• 《工程索引》(EI)刊源期刊
  • 中文核心期刊(综合性理工农医类)
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

结合多尺度分割和随机森林的变质矿物提取

唐淑兰 孟勇 王国强 卜涛

唐淑兰, 孟勇, 王国强, 卜涛. 结合多尺度分割和随机森林的变质矿物提取[J]. 工程科学学报. doi: 10.13374/j.issn2095-9389.2020.09.08.004
引用本文: 唐淑兰, 孟勇, 王国强, 卜涛. 结合多尺度分割和随机森林的变质矿物提取[J]. 工程科学学报. doi: 10.13374/j.issn2095-9389.2020.09.08.004
TANG Shu-lan, MENG Yong, WANG Guo-qiang, BU Tao. Extraction of metamorphic minerals by multiscale segmentation combined with random forest[J]. Chinese Journal of Engineering. doi: 10.13374/j.issn2095-9389.2020.09.08.004
Citation: TANG Shu-lan, MENG Yong, WANG Guo-qiang, BU Tao. Extraction of metamorphic minerals by multiscale segmentation combined with random forest[J]. Chinese Journal of Engineering. doi: 10.13374/j.issn2095-9389.2020.09.08.004

结合多尺度分割和随机森林的变质矿物提取

doi: 10.13374/j.issn2095-9389.2020.09.08.004
基金项目: 中国地质调查局资助项目(DD20179403;DD20190364;DD20190812);陕西省教育厅资助项目(18JK0317);陕西省自然科学基础研究计划资助项目(2020JM-585)
详细信息
    通讯作者:

    E-mail:16392800@qq.com

Extraction of metamorphic minerals by multiscale segmentation combined with random forest

More Information
  • 摘要: 为提高遥感影像变质矿物提取精度,提升变质带的识别效果,以甘肃北山ASTER影像为研究区,结合了比值运算、多尺度分割、随机森林分类法进行变质矿物提取。首先,通过矿物特征性光谱特征构造比值运算公式、进行影像增强;然后,对增强影像进行基于光谱及变差函数的多尺度分割;接着,采用随机森林法提取目标矿物;最后,通过野外勘查、采样、薄片鉴定进行精度评价。结果表明,黑云母、白云母、角闪石在ASTER影像上具有鉴定性特征,提取精度分别为85.4088%、84.7640%和85.7308%;其他含量较少的变质矿物提取精度可达到60%以上。多尺度分割能充分利用矿物的丛集特征;变差函数纹理能增强形态特征对矿物的区分能力;随机森林分类法对矿物混合引起的噪声不敏感、提取结果稳定。

     

  • 图  1  研究区地质简图

    Figure  1.  Geological sketch of the study area

    图  2  标志性矿物反射率曲线

    Figure  2.  Reflectance curve of marker minerals

    图  3  技术流程

    Figure  3.  Technical process

    图  4  比值增强结果。(a)Bi;(b)Mus;(c)Am;(d)Chl;(e)Gt;(f)Act

    Figure  4.  Ratio enhancement results: (a) Bi; (b) Mus; (c) Am; (d) Chl; (e) Gt; (f) Act

    图  5  多尺度分割流程

    Figure  5.  Multiscale segmentation process

    图  6  GS值变化趋势

    Figure  6.  Change trend of GS values

    图  7  多尺度分割结果。(a)Bi;(b)Mus;(c)Am;(d)Chl;(e)Gt;(f)Act

    Figure  7.  Multiscale segmentation results: (a) Bi; (b) Mus; (c) Am; (d) Chl; (e) Gt; (f) Act

    图  8  特征重要程度排名

    Figure  8.  Ranking of feature importance

    图  9  决策树个数选择

    Figure  9.  Number selection of decision trees

    图  10  矿物提取结果。(a)Bi;(b)Mus;(c)Am;(d)Chl;(e)Gt;(f)Act

    Figure  10.  Mineral extraction results: (a) Bi; (b) Mus; (c) Am; (d) Chl; (e) Gt; and (f) Act

    图  11  部分样品显微照片。(a)云母石英片岩;(b)石榴石白云母斜长片麻岩;(c)蛇纹石透辉石白云质大理岩;(d)钠长石绿泥石石英千枚岩

    Figure  11.  Micrograph of some samples: (a) mica quartz schist; (b) garnet muscovite plagioclase gneiss; (c) serpentine diopside dolomitic marble; (d) albite chlorite quartz phyllite

    Q—Quartz;Pl—Plagioclase;Kf—K-feldspar;Ser—Sericite;Am—Amphibole;Bi—Biotite;Di—Diopside;Act—Actinolite;Serp—Serpentine,Cc—Carbonate minerals;Mus—Muscovite;Gt—Garnet;Chl—Chlorite;Ep—Epidote

    表  1  矿物的吸收谱带与ASTER波段的对应关系

    Table  1.   Correspondence relation between the absorption bands of the minerals and ASTER bands

    MineralASTER band
    15678910111213
    BiReflexAbsorptionReflex
    MusAbsorptionReflexAbsorptionReflex
    AmReflexAbsorptionReflex
    ChlAbsorptionReflexAbsorptionReflex
    GtAbsorptionReflex
    ActReflexAbsorptionReflex
    下载: 导出CSV

    表  2  各矿物比值公式

    Table  2.   Ratio formula of minerals

    BiMusAmChlGtAct
    (b12+b10)/b11(b5+b7)/b6(b6+b9)/(b8+b7)(b1+b9)/b8b13/b12(b6+ b9)/b8
    下载: 导出CSV

    表  3  矿物样本数

    Table  3.   Mineral samples

    BiMusAmChlGtAct
    1577134819451403912832
    下载: 导出CSV

    表  4  不同特征数量矿物提取精度

    Table  4.   Extraction precision of minerals with different characteristic numbers

    FeaturesExtraction precision/%
    BiMusAmChlGtAct
    180.004175.121272.375566.005264.656460.0027
    282.342176.234275.113767.231165.003360.0456
    383.030276.780276.023267.612167.911160.0101
    483.001276.876775.354567.568965.588960.01
    582.463276.206975.118266.786565.342160.0043
    681.879576.195174.114766.001165.00159.9876
    780.78976.002273.243365.504564.776859.3425
    879.657475.546772.138964.867564.334559.0001
    978.675974.345271.351163.786562.997658.3456
    下载: 导出CSV

    表  5  部分样品薄片鉴定结果

    Table  5.   Identification results of some sample slices

    Sample numberSampling locationLithologyMineral composition
    LongitudeLatitude
    D015896°32′13.1″41°59′41.4″Albite epidote chlorite schistQuartz 48%,Feldspar 25%,Chlorite 12%,Epidote 8%,
    Biotite 3%,Sphene 3%
    D012696°32′53.1″41°59′20.4″Plagioclase amphiboliteAmphibole 75%,Plagioclase 15%,Quartz 5%,Carbonate minerals 4%,Opaque minerals 1%
    D012396°32′56.6″41°59′19.5″Garnet muscovite plagioclase gneissMuscovite 30%,Feldspar 62%,Quartz 5%,Garnet 3%
    D012196°32′57.6″41°59′19.3″Biotite plagioclase gneissQuartz 45%,Plagioclase 33%,Biotite 20%,Amphibole 2%
    D011796°33′8.2″41°59′17.8″Biotite plagioclase gneissQuartz 28%,Plagioclase 25%,Biotite 25%,Chlorite 15%,
    K-feldspar 5%,Opaque minerals 2%
    D010796°33′16.8″41°59′7.5″TonaliteQuartz 42%,Feldspar 34%,Biotite 12%,Amphibole 8%,Carbonate minerals 2%,Sericite 2%
    D010596°33′16.6″41°59′4″Garnet biotite plagioclase gneissQuartz 50%,Feldspar 31%,Biotite 10%,Garnet 5%,
    Opaque minerals 3%,Apatite 1%
    D010396°33′16.3″41°59′3″Garnet biotite plagioclase gneissQuartz 40%,Plagioclase 30%,K-feldspar 7%,Biotite 12%,Garnet 3%
    D112596°31′36.8″41°57′24.3″Serpentine diopside dolomitic marbleCalcite 49%,Diopside 32%,Serpentine 14%,Actinolite 5%
    D090196°40′47.7″41°55′39.2″Albite chlorite quartz phylliteQuartz 32%,Plagioclase 16%,Chlorite 48%,Epidote 4%,Sphene
    D042096°34′35.6″41°52′36.5″Plagioclase amphibolitePlagioclase 55%,Amphibole 30%,Quartz 10%,Biotite 3%,Epidote 2%
    D042696°34′34.5″41°52′29″Mica quartz schistQuartz 50%,Muscovite 30%,Biotite 20%
    D045096°34′14.9″41°51′38.6″Plagioclase hornblende gneissPlagioclase 35%,Amphibole 55%,Epidote 5%,Quartz 5%
    D100796°30′44.9″41°50′45.1″Mica monzonite gneissK-feldspar 30%,Plagioclase 25%,Quartz 27%,
    Biotite 14%,Muscovite 4%
    D005596°33′49″41°50′6.3″Biotite plagioclase gneissPlagioclase 38%,Quartz 35%,Biotite 20%,Muscovite 3%,Chlorite 4%
    D011396°34′19.3″41°51′46″Plagioclase hornblende gneissAmphibole 45%,Albite 37%,Microcline 10%,Quartz 5%,Pyroxene 2%,Opaque minerals 1%
    下载: 导出CSV

    表  6  精度评价

    Table  6.   Accuracy evaluation

    MineralPA/%UA/%OA/%Kappa
    Bi80.9578.6485.40880.7779
    Mus83.3575.6084.76400.7833
    Am79.7477.5585.73080.7748
    Chl68.7463.7670.69330.5938
    Gt58.4258.4365.59920.5462
    Act59.6164.4166.75090.5560
    下载: 导出CSV

    表  7  本文方法与其他方法提取精度对比

    Table  7.   Comparison of extraction accuracy between the present method and other methods

    MineralExtraction accuracy/%
    Ratio + threshold
    segmentation
    Ratio +SVMMethod of
    this paper
    Bi77.354681.134185.4088
    Mus81.283082.987084.7640
    Am76.968481.100285.7308
    Chl64.659466.453270.6933
    Gt61.842263.188665.5992
    Act62.784764.235166.7509
    下载: 导出CSV
  • [1] Diener J F A, White R W, Link K, et al. Clockwise, low-P metamorphism of the Aus qranulite terrain, southern Namibia, during the Mesoproterozoic Namaqua Oroqeny. Precambrian Res, 2013, 224: 629 doi: 10.1016/j.precamres.2012.11.009
    [2] Xie M H, Zhang Q, Chen S B, et al. Extraction of alteration anomaly information by feature-based principal component analysis from ASTER data. Editorial Committe Earth Sci J China Univ Geosci, 2015, 40(8): 1381

    谢明辉, 张奇, 陈圣波, 等. 基于特征导向主成分分析遥感蚀变异常提取方法. 地球科学—中国地质大学学报, 2015, 40(8):1381
    [3] Zadeh M H, Tangestani M H, Roldan F V, et al. Sub-pixel mineral mapping of a porphyry copper belt using EO-1 Hyperion data. Adv Space Res, 2014, 53(3): 440 doi: 10.1016/j.asr.2013.11.029
    [4] Wu Z C, Ye F W, Guo F S, et al. A review on application of techniques of principle component analysis on extracting alteration information of remote sensing. J Geo-Inf Sci, 2018, 20(11): 1644 doi: 10.12082/dqxxkx.2018.180195

    吴志春, 叶发旺, 郭福生, 等. 主成分分析技术在遥感蚀变信息提取中的应用研究综述. 地球信息科学学报, 2018, 20(11):1644 doi: 10.12082/dqxxkx.2018.180195
    [5] Liu Y Z, Lai H R, Zhang D W, et al. Change detection of high resolution remote sensing image alteration based on multi-feature mixed kernel SVM model. Remote Sens Land Resour, 2019, 31(1): 16

    刘义志, 赖华荣, 张丁旺, 等. 多特征混合核 SVM 模型的遥感影像变化检测. 国土资源遥感, 2019, 31(1):16
    [6] He Z H, He B B. Weight spectral angle mapper (WSAM) method for hyperspectral mineral mapping. Spectrosc Spectr Anal, 2011, 31(8): 2200 doi: 10.3964/j.issn.1000-0593(2011)08-2200-05

    何中海, 何彬彬. 基于权重光谱角制图的高光谱矿物填图方法. 光谱学与光谱分析, 2011, 31(8):2200 doi: 10.3964/j.issn.1000-0593(2011)08-2200-05
    [7] Kaur S, Bansal R K, Mittal M, et al. Mixed pixel decomposition based on extended fuzzy clustering for single spectral value remote sensing images. J Indian Soc Remote Sens, 2019, 47(3): 427 doi: 10.1007/s12524-019-00946-2
    [8] Feng W Q, Sui H G, Tu J H, et al. Change detection method for high resolution remote sensing images using random forest. Acta Geodaet Cartograph Sin, 2017, 46(11): 1880 doi: 10.11947/j.AGCS.2017.20170074

    冯文卿, 眭海刚, 涂继辉, 等. 高分辨率遥感影像的随机森林变化检测方法. 测绘学报, 2017, 46(11):1880 doi: 10.11947/j.AGCS.2017.20170074
    [9] Booysen R, Zimmermann R, Lorenz S, et al. Towards multiscale and multisource remote sensing mineral exploration using RPAS: a case study in the Lofdal carbonatite-hosted REE deposit, Namibia. Remote Sens, 2019, 11(21): 2500 doi: 10.3390/rs11212500
    [10] Cid Y D, Muller H, Platon A, et al. 3D solid texture classification using locally-oriented wavelet transforms. IEEE Trans Image Process, 2017, 26(4): 1899 doi: 10.1109/TIP.2017.2665041
    [11] Wang M, Zhang X C, Wang J Y, et al. Forest resource classification based on random forest and object oriented method. Acta Geodaet Cartograph Sin, 2020, 49(2): 235 doi: 10.11947/j.AGCS.2020.20190272

    王猛, 张新长, 王家耀, 等. 结合随机森林面向对象的森林资源分类. 测绘学报, 2020, 49(2):235 doi: 10.11947/j.AGCS.2020.20190272
    [12] You Y F, Wang S Y, Wang B, et al. Study on hierarchical building extraction from high resolution remote sensing imagery. J Remote Sens, 2019, 23(1): 125

    游永发, 王思远, 王斌, 等. 高分辨率遥感影像建筑物分级提取. 遥感学报, 2019, 23(1):125
    [13] Li J Y, Zhao Y K, Xue Z E, et al. A survey of model compression for deep neural networks. Chin J Eng, 2019, 41(10): 1229

    李江昀, 赵义凯, 薛卓尔, 等. 深度神经网络模型压缩综述. 工程科学学报, 2019, 41(10):1229
    [14] Cracknell M J, Reading A M. Geological mapping using remote sensing data: A comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information. Comput Geosci, 2014, 63: 22 doi: 10.1016/j.cageo.2013.10.008
    [15] Harris J. R, He J X, Rainbird R, et al. R, He J X, Rainbird R, et al. A comparison of different remotely sensed data for classifying bedrock types in Canadas arctic:application of the robust classification method and random forests. Geosci Can, 2014, 41(4): 557
    [16] Hossain M D, Chen D M. Segmentation for object-based image analysis (OBIA): A review of algorithms and challenges from remote sensing perspective. ISPRS J Photogramm Remote Sens, 2019, 150: 115 doi: 10.1016/j.isprsjprs.2019.02.009
    [17] Diaz G F, Ortiz J M, Silva J F, et al. Variogram-based descriptors for comparison and classification of rock texture images. Math Geosci, 2020, 52(4): 451 doi: 10.1007/s11004-019-09833-5
    [18] Zhang L, Liu Z, Ren T W, et al. Identification of seed maize fields with high spatial resolution and multiple spectral remote sensing using random forest classifier. Remote Sens, 2020, 12(3): 362 doi: 10.3390/rs12030362
    [19] Zhu J J, Fan X T, Du X P. Geometric feature representation and building extraction based on geometric features. J Appl Sci, 2015, 33(1): 9 doi: 10.3969/j.issn.0255-8297.2015.01.002

    朱俊杰, 范湘涛, 杜小平. 几何特征表达及基于几何特征的建筑物提取. 应用科学学报, 2015, 33(1):9 doi: 10.3969/j.issn.0255-8297.2015.01.002
    [20] Masoumi F, Eslamkish T, Abkar A A, et al. Integration of spectral, thermal, and textural features of ASTER data using random forests classification for lithological mapping. J Afric Earth Sci, 2017, 129: 445 doi: 10.1016/j.jafrearsci.2017.01.028
    [21] Pournamdari M, Hashim M, Pour A B. Spectral transformation of ASTER and Landsat TM bands for lithological mapping of Soghan ophiolite complex, South Iran. Adv Space Res, 2014, 54(4): 694 doi: 10.1016/j.asr.2014.04.022
    [22] Zhang B, He B B. Multi-scale segmentation of high-resolution remote sensing image based on improved watershed transformation. J Geo-Inf Sci, 2014, 16(1): 142

    张博, 何彬彬. 改进的分水岭变换算法在高分辨率遥感影像多尺度分割中的应用. 地球信息科学学报, 2014, 16(1):142
  • 加载中
图(11) / 表(7)
计量
  • 文章访问数:  276
  • HTML全文浏览量:  144
  • PDF下载量:  10
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-09-08
  • 网络出版日期:  2021-01-08

目录

    /

    返回文章
    返回