Monocular 3D scene reconstruction at absolute scale

In this article we propose a method for combining geometric and real-aperture methods for monocular three-dimensional (3D) reconstruction of static scenes at absolute scale. Our algorithm relies on a sequence of images of the object acquired by a monocular camera of fixed focal setting from different viewpoints. Object features are tracked over a range of distances from the camera with a small depth of field, leading to a varying degree of defocus for each feature. Information on absolute depth is obtained based on a Depth-from-Defocus approach. The parameters of the point spread functions estimated by Depth-from-Defocus are used as a regularisation term for Structure-from-Motion. The reprojection error obtained from bundle adjustment and the absolute depth error obtained from Depth-from-Defocus are simultaneously minimised for all tracked object features. The proposed method yields absolutely scaled 3D coordinates of the scene points without any prior knowledge about scene structure and camera motion. We describe the implementation of the proposed method both as an offline and as an online algorithm. Evaluating the algorithm on real-world data, we demonstrate that it yields typical relative scale errors of a few per cent. We examine the influence of random effects, i.e. the noise of the pixel grey values, and systematic effects, caused by thermal expansion of the optical system or by inclusion of strongly blurred images, on the accuracy of the 3D reconstruction result. Possible applications of our approach are in the field of industrial quality inspection; in particular, it is preferable to stereo cameras in industrial vision systems with space limitations or where strong vibrations occur.     

基于无人机遥感影像拓扑分析的三维重建

在无需任何地面控制点或其它先验知识前提下,探索一种基于无人机遥感影像的三维重建方法.利用无人机飞控数据建立的影像拓扑结构,依次通过特征点提取、影像匹配、从运动恢复结构等步骤估计出相机位置和姿态参数,并恢复出场景特征点云信息,最后对重建精度进行分析.试验结果表明,文中提出的方法可快速、可靠地实现较高精度的三维模型重建.     

3D Motion parameters determination based on binocular sequence images

Exactly capturing three dimensional (3D) motion information of an object is an essential and important task in computer vision, and is also one of the most difficult problems. In this paper, a binocular vision system and a method for determining 3D motion parameters of an object from binocular sequence images are introduced. The main steps include camera calibration, the matching of motion and stereo images, 3D feature point correspondences and resolving the motion parameters. Finally, the experimental results of acquiring the motion parameters of the objects with uniform velocity and acceleration in the straight line based on the real binocular sequence images by the mentioned method are presented.     

Camera localization for augmented reality and indoor positioning: a vision-based 3D feature database approach

ABSTRACT

The recent fast development in computer vision and mobile sensor technology such as mobile LiDAR and RGB-D cameras is pushing the boundary of the technology to suit the need of real-life applications in the fields of Augmented Reality (AR), robotics, indoor GIS and self-driving. Camera localization is often a key and enabling technology among these applications. In this paper, we developed a novel camera localization workflow based on a highly accurate 3D prior map optimized by our RGB-D SLAM method in conjunction with a deep learning routine trained using consecutive video frames labeled with high precision camera pose. Furthermore, an AR registration method tightly coupled with a game engine is proposed, which incorporates the proposed localization algorithm and aligns the real Kinetic camera with a virtual camera of the game engine to facilitate AR application development in an integrated manner. The experimental results show that the localization accuracy can achieve an average error of 35?cm based on a fine-tuned prior 3D feature database at 3?cm accuracy compared against the ground-truth 3D LiDAR map. The influence of the localization accuracy on the visual effect of AR overlay is also demonstrated and the alignment of the real and virtual camera streamlines the implementation of AR fire emergency response demo in a Virtual Geographic Environment.     

基于结构光和单CCD相机的物体表面三维测量

非接触式物体表面三维自动测量是计算机视觉领域的中心任务之一 ,围绕这个问题 ,提出了一种利用结构光 ,单 CCD相机和双定向技术实现物体表面三维自动测量的新方法。采用该方法 ,无需测定相机和结构光光截面之间的相对位置 ,在单目序列影像上就可测量出物体表面的三维坐标。     

双目序列影像3维运动物体定位跟踪

将计算机视觉中立体和运动视觉相结合,通过数字摄影测量方法,对智能视觉监控中计算机系统所获得的双序列图像通过物方“图像”分析法完成对运动物体空间位置的定位、量测及其跟踪,其中包括:摄像机检校,立体-运动双匹配约束,运动参数的求解及其云台运动控制等内容。给出采用所述方法,从真实双目序列影像中获取物体以匀速直线运动和匀加速直线运动云台运动控制的实验结果。     

低成本大视场深度相机阵列系统

在测距传感器不断轻量化、小型化以及室内外地图一体化导航应用的驱动下,三维（3D）室内移动测量成为当今研究和应用的热点,在室内建模、室内定位等新兴领域中的应用越来越广泛。3D室内移动测量系统通常配备激光扫描仪、全景相机、惯性测量单元（inertial measurement unit,IMU）系统和里程计等传感器,虽能实现3D室内点云数据的采集,但其距离传感器-激光扫描仪价格昂贵且便携性较差。彩色深度（RGB depth,RGB-D）相机为低成本3D室内移动测量系统构建提供了新的距离成像传感器选择,但主流型号RGB-D相机视场角小,继而导致数据采集效率远低于传统激光扫描仪,难以做到点云数据的完整覆盖与稳健采集,且易造成同时定位与制图（simultaneous localization and mapping,SLAM）过程中跟踪失败。针对以上问题,构建了一种低成本室内3D移动测量系统采集设备,通过组合多台消费级RGB-D相机构成大视场RGB-D相机阵列,提出了一种阵列RGB-D相机内外参数标定方法,并通过实验检验了设计系统采集的点云数据的精度。     

From 2D TO 3D Through Modelling Based On A Single Image

Three-dimensional modelling from single images remains an interesting topic of investigation in the research community, even though range sensors are becoming a common alternative for the generation of 3D information. The interest in single-image-based modelling is motivated by a wide spectrum of applications such as cultural heritage, civil engineering, urban planning and even criminology. In this paper a complete new production flowline is presented for modelling based on a single image. The modelling process consists of a series of familiar steps in photogrammetry and computer vision: feature extraction, vanishing point computation, camera self-calibration, 3D reconstruction and dimensional analysis. In particular, the methodology developed for single-image-based modelling takes a scientific approach combining several proven techniques with robust estimators. Finally, in order to demonstrate its capabilities, the reported examples include several real situations applied in different contexts.     

3D Motion parameters determination based on binocular sequence images

Introduction Amongexistingvisionmoniteringandtheesti mationof3Dmotion,nearlyallinvestigations aremoniteringandtracingthemotionobject basedonsinglesequenceimages.Themotionin formationbyanalyzingthesinglesequenceima gesisrelative,whichincludesascaleoffactor…     

基于多像灭点的相机定标

近年来,3维目标建模一直是计算机视觉及摄影测量领域的研究热门,其中拍摄目标的相机(或摄像机)定标是问题的关键之一.详细阐述了基于单像、利用灭点对相机进行定标的理论的特点及不足,并对其进行误差分析,从而提出了一种新的基于多方位、多像的灭点定标方法.这种方法克服了原有理论的缺陷,使标定出的相机内外方位参数更加精确、稳定.     

基于控制点约束影像的密集匹配及其在考古发掘中的应用

针对大场景考古挖掘现场的三维重建情况,选取半全局匹配策略作为研究基础,设计了一种基于附加控制点约束的半全局匹配算法进行序列影像密集匹配。将稀疏匹配中的特征提取和匹配技术用于提取初始特征,并由这些初始特征转化的同名特征点,生成视差空间影像中的视差控制点,以此作为一种可靠的约束,提高其密集匹配的精度。同时,采用影像分块的策略,将原始大核线影像分成若干对小核线影像,进行密集匹配,以达到提高计算效率,改善计算结果的目的。实验证明,该方法可实现大面积考古挖掘现场的快速三维重建,并且能够在进行文物形态三维重建的同时获取挖掘现场文物分布的正射影像平面图,为准确记录挖掘现场文物分布位置及考古发掘、调查及遗址保护规划编制等提供科学依据。     

无序航空遥感影像的三维地形重建

无序航空影像的三维重建是摄影测量和计算机视觉领域研究的热点问题。提出一种可以不依赖任何辅助信息,由无序航空遥感影像全自动重建三维地形模型的算法流程。实验通过3组具有代表性的影像数据集验证了该方法的有效性和适用性。对重建后的三维地形模型的绝对精度检验表明,该方法重建的三维模型不仅具有较高的平面精度,而且当影像的基高比较好时,也可以获得较高的高程精度。     

从摄影测量到计算机视觉

首先回顾了摄影测量的历史,从透视几何、成像设备、摄影平台、测量法和测量工具等4个方面较系统地总结了前人的贡献。其次,简要介绍了计算机视觉的起源,并从几何角度分析了计算机视觉与摄影测量之间的紧密联系,探讨了两者在实用上的一些区别。再次,从语义方面,分析了遥感学科的发展,与机器学习和计算机视觉之间的关系,以及目前深度学习和连接主义的盛行。最后,展望了摄影测量的未来,指出与计算机视觉、人工智能等学科的进一步交叉融合是摄影测量发展的必然之路。     

矿体信息的八叉树存储和检索技术

近几年来，在计算机绘图、计算机视觉和数字图象处理等方面三维目标的八叉树表示成为热门论题。本文介绍一种八叉树编码，并将它应用于矿体信息的存储和检索，取得了明显的效果。针对八叉树的构成较费机时的问题，我们提出了一种从三维栅格变换成八叉树的算法，并在VAX3100型工作站上试验。结果表明，所提出的算法其时间复杂度与栅格数大体呈线性关系，用八叉树存储矿体信息占用的存储空间一般仅为栅格表示的10－30％。     

影像畸变对基本矩阵估计精度的影响分析

由于镜头制造工艺的限制和拍摄条件及环境的影响,影像本身都存在或多或少的畸变误差,这种误差通过传播和累积给影像的后期处理及各种应用造成了不稳定因素。针对计算机立体视觉中基本矩阵的估计精度问题进行了深入研究,通过对相机非线性畸变的自动纠正,分别获取了校正前和校正后的基本矩阵。实验数据表明,在对影像进行畸变校正后估计出来的基本矩阵在平均核线距离和平均余差上都明显小于畸变校正前的。     

利用单相机和神经网络估计的室内定位导航

由于三维场景与二维图像之间存在着非线性和高度复杂的关系,使用相机对用户的位置进行估计需要建立复杂的数学模型。针对该问题,本文提出了使用神经网络估计的单相机进行室内定位的方法。室内定位系统的主要优点是LED能够使用可见光通信发送其位置信息。首先,该方法充分利用LED光线的投影不变性,借助图像传感器通信（ISC）完成虚拟直线的构建;然后,运用神经网络估计从该虚拟直线中提取出相机的方向信息;最后,使用一个简单数学方程估计用户位置。仿真试验考虑了4种情形,结果表明,本文提出的方法性能优于同类方法,对于一个房间内的大部分地方,定位误差在35 mm以内。     

Real-time fusion of multiple videos and 3D real scenes based on optimal viewpoint selection

3D real scenes are a digital virtual space that represents and portrays the real world in a photorealistic, three-dimensional, and sequential manner. Existing methods for constructing and updating 3D models, such as oblique photography and laser scanning, are difficult to meet the demand of perceiving the real world intuitively, dynamically, and in real time. In recent years, the method of integrating rapidly rising video data and 3D models has become increasingly popular. Compared with existing methods, it enhances the real-time perception of 3D scenes by taking advantage of the real-time character of videos and the intuitive character of 3D models. In this article, we propose a real-time fusion method of multiple videos and 3D real scenes based on optimal viewpoint selection. To begin, 3D reconstruction and video camera calibration were used to prepare the basic data for the fusion of videos and 3D model. Second, a visible-surface detection-based video space restoration method was provided, and the overlapping region between multiple videos was determined. Third, to split the overlapping region into the corresponding camera spaces, a segmentation method based on optimal viewpoint selection was given. Finally, the 2D videos were dynamically fitted to the 3D model using the dynamic texture mapping method, while accomplishing the fusing and rendering of the 3D real scene. After experimental verification, the overall effect of the multiple videos and 3D real scene fusion system implemented using the method proposed in this article is better, while the algorithm is less time-consuming and efficient in rendering.     

一种基于无人机序列图像的地形地貌三维快速重建方法

提出了一种基于无人机序列图像的地形地貌三维重建方法,该方法采用Harris特征点和SIFT特征向量来提取图像特征,实现图像配准;采用准透视投影模型和因子化方法对未标定的图像序列进行自动标定;通过高效次优解三角化方法获取三维点云坐标;通过准稠密化扩散算法对三维点云进行稠密化;采用捆绑调整算法提高了空间三维点云的精度;采用Possion表面重建方法对三维点云进行了网格化处理.本文为无人机序列图像的应用提供了一个新的思路,拓展了无人机的应用空间.