A 3-D RECONSTRUCTION METHOD BASED ON THE CONSTRAINT OF EPIPOLAR GEOMETRY

This paper combines the least-square method and iteration method to get the fundamental matrix and develops a new evaluation function based on the epipolar geometry. During the iteration, with the evaluation function as a measurment, the points which bring larger noise are deleted, and the points with smaller noise are retained, thus the precision of our method is increased. The experiment results indicate the new method is precise in calculation, stable in performance and resistant to noise.

A DIFFERENTIAL GEOMETRIC DESCRIPTION FOR TIME-INDEPENDENT CHETAEV'S NONHOLONOMIC MECHANICAL SYSTEM WITH UNILATERAL CONSTRAINTS

By applying the framework of the tangent bundle geometry to the method of Lagrange multi- pliers,a geometric description of Chetaev's nonholonomic systems subjected to unilateral nonholonomic con- straints trod unilateral holonomic constraints respectively in time-independent circumstances is presented.

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/Hh K-p2 h XNn U.

A geometric framework for time-dependent mechanical systems with unilateral constraints

The description of modern differential geometry for time-dependent Chetaev nonholonomic mechanical systems with unilateral constraints is studied. By using the structure of exact contact manifold, the geometric framework of time- dependent nonholonomic mechanical systems subject to unilateral nonholonomic constraints and unilateral holonomic constraints respectively is presented.

Feature matching based on geometric constraints in weakly calibrated stereo views of curved scenes

The identification of the correspondences of points of views is an important task. A new feature matching algorithm for weakly calibrated stereo images of curved scenes is proposed, based on mere geometric constraints. After initial correspondences are built via the epipolar constraint, many point-to-point image mappings called homographies are set up to predict the matching position for feature points. To refine the predictions and reject false correspondences, four schemes are proposed. Extensive experiments on simulated data as well as on real images of scenes of variant depths show that the proposed method is effective and robust.

Influence of external constraint and rolling geometry on deformation banding of copper single crystals with {123}<634> orientation

In order to further understand the similarity and difference betweendeformation mechanisms of single crystals and poly-crystalline materials, the influence of externalconstraint and rolling geometry on the deformation behaviour of copper single crystals with{123}<634> orientation was investigated by embedding them into metal frames of different strengths.The metal frames were made of aluminum and mild steel, respectively. The results show that thedeformation banding degree of the crystal increases with the strength of metal frame and shearstrain. For the crystals rolled under lower (gamma)g ((gamma)g is the ratio of the geometricalredundant shear strain to the normal rolling strain), the deformation is homogeneous. For thecrystals rolled under higher (gamma)g, the deformation is extremely inhomogeneous. The deformationis more homogeneous in the crystals rolled in steel frames than that rolled in aluminum frames. TheS-orientation is more stable in the crystals rolled under lower (gamma)g than that rolled underhigher (gamma)g.

SEMANTIC CONSTRAINT MODELER FOR 2D AND 3D GEOMETRY

Design changes for 2D & 3D geometry are the most important features in the process of product design.Constraint modeling for variationl geometry based on geometric reasoning is one of the best approaches for this goal.However,it is difficult for the proposed systems to maintain or handle the consistency and completeness of the constraint model of the design objects.To change this situation,a semantic model and its control approach are presented,aiming at the integration of the data,knowledge and method related to design objects.Aconstraint definition system for in- teractively defining the semantic model and a prototype modeler based on the semantic model are also implemented to examine the idea which is extended to 3D geometric design too.

基于条纹投影三目系统的舌面完整点云获取方法

传统的舌诊过程存在客观性较差的问题,将计算机视觉技术应用于舌诊可以有效推进舌诊客观化。双目立体视觉结合结构光条纹投影技术是三维测量的常用手段,但对于舌诊的测量场景,由于舌体表面常带有津液和口水等,造成条纹图像出现分布随机性较大的高反光区域,导致相位解算错误和点云缺失。本文提出了一种基于光栅投影的三目测量系统,由3个相机构成1个三目和3个双目子系统。在相位和级次约束基础上引入双极线约束,提高三目立体匹配精度,并利用匹配点补充优化三目匹配点集,重建高反光区域点云。结果显示,对比传统双目系统,本系统的匹配精度和重建精度均得到提升,特别是在真实舌面测量中能够生成纹理清晰、特征完整的点云,对舌面高反光区域进行了有效测量,有助于舌诊的客观化进行。

基于共形几何的面部模型插值构建算法

针对传统三维模型构建方法难以获取连续维度的高质量面部模型问题,提出一种以不同表情的多面部模型为数据源基于共形几何的面部模型插值构建技术。利用准共形映射算法将面部模型降维到二维平面;提出一种插值算法对多模型形状特征进行线性插值,为构建过渡模型定义几何约束,同时提出一种自适应模型选择算法在数据源中自适应选择基础模型;通过几何约束引导准共形迭代改变基础模型形状;将变化后的二维模型转化到三维空间,构建具有过渡表情的三维面部模型。实验结果表明,该算法的有效性和运行效率都得到大幅提高。

基于几何约束的倾斜影像特征匹配方法

针对倾斜影像视角变换较大、重复纹理导致匹配数量少、匹配精度不高的问题,提出一种适用于倾斜影像的特征点、线分级匹配方法.首先,用直线提取(检测)算法(LSD)获取影像直线特征,并将直线特征以一定约束进行直线组对,构建直线对区域与改进的SIFT(scale-invariant feature transform)特征描述符进行匹配,使用RANSAC算法剔除误匹配,获得初始匹配结果后再进行核线约束;然后,利用已获得直线对区域进行影像局部纠正,在纠正后的局部影像上采用SIFT匹配并反算回原始影像,利用得到的同名点全局纠正倾斜影像,并进行特征点匹配与采用基于方格的运动统计算法(GMS)剔除误匹配,仍将匹配结果反算回原始影像上;最后,将仿射尺度不变特征变化结果与点拓展匹配结果进行合并,得到最终匹配结果.试验结果表明:本文方法匹配正确率与经典的仿射不变匹算法(ASIFT)的正确率相差不大,但匹配数量却是ASIFT算法的1倍~3倍.

A DIRECTED GRAPH ALGORITHM OF VARIATIONAL GEOMETRY BASED ON GEOMETRIC REASONING

The undirected graph to express engineering drawings is discussed .The principle to re-solve and reason the undirected graph is presented, and the algorithm finally transforms theundirected graph into the resolvable directed graph. Therefore,a rapid and simple way is suppliedfor variational design. A prototype of this algorithm has been implemented, and some examplesare given.

(3-RPS)+(2-RCR)混联机构末端约束分析

为探索“并+并”型少自由度混联机构末端约束的特点,以(3-RPS)+(2-RCR)机构为研究对象,提出了求解其末端约束的螺旋系求交法。阐述了(3-RPS)+(2-RCR)机构末端约束/自由度组成原理,给出了末端约束/自由度计算公式;结合线几何分析了机构在不同几何位形下的末端自由度数目;应用解析几何理论和螺旋理论建立子约束螺旋系对应的直纹面和母线方程,得到了螺旋三系和四系的交集解析模型,确定了机构末端约束螺旋;讨论了不同几何位形下的末端约束/自由度性质,给出机构在3种不同位形下末端约束求解的数值算例。研究表明,在一般位形下,该机构末端约束并非约束力/力偶,而是一般形式的力螺旋。提出的螺旋系交集求解方法为此类混联机构末端约束问题研究提供了有效的解决方案。

多目鱼眼视觉SLAM特征点误匹配的剔除优化

为了解决由于鱼眼图像显著失真和明显的视角差异而导致的定位精度下降的问题,提出了一种去除多目鱼眼视觉SLAM系统中误匹配特征点的策略。该策略采用从粗到细的误匹配特征点去除过程,在粗匹配阶段,使用阈值为0.6的匹配算法获得粗匹配阶段的初始点集。在精细去除阶段,采用预校准的多摄像机模型将匹配的特征点转换为同一坐标系,并将其作为承载向量投影到单位球上,利用球上的外极约束去除不匹配的特征点。在去除不匹配的特征点后,在投影球面上建立重投影误差函数,对初始姿态点和映射点进行非线性优化。该策略在24 000张鱼眼图像上进行了测试,结果表明,该剔除策略显著降低了失配率,提高了初始化和定位精度,有效地提高了系统的定位精度和性能效率。

不同分布下红外主动目标特征点配准方法研究

视觉测量中经常需要用到特征匹配来计算位姿信息,但尚无针对红外主动目标设计特征匹配可用的算法,为实现对不同分布红外主动目标的匹配,本文提出了一种通用的两阶段特征点匹配方法。第一阶段为粗配准,首先检测图像特征点集的凸包,获取最外围点;通过构建三角形特征集,并使用马氏距离进行相似三角形计算搜索实现快速粗配准。第二阶段为精匹配,首先通过粗匹配特征计算欧拉角避免匹配结果的180°旋转对称;针对粗配准后的可能存在的特征点缺失问题,采用极线约束精匹配策略,充分利用已匹配特征点的几何信息,有效实现对剩余点的精确匹配。理论分析与实验表明,在13个红外发光点组成的旋转对称点集及非旋转对称点集下,该方法在绝对大小0°~40°的旋转范围内能高效匹配,实验测试极限性能能够达到50°,并对实际场景下特征点的遮挡等情况具有较好的鲁棒性,实验结果验证其适应性与稳定性,具有较高的实用价值。

基于背景修复的动态SLAM

视觉同时定位与地图构建(Simultaneous localization and mapping,SLAM)过程中,动态物体引入的干扰信息会严重影响定位精度。通过剔除动态对象,修复空洞区域解决动态场景下的SLAM问题。采用Mask-RCNN获取语义信息,结合对极几何方法对动态对象进行剔除。使用关键帧像素加权映射的方式对RGB和深度图空洞区域进行逐像素恢复。依据深度图相邻像素相关性使用区域生长算法完善深度信息。在TUM数据集上的实验结果表明,位姿估计精度较ORB-SLAM2平均提高85.26%,较DynaSLAM提高28.54%,在实际场景中进行测试依旧表现良好。

动态场景下基于YOLOv5和几何约束的视觉SLAM算法

目的移动智能体在执行同步定位与地图构建(Simultaneous Localization and Mapping,SLAM)的复杂任务时,动态物体的干扰会导致特征点间的关联减弱,系统定位精度下降,为此提出一种面向室内动态场景下基于YOLOv5和几何约束的视觉SLAM算法。方法首先,以YOLOv5s为基础,将原有的CSPDarknet主干网络替换成轻量级的MobileNetV3网络,可以减少参数、加快运行速度,同时与ORB-SLAM2系统相结合,在提取ORB特征点的同时获取语义信息,并剔除先验的动态特征点。然后,结合光流法和对极几何约束对可能残存的动态特征点进一步剔除。最后,仅用静态特征点对相机位姿进行估计。结果在TUM数据集上的实验结果表明,与ORB-SLAM2相比,在高动态序列下的ATE和RPE都减少了90%以上,与DS-SLAM、Dyna-SLAM同类型系统相比,在保证定位精度和鲁棒性的同时,跟踪线程中处理一帧图像平均只需28.26 ms。结论该算法能够有效降低动态物体对实时SLAM过程造成的干扰,为实现更加智能化、自动化的包装流程提供了可能。

一种改进的视图几何基本矩阵估计法

多视图几何中的基本矩阵估计需要利用准确的对应点,但是图像噪声或光线变化会产生错误匹配,进而严重影响基本矩阵估计的准确度。为提高基本矩阵估计的准确性,文章提出了一种基于对极约束梯度的迭代方法去估计基本矩阵。该方法能在最少的迭代次数下迅速剔除两视图匹配过程中的错误匹配点。然后再加入对应点相关性的约束,可以得到最佳对应点集合用于估计基本矩阵。通过在各类不同场景的图像上实验分析可以发现,该方法相比于其他方法估计基本矩阵误差至少降低20%。

基于稀疏和稠密图像匹配与对极约束的树高提取改进算法

树高是监测森林状况的重要参数,摄影测量法具有低成本、灵活的特性,是树高采集的重要方法之一.作为一种被动遥感方式,传统的摄影测量方法往往需要数量较多,重叠率较高的图像数据,这与传统图像特征的稀疏性有关.为了提高图像数量受限条件下的树高提取精度,提出将稀疏特征匹配和稠密像素匹配相结合,并使用对极约束过滤外点的方法,得到稠密且精度较高的匹配结果,并通过三维重建算法得到森林场景点云.该方法在少量图像的情况下就可以较为完整地重建森林场景并提取树高,将提取的树高与机载激光雷达(light detection and ranging,LiDAR)点云的结果进行对比,相关系数为0.91,最大误差为1.64 m.该算法只需要少量的重叠图像,这表明了该算法在处理高分辨率卫星图像方面具有一定潜力.

融合AMF与EGC的10 kV不停电作业安全距离检测方法

检测作业人员与带电体间的距离是否超限是保障10 kV不停电作业安全的关键。针对传统的立体视觉测距方法精度与实时性不足的问题,提出一种融合自适应多尺度特征(adaptive multi-scale features,AMF)网络与对极几何约束(epipolar geometry constraints,EGC)的安全距离检测方法。首先,通过实例分割精确提取双目图像中人员关键部位与带电体的轮廓。其次,利用EGC约束特征匹配点的搜索范围,通过AMF突出匹配点相关特征并为多尺度特征分配自适应权重从而获得多尺度融合特征,AMF通过其联合注意力模块提高特征点表示能力与匹配准确度,其全局-局部融合模块通过联合左右图特征为多尺度代价聚合提供更鲁棒的特征表示;最后,通过3D代价聚合减少参数量,从而提高检测速度;通过关键点视差计算进行安全距离评估,从而实现作业人员与带电体间的距离检测。实验结果表明,所提方法测距精确度达到94.6%,帧率达到28.9帧/s,满足10 kV不停电作业现场安全距离检测的精确性与实时性的要求。

基于改进目标检测的动态场景SLAM研究

针对单目SLAM在动态场景下存在的对极约束误匹配问题,提出一种基于目标检测的动态特征点选择方法,通过在特征提取时剔除SLAM系统前端图像帧中动态特征点,提高SLAM的定位精度。提出了一个改进的目标检测网络,利用重叠面积、距离相似度和余弦相似度构建描述边界框的回归损失函数,实现目标的准确定位,获得当前图像帧中物体特征点范围。判断物体类别,对于标记为动态的物体根据目标检测结果剔除前端图像帧中的动态特征点。根据静态特征点,采用对极约束进行两帧图像间的特征匹配估计位姿,对单目相机运动进行跟踪、建图与闭环检测。通过对目标检测网络的主干进行结构重参数化改进,提升推理过程的速度,保证整体系统运行的实时性。在公开数据集KITTI的11个序列上的实验结果表明:改进后的系统比ORB-SLAM3系统定位精度提升了23.4%,帧率可以达到30帧/s以上,在保证实时运行的条件下能有效提高动态场景下单目SLAM系统定位精度。