彩色扫描地形图中街区式居民地的自动识别

为自动识别彩色扫描地形图中使用晕线填充绘制的街区式居民地,首先通过Gabor滤波检测晕线得到居民地候选区;然后在候选区中利用曲线跟踪算法识别居民地轮廓;最后进行线性插值连接和几何校正,以解决居民地轮廓不闭合和道路两侧居民地整齐排列问题.通过对5幅典型的居民地样本的实验,论证了文中方法的有效性和实用性.     

纹理图象亮度阈值法提取SAR图象居民地

由于微波辐射的复杂特性，从合成孔径雷达图象上提取类似于居民地复杂结构的目标物的研究仍处于探索中．通过研究居民地对合成孔径雷达(SAR)的微波散射特性，分析居民地在SAR图象上的纹理特征，综合利用纹理分析、模式识别和颜色空间变换技术，提出了一种新的提取雷达图象上居民地的方法．该方法在共生矩阵纹理分析的基础上，选取3个合适的特征分量合成彩色纹理特征图象，再通过HIS变换获得亮度分量，使用亮度阈值分割图象来提取出居民地．此方法的特点是，其受雷达系统影响较小，适应性较强，以二值图象的形式记录居民地的提取结果．试验表明，利用此方法在SAR图象上提取居民地具有70％以上的正确识别率．     

空间关系信息和颜色信息相结合的地形图分层算法

在对地形图图象颜色进行误差分析的基础上，指出目前在地形图分层算法设计中，由于仅考虑地形图色彩信息而存在许多不足，因此提出了地形图像素空间关系信息的概念，并讨论了像素空间关系信息的提取方法，进而给出一个将地形图像素的空间关系信息与颜色信息相结合，以实现彩色地形图分层的新算法．实验表明，此算法可有效地抑制地形图图象的颜色误差和提高分层的精度，从而为地形图的分层识别及自动矢量化奠定了良好的基础．     

遥感地形图象的灰度与分形分析

为了能够更加充分、准确地在遥感地形图象中利用分形信息,需要将其与其他特征配合使用。文章通过从视觉成像的角度,深入地剖析物体不同区域的形状和位置对成像灰度的影响,进而将有关结论与图象分形指数数据相结合,应用于基于图象内容的遥感图象的区域(标识)分割,取得了令人满意的效果,从中检查出分形数据中对应于图象深灰度区无意义的数值部分,从而保证了分形数据的可靠性,同时也说明了结合灰度或其它信息于分形图象应用的图象分析方式是十分必要的。     

从Range数据生成高精度高分辨率地形图象

本文提出了从Ｒａｎｇｅ图象生成高精度高分辨率地形图象的计算机方法。其中包括Ｒａｎｇｅ传感器的模型的建立、金字塔结构插补法及多方位Ｒａｎｇｅ图象的融合。通过一系列的实验证明了该方法简单、实用并能得到较高精度的地形图象。     

图象匹配的一种量度及其在扫描地形图要素提取中的应用

本文提出了图象匹配的一种量度,这种图象匹 配的量度既考虑了差异信号的积累及其分布（结构）的特点,还考虑了异常差异信号的处理 ．同时提出了基于图象匹配量度的扫描地形图中对称形状要的素提取算法．通过实际算例, 验证了所提出匹配量度和所算法的有效性与实用性,这对扫描地形图的矢量化和模式识别理 论都有着重要的意义．     

规划地形图的预处理和细化

本文从扫描仪扫描的地形图数据开始，利用一种独立宽度的快速细化算法对图象进行细化，最终将地形图数据转换成ＡｕｔｏＣＡＤＳＫ ＷＧＥＴ Ｒ ＬＴＵ     

藤泽生态智能街区

日本藤泽 SST 委员会（一个以松下公司为首的联盟,松下公司是推动藤泽生态智能街区（Fujisawa Sustainable Smart Town-藤泽 SST）发展的领头羊）今日为这一位于东京郊区、颇具前瞻性的街区举行隆重开幕式。由于该街区的核心设施支持其可持续发展,且其社区目前已投入运营,藤泽 SST 正从施工阶段进入一个新阶段,该街区现已全面发展成为一个高度重视居民生活方式的生态智能街区。     

国土卫星资料用于1:5万、1:10万地形图修测通过鉴定

利用国土卫星资料进行黄河三角洲1:5万、1:10万地形图修测方法的研究,已由国家测绘局测绘科学研究所完成,于5月26日在京通过鉴定。修测方法与实验成果表明,采用计算机图像处理手段,利用国土卫星资料对居民地稀少的平坦地区、不可达地区进行1:10万比例尺地形图地物修测,某些中小比倒尺专题地图的制作,方法是先进的、可行的。     

通用型“手—眼”式多关节机器人视觉系统物像关系的研究

本文着重研究了“手-眼”式通用型多关节机器人视觉系统中基体坐标系.物体坐标系和图象坐标系之间的关系.利用空间坐标系的投影变换和映射等方法,推导了“手-眼”式机器人系统中摄象机图象点和空间点对应的数学关系式.同时对固定式也进行了探讨.本文以多关节机器人视觉系统的实际情况为基础,在实际的机器人坐标系上导出了一个简便实用的算法,可以通过对摄象机摄取的图象中的点的坐标运算,求出其对应的空间点在机器人基体坐标中的坐标,因而能迅速准确地引导机器人根据视觉图象正确地运行到所求的空间点的位置.     

Vector watermarking scheme for GIS vector map management

A geographical information services (GIS) can be provided on the basis of a digital map, which is the fundamental form of representation of data in a GIS. Because the process of producing a digital map is considerably complex and the maintenance of a digital map requires substantial monetary and human resources, a digital map is very valuable and requires copyright protection. A digital map consists of a number of layers that are categorized in terms of topographical features and landmarks. Therefore, any unauthorized person can forge either an entire digital map or the feature layers of the map. In this paper, we present a robust and invisible watermarking scheme based on polylines and polygons for the copyright protection of a GIS digital map. The proposed scheme clusters all polylines and polygons in the feature layers of the map on the basis of the polyline length and the polygon area. And then a watermark is embedded in GIS vector data on the basis of the distribution of polyline length and polygon area in each group by moving all vertices in polylines and polygons within a specified tolerance. Experimental results confirm that the proposed scheme is more robust against geometric attacks, such as rotation, scaling, and translation (RST) transformations, data addition, cropping, breaking, and filleting attacks, and layer attacks with rearrangement and cropping, when compared with conventional schemes. Moreover, the scheme also satisfies data position accuracy.     

A parallel intersection algorithm for vector polygon overlay

A parallel intersection algorithm for speeding the creation of a composite network of polygons whose identities relate to the original polygons from which they are formed in vector geographic information systems (ISs) is described. The algorithm reduces unnecessary intersection checking, especially when polygon density is high. Single-stream and multiple-stream versions of the algorithm are discussed. Experimental results illustrating the overall performance of the parallel algorithm are presented     

Systolic algorithms for rectilinear polygons

We develop systolic algorithms for the OR, AND, Oversizing, and Undersizing of rectilinear polygons. These algorithms work on an edge representation of the polygons rather than on a bit map representation. The algorithms are to be run on a systolic chain of processors. The edges are input at the left end of this chain. From here, they ‘float’ as far to the right as necessary. As edges float to the right, they compare themselves with edges that are resident in the processors they are floating through. During this comparison the output polygons are generated. Output polygons float to the left. These polygons are output from the left end of the chain. The throughput of the systolic system can be improved by increasing the length of the processor chain.     

深度时空能量特征表示下的人体行为识别

目的 利用深度图序列进行人体行为识别是机器视觉和人工智能中的一个重要研究领域,现有研究中存在深度图序列冗余信息过多以及生成的特征图中时序信息缺失等问题。针对深度图序列中冗余信息过多的问题,提出一种关键帧算法,该算法提高了人体行为识别算法的运算效率;针对时序信息缺失的问题,提出了一种新的深度图序列特征表示方法,即深度时空能量图（depth spatial-temporal energy map,DSTEM）,该算法突出了人体行为特征的时序性。方法 关键帧算法根据差分图像序列的冗余系数剔除深度图序列的冗余帧,得到足以表述人体行为的关键帧序列。DSTEM算法根据人体外形及运动特点建立能量场,获得人体能量信息,再将能量信息投影到3个正交轴获得DSTEM。结果 在MSR_Action3D数据集上的实验结果表明,关键帧算法减少冗余量,各算法在关键帧算法处理后运算效率提高了20% 30%。对DSTEM提取的方向梯度直方图（histogram of oriented gradient,HOG）特征,不仅在只有正序行为的数据库上识别准确率达到95.54%,而且在同时具有正序和反序行为的数据库上也能保持82.14%的识别准确率。结论 关键帧算法减少了深度图序列中的冗余信息,提高了特征图提取速率;DSTEM不仅保留了经过能量场突出的人体行为的空间信息,而且完整地记录了人体行为的时序信息,在带有时序信息的行为数据上依然保持较高的识别准确率。     

MAGELLAN: Map Acquisition of GEographic Labels by Legend ANalysis

A system named MAGELLAN (denoting Map Acquisition of GEographic Labels by Legend ANalysis) is described that utilizes the symbolic knowledge found in the legend of the map to drive geographic symbol (or label) recognition. MAGELLAN first scans the geographic symbol layer(s) of the map. The legend of the map is located and segmented. The geographic symbols (i.e., labels) are identified, and their semantic meaning is attached. An initial training set library is constructed based on this information. The training set library is subsequently used to classify geographic symbols in input maps using statistical pattern recognition. User interaction is required at first to assist in constructing the training set library to account for variability in the symbols. The training set library is built dynamically by entering only instances that add information to it. MAGELLAN then proceeds to identify the geographic symbols in the input maps automatically. MAGELLAN can be fine-tuned by the user to suit specific needs. Recognition rates of over 93% were achieved in an experimental study on a large amount of data. Received January 5, 1998 / Revised March 18, 1998     

Point-in-polygon tests for geometric buffers

The point-in-polygon problem is often encountered in geographical information systems. The algorithms usually work on polygons defined by straight edges. In some situations, however, polygons containing circular arcs are applied. In geographical information systems these polygons are usually considered as geometric buffers, geodesic offsets, or geodesic parallels. This paper presents three algorithms suitable for providing information about the containment of a point in geometric buffers: the Ray-crossing method, the Cell-Based Algorithm and the Approximate approach. An extensive experimental section allows the reader to select the most efficient algorithm for practical problems.     

Visiting convex regions in a polygonal map

This paper is concerned with a variant of the multi-goal path planning in which goals are represented as convex polygons. The problem is to find a closed shortest path in a polygonal map such that all goals are visited. The proposed solution is based on a self-organizing map (SOM) algorithm for the traveling salesman problem. Neurons’ weights are considered as nodes inside the polygonal domain and connected nodes represent a path that evolves according to the proposed adaptation rules. In addition, a reference algorithm based on the solution of the traveling salesman problem and the consecutive touring polygons problem is provided to find high quality solutions of the created set of problems. The problems are designed to represent various inspection and patrolling tasks and can form a kind of benchmark set for multi-goal path planning algorithms. The performance of the algorithms is examined in this problem set, which includes an instance of the watchman route problem with restricted visibility range. The proposed SOM based algorithms provide a unified approach to solve various visibility based routing problems in polygonal maps while they provide a competitive quality of solutions to the reference algorithm with significantly lower computational requirements.     

Algorithmic provision of a universal method for word-form generation and recognition

A universal method for word-form recognition and generation is proposed. It includes the model of word formation in natural languages and algorithms for word-form generation and recognition. In the word-formation model, abstracting from typical notions in the morphology of natural languages takes place and word formation is reduced to transformations of the word stem by transformation chains (finite sequences). The classification of transformation chains and the algorithm for their automatic construction are discussed.     

一种移动机器人环境模型——灰色定性地图

针对移动机器人的环境建模问题,提出一种综合拓扑地图和儿何地图特点的混合环境模型——灰色定性地图.用凸剖分算法将环境中的自由空间分解为一组凸多边形.灰色定性地图的定性层由凸多边形及其之间的邻接关系构成,用于模拟人类在路径规划时的高层定性推理.定量层由凸多边形顶点的坐标和势场向量构成,用于决定机器人在连续空间中的运动方向和速度.理论分析和实验均表明:灰色定性地图可以模拟人类对环境认知的知识表达,并且可以仪由凸多边形邻接信息和顶点信息支持机器人完成路径规划且确保路径的平滑性,有效地降低了环境模型的空间复杂度.     

Perceptual encryption with compression for secure vector map data processing

With the rapidly rising interest in geographic information system (GIS) contents, a large volume of valuable map data has been unlawfully distributed by pirates. Therefore, the secure storage and transmission of classified national digital map datasets have been increasingly threatened. As the importance of secure, large-volume map datasets has increased, vector map security techniques that focus on secure network and data encryption have been studied. These techniques are required to ensure access control and prevent illegal copying of digital maps. This paper presents perceptual encryption on the vector compression domain for copy protection and access control of vector maps. Our algorithm compresses all vector data of polylines and polygons by lossless minimum coding object (MCO) units and perceptually encrypts using two processes using the mean points and directions of MCOs. The first process changes the position of vector data by randomly permuting the mean points of MCOs, the so-called position encryption. The second process changes the geographic shape by circularly encrypting the directions of vertices in MCOs by the XOR operator. Experimental results have verified that our algorithm can encrypt GIS digital maps effectively and simply and can also improve the compression ratio, unlike general data encryption techniques, and thus, our algorithm is very effective for a large volume of GIS datasets.