基于稀疏判别分析的高光谱影像特征提取     

周亚文  董广军  薛志祥  黎珂  王惠英 《测绘科学技术学报》2017,34(4)

针对当前特征提取方法不能充分挖掘高光谱影像稀疏特性的问题,提出一种基于稀疏判别分析的高光谱影像特征提取方法。首先,在线性判别分析的系数向量中引入稀疏正则项来捕获具有更强判别能力的特征,将高光谱影像映射至低维稀疏的子空间;然后,利用迭代优化方法对模型进行求解。利用Salinas和Pavia University高光谱影像进行对比实验,所提方法与分类方法结合用于影像分类时,其分类精度优于其他方法,总体分类精度分别达到97.42%和97.64%。  相似文献   

面向高光谱图像分类的半监督空谱判别分析   总被引：2，自引：2，他引：0  

侯榜焕  王锟  姚敏立  贾维敏  王榕 《测绘学报》2017,46(9):1098-1106

为充分利用高光谱图像蕴藏的空间信息提升分类精度,提出了面向高光谱图像分类的半监督空谱判别分析(S3 DA)算法。考虑高光谱图像数据集的空间一致性,首先利用少量标记样本定义类内散度矩阵,保存数据集同类像元的光谱近邻结构;再利用无标记样本定义空间近邻像元散度矩阵,揭示像元间的空间近邻结构和地物的空间分布结构信息。S3 DA既保持数据集在光谱域的可分性,又保存了无标记样本蕴藏的空间域近邻结构,增强了同类像元和空间近邻像元在投影子空间的聚集性,从而提升分类性能。在PaviaU和Indian Pines数据集的试验表明,总体分类精度分别达到81.50%和71.77%。与传统的光谱方法比较,该算法能有效提升高光谱图像数据集的地物分类精度。  相似文献   

AMSR2辐射率资料同化对台风“山神”分析和预报的影响研究   总被引：3，自引：2，他引：1  

杨春  闵锦忠  刘志权 《大气科学》2017,41(2):372-384

在WRFDA-3DVar（Weather Research and Forecasting model's 3-dimensional variational data assimilation）的框架下,添加了新的探测器AMSR2（Advanced Microwave Scanning Radiometer 2）微波辐射率资料的同化模块,实现了AMSR2辐射率资料在中小尺度同化系统中的有效使用。台风"山神"（Son-Tinh）直接同化AMSR2资料的个例试验结果表明,AMSR2资料可以很好的探测出台风的形态,并且与没有同化该资料的控制试验相比,同化AMSR2辐射率资料可以有效提高模式分析场的质量,进一步提高了台风中心气压,最大风速和台风路径的预报。  相似文献   

基于HJ-1A高光谱影像的湿地精细分类     

张雅春  那晓东  臧淑英 《地理科学进展》2018,37(12):1705-1712

混合像元的存在不仅影响了基于高光谱影像的地物识别和分类精度,而且已成为遥感科学向定量化发展的主要障碍。本文以扎龙湿地为试验区,以环境一号卫星采集的高光谱影像为数据源,分别采用传统的全约束最小二乘光谱解混算法(fully constrained least squares spectral unmixing algorithm, FCLS)与基于稀疏约束最小二乘光谱解混算法(sparse constrained least squares spectral unmixing algorithm, SUFCLS)实现了试验区湿地的精细分类,并对两种分类结果的表现及其分类精度进行了对比分析。研究结果表明：SUFCLS算法能够自适应的从光谱库中选择场景中所占比例最高的一组端元,并将此端元的组合应用于传统的全约束最小二乘光谱解混中实现不同湿地类型丰度的提取,该算法充分考虑了端元的空间异质性,弥补了FCLS算法在端元选取过程中的不足。精度验证结果表明与FCLS算法相比,SUFCLS算法分类结果的均方根误差更小,丰度的相关系数更高,因此该方法对于提高湿地解混精度以及实现湿地精细化分类具有重要意义。  相似文献   

基于KL-ISOMAP的高光谱图像彩色可视化     

王立国  吴飞 《南京气象学院学报》2018,10(1):63-71

标志点等距映射（L-ISOMAP）作为一种降维方法,在高光谱图像可视化中极具潜力.针对L-ISOMAP算法标志点代表性不足以及计算代价较高的问题,提出了基于K-medoids聚类算法的改进型L-ISOMAP算法（KL-ISOMAP）,进而形成可视化方法.该可视化方法由以下几部分组成：1）通过改进型K-medoids算法选择标志点;2）根据相似度剔除相似像元;3）实现剩余像元的非线性降维;4）完成降维结果的可视化.实验结果表明,KL-ISOMAP算法一方面有效地提高了标志点的内在结构代表性,进而取得了更好的可视化效果;另一方面可通过对相似阈值的设置,加快算法的运算速度.由此形成的可视化方法有着较好的视觉效果、距离保持特性以及像元可分性.  相似文献   

Value-added Impact of Geostationary Hyperspectral Infrared Sounders on Local Severe Storm Forecasts——via a Quick Regional OSSE     

Zhenglong LI  Jun LI  Pei WANG  Agnes LIM  Jinlong LI  Timothy J.SCHMIT  Robert ATLAS  Sid-Ahmed BOUKABARA  Ross N.HOFFMAN 《大气科学进展》2018,35(10):1217-1230

Accurate atmospheric temperature and moisture information with high temporal/spatial resolutions are two of the key parameters needed in regional numerical weather prediction(NWP) models to reliably predict high-impact weather events such as local severe storms(LSSs). High spectral resolution or hyperspectral infrared(HIR) sounders from geostationary orbit(GEO) provide an unprecedented source of near time-continuous, three-dimensional information on the dynamic and thermodynamic atmospheric fields—an important benefit for nowcasting and NWP-based forecasting. In order to demonstrate the value of GEO HIR sounder radiances on LSS forecasts, a quick regional OSSE(Observing System Simulation Experiment)framework has been developed, including high-resolution nature run generation, synthetic observation simulation and validation, and impact study on LSS forecasts. Results show that, on top of the existing LEO(low earth orbit) sounders, a GEO HIR sounder may provide value-added impact [a reduction of 3.56% in normalized root-mean-square difference(RMSD)] on LSS forecasts due to large spatial coverage and high temporal resolution, even though the data are assimilated every 6 h with a thinning of 60 km. Additionally, more frequent assimilations and smaller thinning distances allow more observations to be assimilated, and may further increase the positive impact from a GEO HIR sounder. On the other hand, with denser and more frequent observations assimilated, it becomes more difficult to handle the spatial error correlation in observations and gravity waves due to the limitations of current assimilation and forecast systems(such as a static background error covariance). The peak reduction of 4.6% in normalized RMSD is found when observations are assimilated every 3 h with a thinning distance of 30 km.  相似文献   

低通滤波器在高光谱影像分类中的应用     

杨哲海  张俊  李之歆 《海洋测绘》2011,31(5):44-47

研究了低通滤波器对类别可分性的改善原理,指出将其应用于高光谱影像分类有利于获取更为准确的类别分布信息,进而提高影像分类精度。最后通过实验对低通滤波器在高光谱影像分类中的表现进行了验证。  相似文献   

高光谱热红外星上辐亮度图像模拟及初步应用     

欧阳晓莹  周书贵 《遥感学报》2021,25(8):1633-1645

基于卫星数据的热红外图像模拟可以为热红外大气校正、地表温度和发射率反演和前期验证提供数据支撑,同时也可以为热红外传感器的波段设置和优化提供参考。热红外图像模拟是进行热红外定量遥感研究的有效手段。本研究利用Terra星上搭载的ASTER（Advanced Spaceborne Thermal Emission and Reflection Radiometer）遥感数据所反演得到的地表温度和发射率产品,基于高光谱辐射传输模型,模拟8—14 μm（714—1250 cm^-1）,波谱分辨率为0.25 cm^-1的星上TOA（Top of Atmosphere）高光谱热红外成像模拟数据。在此基础上,结合高光谱热红外图像数据的特点,实现了温度和发射率分离算法,以及对比了不同的基于图像的大气校正算法。结果显示,本文提出的热红外图像模拟方法可行,能够为评价不同的大气校正、温度和发射率分离算法提供有效的数据支撑。  相似文献   

煤层气赋存的分形特征研究          下载免费PDF全文

王辰  冯增朝  周动  赵东  蔡婷婷 《地球物理学报》2019,62(9):3571-3579

本文利用红外热成像手段,对微小煤样内的甲烷吸附区进行了观察,并评估其吸附特征与在煤中的分布规律.研究表明煤中存在不同尺度与甲烷吸附能力的甲烷富集区,吸附/解吸甲烷时,甲烷富集区比邻近区域具有更明显的升温/降温现象.通过图像处理的方法对不同吸附压力条件下的红外热像图中的甲烷富集区进行提取,采用盒维数进行统计发现甲烷富集区符合分形规律.试验表明随着吸附压力升高,甲烷富集区的分形维数增大,分布初值减小.对两个不同煤田的煤层气富集区进行统计表明：从微米级到千米级尺度范围内,甲烷富集区分布具有分形特征,且分形维数均在1.5~2.00之间.  相似文献   

Exploring hyperspectral bands and estimation indices for leaf nitrogen accumulation in wheat     

Xia Yao  Yan ZhuYongChao Tian  Wei FengWeiXing Cao 《International Journal of Applied Earth Observation and Geoinformation》2010

Hyperspectral sensing can provide an effective means for fast and non-destructive estimation of leaf nitrogen (N) status in crop plants. The objectives of this study were to design a new method to extract hyperspectral spectrum information, to explore sensitive spectral bands, suitable bandwidth and best vegetation indices based on precise analysis of ground-based hyperspectral information, and to develop regression models for estimating leaf N accumulation per unit soil area (LNA, g N m⁻²) in winter wheat (Triticum aestivum L.). Three field experiments were conducted with different N rates and cultivar types in three consecutive growing seasons, and time-course measurements were taken on canopy hyperspectral reflectance and LNA under the various treatments. Then, normalized difference spectral indices (NDSI) and ratio spectral indices (RSI) based on the original spectrum and the first derivative spectrum were constructed within the range of 350–2500 nm, and their relationships with LNA were quantified. The results showed that both LNA and canopy hyperspectral reflectance in wheat changed with varied N rates, with consistent patterns across different cultivars and seasons. The sensitive spectral bands for LNA existed mainly within visible and near infrared regions. The best spectral indices for estimating LNA in wheat were found to be NDSI (R₈₆₀, R₇₂₀), RSI (R₉₉₀, R₇₂₀), NDSI (FD₇₃₆, FD₅₂₆) and RSI (FD₇₂₅, FD₅₁₆), and the regression models based on the above four spectral indices were formulated as Y = 26.34x^1.887, Y = 5.095x − 6.040, Y = 0.609 e^3.008x and Y = 0.388x^1.260, respectively, with R² greater than 0.81. Furthermore, expanding the bandwidth of NDSI (R₈₆₀, R₇₂₀) and RSI (R₉₉₀, R₇₂₀) from 1 nm to 100 nm at 1 nm interval produced the LNA monitoring models with similar performance within about 33 nm and 23 nm bandwidth, respectively, over which the statistical parameters of the models became less stable. From testing of the derived equations, the model for LNA estimation on NDSI (R₈₆₀, R₇₂₀), RSI (R₉₉₀, R₇₂₀), NDSI (FD₇₃₆, FD₅₂₆) and RSI (FD₇₂₅, FD₅₁₆) gave R² over 0.79 with more satisfactory performance than previously reported models and physical models in wheat. It can be concluded that the present hyperspectral parameters of NDSI (R₈₆₀, R₇₂₀), RSI (R₉₉₀, R₇₂₀), NDSI (FD₇₃₆, FD₅₂₆) and RSI (FD₇₂₅, FD₅₁₆) can be reliably used for estimating LNA in winter wheat.  相似文献