.     

基于YOLOv3和EPnP算法的多药盒姿态估计

针对机械臂药盒抓取操作中对药盒定位和姿态估计的要求,提出一种基于YOLOv3深度学习算法和EPnP算法相结合的多药盒姿态估计方法,此方法主要分为多药盒定位和姿态估计两部分;首先通过YOLOv3算法实现药盒的快速精确定位,并通过定位框分割出单个药盒;然后进行特征提取和特征匹配并估计单应矩阵;通过单应矩阵的透视矩阵变换求得药盒平面4个角点的像素坐标并作为EPnP求解所需的2D点,结合药盒先验尺寸信息在相机坐标系下构建药盒对应的3D点坐标以实现药盒姿态求解;通过结合OptiTrack系统设计了药盒姿态精度对比实验,结果表明,该算法充分发挥了YOLOv3算法兼具快速性和准确性的优势,并且具有良好的姿态估计精度,总体算法速度达到15 FPS,药盒姿态估计平均误差小于0.5°。     

An Iterative Pose Estimation Algorithm Based on Epipolar Geometry With Application to Multi-Target Tracking

This paper introduces a new algorithm for estimating the relative pose of a moving camera using consecutive frames of a video sequence. State-of-the-art algorithms for calculating the relative pose between two images use matching features to estimate the essential matrix. The essential matrix is then decomposed into the relative rotation and normalized translation between frames. To be robust to noise and feature match outliers, these methods generate a large number of essential matrix hypotheses from randomly selected minimal subsets of feature pairs, and then score these hypotheses on all feature pairs. Alternatively, the algorithm introduced in this paper calculates relative pose hypotheses by directly optimizing the rotation and normalized translation between frames, rather than calculating the essential matrix and then performing the decomposition. The resulting algorithm improves computation time by an order of magnitude. If an inertial measurement unit (IMU) is available, it is used to seed the optimizer, and in addition, we reuse the best hypothesis at each iteration to seed the optimizer thereby reducing the number of relative pose hypotheses that must be generated and scored. These advantages greatly speed up performance and enable the algorithm to run in real-time on low cost embedded hardware. We show application of our algorithm to visual multi-target tracking (MTT) in the presence of parallax and demonstrate its real-time performance on a 640 × 480 video sequence captured on a UAV. Video results are available at https://youtu.be/HhK-p2hXNnU.       

Autocalibration of a projector-camera system

This paper presents a method for calibrating a projector-camera system that consists of multiple projectors (or multiple poses of a single projector), a camera, and a planar screen. We consider the problem of estimating the homography between the screen and the image plane of the camera or the screen-camera homography, in the case where there is no prior knowledge regarding the screen surface that enables the direct computation of the homography. It is assumed that the pose of each projector is unknown while its internal geometry is known. Subsequently, it is shown that the screen-camera homography can be determined from only the images projected by the projectors and then obtained by the camera, up to a transformation with four degrees of freedom. This transformation corresponds to arbitrariness in choosing a two-dimensional coordinate system on the screen surface and when this coordinate system is chosen in some manner, the screen-camera homography as well as the unknown poses of the projectors can be uniquely determined. A noniterative algorithm is presented, which computes the homography from three or more images. Several experimental results on synthetic as well as real images are shown to demonstrate the effectiveness of the method.     

MultiCol Bundle Adjustment: A Generic Method for Pose Estimation,Simultaneous Self-Calibration and Reconstruction for Arbitrary Multi-Camera Systems

In this paper, we present a generic, modular bundle adjustment method for pose estimation, simultaneous self-calibration and reconstruction for multi-camera systems. In contrast to other approaches that use bearing vectors (camera rays) as observations, we extend the common collinearity equations with a general camera model and include the relative orientation of each camera w.r.t to the fixed multi-camera system frame yielding the extended collinearity equations that directly express all image observations as functions of all unknowns. Hence, we can either calibrate the camera system, the cameras, reconstruct the observed scene, and/or simply estimate the pose of the system by including the corresponding parameter block into the Jacobian matrix. Apart from evaluating the implementation with comprehensive simulations, we benchmark our method against recently published methods for pose estimation and bundle adjustment for multi-camera systems. Finally, all methods are evaluated using a 6 degree of freedom ground truth data set, that was recorded with a lasertracker.