基于极坐标区间运算的2D形状匹配

形状匹配是遥感图像目标识别、字符识别、手形识别和步态识别等任务中的关键步骤之一.针对刚体识别任务中形状匹配易受方向、尺度和位置等仿射变化量影响的情况,提出了一种新的基于极坐标区间运算的2D形状匹配算法.该算法首先以形状区域的中心点为极点,区域的最长轴方向为极轴,对形状区域进行归一化的极坐标变换;然后定义了同一角度对应的区域内点区间之间的运算;最后定义了两个区域归一化极坐标变换结果在区间运算下的相似度函数,用以表征两个区域之间的匹配度.从可见光遥感图像中提取的实物图像实验结果证明,该方法能够有效归类相似形状,并能区分各类不同的形状.     

基于改进的3维ICP匹配的单目视觉里程计

针对目前流行的单目视觉里程计当移动机器人做“近似纯旋转运动”时鲁棒性不强的问题,从理论上分析了其定位鲁棒性不高的原因,提出了一种基于改进的3维迭代最近点（ICP）匹配的单目视觉里程计算法．该算法首先初始化图像的边特征点对应的深度值,之后利用改进的3维ICP算法迭代求解2帧图像之间对应的3维坐标点集的6维位姿,最后结合边特征的几何约束关系利用扩展卡尔曼深度滤波器更新深度值．改进的ICP算法利用反深度不确定度加权、边特征梯度搜索与匹配等方法,提高了传统ICP算法迭代求解的实时性和准确性．并且将轮子里程计数据作为迭代初始值,能够进一步提高定位算法的精度和针对“近似纯旋转运动”问题的鲁棒性．本文采用3个公开数据集进行算法验证,该算法在不损失定位精度的前提下,能够有效提高针对近似纯旋转运动、大场景下的鲁棒性．单目移动机器人利用本文算法可在一定程度上校正里程计漂移的问题．     

使用NDT激光扫描匹配的移动机器人定位方法

提出一种将基于扫描匹配的蒙特卡洛定位方法,作为移动机器人完成自主任务的鲁棒性定位方法． 采用一种新的正态分布转换(NDT)激光扫描匹配算法,将从单个激光扫描重构的2D离散数据点集转换成2维平面内分段连续可微的概率分布,并使用Hessian矩阵法与另外的扫描相匹配,可以避免点与点之间对应的复杂问题．实验结果表明,该定位算法可以利用自然环境特征有效地完成室内环境下的自主定位．     

3D Multi-Layered Normal Distribution Transform for Fast and Long Range Scan Matching

Simultaneously Localization and Mapping (SLAM) problem requires a sophisticated scan matching algorithm, in which two consecutive point clouds belonging to highly correlated scene are registered by finding the rigid body transformation parameters when an initial relative pose estimate is available. A well-known scan matching method is the Iterative Closest Point (ICP) algorithm, and the basis of the algorithm is the minimization of an error function that takes point correspondences into account. Another 3D scan matching method called Normal Distribution Transform (NDT) has several advantages over ICP such as the surface representation capability, accuracy, and data storage. On the other hand, the performance of the NDT is directly related to the size of the cell, and there is no proved way of choosing an optimum cell size. In this paper, a novel method called Multi-Layered Normal Distribution Transform (ML-NDT) using various cell sizes in a structured manner is introduced. In this structure a number of layers are used, where each layer contains different but regular cell sizes. In the conventional NDT, the score function is chosen as Gaussian probability function which is minimized iteratively by Newton optimization method. However, the ML-NDT score function is described as the Mahalanobis distance function, and in addition to Newton optimization method, Levenberg–Marquardt algorithm is also adapted to the proposed method for this score function. The performance of the proposed method is compared to the original NDT, and the effects of the optimization methods are discussed. Moreover, an important issue in a scan matching algorithms is the subsampling strategy since the point cloud contains huge amount of data which has a non-uniform distribution. Therefore, the application of a sampling strategy is a must for fast and robust scan matching. In the performance analysis, two sampling strategies are investigated which are random sampling and grid based sampling. The method is successfully applied to experimentally obtained datasets, and the results show that ML-NDT with grid based sampling provides a fast and long range scan matching capability.     

3D Visual Odometry for Road Vehicles

This paper describes a method for estimating the vehicle global position in a network of roads by means of visual odometry. To do so, the ego-motion of the vehicle relative to the road is computed using a stereo-vision system mounted next to the rear view mirror of the car. Feature points are matched between pairs of frames and linked into 3D trajectories. Vehicle motion is estimated using the non-linear, photogrametric approach based on RANSAC. This iterative technique enables the formulation of a robust method that can ignore large numbers of outliers as encountered in real traffic scenes. The resulting method is defined as visual odometry and can be used in conjunction with other sensors, such as GPS, to produce accurate estimates of the vehicle global position. The obvious application of the method is to provide on-board driver assistance in navigation tasks, or to provide a means for autonomously navigating a vehicle. The method has been tested in real traffic conditions without using prior knowledge about the scene nor the vehicle motion. We provide examples of estimated vehicle trajectories using the proposed method and discuss the key issues for further improvement.     

二维振镜逐点扫描激光显示最大分辨率研究

要获得二维振镜逐点扫描式激光显示的最大分辨率,激光束应该在给定的时间T内在屏幕上扫描最多的点,T等于1/f,f为帧频.假定振镜扫描一个点需要的最小时间为t,则最大分辨率等于T/t.与传统的基于电场偏转或磁场偏转的光栅扫描不同,振镜扫描是基于机械偏转.振镜小角度阶跃响应时间决定了偏转角度阶跃越大,振镜转到目标位置的响应时间就越长.光栅扫描的水平消隐和垂直消隐都会导致大角度阶跃响应,从而导致扫描线所花的时间几乎与消隐的时间相同,因此,采用光栅扫描只能获得将近一半的最大分辨率.对任何给定的二维振镜扫描系统,本文提出了一种新的逐点一致扫描方法,使每个点的扫描显示时间均为最小时间t,完全消除了水平和垂直消隐,从而获得最大的扫描显示分辨率.     

A Probabilistic Framework for Sonar Scan Matching Localization

Scan matching is a popular localization technique based on comparing two sets of range readings gathered at consecutive robot poses. Scan matching algorithms implicitly assume that matching readings correspond to the same object in the environment. This is a reasonable assumption when using accurate sensors such as laser range finders and that is why they are extensively used to perform scan matching localization. However, when using other sensors such as ultrasonic range finders or visual sonar, this assumption is no longer valid because of their lower angular resolution and the sparsity of the readings. In this paper we present a sonar scan matching framework, the spIC, which is able to deal with the sparseness and low angular resolution of sonar sensors. To deal with sparseness, a process to group sonar readings gathered along short robot trajectories is presented. Probabilistic models of ultrasonic and odometric sensors are defined to cope with the low sonar angular resolution. Consequently, a probabilistic scan matching process is performed. Finally, the correction of the whole robot trajectory involved in the matching process is presented as a constrained optimization problem.     

Succinct 2D Dictionary Matching

The dictionary matching problem seeks all locations in a given text that match any of the patterns in a given dictionary. Efficient algorithms for dictionary matching scan the text once, searching for all patterns simultaneously. Existing algorithms that solve the 2-dimensional dictionary matching problem all require working space proportional to the size of the dictionary. This paper presents the first efficient 2-dimensional dictionary matching algorithm that operates in small space. Given d patterns, D={P ₁,…,P _d }, each of size m×m, and a text T of size n×n, our algorithm finds all occurrences of P _i , 1≤i≤d, in T. The preprocessing of the dictionary forms a compressed self-index of the patterns, after which the original dictionary may be discarded. Our algorithm uses O(dmlogdm) extra bits of space. The time complexity of our algorithm is close to linear, O(dm ²+n ² τlogσ), where τ is the time it takes to access a character in the compressed self-index and σ is the size of the alphabet. Using recent results τ is at most sub-logarithmic.     

Correlation-Based Scan Matching Using Ultrasonic Sensors for EKF Localization

This paper presents a localization method for a mobile robot equipped with only low-cost ultrasonic sensors. Correlation-based Hough scan matching was used to obtain the robot’s pose without any predefined geometric features. A local grid map and a sound pressure model of ultrasonic sensors were used to acquire reliable scan results from uncertain and noisy ultrasonic sensor data. The robot’s pose was measured using correlation-based Hough scan matching, and the covariance was calculated. Localization was achieved by fusing the measurements from scan matching with the robot’s motion model through the extended Kalman filter. Experimental results verified the performance of the proposed localization method in a real home environment.     

二维逐步正交匹配追踪算法

在图像等二维信号的应用与处理上,常规压缩感知理论框架存在重构算法效果差、图像块效应明显、对噪声敏感等问题。针对这些问题,根据现有二维观测模型和二维重构算法设计思想,可以设计一种新的重构算法：二维逐步正交匹配追踪算法。该算法借鉴了相关一维重构算法的设计思想,通过每次迭代选取符合阈值条件的多列原子进而正交化处理的步骤,提升了重构效率,改善了恢复图像质量。理论分析和实验结果表明,提出的算法在重构时间得到控制的情况下,得到的图像信噪比有较大提升,超越了现有典型的二维重构算法。     

基于形状轮廓特征的金字塔匹配算法

形状检索在计算机视觉中一直是一个具有挑战性的问题，其中对形状特征直方图距离的测量是评价形状检索算法优劣的一个重要因素。针对轮廓特征的直方图距离测量，算法引进一种在图像分类领域中应用广泛的金字塔匹配算法。不同于其他传统的直方图度量算法，金字塔匹配算法将形状的轮廓分成若干块，给每一块分配相应的权重，然后分别统计块中的特征，再计算特征的加权和进行相似度的测量。通过在不同形状数据集下实验，该方法能够有效地进行形状匹配和检索，且能得到较好的形状匹配精度。     

单目相机-3维激光雷达的外参标定及融合里程计研究

针对单目相机与3维激光雷达的融合里程计问题,提出了双阶段外参标定方法和基于混合残差的融合里程计方法.双阶段相机-激光雷达外参标定结合了基于运动和基于互信息2种标定方法.第1阶段为基于运动的外参标定法,在无初值的情况下得到外参的粗估计.第2阶段为基于互信息的外参标定法,以第1阶段的结果作为初值,利用互信息原理校准激光雷达反射率和相机灰度值,来优化标定结果.为进一步提高标定精度,第2阶段采用了一种针对稀疏激光雷达点云的遮挡点检测方法.所提出的双阶段外参标定方法在无需预设初值的前提下保证了标定结果的精度.在此基础上,提出了一种基于混合残差的相机与激光雷达融合里程计方法.该方法同时利用图像的直接和非直接图像特征计算重投影残差和光度残差.然后将不同类型的残差统一到非线性优化框架下,实现里程计估计.针对激光雷达数据稀疏性带来的深度信息缺失的问题,提出了一种基于颜色信息的深度插值方法,有效补充了特征点数量.最后,基于实物和公共数据集实验,对所提出的外参标定和融合里程计算法的鲁棒性和精度进行了评估.实验结果表明,所提出的外参标定方法可以在没有初值的情况下,给出精确的外参估计;所提出的融合里程计方法在公共数据集上和实物实验中均表现出了良好的估计精度和鲁棒性.     

平面点匹配的一点校准算法

点模式匹配是一项重要的视觉课题。对于一个平面点集,由平移和旋转并伴有一定噪声作用产生另一点集,提出一个基于一点校准的点模式快速匹配算法,并推广到带有属性点的匹配问题中。基于一点校准的点模式匹配算法,其计算复杂性为O(mn),其中m,n分别是两个点集所含点的个数,比基于两点距离近似相等的校准匹配算法,其计算复杂性为O(m2nl)(其中l为第二个点集中与第一个点集中任两个点的距离近似相等的平均个数),极大地减少了计算量。     

一种新的二维开曲线匹配算法研究

在提取碎片轮廓的基础上,提出了一种基于相似变换下的新的尺寸不变为标示符的二维开曲线匹配方法。基本思想是首先以弧长的曲率绝对值的积分方法,通过对轮廓重采样来计算轮廓曲线上的特征点,特征点分曲线为若干段,然后特征段之间的Hausdorff距离来比较两曲线的段的相似性,当Hausdorff距离小于给定的容差时,可认为相应的轮廓是匹配的,实验证明算法更快有效。     

基于Hausdorff距离的2D形状匹配改进算法

在计算机视觉检测中,常常需要将两幅图象在空间上配准,以便进行后续的检测过程,该文提出将Ｈａｕｓｄｏｒｆｆ距离作为物体轮廓相似性的测度,并用遗传算法进行最佳形状匹配的快速搜索,根据遗传搜索的结果再进行一次线性搜索,从而提高解的精度,实验结果证明了该方法能快速,精确地对两幅２Ｄ形状进行匹配。     

历史建筑的空间信息采集——三维激光扫描技术应用

本文介绍了三维激光扫描技术应用于历史建筑现状空间信息采集方面的研究和实验。     

基于2D轮廓图的三维模型相似性比较研究

将三维模型分别从正视、侧视、俯视3个角度投影到3个平面.再将3个平面上的2D投影轮廓图等分成若干个扇形区域.计算每个区域内的顶点与模型重心的最大距离.如此分别得到三个平面上2D轮廓图的特征向量.提取每个模型的这3个特征向量作为其形状描述符,然后进行接下来的模型相似性匹配.实验结果表明:该方法不但简便而且具有较好的三维模型检索准确性.     

A Randomized O(log2 k)-Competitive Algorithm for Metric Bipartite Matching

We consider the online metric matching problem in which we are given a metric space, k of whose points are designated as servers. Over time, up to k requests arrive at an arbitrary subset of points in the metric space, and each request must be matched to a server immediately upon arrival, subject to the constraint that at most one request is matched to any particular server. Matching decisions are irrevocable and the goal is to minimize the sum of distances between the requests and their matched servers. We give an O(log² k)-competitive randomized algorithm for the online metric matching problem. This improves upon the best known guarantee of O(log³ k) on the competitive factor due to Meyerson, Nanavati and Poplawski (SODA ’06, pp. 954–959, 2006). It is known that for this problem no deterministic algorithm can have a competitive better than 2k?1, and that no randomized algorithm can have a competitive ratio better than lnk.     

A Tree Matching Algorithm and VLSI Architecture for Real-Time 2D Object Classification

This paper presents a real-time classification algorithm for two-dimensional (2D) object contours using a tree model which is implemented in a modular very large scale integration (VLSI) architecture. The hardware implementation takes advantage of pipelining, parallelism, and the speed of VLSI technology to perform real-time object classification. Using the multiresolution tree model, the classification algorithm is invariant under 2D similarity transformations and recognizes the visible portions of occluded objects. The VLSI classification system is implemented in 0.8 mm CMOS and is capable of performing 34 000 matchings per second.