基于距离图像的定性识别

本文提出的定性描述图表示方法能在无模型指导的情况下有效地实现遮挡物体的分离,并将识别过程转化为图或子图同构的问题,还提出了用"提纯"与"搜索"相结合的递归过程来判定图或子图同构.实验证明了该方法的有效性和稳定性.     

Curve and Surface Duals and the Recognition of Curved 3D Objects from their Silhouettes

This article addresses the problem of recognizing a solid bounded by a smooth surface in a single image. The proposed approach is based on a new representation for two- and three-dimensional shapes, called their signature, that exploits the close relationship between the dual of a surface and the dual of its silhouette in weak-perspective images. Objects are modeled by rotating them in front of a camera without any knowledge of or constraints on their motion. The signatures of their silhouettes are concatenated into a single object signature. To recognize an object from novel viewpoint other than those used during modeling, the signature of the contours extracted from a test photograph is matched to the signatures of all modeled objects signatures. This approach has been implemented, and recognition examples are presented.     

图像3D轮廓提取

针对现有3D轮廓提取方法计算量大、图像立体匹配难、图片中含有大量噪音的问题,提出了一种利用早期认知视觉系统提取图像3D轮廓的方法.早期认知视觉是连接早期视觉和认知视觉的中间平台,通过早期认知视觉系统提取出图像的2D基元,2D基元是图片小块,有丰富的语义信息包括位置,方向,相位和三色值;再由两个立体图像的相一致的2D基元...     

复杂断层轮廓集分段分面三角化表面重构

针对多嵌套、多分支任意复杂断层轮廓集的三角化表面重建,提出一种基于轮廓拓扑分类编码和结构识别的分段分面表面重构方法(DS-P).通过设计一种拓扑编码方案,提出确定轮廓匹配关系、分支及分支类型的准则;讨论了多轮廓合并、单轮廓分裂及嵌套分支、连通分支处理方法;设计了任意复杂断层轮廓集表面重建的软件系统架构和工作流程.实验结果表明,该方法应用简单、运算效率高、可靠性强.与经典方法和BPLI方法相比,文中方法不仅能更好地处理轮廓匹配中的二义性及分支问题,还能有效地解决导致BPLI方法失效的投影面内边重叠和多重交叉、轮廓嵌套、轮廓严重偏置、轮廓线释放等情况下的表面重构问题.     

三维物体识别研究进展

出于工业和医疗等领域大量现实应用的需要,如今三维物体识别已成为一个很活跃的研究领域。一般来说,三维物体识别系统可以通过两个阶段的处理来完成三维物体的识别和定位,首先用传感器获取的场景输入数据来得到场景的表达;然后将它与数据库中存储的物体表达相匹配。为了推动该领域研究进一步发展,因而对近１０ａ年中该识别过程中必须解决的感传器类型、三维物体表达方法和匹配策略等３个方面问题的研究成果进行了综述,对主要方法进行分类和总结;并提出了一些三维视觉系统中还需要深入研究的问题,包括对所研究物体形状的限制、复杂背景的影响和表达以及识别中的“整体和局部”的矛盾等。     

3D Reconstruction of Complex Polyhedral Shapes from Contours using a Simplified Generalized Voronoi Diagram

We are interested in modelling the suface of very irregular objects known through a few planar polygonal cross-sections. This problem is considered difficult when severe topology and morphology variations appear between neighbouring cross-sections (multi-branching, holes, disconnected areas). Only few methods deal with this problem in a systematic way. The paper describes an original method allowing to build, in a fully automatic and systematic way, an external surface with a valid topology in any case. It moreover allows to adjust details of the reconstructed surface in view of the morphologies and topologies of the various initial cross-sectional contours. At first, a global correspondence is operated between each couple of adjacent cross-sections by extracting polygonal areas of difference. Next steps are based on the computation in each area of difference of the bisector network, a well-defined simplified generalised Voronoi diagram. This structure is used both for connecting initial contour points and for interpolating new intermediate portions of contours. It depends on the complexity of initial 2D shapes. Interpolation stage is then recursively operated until a satisfactory surface has been obtained or until a maximum number of new intermediate cross-sectional contours have been built. The valid final suface is directly obtained by concatenating all the tiling areas of difference without need of any post processing step. The processing of several real data related to geological bodies or human organs has proved that the described method allows detailed modelling of irregular objects with very performing CPU times. The reconstruction appears insensitive to severe variations of the object shape, including apparitions of holes or disconnections.     

基于单幅图像的三维对称自由形体重建

为了方便快捷地重建出输入图像中的物体,基于单幅图像,提出一种利用二维手绘线画图重建生成三维对称自由形体的方法.在以单幅图像为背景的画布上,用户首先根据图像中的物体位置为待重建模型指定一个对称面;然后为确定了对称面的物体绘制出其各个子部分的手绘线条,每个子部分通常由4条手绘曲线表示,即1对对称曲线和1对非对称的一般曲线,对称曲线的深度坐标信息可以利用物体对称面信息进行计算,一般曲线的深度坐标信息则可以由同一子部分的三维对称构造曲线计算得到;利用恢复了深度信息的三维构造曲线,自由形体的每个部分可以分别由1对对称构造曲线和1对非对称构造曲线利用旋转混合方法生成其参数曲面,并离散化为三角网格表示;根据输入图像中物体的纹理信息进一步合成自由形体每一部分的表面纹理,最终得到三维物体.实验结果表明,该方法得到的三维自由形体具有较强的真实感.     

基于形态图表示的三维物体识别算法

基于形态图表示的三维物体识别的基本思路是：首先建立待识别物体的模型库，找出模型集中所有模型物体的形态图和特征视图，并提取以它们的拓扑结构信息和几何信息；其次对物体真实图像作轮廓提取和0边界跟踪，得到二维图像的线架图，同时提取出它的拓扑结构信息和几何信息；最后将物体图像的拓扑结构信息和几何信息与模型库中模型物体的拓扑结构信息和几何信息匹配，从而达到识别的目的。文中提出了在生成线图链码时提取其拓扑结构信息和几何信息的方法，由拓扑结构信息和几何信息构造特征矩阵的方法，以及识别过程中特征矩阵的匹配算法。     

复杂表面物体3D模型的获取方法

提出了一种从真实物体中获得其3D模型的方法.该方法通过TOF- Camera获得原始的点云数据,在对点云数据进行三角化、分割、滤波去噪等处理后得到部分物体模型,然后再应用ICP(迭代最近点)算法对其进行配准.配准过程中为了节省内存,删掉重叠的冗余数据.最后对生成的数据进行网格重建,得到完整的网格模型.实验表明该方法能较为快速地获取真实物体的3D模型,显著提高TOF相机获取数据的质量.     

On Photometric Issues in 3D Visual Recognition from a Single 2D Image

We describe the problem of recognition under changing illumination conditions and changing viewing positions from a computational and human vision perspective. On the computational side we focus on the mathematical problems of creating an equivalence class for images of the same 3D object undergoing certain groups of transformations—mostly those due to changing illumination, and briefly discuss those due to changing viewing positions. The computational treatment culminates in proposing a simple scheme for recognizing, via alignment, an image of a familiar object taken from a novel viewing position and a novel illumination condition. On the human vision aspect, the paper is motivated by empirical evidence inspired by Mooney images of faces that suggest a relatively high level of visual processing is involved in compensating for photometric sources of variability, and furthermore, that certain limitations on the admissible representations of image information may exist. The psychophysical observations and the computational results that follow agree in several important respects, such as the same (apparent) limitations on image representations.     

基于知识的WWW图像中主体的识别

图像主体识别在图像检索中具有重要意义。单纯利用图像分析识别图像主体相当困难。文章提出了利用WWW中的相关文本做提示,根据图像分析得到的图像主体视觉特征和图像主体知识库识别图像主体的方法,阐述了从WWW中提取图像主体名和视觉特征描述词的方法以及图像主体区域分割、视觉特征识别方法和结合图像主体知识库识别图像主体的方法。最后给出了初步的实验结果。     

三维工业物体的多重描述与识别处理

提出了一种三维工业物体的多重描述与识别方法，在描述中采用了整体形状描述，基元属性描述和关系 描述相结合的多重描述策略；在识别过程中#首先根据物体的整体描述产生关于物体身份的初步假设，然后提出三 种修剪算法，充分利用关系数据结构的多重约束作为知识启发来修剪搜索树#最后根据距离测度函数实现精匹配。 实验验证了上述处理的正确性和一般性。     

三维工业物体的多重描述与识别处理

提出了一种三维工业物体的多重描述与识别方法。在描述中采用了整体形状描述，基元属性描述和关系描述相结合的多重描述策略；在识别过程中，首先根据物体的整体描述产生关于物体身份的初步假设，然后提出三种修剪算法，充分利用关系数据结构的多重约束作为知识启发来修剪搜索树，最后根据距离测度函数实现精匹配。实验验证了上述处理的正确性和一般性。     

针对小目标的遥感图像解译识别系统

当前各种遥感解译系统无法对多种不同目标提供一致的交互解译,且无法满足弱小目标特定的解译需求,针对该问题,基于GrabCut算法设计实现一种交互式的遥感解译识别系统。包括不同目标的特征数据库建立、感兴趣区域定位、交互式目标提取及目标解译识别等主要模块。对飞机目标的解译示例表明,该解译系统不依赖于具体的目标特征,可为遥感图像的解译工作提供良好的支持。     

基于三视图的三维形体重建技术

基于工程图纸的三维形体的重建技术是根据形体的二维视图中的几何信息和拓扑信息,生成相应的三维形体,这是一个从爸维到高维的构造过程,文中提出了一个三维形体重建算法,该算法首先根据三视图生成形体的线框图,然后应用左邻边搜索策略求出线框图内的所有面及相应的极小环,最后利用Ｍｏｅｂｉｕｓ规则及工程图的性质,删除重建过程中生成的非法元素,该方法利用二几何基元和三维几何基元的几何性质及生成关系,减少了重建过程中     

Reconstruction of 3D Objects from Orthographic Projections

An algorithm for automatic reconstruction of 3D objects from their orthographic projections is presented in this paper. It makes some improvements to, and complements the, Wesley-Markowsky algorithm, which is a typical hierarchical reconstruction algorithm limited to polyhedral objects, and extracts the idea of pattern recognition expressed in the Aldefeld algorithm. It is shown in theory by analysis and in practice by implementation that the proposed algorithm successfully rejected pathological cases and found all solutions with the same set of orthographic views. Compared with the existing algorithms presented in references, this algorithm covers some more complex cases of objects incorporating cylinders.     

3D Surface Reconstruction Using Occluding Contours

This paper addresses the problem of 3D surface reconstruction using image sequences. It has been shown that shape recovery from three or more occluding contours of the surface is possible given a known camera motion. Several algorithms, which have been recently proposed, allow such a reconstruction under the assumption of a linear camera motion. A new approach is presented which deals with the reconstruction problem directly from a discrete point of view. First, a theoretical study of the epipolar correspondence between occluding contours is achieved. A correct depth formulation is then derived from a local approximation of the surface up to order two. This allows the local shape to be estimated, given three consecutive contours, without any constraints on the camera motion. Experimental results are presented for both synthetic and real data.     

曲面浅浮雕生成算法

为了在三维网格上快速生成曲面浅浮雕造型,提出一种利用三维模型半自动生成曲面浅浮雕的算法.首先利用图像的边缘检测方法来获取模型在透视场景中的边缘点,并将其与被贴的曲面载体进行位置匹配,获得Poisson方程的Dirichlet边界值;然后对模型高度场的梯度值进行压缩;最后利用确定边界条件的Poisson方程对模型压缩后的梯度场进行求解,还原生成浮雕模型.利用文中算法可以生成贴于曲面上的浅浮雕模型.