多视点距离图象集成的截平面法

利用截平面进行了多视点距离图象的集成。和基于三维空间上的几何特征或直接进行曲面匹配的集成方法相比，截平面法具有计算简单等优点。所得到的物体轮廓曲线表示也很容易转换为更高一级的表示。实验结果表明，截平面法在表示的精度和处理速度上都有很好的实用价值。     

Study of three—dimensional PET and MR image registration based on higher—order mutual information

Mutual information has currently been one of the most intensively reserached measures.It has been proven to be accurate and effective registration measure.Despite the general promising results,mutual information sometimes smight lead to misregistration because of neglecting spatial information and treating intensity variations with undue sensitivity.In this paper,an extension of mutual information framework was proposed in which higher-order spatial information regarding image structures was incorporated into the registration processing of PET and MR.The second-order estimate of mutual information algorithm was applied to the registration of seven patients.Evaluation from Vanderbilt University and our visual inspection showed that sub-voxel accuracy and robust results were achieved in all cases with second-order mutual information as the similarity measure and with Powell‘s multidimensional direction set method as optimization strategy.     

Recognition of spatial point patterns

Complex patterns may sometimes be efficiently represented by a small number of points extracted from the image on the basis of atypical properties of neighborhoods of the points. In this paper we describe theoretical and experimental results on the use of sequences of interpoint distances extracted from a noisy point image to match the image with one of a set of prototypes. Minimal spanning tree and nearest neighbor distances are used for these computations. The methods applied are invariant under translation and rotation of the image and could be made invariant to scale changes. Several distance measures between classes are defined. Sufficient conditions for the separability of classes are given in terms of these measures.     

Sonar Image Registration and Mosaic Based on Line Detection and Triangle Matching

Image registration is an important research topic in the field of computer vision, in which the registration and mosaic of side-scan sonar images is the keypoints of underwater navigation. However, the image registration method of keypoints is not suitable for sonar images which do not have obvious feature points. Therefore, a method of sonar-image regis-tration and mosaic based on line segment extraction and triangle matching is proposed in this paper. Firstly, in order to extract features from sonar image, the LSD method is introduced to detect line feature from images, and line segments are filtered by the principle of attention; after that, triangles are formed from line segments, an image transformation matrix can be calculated through the heuristic greedy algorithm from these triangles; finally, images are merged based on the transformation information. On the basis of practical tests, it is found that, the feature extraction method used in this paper can better describe the outline of underwater terrain, and there is no obvious stitching gap between the result of sonar images stitched. Experimental results show that the proposed method is effective than the keypoints method of the registration and mosaic of sonar images.     

孤峰含韵 北国流香——北京鹫峰国际梅园建筑设计

北京鹫峰梅品种登录国际精品园（简称“国际梅园”）是一座集教学、科研、生产、旅游于一体的梅国际登录精品展示园,包括梅博物馆、书画院和品梅屋三个主体园林建筑。该文从选址、平面空间、建筑风格等方面入手,阐述了国际梅园主体建筑的“江南风格”设计理念,并详细分析了各建筑的园林造型设计手法。     

北京鹫峰国际梅园规划与建设简介

我国已获梅花品种国际登录权,随着抗寒梅花研究取得的成果,北京林业大学在北京鹫峰建设的梅品种登录国际精品园(简称"国际梅园"),拟建成一座集教学、科研、生产、旅游于一体的精品展示园.该园根据梅的"二元分类"系统进行展示,并与梅的古老文化相结合,建成后将对梅花研究、旅游与生产事业起到推动作用.     

Et in Arcadia ego,Et in Arcadia est

Architect, academic and broadcaster Kevin Rhowbotham scrutinises the reasoning and value of the New Pastoralism project. He dispels the Arcadian impulse as ‘a specious and mythicised image of the rural’, calling upon architects to seek a true understanding of rural conditions in relation to the urban.     

Assessment of target types and layouts in 3D laser scanning for registration accuracy

3D laser scanning technology is now widely and increasingly used in several construction tasks such as indoor mapping, project control, construction metrology and automation, development of as-built models, and resource management through scanning, data processing, and modeling stages. The accuracy of these stages affects the quality of the end product and can be improved by decreasing the errors caused by manual work processes. This paper focuses specifically on data acquisition errors caused by target setup, acquisition, and reorientation. The paper explores how different target types and target layouts affect registration accuracy. A total of twelve tests were conducted with phase-based and time-of-flight scanners in both exterior and interior scan scenes in order to assess registration errors and time inefficiencies associated with current scanning practices. The paper compares different target types (paper, paddle, and sphere) and presents the lessons learned to achieve optimal target layout design.     

相位测量轮廓术中的距离像配准

对用相位测量轮廓术( PMP) 测量得到的不同视点距离像间的配准进行了研究。将逆向校准用于加速控制点和对应点的粗选,逆向校准所需的参数是在系统校准过程中直接计算得到的。以调制度作为度量对应点对可靠度的指标,实现不同对应点对对目标函数的区别性贡献。实验统计结果表明,该方法的配准误差约为系统测量误差的66%。     

套准偏差自动检测方法

目前,国内多色印刷机多采用手动方式调整套准精度,自动化程度较低,为解决该问题,提出一种套准偏差自动检测方法。基于视觉成像原理拍摄套准标记图像,采用图像分析理论建立套准偏差计算方法。通过彩色图像矢量信号滤波法预处理标记图像并提取图像目标,给出青(C)、品红(M)、黄(Y)、黑(B)四种原色及其复合色像素的分色归类模型,在此基础上检测四种原色套准标记的边缘像素,进一步结合最小二乘和Hough变换法拟合套准标记的多条边缘直线,最后在图像中计算四种原色特征直线之间的偏移距离,通过视觉标定给出物空间的套准偏差。试验结果表明该方法自动检测套准偏差的精度高于20 μm,符合国家印刷行业标准规定的套准精度要求,适用于以C、M、Y、K合成原理为基础的双色、四色胶印系统。