Mineral identification from hyperspectral images based on the optimized K-P-Means unmixing method
-
摘要: 有效的高光谱混合像元分解方法可以提高矿物信息提取的精度。为进一步研究高光谱混合像元分解方法,采用线性光谱混合模型解释高光谱图像的成像机制,用不同矿物端元的线性组合表达混合像元。在最大似然估计的框架下,利用期望最大算法对混合像元的端元和丰度进行估计。针对端元提取易受异常值影响的问题,提出基于随机抽样一致算法的稳健的K-P-Means算法,优化端元提取过程。利用光谱角度距离和光谱信息散度评价估计端元和真实端元的一致性; 利用结构相似性和峰值信噪比衡量估计的丰度和端元重新获得的图像与原图像的相似性。多种仿真数据指标显示,该优化模型可以获得精度较高的端元和丰度估计结果。通过将提取的端元与美国地质调查局光谱库提供的矿物波谱曲线进行匹配来确定矿物类型,真实数据采用内华达州铜矿区的AVIRIS高光谱传感器Cuprite数据集。矿物提取结果显示,该模型对绿泥石等8种类别的主要矿物识别结果较好,矿物聚集性明显,与实际情况一致。该方法不仅可以较好地提取矿物信息,而且可以有效抵制噪声的影响。Abstract: An effective unmixing method of hyperspectral mixed pixels can improve the precision of mineral information extraction. To further study such unmixing methods, this study explained the imaging mechanism of hyperspectral images using a linear spectral mixing model. The linear combinations of different mineral endmembers were used to express mixed pixels. The expected maximum (EM) algorithm was used to estimate the endmembers and abundance of mixed pixels under the framework of maximum likelihood estimation. A robust K-P-Means algorithm based on a random sampling consensus algorithm was proposed to improve the endmember optimization process, aiming to resist the impacts of anomalies on endmember extraction. The spectral angular distance and the spectral information divergence were used to assess the consistency between the estimated endmembers and the real endmembers. To obtain the similarity between the image and the original image, the structural similarity and the peak signal-to-noise ratio were used to measure the estimated abundance and endmembers. Various simulation data indicators show that the optimized model can obtain more precise estimations of endmembers and abundance. The mineral types were determined by matching the extracted endmembers with the mineral spectrum curves provided by the USGS spectral library. The actual data originated from the Cuprite data set of the AVIRIS hyperspectral sensor for the Nevada copper mining area. The results of mineral extraction showed that the model proposed in this study yielded satisfactory recognition results for eight types of main minerals including chlorite, which showed significant mineral aggregation and were consistent with the actual situation. Therefore, the method proposed in this study can extract precise mineral information while effectively resisting the impacts of noise.
-
Key words:
- mineral /
- hyperspectral image /
- endmember /
- unmixing /
- robust
-
-
[1] 李根军, 杨雪松, 张兴, 等. ZY1-02D高光谱数据在地质矿产调查中的应用与分析[J]. 国土资源遥感, 2021, 33(2):134-140.doi: 10.6046/gtzyyg.2020190.
[2] Li G J, Yang X S, Zhang X, et al. Application and analysis of ZY1-02D hyperspectral data in geological and mineral survey[J]. Remote Sensing for Land and Resources, 2021, 33(2):134-140.doi: 10.6046/gtzyyg.2020190.
[3] 田青林, 潘蔚, 李瑶, 等. 基于小波包变换和权重光谱角度制图的岩心高光谱蚀变信息提取[J]. 国土资源遥感, 2019, 31(4):41-46.doi: 10.6046/gtzyyg.2019.04.06.
[4] Tian Q L, Pan W, Li Y, et al. Extraction of alteration information from hyperspectral core imaging based on wavelet packet transform and weight spectral angle mapper[J]. Remote Sensing for Land and Resources, 2019, 31(4):41-46.doi: 10.6046/gtzyyg.2019.04.06.
[5] 张帅洋, 华文深, 应家驹, 等. 高光谱线性解混研究进展[J]. 激光杂志, 2021, 42(3):17-21.
[6] Zhang S Y, Hua W S, Ying J J, et al. Research on the development of hyperspectral linear unmixing[J]. Laser Journal, 2021, 42(3):17-21.
[7] 甘甫平, 王润生, 马蔼乃. 基于特征谱带的高光谱遥感矿物谱系识别[J]. 地学前缘, 2003, 10(2):445-454.
[8] Gan F P, Wang R S, Ma A N. Spectral identification tree(SIT) for mineral extraction based on spectral characteristics of minerals[J]. Earth Science Frontiers, 2003, 10(2):445-454.
[9] 张川, 叶发旺, 徐清俊, 等. 新疆白杨河铀铍矿区航空高光谱矿物填图及蚀变特征分析[J]. 国土资源遥感, 2017, 29(2):160-166.doi: 10.6046/gtzyyg.2017.02.23.
[10] Zhang C, Ye F W, Xu Q J, et al. Mineral mapping and analysis of alteration characteristics using airborne hyperspectral remote sensing data in the Baiyanghe uranium and beryllium ore district,Xinjiang[J]. Remote Sensing for Land and Resources, 2017, 29(2):160-166.doi: 10.6046/gtzyyg.2017.02.23.
[11] Chaudhry F, Wu C C, Liu W M, et al. Pixel purity index-based algorithms for endmember extraction from hyperspectral imagery[J]. Recent Advances in Hyperspectral Signal and Image Processing, 2006:29-62.
[12] Winter M E. Comparison of approaches for determining endmembers in hyper-spectral data[C]// IEEE Aerospace Conference Proceedings.IEEE, 2000(3):305-313.
[13] Nascimento J M P, Dias J M B. Vertex component analysis:A fast algorithm to unmix hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(2):898-910.
[14] 吴波, 汪小钦, 张良培. 端元光谱自动提取的总体最小二乘迭代分解[J]. 武汉大学学报(信息科学版), 2008, 33(5):457-460.
[15] Wu B, Wang X Q, Zhang L P. Iterative abstraction of endmember based on total least square for mixture pixel decomposition[J]. Geomatics and Information Science of Wuhan University, 2008, 33(5):457-460.
[16] Roberts D A, Gardner M, Church R, et al. Mapping chaparral in the Santa Monica Mountains using multiple endmember spectral mixture models[J]. Remote Sensing of Environment, 1998, 65(3):267-279.
[17] Asner G P, Lobell D B. A biogeophysical approach for automated SWIR unmixing of soils and vegetation[J]. Remote Sensing of Environment, 2000, 74(1):99-112.
[18] Song C. Spectral mixture analysis for subpixel vegetation fractions in the urban environment:How to incorporate endmember variability?[J]. Remote Sensing of Environment, 2005, 95(2):248-263.
[19] 吴柯, 张良培, 李平湘. 一种端元变化的神经网络混合像元分解方法[J]. 遥感学报, 2007, 11(1):20-26.
[20] Wu K, Zhang L P, Li P X. A neural network method of selective endmember for pixel unmixing[J]. Journal of Remote Sensing, 2007, 11(1):20-26.
[21] 林红磊, 张霞, 孙艳丽. 基于单次散射反照率的矿物高光谱稀疏解混[J]. 遥感学报, 2016, 20(1):53-61.
[22] Lin H L, Zhang X, Sun Y L. Hyperspectral sparse unmixing of minerals with single scattering albedo[J]. Journal of Remote Sensing, 2016, 20(1):53-61.
[23] Xu L L, Li J, Wong A, et al. K-P-Means:A clustering algorithm of K “Purified” Means for hyperspectral endmember estimation[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(10):1787-1791.
[24] Fischler M A, Bolles R C. Random sample consensus:A paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6):381-395.
[25] 王润生, 杨苏明, 阎柏琨. 成像光谱矿物识别方法与识别模型评述[J]. 国土资源遥感, 2007, 19(1):1-9.doi: 10.6046/gtzyyg.2007.01.01.
[26] Wang R S, Yang S M, Yan B K. A review of mineral spectral identification methods and models with imaging spectrometer[J]. Remote Sensing for Land and Resources, 2007, 19(1):1-9.doi: 10.6046/gtzyyg.2007.01.01.
[27] Dempster A P, Laird N M, Rubin D B. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society(Series B), 1977, 39(1):1-38.
[28] Lawson C L, Hanson R J. Solving least squares problems[M]. Englewood Cliffs: Prentice-Hall, 1974:161.
[29] 郭继东, 向辉. 一个基本矩阵的鲁棒估计算法[J]. 计算机应用, 2005, 25(12):2845-2848.
[30] Guo J D, Xiang H. A robust method for estimating the fundamental matrix[J]. Computer Applications, 2005, 25(12):2845-2848.
[31] Chang C I, Heinz D C. Constrained subpixel detection for remotely sensed images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000, 38(3):1144-1159.
[32] Zhou W, Alan C B, Hamid R S, et al. Image quality assessment:From error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.
[33] Huynh-Thu Q, Ghanbari M. Scope of validity of PSNR in image/video quality assessment[J]. Electronics Letters, 2008, 44(13):800-801.
-
计量
- 文章访问数: 679
- PDF下载数: 50
- 施引文献: 0
下载: