基于单幅全向图像的空间水平直线定位新方法

研究了在没有先验知识的前提下,基于单幅全向图像定位空间水平直线的问题.在已有算法的基础上,分析和推导了空间水平直线在全向成像系统中的成像特点,指出基于直线在全向图中的两个像点即可重建该水平直线,并相应地提出了一种基于"主像点/非主像点"的空间水平直线定位算法.试验表明,在不同的像点提取精度下,对于不同空间水平直线,本方法均能取得较好结果.     

折反射全向图像与遥感图像配准的建筑物高度提取算法

提出一种折反射全向图像与遥感图像配准的建筑物高度提取算法,可应用于大范围三维城市重建。首先,利用全向Hough变换方法提取折反射全向图像中建筑物的顶部边界线;然后基于提取的边界线,根据空间水平直线全向成像的角度不变性对折反射全向图像与遥感图像进行配准;最后利用配准结果,依据折反射全向图成像模型计算建筑物高度。实验结果证明该方法简捷易行且计算结果准确,误差较小。     

单-双镜面组合结构的全向深度获取系统

为避免成像系统对于单视点约束的要求,提高场景深度获取的准确性和灵活性,设计了一个由单透视相机、双抛物反射镜面同轴放置所构成的非单视点全向深度获取系统.首先分析了实现单视点约束存在的困难及基于非单视点成像系统获取深度的可行性;然后提出了在双镜面全向成像和单镜面全向成像2种不同方式下的深度计算方法;最后通过误差分析研究了镜面面型、基线距离及空间点位置对深度恢复结果的影响,并由此优化系统配置参数,使深度估计的总体误差保持在2%以内.该系统不仅可基于双反射镜面全向立体成像恢复水平方向360°的场景深度,也可仅利用单反射镜面全向成像获取空间线特征的三维信息.实验结果表明,文中系统具有较高的准确度,可用于不同精细程度需求下的摄影测量、三维重建、机器人导航等场合.     

基于夹角的直线检测算法

为了能有效解决Hough变换计算量大、处理速度慢等问题,提出了一种基于夹角的直线提取算法.该算法直接在图像空间提取直线,通过判断图像中任意三点形成的直线夹角,获得一条可能的直线,然后再在数据空间中进一步判定这条直线的真实性.实验证明,该算法具有较高的直线检出率、检测精度和运行速度,与具有类似检出率的算法相比虚假直线数较少,综合性能具有优势.     

半自动全向图与卫星遥感图快速配准

折反射全向图和卫星遥感图配准属于异构传感器图像配准问题,目前快速有效的解决方法比较少,但应用需求又比较多,鉴于此,提出了一种基于等角原理的半自动快速配准算法。通过全向Hough变换方法提取全向图中建筑物顶部轮廓直线,同时手工找出卫星图中建筑物顶部轮廓直线,通过角度关系结合投票方法计算出全向图可能拍摄位置,并用所有可能位置组成可行集,从可行集中选出最满意解。仿真实验与实景实验均表明该方法快速有效。     

一种基于激光传感器的自适应直线提取算法

针对Split-and-Merge直线提取算法对参数敏感和运算效率低的问题,提出一种基于该算法的自适应直线提取方法,根据自适应阈值对激光数据进行邻近点簇分割,基于Prototype-based fuzzy clustering算法对邻近点簇进行线段分割,利用最小二乘拟合直线参数。实验结果证明,该方法显著提高了线段分割的鲁棒性和线段提取的精度,以及算法的运算效率。     

基于立体折反射全向成像的柱面全景深度估算

针对立体视觉原理的新型立体折反射全向成像系统结构设计和面向立体柱面全景像对的局域灰度相关对应点快速匹配算法,从捕获的全向市体影像中提取有效深度信息,用于辅助全向视频分析处理中的对象检测和跟踪.采用单相机和两个不同参数的抛物面型反射镜构造了一种共轴结构的折反射全向立体成像装置,捕获的存在一定视差的原始全向立体像对被投影展开为立体柱面全景像对,而后通过特定对应点匹配算法提取稠密的深度信息.对应点匹配算法采用局部区域灰度相关的算了,并充分利用了双向匹配和柱面全景的外极线约束来提高匹配的速度和准确度.仿真实验有效恢复了场景深度信息,证明了整套装置结构设计及深度估计方法的有效性.     

采用空间一致生长策略的多视图三维重建

针对复杂环境因素影响下场景三维重建结果难以同时获得高重建精度和高重建完整度的问题,提出一种基于空间一致生长的多视图三维重建算法.该算法对基于特征点生长的三维重建算法框架进行拓展,新增了有条件的初值矫正环节,同时对已有的生长和滤波环节进行更替和改进.首先使用SFM从输入图像中提取稀疏种子点;然后直接在固定的世界坐标系中从所有种子点出发向其邻近三维空间扩展,得到生长点的初始位置和方向,并通过优化确定生长点的最终位置和方向,在优化前和优化中根据生长点的当前位置和方向不断选取和更换最佳主、副图,提高优化质量;再利用邻域已重建点云有条件地矫正生长点的位置和方向,并以此作为初值再次优化,避免优化收敛到局部极值,提高生长点的重建精度;最后设计光滑、深度和方向三方面的自适应一致性滤波,在减少误删的同时及时删除误差点,防止误差蔓延.实验结果表明,文中算法的重建精度和完整度均明显超过当前流行的PMVS算法;与高精度DAISY算法相比,在完整度大大提高的前提下,该算法的精度与其基本持平.     

基于射影几何的CCD相机几何模型研究

为提高由多幅二维图像解算出的空间坐标信息的精度,基于射影几何原理,提出一种像方空间与物方空间的几何形状计算方法。分析电荷耦合器件( CCD)相机成像射影几何原理,根据透视变换和交比不变性质,利用直线之间存在平行、垂直和相交等关系,建立基于直线特征的相机成像几何模型,已知相机参数,证明并推导像方空间二维影像和物方空间形状与坐标信息的几何转换关系。分析结果表明,该方法结合了整幅图像的几何信息,能提高空间点等几何特征的坐标信息计算精度,以及视觉测量和三维重建的精度。     

一种基于平面控制直线约束的非量测相机检校方法

光束法自检校为一种经典的适合于非量测相机的检校算法,但其解算精度易受到大量像点坐标观测值的影响.本文讨论一种基于平面控制直线约束的非量测相机检校方法.该方法利用平面格网控制场中的直线特征对格网像点坐标及畸变参数进行直线几何约束.详细推导了该方法的直线约束方程,对检校实验结果从控制场格网点直线性、构像残差等方面进行分析.经实验验证,相较传统的光束法自检校,该附加直线约束的检校方法可有效提高检校结果精度.     

A 2-point algorithm for 3D reconstruction of horizontal lines from a single omni-directional image

Reconstruction of 3D scenes with abundant straight line features has many applications in computer vision and robot navigation. Most approaches to this problem involve stereo techniques, in which a solution to the correspondence problem between at least two different images is required. In contrast, 3D reconstruction of straight horizontal lines from a single 2D omni-directional image is studied in this paper. The authors show that, for symmetric non-central catadioptric systems, a 3D horizontal line can be estimated using only two points extracted from a single image of the line. One of the two points is the symmetry point of the image curve of horizontal line, and the other is a generic point on the image curve. This paper improves on several prior works, including horizontal line detection in omni-directional image and line reconstruction from four viewing rays, but is simpler than those methods while being more robust. We evaluate how the precision of feature point extraction can affect line reconstruction accuracy, and discuss preliminary experimental results.     

遥感图像辅助的折反射全向图三维重构

提出了一种针对室外场景的单幅折反射全向图三维重构方法,能够自动重构出全向图中360°视野内景物的三维模型,并实现自由漫游。基于全向图与遥感图匹配把全向图分为水平地面、垂直建筑物立面和垂直背景景物面三类区域,得到全向图场景的基本结构;在此基础上利用折反射光路投射模型计算出全向图中每个像素点的三维几何位置,从而实现了折反射全向图的重构。实验证明该方法具有采集简单、视野大、处理过程全自动化、能够重构非平面场景等特点。     

Hypercatadioptric line images for 3D orientation and image rectification

In central catadioptric systems 3D lines are projected into conics. In this paper we present a new approach to extract conics in the raw catadioptric image, which correspond to projected straight lines in the scene. Using the internal calibration and two image points we are able to compute analytically these conics which we name hypercatadioptric line images. We obtain the error propagation from the image points to the 3D line projection in function of the calibration parameters. We also perform an exhaustive analysis on the elements that can affect the conic extraction accuracy. Besides that, we exploit the presence of parallel lines in man-made environments to compute the dominant vanishing points (VPs) in the omnidirectional image. In order to obtain the intersection of two of these conics we analyze the self-polar triangle common to this pair. With the information contained in the vanishing points we are able to obtain the 3D orientation of the catadioptric system. This method can be used either in a vertical stabilization system required by autonomous navigation or to rectify images required in applications where the vertical orientation of the catadioptric system is assumed. We use synthetic and real images to test the proposed method. We evaluate the 3D orientation accuracy with a ground truth given by a goniometer and with an inertial measurement unit (IMU). We also test our approach performing vertical and full rectifications in sequences of real images.     

基于编码孔径的折反射散焦模糊图像复原

360度折反射成像系统由于其曲面反射的成像特点,获得的全向图像会不可避免地产生散焦模糊问题,使得全向图像的应用受到限制。针对全向图像成像过程中的散焦模糊问题,首先通过分析折反射系统中入射光线和图像模糊的关系,建立全向图像散焦数学模型;然后利用编码孔径技术估计出图像中各个位置的模糊程度;最后通过反卷积算法复原图像。通过该方法,可以很好地消除全向图像的散焦模糊,获得全聚焦的清晰全向图像。获得的全聚焦全向图像在全向智能视频监控、战场环境全向智能感知以及机器人全向视觉等领域具有较大应用价值。     

Calibration of Central Catadioptric Cameras Using a DLT-Like Approach

In this study, we present a calibration technique that is valid for all single-viewpoint catadioptric cameras. We are able to represent the projection of 3D points on a catadioptric image linearly with a 6×10 projection matrix, which uses lifted coordinates for image and 3D points. This projection matrix can be computed from 3D–2D correspondences (minimum 20 points distributed in three different planes). We show how to decompose it to obtain intrinsic and extrinsic parameters. Moreover, we use this parameter estimation followed by a non-linear optimization to calibrate various types of cameras. Our results are based on the sphere camera model which considers that every central catadioptric system can be modeled using two projections, one from 3D points to a unitary sphere and then a perspective projection from the sphere to the image plane. We test our method both with simulations and real images, and we analyze the results performing a 3D reconstruction from two omnidirectional images.     

双曲面折反射全景图像的柱面解算研究

折反射全景视觉导航是自主移动机器人研究领域一项新兴技术,但由该视觉传感器生成的原始图像是严重畸变的,不适合机器人的目标定位和跟踪等任务。基于此,提出一种全景图像中心定位方法,将双线性内插值法应用于图像的采样,实现双曲面折反射全景图像的柱面还原解算。实验结果显示,还原后的图像人机交互性能有一定的提高。     

Identical Projective Geometric Properties of Central Catadioptric Line Images and Sphere Images with Applications to Calibration

Central catadioptric cameras are imaging devices that use mirrors to enhance the field of view while preserving a single effective viewpoint. Lines and spheres in space are all projected into conics in the central catadioptric image planes, and such conics are called line images and sphere images, respectively. We discovered that there exists an imaginary conic in the central catadioptric image planes, defined as the modified image of the absolute conic (MIAC), and by utilizing the MIAC, the novel identical projective geometric properties of line images and sphere images may be exploited: Each line image or each sphere image is double-contact with the MIAC, which is an analogy of the discovery in pinhole camera that the image of the absolute conic (IAC) is double-contact with sphere images. Note that the IAC also exists in the central catadioptric image plane, but it does not have the double-contact properties with line images or sphere images. This is the main reason to propose the MIAC. From these geometric properties with the MIAC, two linear calibration methods for central catadioptric cameras using sphere images as well as using line images are proposed in the same framework. Note that there are many linear approaches to central catadioptric camera calibration using line images. It seems that to use the properties that line images are tangent to the MIAC only leads to an alternative geometric construction for calibration. However, for sphere images, there are only some nonlinear calibration methods in literature. Therefore, to propose linear methods for sphere images may be the main contribution of this paper. Our new algorithms have been tested in extensive experiments with respect to noise sensitivity.