基于增强现实技术的景观规划系统

增强现实是把计算机产生的虚拟物体或其他信息合成到用户看到的真实世界中的一种技术,利用增强现实技术,设计人员能够有效地进行建筑布局的规划和设计,本文介绍了一个典型的增强现实系统-景观规划系统的实现,针对合成虚拟景物和真实场景过程中需要解决的几何一致性和光照一致性问题,采用了局部三维重建和交互的相机定标技术来实现几何一致性;对于光照一致性,则采用了光照交互指定和自动恢复相结合的方法,同时还考虑了虚拟物体投射的阴影,针对不同场景的实际应用,依据系统生成的结果合成图象,设计人员能够比较有效地完成对景观规划结果的直观评估。     

A local space–time kriging approach applied to a national outpatient malaria data set

Increases in the availability of reliable health data are widely recognised as essential for efforts to strengthen health-care systems in resource-poor settings worldwide. Effective health-system planning requires comprehensive and up-to-date information on a range of health metrics and this requirement is generally addressed by a Health Management Information System (HMIS) that coordinates the routine collection of data at individual health facilities and their compilation into national databases. In many resource-poor settings, these systems are inadequate and national databases often contain only a small proportion of the expected records. In this paper, we take an important health metric in Kenya (the proportion of outpatient treatments for malaria (MP)) from the national HMIS database and predict the values of MP at facilities where monthly records are missing. The available MP data were densely distributed across a spatiotemporal domain and displayed second-order heterogeneity. We used three different kriging methodologies to make cross-validation predictions of MP in order to test the effect on prediction accuracy of (a) the extension of a spatial-only to a space–time prediction approach, and (b) the replacement of a globally stationary with a locally varying random function model. Space–time kriging was found to produce predictions with 98.4% less mean bias and 14.8% smaller mean imprecision than conventional spatial-only kriging. A modification of space–time kriging that allowed space–time variograms to be recalculated for every prediction location within a spatially local neighbourhood resulted in a larger decrease in mean imprecision over ordinary kriging (18.3%) although the mean bias was reduced less (87.5%).     

A Similarity-Based Aspect-Graph Approach to 3D Object Recognition

This paper describes a view-based method for recognizing 3D objects from 2D images. We employ an aspect-graph structure, where the aspects are not based on the singularities of visual mapping but are instead formed using a notion of shape similarity between views. Specifically, the viewing sphere is endowed with a metric of dis-similarity for each pair of views and the problem of aspect generation is viewed as a segmentation of the viewing sphere into homogeneous regions. The viewing sphere is sampled at regular (5 degree) intervals and the similarity metric is used in an iterative procedure to combine views into aspects with a prototype representing each aspect. This is done in a region-growing regime which stands in contrast to the usual edge detection styles to computing the aspect graph. The aspect growth is constrained such that two aspects of an object remain distinct under the given similarity metric. Once the database of 3D objects is organized as a set of aspects, and prototypes for these aspects for each object, unknown views of database objects are compared with the prototypes and the results are ordered by similarity. We use two similarity metrics for shape, one based on curve matching and the other based on matching shock graphs, which for a database of 64 objects and unknown views of objects from the database give a recall rate of (90.3%, 74.2%, 59.7%) and (95.2%, 69.0%, 57.5%), respectively, for the top three matches; cumulative recall rate based on the top three matches is 98% and 100%, respectively. The result of indexing unknown views of objects not in the database also produce intuitive matches. We also develop a hierarchical indexing scheme to prune unlikely objects at an early stage to improve the efficiency of indexing, resulting in savings of 35% at the top level and of 55% at the next level, cumulatively.     

三维物体的形态图表达方法

三维物体的表达方法是计算机视觉中的关键问题之一,现有的各种三维物体表达方法虽然在各自的识别中得到应用,但都存在各自的局限性,用形态图表达三维物体是一种以视点为中心的表达方法,由于它列举了一个物体所有可能的“定性”形象,即它可使用最少的二维投影线图（特征视图）来表达一个完整的三维物体,因此使三维物体识别转化为2D与2D的匹配,该文首先定义了二维线图拓扑结构等价的判别准则,然后给出了构造透明物体形态图的方法,最后根据拓扑结构等价准则来得到不透明物体的形态图和特征图,并用圆锥与圆柱相交的实例进行了验证。     

On the numerical solution of space–time fractional diffusion models

A flexible numerical scheme for the discretization of the space–time fractional diffusion equation is presented. The model solution is discretized in time with a pseudo-spectral expansion of Mittag–Leffler functions. For the space discretization, the proposed scheme can accommodate either low-order finite-difference and finite-element discretizations or high-order pseudo-spectral discretizations. A number of examples of numerical solutions of the space–time fractional diffusion equation are presented with various combinations of the time and space derivatives. The proposed numerical scheme is shown to be both efficient and flexible.     

基于形态及受约束结构的三维物体建模方法

文中提出一种基于物体形态及受约束结构的三维物体建模方法,该方法利用具有透视不变性的三维结构来表达物体的各个形态。利用该表达方法可以使机器视觉系统在用单幅灰度图像识别物体时,在模型索引阶段避开求解物体位姿、摄像机参数、特征对应等复杂问题,从而实现先索引后匹配的识别策略,提高识别物体的实时性。文中首先论述了透视不变性和具有透视不变性的受约束结构的基本概念;其次,给出了用受约束结构进行三维物体建模的一般方法和应用实例;最后,指出了这种方法的不足和进一步的研究方向。     

Space–time modelling of air quality for environmental-risk maps: A case study in South Portugal

Since the 1960s, there has been a strong industrial development in the Sines area, on the southern Atlantic coast of Portugal, including the construction of an important industrial harbour and of, mainly, petrochemical and energy-related industries. These industries are, nowadays, responsible for substantial emissions of SO₂, NO_x, particles, VOCs and part of the ozone polluting the atmosphere. The major industries are spatially concentrated in a restricted area, very close to populated areas and natural resources such as those protected by the European Natura 2000 network. Air quality parameters are measured at the emissions’ sources and at a few monitoring stations. Although air quality parameters are measured on an hourly basis, the lack of representativeness in space of these non-homogeneous phenomena makes even their representativeness in time questionable. Hence, in this study, the regional spatial dispersion of contaminants is also evaluated, using diffusive-sampler (Radiello Passive Sampler) campaigns during given periods. Diffusive samplers cover the entire space extensively, but just for a limited period of time.In the first step of this study, a space–time model of pollutants was built, based on a stochastic simulation—direct sequential simulation—with local spatial trend. The spatial dispersion of the contaminants for a given period of time—corresponding to the exposure time of the diffusive samplers—was computed by ordinary kriging. Direct sequential simulation was applied to produce equiprobable spatial maps for each day of that period, using the kriged map as a spatial trend and the daily measurements of pollutants from the monitoring stations as hard data.In the second step, the following environmental risk and costs maps were computed from the set of simulated realizations of pollutants: (i) maps of the contribution of each emission to the pollutant concentration at any spatial location; (ii) costs of badly located monitoring stations.     

Comparative study of different numerical approaches in space–time CESE framework for high-fidelity flow simulations

With the advancement of computer hardware, the trend of research in computational fluid dynamics is moving towards development of highly accurate, unstructured-mesh compatible, robust and efficient numerical methods for simulating problems involving strong transient effects and relatively complex geometries as well as physics. The space–time conservation element and solution element method is a genuinely multi-dimensional, unstructured-mesh compatible numerical framework, which was built from a consistent and synergetic integration of conservation laws in the space–time domain to avoid the limitations of conventional schemes, such as the use of 1-D flux reconstruction with a Riemann solver. It has been shown that the framework can be used for time-accurate simulations of a variety of problems involving unsteady waves, strong flow discontinuities, and their interactions with remarkable accuracy. However, this method at its current state has encountered the challenge in balancing the robustness and numerical accuracy when highly stretched meshes were used in viscous flow simulation. In this paper, we briefly discuss various numerical approaches developed for this framework thus far as well as their strengths and weaknesses, and conduct a comparative study of their numerical accuracies using some 2-D viscous benchmark test cases. The application of this method in realistic, complex 3-D problems is also included here to demonstrate its computational efficiency in large-scale computing.     

Kinect 下深度信息获取技术及其在三维目标识别中的应用综述

微软公司 2010 年推出的 Kinect 深度传感器能够同步提供场景深度和彩色信息,其应用的一个关键领域就是目标识别。传统的目标识别大多限制在特殊的情形,如：手势识别、人脸识别,而大规模的目标识别是近年来的研究趋势。通过 Kinect 得到的 RGB-D 数据集多为室内和办公环境下获取的多场景、多视角、分目标类型的数据集,为大规模的目标识别算法设计提供了学习基础。同时,Kinect 获取的深度信息为目标识别提供了强有力的线索,利用深度信息的识别方法较以前的方法具有无法比拟的优势,大大地提高了识别的精度。文章首先对 Kinect 的深度获取技术做了详细介绍;其次对现有的 3D 目标识别方法进行综述,接着对已有的 3D 测试数据集进行分析和比较;最后对文章进行小结以及对未来 3D目标识别算法和 3D 测试数据集的发展趋势作了简单的阐述。     

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。     

虚拟的“真实”——交互动画中仿真蒙皮的探索

柔性蒙皮的皮肤不像刚性蒙皮那么僵硬,本文的目的就在于将长期应用于传统影视动画制作中的柔性蒙皮技术移植到交互领域中,即改变目前应用于交互领域中的角色几何体及其动画信息的数据结构,重新塑造一种信息文件的结构方式,使得在实时骨骼蒙皮的过程中,皮肤顶点受骨骼的影响值不会受到限制,达到真正意义上的柔性节点蒙皮,从而为交互状态下的角色动画提供一种新的动画解决方案。     

3D Object Recognition in Cluttered Environments by Segment-Based Stereo Vision

We propose a new method for 3D object recognition which uses segment-based stereo vision. An object is identified in a cluttered environment and its position and orientation (6 dof) are determined accurately enabling a robot to pick up the object and manipulate it. The object can be of any shape (planar figures, polyhedra, free-form objects) and partially occluded by other objects. Segment-based stereo vision is employed for 3D sensing. Both CAD-based and sensor-based object modeling subsystems are available. Matching is performed by calculating candidates for the object position and orientation using local features, verifying each candidate, and improving the accuracy of the position and orientation by an iteration method. Several experimental results are presented to demonstrate the usefulness of the proposed method.     

Efficient 3D object recognition using foveated point clouds

Recent hardware technologies have enabled acquisition of 3D point clouds from real world scenes in real time. A variety of interactive applications with the 3D world can be developed on top of this new technological scenario. However, a main problem that still remains is that most processing techniques for such 3D point clouds are computationally intensive, requiring optimized approaches to handle such images, especially when real time performance is required. As a possible solution, we propose the use of a 3D moving fovea based on a multiresolution technique that processes parts of the acquired scene using multiple levels of resolution. Such approach can be used to identify objects in point clouds with efficient timing. Experiments show that the use of the moving fovea shows a seven fold performance gain in processing time while keeping 91.6% of true recognition rate in comparison with state-of-the-art 3D object recognition methods.     

几何不变性及其在3D物体识别中的应用

三维物体识别是计算机视觉研究的重要内容之一,它要求从3D物体的2D图象中识别和定位物体．由于物体成像时会受到观察视角、摄像机参数的影响,因此使得同一物体在不同观察视角、不同摄像机参数等条件下所得到的图象存在差异．但由于几何不变性方法可以有效地消除这种差异带给3D物体识别的不利影响,所以,近20年来这种方法受到了广泛的关注和研究．为使人们了解该领域的研究现状,以对该领域的研究有所启发,首先讨论了基于几何不变性的3D物体识别方法的研究内容,包括研究的几何框架和其不变性以及几何不变性在3D物体识别中的主要应用;其次,总结性地评述了该领域的研究现状;最后,提出了研究的发展方向．     

环视图表示下的无监督三维物体检索

为了解决基于多视图的三维物体检索方法过度依赖基于人工标注的有监督训练的问题,提出了一种基于环视图的无监督三维物体检索算法.首先,训练面向多圈环视图的无监督深度网络模型,通过随机数据混合增强学习不同形状之间的内在联系;其次,基于最优匹配方法计算物体间的相似性,其中,最优匹配是利用2个物体环视图间最小距离的平均值计算得到;最后,利用环视图特征过滤算法去除冗余数据,能够在保持精度稳定的情况下,有效地减少相似性匹配的计算代价.在ModelNet40数据集和SHREC15数据集上进行实验,文中方法精度指标mAP分别为41.2%和54.5%.实验结果表明,该无监督三维物体检索方法取得了优异的性能,有效地降低了人工标注的成本.     

三维虚拟物体表面重建的研究

在激光扫描共焦显微三维成像,CT成像,MRI成像,以及在图象处理和识别中,三维物体的显示是必不可少的,目前,最流行的显示方式是虚拟物体的三维重建,通常虚拟物体三维重中以采用体素级重建,可也以采用切片极重建,由于切片级重建仍需要解决物体轮廓对应,分叉曲面,轮廓拼接等关键性问题,为此,提出了一些新的方法,在这些方法中,轮廓的对应采用OR运算和AND运算来确定,如果两个轮廓的OR和ND运算结果满足预先设置的准则,则这两个轮廓相对应;分叉曲面采用数字形态学方法来分解,其由形态学方法生成的边界就是分叉曲面的分割线,轮廓拼拦则是将对应轮廓经多边形简化后,由三角形接拼法来构成表面,且三角形是根据最小轮廓跨接边准则来构建的,通过对这些方法进行的实验结果表明,理论与实际完全相符,这些方法的优点是编程简单,运算速度快。     

Robust 3D face recognition based on resolution invariant features

A novel resolution invariant local feature based method is proposed for 3D face recognition. Scale space extrema on shape index images and texture images are detected and matched, through which resolution and noise insensitive face matching is achieved without complex preprocessing and normalization. An outlier removal strategy is designed to eliminate incorrect matching points while keeping relevant ones. Six different scale invariant similarity measures are proposed and fused at the score level, which increases the robustness against expression variations. Systematical experiments are conducted on the FRGC v2.0 database, achieving in the neutral vs. all experiment a verification rate of 90.7% with un-normalized similarity scores, and 96.3% with normalized similarity scores at False Acceptance Rate (FAR) of 0.1%, and 96.2% rank-1 identification rate, which are comparable to the state of the art, and promising considering the significantly reduced preprocessing requirement.