基于支撑向量机概率输出的高光谱影像混合像元分解   总被引：5，自引：0，他引：5  

吴波  张良培  李平湘 《武汉大学学报(信息科学版)》2006,31(1):51-54

提出利用支撑向量机（SVM）后验概率来分解高光谱影像的混合像元，通过支撑向量机的输出值转化为两两配对的后验概率，再由两两配对的概率值求得多类后验概率，并以像元所属类别的后验概率作为地物的组分信息。实验结果表明，该方法能较好地估计出混合像元的组分比。  相似文献   

基于高光谱遥感数据提取森林结构参数的研究     

曾源  Michael E. Schaepman  吴炳方  Jan G. P. W. Clevers  Arnold K. Bregt 《遥感学报》2007,11(5):648-658

以位于三峡库区的龙门河森林自然保护区为研究区,综合利用线性光谱混合模型和几何光学模型,基于高光谱遥感数据提取森林结构参数是本文研究的重点。在研究区地面调查数据的基础上,通过高光谱数据和混合光谱分解法,获得反演几何光学模型所需的四分量参数,根据背景光照分量与森林植被冠层各参数间的关系,反演得到森林冠层郁闭度及平均冠幅的定量分布图,并利用37个野外实测样本进行结果验证。  相似文献   

基于正则MAP模型的遥感影像亚像元定位     

吴柯  李平湘  张良培  沈焕锋 《武汉大学学报(信息科学版)》2007,32(7):593-596

为了更好地解决亚像元的定位问题，基于超分辨率影像重建的技术，结合亚像元定位理论，提出了一种应用于亚像元定位的正则MAP估计模型，并且通过真实数据进行了检验。实验表明，该模型是一种简单、有效地解决亚像元定位问题的方法。  相似文献   

一种多/高光谱遥感图像端元提取的凸锥分析算法   总被引：3，自引：0，他引：3  

褚海峰  翟中敏  赵银娣  李平湘  张良培 《遥感学报》2007,11(4):460-467

凸锥分析方法常用于多光谱和高光谱遥感图像的端元提取。遥感图像中的每个像元都可以看作一个多维向量,整幅影像看作由离散的非负向量构成的凸锥,通过寻找凸锥的角点来自动获取图像的端元。本文提出了一种自动选择最佳凸锥角点的方法,应用到传统的凸锥分析方法中,提高了凸锥分析方法的效率。利用模拟数据和真实数据实验验证了算法的可行性。  相似文献   

用可见光与红外云图资料综合作降雨量估算的试验     

郑媛媛  冯志娴  郭萍 《热带气象学报》1998,(3)

利用红外和可见光云图亮温资料估算单站降水量级,结果发现红外和可见光云图结合估算降水量效果比单用红外云图效果要好,大雨的空报率明显降低。  相似文献   

无人机与卫星影像的叶面积指数遥感反演研究   总被引：1，自引：0，他引：1  

孙越  顾祝军  李栋梁 《测绘科学》2021,46(2):106-112,145

针对卫星遥感影像获取的叶面积指数精度较低的问题,该文结合无人机低空航拍影像和卫星影像,基于最小二乘法建立了一种叶面积指数遥感反演方法,并与卫星影像像元二分模型进行了比较。结果表明:从单一植被类型到整体植被叶面积指数的反演,新方法均优于卫星影像的像元二分法,两者整体相对误差分别为27%和35%。4种植被类型中,草本植物对模型的反演精度影响较大,两者相对误差分别为32%和56%。使用该方法准确计算了长汀县相关区域叶面积指数分布,与他人结果一致。该方法提高了卫星遥感影像获取叶面积指数的精度,为大面积高精度估算区域植被提供了一种方法。  相似文献   

基于FastICA算法和MODIS数据的水稻面积提取   总被引：1，自引：0，他引：1       下载免费PDF全文

耿利宁  景元书  杨沈斌  浩宇 《大气科学学报》2015,38(6):819-826

以苏、皖、赣三省为研究区域,采用FastICA算法从MODIS数据中提取2010年水稻种植面积,并验证该算法在混合像元分解中的有效性。在对2010年46景8 d合成地表反射率产品数据进行预处理的基础上,结合MODIS土地利用产品和平滑滤波算法,构建耕地类型像元的I_LSW和I_NDV时相变化曲线。依据I_LSW和I_NDV曲线在水稻移栽期前后的变化规律,并根据由各地区水稻I_NDV时相曲线计算得到水稻相似性指数,从MODIS影像中提取水稻像元。采用FastICA算法对潜在水稻像元水稻生长期内的I_NDV时相曲线进行分解,计算每个像元的水稻丰度,绘制水稻丰度图,获取研究区各省水稻分布和种植面积。利用统计年鉴数据和样方资料对FastICA算法提取的水稻面积进行了验证。结果显示:采用水稻相似性曲线有利于提高稻田识别效率,所获取的水稻分布与实际情况吻合;FastICA算法能够分解不同地区水稻I_NDV时相曲线;与统计资料比较,江苏、安徽、江西三省水稻面积的提取精度分别为86.4%、87.9%、51.5%。江西水稻面积提取误差主要出现在地形起伏较大的山区。  相似文献   

大伙房库区近30年来植被覆盖变化分析   总被引：1，自引：0，他引：1  

迟瑶  王艳慧  王崇 《地理信息世界》2014,(6)

根据像元二分模型原理,利用1983年、2000年、2011年大伙房库区遥感影像数据提取植被覆盖遥感信息,结合植被指数计算植被覆盖度,分析比较大伙房库区不同时期植被覆盖的变化,研究大伙房库区这三个时期植被覆盖动态变化规律,为大伙房库区的生态建设和可持续发展提供决策支持。结果显示:1近30年以来,大伙房库区植被覆盖等级分布不均衡,高植被覆盖区过分集中在北部地带,西部则多为低植被覆盖区;2大伙房库区高植被覆盖面积在减少、低植被覆盖面积在增加;3大伙房库区植被覆盖总面积在下降,库区的生态环境已经遭到了破坏;4政策建议:加强监测与监管力度,合理开发利用矿产资源,积极响应国家"退耕还林、退耕还草"号召。  相似文献   

Topographic and spectral data resolve land cover misclassification to distinguish and monitor wetlands in western Uganda     

《ISPRS Journal of Photogrammetry and Remote Sensing》2014

Wetlands provide vital wildlife habitat and ecosystem services, but changes in human land use has made them one of the world’s most threatened ecosystems. Although wetlands are generally protected by law, growing human populations increasingly drain and clear them to provide agricultural land, especially in tropical Africa. Managing and conserving wetlands requires accurately monitoring their spatial and temporal extent, often using remote sensing, but distinguishing wetlands from other land covers can be difficult. Here, we report on a method to separate wetlands dominated by papyrus (Cyperus papyrus L.) from spectrally similar grasslands dominated by elephant grass (Pennisetum purpureum Schumach.). We tested whether topographic, spectral, and temperature data improved land cover classification within and around Kibale National Park, a priority conservation area in densely populated western Uganda. Slope and reflectance in the mid-IR range best separated the combined papyrus/elephant grass pixels (average accuracy: 86%). Using a time series of satellite images, we quantified changes in six land covers across the landscape from 1984 to 2008 (papyrus, elephant grass, forest, mixed agriculture/bare soil/short grass, mixed tea/shrub, and water). We found stark differences in how land cover changed inside versus outside the park, with particularly sharp changes next to the park boundary. Inside the park, changes in land cover varied with location and management history: elephant grass areas decreased by 52% through forest regeneration but there was no net difference in papyrus areas. Outside the park, elephant grass and papyrus areas decreased by 61% and 39%, mostly converted to agriculture. Our method and findings are particularly relevant in light of social, biotic, and abiotic changes in western Uganda, as interactions between climate change, infectious disease, and changing human population demographics and distribution are predicted to intensify existing agricultural pressure on natural areas.  相似文献   

Quantifying uncertainty in remote sensing-based urban land-use mapping     

《International Journal of Applied Earth Observation and Geoinformation》2014

Land-use/land-cover information constitutes an important component in the calibration of many urban growth models. Typically, the model building involves a process of historic calibration based on time series of land-use maps. Medium-resolution satellite imagery is an interesting source for obtaining data on land-use change, yet inferring information on the use of urbanised spaces from these images is a challenging task that is subject to different types of uncertainty. Quantifying and reducing the uncertainties in land-use mapping and land-use change model parameter assessment are therefore crucial to improve the reliability of urban growth models relying on these data. In this paper, a remote sensing-based land-use mapping approach is adopted, consisting of two stages: (i) estimating impervious surface cover at sub-pixel level through linear regression unmixing and (ii) inferring urban land use from urban form using metrics describing the spatial structure of the built-up area, together with address data. The focus lies on quantifying the uncertainty involved in this approach. Both stages of the land-use mapping process are subjected to Monte Carlo simulation to assess their relative contribution to and their combined impact on the uncertainty in the derived land-use maps. The robustness to uncertainty of the land-use mapping strategy is addressed by comparing the most likely land-use maps obtained from the simulation with the original land-use map, obtained without taking uncertainty into account. The approach was applied on the Brussels-Capital Region and the central part of the Flanders region (Belgium), covering the city of Antwerp, using a time series of SPOT data for 1996, 2005 and 2012. Although the most likely land-use map obtained from the simulation is very similar to the original land-use map – indicating absence of bias in the mapping process – it is shown that the errors related to the impervious surface sub-pixel fraction estimation have a strong impact on the land-use map's uncertainty. Hence, uncertainties observed in the derived land-use maps should be taken into account when using these maps as an input for modelling of urban growth.  相似文献