集成多时相ETM+影像的证据推理湿地遥感分类

选择黑龙江省扎龙湿地自然保护区作为研究区,开展了基于Dempster-Shafer理论的证据推理方法(ER)湿地遥感空间分类研究,提出了一种针对ETM+多波段遥感影像的计算证据支持度的新算法,利用证据推理方法集成研究区5个时相的ETM+影像。研究表明,证据推理方法能有效集成多时相ETM+影像实现湿地空间分类,其总体分类精度比基于任一单时相影像的最大似然法(MLC)分类精度都高,提高幅度约为2%~12%。     

三峡库区岩性智能分类研究

三峡库区岩体上方覆盖着厚实的土壤和茂密的植被,是高植被覆盖区,岩性信息弱,因此岩性识别和分类困难,没有成熟的方法可循。针对三峡库区进行岩性分析,选择三峡库区巴东城区作为研究区域,采用2000年5月成像的ETM+遥感影像,构造纹理、光谱、植被覆盖等17个分类因子,将遥感影像与地质图叠加,选取1 101个样本点,采用决策树C4.5算法,挖掘出三峡库区巴东县处岩性的解译规则和知识,决策树的学习精度为96.6%,剪枝后精度为95.9%,规则提取的精度为93.1%,提取的规则置信度很高,并基于知识驱动和规则匹配实现了岩性的智能分类,分类精度较高为90.11%;将分类结果与IsoData方法、K-Means方法、马氏距离法、最大似然法、最小距离法、平行六面体方法等6种方法的分类结果进行比较,试验结果证明,决策树方法的分类结果最好,精度明显高于其他6种方法。     

基于决策树模型的上海城市湿地遥感提取与分类

城市湿地是上海重要的生态基础并具有复杂多变的自然特性。研究采用决策树分类方法,以TM影像多光谱波段特征为主要分类变量,采用经K-T变换、IHS变换等光谱增强后的数据以及利用灰度共生矩阵分析影像第一主成分的纹理统计量作为辅助分类变量,结合城市湿地几何特征信息,构建上海城市湿地决策树分类模型,进行上海市湿地信息的遥感提取和分类。结果表明：（1）上海城市湿地总面积为1 277.40 km²;其中水田面积最大,占总面积的65.30%;其次为河流、库塘、湖泊和芦苇。（2）决策树模型的分类方法在一定程度上提高了城市湿地提取和分类的精度,使其达到89.05%;与传统的最大似然法相比,总精度提高了约10%。     

基于植被抑制法的植被覆盖区多光谱遥感岩性分类

植被的发育限制了遥感在地质学方面的应用, 在植被覆盖区进行岩石填图, 首先要考虑去除植被干扰影响.以内蒙古东乌旗地区为例, 选择先进星载热发射和反射辐射仪(advanced spaceborne thermal emission and reflection radiometer, ASTER)数据, 分别计算研究区内含土壤因子植被指数和不含土壤因子的植被指数, 并对两类不同的植被指数进行主成分分析, 挑选出植被信息被抑制和岩石-土壤信息突出的主成分进行岩性分类, 和利用最大似然法的分类结果进行对比分析, 评价两种方法的岩性分类性能, 植被抑制法的总体分类正确率为82.946 8%, 最大似然法的总体分类正确率为76.364 3%.结果说明在植被覆盖区, 利用植被指数来抑制植被信息是可行的, 和常规分类方法中的最大似然法相比, 大大提高解译的准确性.      

基于MODIS数据的朝鲜半岛土地利用变化信息提取

以朝鲜半岛为研究区域, 基于2000年和2007年的MOD IS数据, 应用线性光谱混合模型进行像元组分分解并提取分类特征, 对像元组分分解后有错分的地物类型结合纹理进行分析, 以决策树模型进行土地利用分类。结果表明, 像元组分分解后的决策树分类结果总体精度达78.346 5% , Kappa系数达0.681 3。与像元组分分解前最大似然法和决策树分类结果相比, 决策树分类精度优于最大似然法, 且像元组分分解方法提高了分类精度。经2000年和2007年像元组分分解后的决策树分类结果对比: 朝鲜耕地面积增加; 韩国耕地面积减少, 居民地面积增加。     

基于HJ-1B卫星数据的积雪面积制图算法研究

积雪是影响气候变化的重要因子, 采用更高时空分辨率的环境减灾卫星遥感数据进行积雪制图算法的研究, 对推进我国自主遥感卫星在积雪监测领域的应用具有重要意义. 采用环境减灾HJ-1B卫星数据, 以青海省果洛藏族自治州达日县为研究区, 应用归一化差值积雪指数(NDSI)法建立了基于HJ-1B卫星数据的积雪面积制图算法, 并比较MODIS与HJ-1B积雪图精度. 结果表明: 研究区HJ-1B积雪制图合理的NDSI阈值为0.37, 总分类精度达到97.97%; 与"真值"影像比较, HJ-1B积雪图K_hat系数为0.911, 高于MODIS的0.817. 说明该研究建立的基于HJ-1B积雪制图算法精度可靠, 适合对研究区积雪进行实时动态监测. HJ-1B更高的空间分辨率对提高研究区积雪覆盖面积监测精度具有重要的使用价值, 但是地形因素是影响HJ-1B数据积雪分类精度的一个重要原因, 随着坡度的增加, 分类误差也随之增大, 尤其是多测误差增加比较显著.     

基于PCA+RBF的多光谱卫星遥感影像分类

多光谱卫星遥感影像具有波段多,信息量大的特点,传统的分类方法难以达到比较高的精度.这里首先采用主成份分析对多波段遥感图像进行降维,再采用训练后的RBF(radial basis function)神经网络做图像的监督分类.通过对ETM 的遥感数据进行实验,结果表明,这种分类方法的分类精度,明显优于最大似然法、最小距离法等传统的分类方法.同时,与基于像元的RBF神经网络法相比,也有一定的优势.     

高光谱遥感油气探测技术

高光谱遥感探测技术已成为探测油气藏的前沿新技术之一.研究以油气微渗漏地表共生异常理论为基础, 采用基于小波主成份分析(principal component analysis, PCA)最大似然分类、端元提取分类、光谱库典型蚀变光谱分类和植被指数决策树分类方法, 对榆林典型稀疏植被地区的进行油气勘探, 提取了与烃异常相关的粘土、碳酸盐、植被异常等相关的专题信息产品, 得出综合异常区图.对照分析已知气井与油气异常区分布, 证明了油气微渗漏信息的提取与识别方法的有效性.      

吉林西部多时相遥感数据分类方案的构建及应用

为了深化遥感监测方法在生态环境调查中的应用,本文以吉林西部为试验区,设计了一种多时相遥感数据分类方案。该方案以物候信息为主,结合地物特征变量(植被、水体和土地信息)构建的多维特征空间数据集用于土地覆被分类。该遥感分类方案提取了9种地表覆被类型,结果表明:地表植被季节变化信息和土地利用信息的引入能明显改善土地覆被的分类精度;与基于原始波段的分类方案相比,多时相遥感数据分类方案的分类精度最好,总体分类精度为95.50%,Kappa系数为95.04%。     

喀斯特地区遥感影像解译新算法——支持向量机算法

现行的遥感影像解译方法有监督分类和非监督分类。在监督分类中有平行算法,最小距离算法、最大似然算法等,而支持向量机是监督分类中的一种新的算法。本研究选择贵阳市花溪区小碧乡局部地区为研究对象,采用SPOT数据,分别运用最大似然算法和支持向量机算法对研究区遥感影像进行解译。通过建立混淆矩阵,来计算分类精度和Kappa系数。结果表明:支持向量机具有分类精度高,分类图斑完整等优点;但在时间的消耗上,支持向量机算法要比最大似然算法长。对于这两种算法而言,都存在地物光谱特征明显相异的地物易于区别,光谱相似的地物容易造成错分的现象,然而支持向量机分类精度要比最大似然分类精度高一些。支持向量机对样本数量具有敏感性,样本数量过多将导致运算时间过长。因此在实际运用中应根据实际情况,选择适合的算法。      

Fine classification of construction land using high-resolution remote sensing images: a case study in planning restricted zone of nuclear power plant

Detailed construction land information plays a significant role in monitoring planning restricted zone of nuclear power plant and ecological environment protection. This study focuses on developing fine classifying method of construction land in planning restricted zone of nuclear power plant using high spatial resolution GF(GaoFen)-1 remote sensing images. The object-oriented classification method is used in this study; the important process of which is image segmentation and classification. Multi-scale segmentation method, rule-based decision tree, and the nearest neighbor classifier are used in classifying construction land classes, i.e., road, industrial, and residential. An optimal segmentation scale is crucial to image segmentation in object-oriented classification. Instead of laborious trial-and-error experiments for optimal image segmentation, the change rates of the local variance in the homogeneous region are calculated to get the optimal segmentation scales. Multi-level classification strategy is used in the following classification. Rule-based decision tree is used to classify road and water, vegetation and non-vegetation, and industrial and residential. And the nearest neighbor classifier is used to classify cropland and forest within the vegetation land use type. The accuracy assessment result shows that the overall accuracy is 89.67% and Kappa coefficient is 0.85 for object-oriented classification, which is much higher than pixel-based maximum likelihood classifier (overall accuracy is 79.17% and Kappa coefficient is 0.74) and support vector machine classifier (overall accuracy is 74.16% and Kappa coefficient is 0.68).     

Sugarcane crop identification from LISS IV data using ISODATA,MLC, and indices based decision tree approach

Image classification is one of the crucial techniques in detecting the crops from remotely sensed data. Crop identification and discrimination provide an important basis for many agricultural applications with various purposes, such as cropping pattern analysis, acreage estimation, and yield estimation. Accurate and faster estimation of crop area is very essential for projecting yearly agriculture production for deciding agriculture policies. Remote sensing is a technique that allows mapping of large areas in a fast and economical way. In many applications of remote sensing, a user is often interested in identifying the specific crop only while other classes may be of no interest. Indian Remote Sensing Satellite (IRS-P6) LISS IV sensor image of spatial resolution 5.8 m has been used to identify the sugarcane crop for the Chhapar village of Muzaffarnagar District, India. Classification of satellite data is one of the primary steps for information extraction for crop land identification. In recent years, decision tree approach to image analysis has been developed for the assessment and improvement of traditional statistically based image classification. In this study, ISODATA, MLC, and vegetation indices based decision tree approaches are used for classifying LISS IV imagery. The 11 vegetation index images have been generated for decision tree classification. All the three methods are compared and it is found that the best performance is given by the decision tree method. Vegetation indices based decision tree method for sugarcane classification, the user’s accuracy, producer’s accuracy, overall accuracy, and kappa coefficient were found 88.17, 86.59, and 87.93% and 0.86 respectively.     

基于多源遥感影像的长春市城市建成区提取

夜光遥感影像记录的城市灯光与人类活动密切相关,已广泛应用于城市信息提取。珞珈一号作为新一代夜光遥感数据源,比以往的夜光数据具有更高的空间分辨率和光谱分辨率,可以更清晰地表达城市建成区范围和内部结构。本文利用珞珈一号夜光遥感影像,通过人类居住指数（human settlement index, HSI）、植被覆盖和建筑共同校正的城市夜光指数（vegetation and build adjusted nighttime light urban index, VBANUI）及支持向量机（support vector machine, SVM）监督分类3种方法对长春市城市建成区进行提取,并与利用NPP/VIIRS（suomi national polar-orbiting partnership/visible infrared imaging radiometer suite）夜光遥感影像、采用同样方法得到的结果对比。结果显示：本文提出的VBANUI提高了传统植被覆盖校正的城市夜光指数（vegetation adjusted nighttime light urban index, VANUI）的提取精度,使用珞珈一号夜光遥感影像通过VBANUI提取的城市建成区结果最优,其Kappa系数为0.80,总体分类精度为90.74%;使用珞珈一号和NPP/VIIRS夜光遥感影像通过HSI按最佳阈值提取城市建成区的Kappa系数分别为0.75和0.72,总体分类精度分别为88.27%和86.54%;复合数据的SVM监督分类法中Landsat-NDBI、Landsat-NDBI-VIIRS、Landsat-NDBI-LJ和Landsat-NDBI-LJlog的Kappa系数分别为0.602、0.627、0.643和0.681,总体分类精度分别为81.11%、81.52%、82.25%和84.48%。研究结果表明：3种提取方法下,均为使用珞珈一号夜光遥感影像的结果优于使用NPP/VIIRS夜光遥感影像的结果,证明相比于NPP/VIIRS夜光遥感影像,珞珈一号夜光遥感影像更适用于城市尺度的建成区范围提取。     

普朗斑岩型铜矿区矿化蚀变特征矿物填图及找矿潜力分析：来自资源一号02D遥感卫星的证据

随着近年来取得重要找矿突破的普朗斑岩型铜矿的规模化开采，进一步摸清首采区外围资源潜力任务紧迫。遥感技术尤其是国产卫星资源一号02D星等高光谱卫星成功发射，为我国高海拔艰苦地区快速精准识别与矿化相关的蚀变矿物提供了可能。针对以往对植被覆盖区高光谱矿物识别有效性方法探索不足，本文选取普朗铜矿区为研究，采用资源一号02D高光谱遥感数据，使用比值植被指数划分植被覆盖区及非植被覆盖区。基于实测波谱，分层次构建了植被覆盖区及非植被覆盖区与普朗铜矿矿化密切相关的绢云母、绿泥石、绿帘石蚀变特征矿物波谱曲线，并采用匹配滤波方法开展了蚀变矿物填图示范应用。野外验证表明：该方法可有效探测普朗斑岩型铜矿外围尤其是首采区东侧植被覆盖区绢云母等蚀变特征矿物分布信息，结果显示普朗首采区东侧具有较大找矿潜力。     

Landsat data to evaluate urban expansion and determine land use/land cover changes in Penang Island,Malaysia

Land surface temperature (LST) plays an important role in local, regional and global climate studies. LST controls the distribution of the budget for radiation heat between the atmosphere and the earth’s surface. Therefore, it is important to evaluate abrupt changes in land use/land cover (LULC). Penang Island, Malaysia has been experiencing a rapid and drastic change in urban expansion over the past two decades due to growth in industrial and residential areas. The aim of this study was to investigate and evaluate the impact of LST with respect to land use changes in Penang Island, Malaysia. Three supervised classification techniques known as maximum likelihood, minimum distance-to-mean and parallelepiped were applied to the images to extract thematic information from the acquired scene by using PCI Geomatica 10.1 image processing software. These remote sensing classification techniques help to examine land-use changes in Penang Island using multi-temporal Landsat data for the period of 1999–2007. Training sites were selected within each scene and seven land cover classes were assigned to each classifier. The relative performance of each technique was evaluated. The accuracy of each classification map was assessed using a reference data set consisting of a large number of samples collected per category. Two Landsat satellite images captured in 1999 and 2007 were chosen to classify the LULC types using the maximum likelihood classification method, determined from visible and near-infrared bands. The study revealed that the maximum likelihood classifier produced superior results and achieved a high degree of accuracy. The LST and normalised difference vegetation index (NDVI) were computed based on changes in LULC. The results showed that the urban (highly built-up) area increased dramatically, and grassland area increased moderately. Inversely, barren land decreased obviously, and forest area decreased moderately. While urban (minimally built-up) area decreased slightly. These changes in LULC caused at significant difference in LST between urban and rural areas. Strong correlation values were observed between LST and NDVI for all LULC classes. The remote sensing technique used in this study was found to be efficient; it reduced the time for the analysis of the urban expansion, and it was found to be a useful tool to evaluate the impact of urbanisation with LST.     

Monitoring and analysis of changes in a wetland landscape in Xingzi county

Wetlands play an important role in water conservation, environmental protection, and biodiversity conservation. Remote sensing is an economical and efficient technique for wetland monitoring which can limit disturbance in sensitive areas and support wetland conservation. In this paper, we used three phases of Thematic Mapper/Enhanced Thematic Mapper plus (TM/ETM+) remote sensing images from October 1989, October 1999, and October 2009 to study wetlands in Xingzi County. The images were segmented using the object-oriented remote sensing image interpretation software eCognition Developer 8.64, then segmented images were classified by slope, digital elevation model (DEM) data, Normalized Difference Vegetation Index (NDVI), Specific Leaf Area Vegetation Index (SLAVI), and Land and Water Masks (LWM) index to produce land type classification maps. Land use change information was obtained by analyzing the superposition of two classification maps of the wetland area from different years. The results showed that landscape patches in Xingzi County displayed fragmentation in their spatial distribution over time. Based on an index of changes in landscape patches, the fastest growing landscape type is grassland, while the fastest decreasing type is irrigated land. Dominant driving factors of changes in Xingzi County’s wetland landscape are population growth and policy changes.     

若尔盖高原地物遥感分类

各种物质在遥感数据中都有其特征的波谱吸收峰。因此通过波谱识别就可以大大减少以往遥感分类方法中的漏分及混分现象。为了解决若尔盖高原地物遥感分类问题,首次对本区ETM多光谱融合数据采用了地物波谱角分类法进行地物识别。分类步骤:遥感数据定标→选择训练区样本→MNF变换减维去噪处理→利用纯净像元指数(PPI)进行样本提纯→利用n-D散度法进行样本重组→波谱角分类(SAM).其分类结果表明,类别精度评价总精度为0.806,kappa系数为0.785.其精度均符合1:5万比例尺的土地详查工作的技术要求。