利用卫星图像结构信息提高城市地物模式识别精度的研究

针对城市地物分布特征及其光谱特点，对卫星遥感数据的空间结构信息应用于城市分类进行了研究。分类结果与传统的统计模式识别方法（Bayes法）相比较简洁、快速，精度提高近2个百分点。     

基于雷达卫星图像的黄淮海原城体系空间结构研究

基于雷达卫星ScanSAR遥感图像分析，根据中心地理论，对黄淮海平原不同地貌，水文等要素影响下的城镇体系空间结构进行研究，结果表明：１）利用雷达遥感对结构信息的灵敏反应和雷达卫星ＳcanSAR合适分辨率，在图像上直接显示出建成区和范围，直观反映出城镇相对等级，这也表明雷达遥感在城市地理研究中的应用潜力，２）黄河海平原城镇空间结构深受自然条件特别是地貌尤其是水文（河流、古河道、湖泊）的影响，城镇体系可划分为５种类型区，３）发展体现了理论上对中心地体系由六边形向五边形或四边形演化的构建模型，４）无论六边形还是五边形的中心地体系，本区体现了理论上对中心地间的距离构造法则与实际情况的良好关系，证衤了克氏的中心地理论在黄淮海平原重要农产区的某种存在。     

卫星图像的解译误差与提高精度的方法

在实际应用中,目视解译仍然是卫星遥感信息应用中的主要技术。通过分析 译可能带来的误差,得出计算机自动矢量化和属性自动识别,是解决所有问题的最终方法。在计算机自动识别尚不成熟时,使用屏幕数据化解译方法,是提高卫星图像应用精度水平的一条途径。     

基于高分辨率卫星影像的城市景观元素特征研究

该文分析了城市景观及城市景观元素的基本特征，利用计算机视觉分析技术，对高分辨率卫星影像上的城市景观元素的基本特征(包括统计特征和纹理特征)分别提出了不同的计算方法，并结合计算结果，对不同的城市景观元素的特征进行分析。结果表明，利用高分辨率卫星影像，可以对城市景观元素进行很好的描述和分析。     

卫星遥感影像中耕地信息的自动提取方法研究

以县（市区）为基本单位，采用遥感图像处理ENVI3.2软件和TM资料，进行了7个县（市区）10个时相的耕地信息自动提取技术研究，结果证明，选择春季时相，TM432波段合成，经几何校正和增强处理，通过交互的非监督分类提取耕地信息，可以获得满意的结果，平均分类精度达到98.22%。     

中巴02B卫星多光谱影像中LBV数据变换方法研究

通过对实际获得的多光谱影像的光谱特征分析,提出了可用于中巴02B卫星多光谱影像的LBV数据变换公式,使得LBV数据变换方法在国产中巴02B卫星数据上的应用成为可能;运用该变换公式处理得到的中巴LBV数据变换图像比中巴原始数据假彩色合成图像颜色更鲜艳,地物类别更易区分,具有更好的目视解译效果。将LBV变换图像与中巴数据假彩色图像分别用最大似然法进行分类,分类图像和精度检验结果表明:用LBV变换公式得到的LBV结果图像能很好地提高图像计算机分类的精度,该变换方法在中巴02B卫星数据的应用中具有很大潜力。     

基于雷达卫星图像的黄淮海平原城镇体系空间结构研究

基于雷达卫星ScanSAR遥感图像分析 ,根据中心地理论 ,对黄淮海平原不同地貌、水文等要素影响下的城镇体系空间结构进行研究。结果表明 :1)利用雷达遥感对结构信息的灵敏反应和雷达卫星ScanSAR合适分辨率 ,在图像上直接显示出建成区的分布和范围 ,直观反映出城镇相对等级 ,这也表明雷达遥感在城市地理研究中的应用潜力 ;2 )黄淮海平原城镇空间结构深受自然条件特别是地貌尤其是水文 (河流、古河道、湖泊 )的影响 ,城镇体系可划分为 5种类型区 ;3)发展了河流影响下的中心地体系由六边形向五边形或四边形演化的构建模型 ;4)无论六边形还是五边形的中心地体系 ,本区体现了理论上对中心地间的距离构建法则与实际情况的良好关系 ,实证了克氏的中心地理论在黄淮海平原重要农产区的某种存在。     

基于环境小卫星CCD影像的水体提取指数法比较

针对湖北省大东湖水网水环境遥感监测需求,开展基于环境小卫星CCD影像的内陆湖库水体提取指数方法研究。以常见的3种水体识别指数为模型,参照使用TM、MODIS等典型传感器进行水体提取的波段选择方式,通过对环境小卫星CCD影像4个波段地物光谱信息的变化趋势分析,发现各波段对水体目标的区分能力;使用指数模型和相应阈值分别计算获得水体特征图像,并以目视判读结合精度评价指标的方式对提取结果进行对比分析。实验结果表明,归一化差异综合水体指数的目视判别效果最好,且具有水陆区分度高和误识别率低的特点,适用于解决水体目标快速提取问题。     

地形图点状符号自动识别中不变性特征参数的提取

特征参数的抽取,是实现地形图中点状符号自动识别的关键。本文根据点状符号在扫描图中可能出现的旋转、缩放等情况,归纳和总结出了４种易于计算的不变性特征,并给出了这些特征的提取方法和部分实验结果。这４种特征参数是:复杂度——用以描述符号外围的复杂程度;扁率——用以反映符号的扁平程度;比重——符号的黑色部分在其整个覆盖区域中所占的比例;偏心率——用以反映符号重心与符号的几何中心的偏离程度。这４种特征参数具有旋转不变性和大小不变性,且便于提取、容易计算。     

基于人眼视域图像识别的风景道视觉景观质量评价

风景道是国家旅游与交通产业融合发展的举措,而视觉景观质量（VLQ）则是风景道建设的依托。当代计算机视觉技术的发展为风景道VLQ的研究带来机遇,使其在方法上能够突破主观与客观之间的二元分割。以云南思小高速为研究对象,通过多镜头组合的等距拍摄方式获取道路景观的双眼视域图像,利用图像识别技术获取图像的像素信息;建构“非量表式语义差异法”,从“自然—人工”“多样—统一”“开阔—幽深”3个维度对视域图像进行像素级别的计算。结果显示,案例地VLQ的特征较为突出,具有高度自然、相对统一和开阔的总体特征;不同行驶方向上的VLQ存在差异,但该差异会随观测尺度的扩大而减小。基于研究结果,本文提出设置支线道路配合突出风景道形象、强化双向道路景观的差异化建设措施。实证研究在风景道VLQ测评方面表现出了直观、精确的特征,反映了本文“主体性与客观性兼顾”的方法论优势。该方法的运用将助力管理机构制定更具科学性的风景道规划、建设与管理决策,推动中国风景道的高质量发展。     

基于树结构的数字遥感图像存储方法与应用

数字遥感图像一般是采用栅格结构来存储。图像中地物的结构特征是隐含其中的。该文从图像识别角度，重点研究了基于树结构的数字遥感图像存储方法。这种方法与遥感中常用的四又树等存储方法不同，它注重图像中地物本身的结构特征。通过树结构使像元按地物目标形成一个个的组合体。该文以机场跑道识别为例，介绍了基于树结构的数字遥感图像存储方法的应用以及将图像变为树的算法。     

Qualitative satellite image analysis: Mapping spatial distribution of farming types in Ethiopia

Satellite images have enormous potential for qualitative land use analysis. This paper presents empirical results that demonstrate how normally invisible dimensions produced by land use can be identified by enriching satellite data with qualitative information from field studies.Land use can be defined as the intentional use of a specific piece of land resulting in patterns of ecological responses that are visible in the land cover and landscape. Responses to land use often result in a heterogeneous combination of reflectance in satellite images. Statistical methods used in the classification of satellite imagery are limited in their capacity to handle categories consisting of heterogeneous combinations of spectral values. To overcome this limitation, a contextual post-classification method has been used to map land cover configurations as related to different agricultural practices in the district of Sodo, Ethiopia.The results show that it is possible to map socio-spatial distribution of different agricultural and socioeconomic practices on a regional level by combining field observations and spatial contextual information. The empirical findings show local agricultural activity variations in cash crop production and subsistence agriculture in the Sodo district of Ethiopia.     

基于GPS的“雪龙”船冲击式破冰模式识别研究

"雪龙"号破冰船是我国目前唯一的极地考察船,破冰航行是极地船舶的重要特征之一。以"雪龙"号破冰船的GPS数据为基础,通过建立模型算法识别冲击式破冰这一特殊的航行状态,在整个中国第28次南极考察航次的数据分析中,整体识别率超过86.1%,识别正确率达到98%以上。利用此算法,在中国第27次南极考察航次的破冰识别率也超过85%,识别正确率达到93.5%。雪龙船两个航次实测GPS数据验证了本文算法的可用性,而破冰识别统计结果表明,不同航次的破冰模式具有较大的差异。     

Comparative assessment of semantic-sensitive satellite image retrieval: simple and context-sensitive Bayesian networks

In recent years, Bayesian networks using unsupervised extracted image features have been applied in many remote sensing information mining systems to enable semantic-sensitive image retrieval. However, a simple Bayesian network insufficiently accounts for the spatial information, that is, the relations among image regions, for the semantic inference process. This drawback significantly impacts the retrieval performance, especially if the utilised features contain no or little spatial information. Therefore, this article proposes a context-sensitive Bayesian network, which infers semantic concepts of image regions based on the spectral and textural characteristics of the regions themselves as well as their contexts, that is, the adjacent regions. In order to compare the context-sensitive Bayesian network with the simple Bayesian network, comprehensive experiments were conducted based on high-resolution multispectral IKONOS imagery. The results show that the incorporation of the image regions' spatial relations not only significantly improves the accuracy of the semantic concepts inference, but also allows more flexibility in choosing the type of low-level features.     

Generating hierarchical strokes from urban street networks based on spatial pattern recognition

Strokes are products of a higher-level aggregation of street segments that can reflect functional importance and perceptual significance that is associated with them in human spatial mental conceptualizations, which is of vital importance for network analysis, street selection, and map generalization. Street properties (e.g., street names) and angles between street segments are the two main elements used for generating street strokes according to the continuity principle of perceptual grouping into networks. However, it is difficult to automatically generate strokes with good continuity from street networks with multiple lanes such as dual carriageways or complex street junctions. This article proposes a method for generating street strokes that maintain good continuity across multiple lanes and complex street junctions. The proposed method first detects dual carriageways and complex junctions in street networks and then generates strokes according to the continuity principle of perceptual grouping. Finally, it groups the generated street strokes across the dual carriageways and complex street junctions to maintain good continuity. Moreover, the generated strokes are hierarchically ranked based on stroke length and centrality measurements. Experimental studies demonstrate the validity and effectiveness of the proposed method. The result shows that the generated street strokes maintain good continuity and reflect well the hierarchical structure of the street networks.     

Intra-annual variability of satellite observed surface albedo associated with typical land cover types in China

Surface albedo is a primary causative variable associated with the process of surface energy exchange. Numerous studies have examined diurnal variation of surface albedo at a regional scale; however, few studies have analyzed the intra-annual variations of surface albedo in concurrence with different land cover types. In this study, we amalgamated surface albedo product data (MCD43) from 2001 to 2008, land-use data (in 2000 and 2008) and land cover data (in 2000); quantitative analyses of surface albedo variation pertaining to diverse land cover types and the effect of the presence/absence of ground snow were undertaken. Results indicate that intra-annual surface albedo values exhibit flat Gaussian or triangular distributions depending upon land cover types. During snow-free periods, satellite observed surface albedo associated with the non-growing season was lower than that associated with the growing season. Satellite observed surface albedo during the presence of ground snow period was 2-4 times higher than that observed during snow-free periods. Surface albedo reference values in typical land cover types have been calculated; notably, grassland, cropland and built-up land were associated with higher surface albedo reference values than barren while ground snow was present. Irrespective of land cover types, the lowest surface albedo reference values were associated with forested areas. Proposed reference values may prove extremely useful in diverse research areas, including ecological modeling, land surface process modeling and radiation energy balance applications.     

基于POI数据的广州零售商业中心热点识别与业态集聚特征分析

商业中心是城市零售活动的重要载体,优化商业资源在城市内部空间的合理配置,摸清不同零售经营形态的区位选择,显得尤为重要。以面向公众服务的商业机构兴趣点（POI）数据为研究对象,提出一种城市商业中心与零售业态集聚区识别的方法;以广州市为例,分析商业活动的热点地区以及零售业态集聚区的空间分布特征。研究表明：① 根据核密度估计法提取的商业中心在等级上表现出由城市中心圈层向外围圈层扩散的趋势,结果符合客观事实。② 以街区为单元,商业网点密度符合局域Getis-Ord G^*指数统计特征的热点区域主要分布在越秀区和天河区,广州市零售业发展的双核心空间格局已经形成。③ 不同的零售业态对商业集聚的区位选择具有显著差异性,百货商店、超市、便利店等零售经营形态的空间集聚特征与该业态的市场定位、经营模式及选址策略基本吻合。总体来看,基于POI数据的广州零售业集聚空间分析结果能够反映实体零售企业行为与广州商业经济分布的相关性,有助于提高政府部门商业规划和零售商选址前期研究的客观性和科学性。     

大连市近岸海域水环境质量、影响因素及调控研究

近些年来,由于经济的发展,废水排放总量的增加,近岸海域水环境恶化已成为大连市主要的生态环境问题。本文运用模糊模式识别模型研究了大连市近岸海域水环境质量的动态变化,并对水环境的影响因素进行分析,从而建立了水环境与其影响因素之间的数学模型。在此研究基础上,运用系统动力学(SD)模型进行水环境调控,提出了大连市水环境经济协调型发展方案,这对于大连市的可持续发展具有重大意义。     

Effects of spatial aggregation approaches on classified satellite imagery

Spatial aggregations of raster data based on the majority rule have been typically used in landscape ecological studies. It is generally acknowledged that (1) dominant classes increase in abundance while minor classes decrease in abundance or even disappear through aggregation processes; and (2) spatial patterns also change with aggregations. In this paper, we examined an alternative, random rule-based aggregation and its effects on cover type abundance and landscape patterns, in comparison with the majority rule-based aggregation. We aggregated a classified TM imagery (about 1.5 million ha) from 30m (4231 × 3717 pixels) incrementally to 990m resolution (132 pixels × 116 pixels). Cover type proportion, mean patch size ratio, aggregation index (AI), and fractal dimension (FD) were used to assess the effects of aggregation. To compare landscapes under different resolutions, we assumed that the landscapes were least distorted if (1) the cover type proportions and mean patch size ratios among classes were maintained, and (2) all cover types responded in the same way for a given index as aggregation levels increased. For example, distortion is introduced by aggregation if some cover types increase their AI values with increasing aggregation levels while other cover types decrease. Our study indicated that the two spatial aggregation techniques led to different results in cover type proportions and they altered spatial pattern in opposite ways. The majority rule-based aggregations caused distortions of cover type proportions and spatial patterns. Generally, the majority rule-based aggregation filtered out minor classes and produced clumped landscapes. Such landscape representations are relatively easy for interpreting and, therefore, are suitable for land managers to conceptualize spatial patterns of a study region. By contrast, the random rule-based aggregations maintained cover type proportions accurately, but tended to make spatial patterns change toward disaggregation. Overall, the measurements of landscape indices used in this study indicated that