Reconnaissance des cultures basée sur les caractéristiques multi-angles du satellite GF-7

  • role: First author第一作者
  • Affiliation:

    State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China

    School of Land Science and Technology, China University of Geosciences, Beijing 100083, China

  • Email:1045376795@qq.com
  • Introduction:孙智虎,研究方向为农业遥感。E-mail: 1045376795@qq.com
SUN Zhihu12,  
  • role: Corresponding author通信作者
  • Affiliation:

    State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China

    Beijing Engineering Research Center for Global Land Remote Sensing Products, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

    Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

  • Email:zhangjs@bnu.edu.cn
  • Introduction:张锦水,研究方向为深度学习与遥感大数据挖掘。E-mail: zhangjs@bnu.edu.cn
ZHANG Jinshui134*,  
  • Affiliation:

    School of Land Science and Technology, China University of Geosciences, Beijing 100083, China

HONG Youtang2,  
  • Affiliation:

    State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China

    Beijing Engineering Research Center for Global Land Remote Sensing Products, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

    Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

YANG Junwen134,  
  • Affiliation:

    Beijing Polytechnic College, Beijing 100042, China

ZHU Shuang5

résumé

L'observation terrestre par télédétection multi-angle peut fournir des caractéristiques de télédétection plus riches et multi-directionnelles, améliorant la distinguabilité entre les types de couvertures terrestres et posant une base de données solide pour une identification précise de la couverture terrestre. GF-7 est le premier satellite chinois de cartographie submétrique après le satellite ZY-3, ce qui offre une opportunité d'utiliser les caractéristiques multi-angles pour résoudre le problème des "objets différents avec des spectres similaires" et d'améliorer la précision de reconnaissance des cultures. Cette étude utilise les données panchromatiques avant, arrière et multispectrales arrière de GF-7, diverses combinaisons de caractéristiques sont entrées dans un classificateur à support vectoriel pour la classification. Par rapport aux caractéristiques spectrales et texturales, l'effet des caractéristiques multi-angles sur la précision de reconnaissance des cultures est analysé. Les résultats montrent que, par rapport à l'utilisation exclusive des caractéristiques spectrales, la combinaison des caractéristiques spectrales et de la différence angulaire augmente la précision de cartographie de l'ail et du blé d'hiver de 4,07 % et 3,15 % respectivement, la précision utilisateur augmentant de 6,73 % et 2,12 % respectivement ; par rapport à l'utilisation des caractéristiques spectrales et texturales, la combinaison des caractéristiques spectrales, texturales et de la différence angulaire augmente la précision de cartographie de l'ail et du blé d'hiver de 3,14 % et 1,01 % respectivement, la précision utilisateur augmentant de 5,11 % et 0,67 % respectivement. L'analyse du test de McNemar montre que cette amélioration de la précision de classification est stable, et l'utilisation des caractéristiques de différence angulaire peut efficacement améliorer la précision de reconnaissance des cultures. Cela est dû au fait que les caractéristiques multi-angles ont des réponses spectrales distinctes pour différents types de cultures lors de l'observation multi-angle, augmentant ainsi la séparabilité entre les cultures, garantissant ainsi la précision de la reconnaissance des cultures par télédétection.

mots-clés

GF-7;machine à vecteurs de support;différence angulaire;télédétection;blé d'hiver;ail;agriculture

References

  1. 1.
    Alshehhi R, Marpu P R, Woon W L and Mura M D. 2017. Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks. ISPRS Journal of Photogrammetry and Remote Sensing, 130: 139-149
  2. 2.
    Chang C C and Lin C J. 2011. LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3): 27
  3. 3.
    Chopping M, Moisen G G, Su L H, Laliberte A, Rango A, Martonchik J V and Peters D P C. 2008. Large area mapping of southwestern forest crown cover, canopy height, and biomass using the NASA Multiangle Imaging Spectro-Radiometer. Remote Sensing of Environment, 112(5): 2051-2063
  4. 4.
    Clayton D G. 1971. Algorithm AS 46: gram-Schmidt Orthogonalization. Applied Statistics, 20(3): 335-338
  5. 5.
    Congalton R G. 1991. A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 37(1): 35-46
  6. 6.
    Dehghan H and Ghassemian H. 2006. Measurement of uncertainty by the entropy: application to the classification of MSS data. International Journal of Remote Sensing, 27(18): 4005-4014
  7. 7.
    Duro D C, Franklin S E and Dubé M G. 2012. A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery. Remote Sensing of Environment, 118: 259-272
  8. 8.
    Foody G M. 2002. Status of land cover classification accuracy assessment. Remote Sensing of Environment, 80(1): 185-201
  9. 9.
    Foody G M and Atkinson P M. 2002. Uncertainty in Remote Sensing and GIS. Chichester: John Wiley and Sons
  10. 10.
    Haralick R M. 1979. Statistical and structural approaches to texture. Proceedings of the IEEE, 67(5): 786-804
  11. 11.
    Huang X, Chen H J and Gong J Y. 2018. Angular difference feature extraction for urban scene classification using ZY-3 multi-angle high-resolution satellite imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 135: 127-141
  12. 12.
    Huang X, Lu Q K and Zhang L P. 2014. A multi-index learning approach for classification of high-resolution remotely sensed images over urban areas. ISPRS Journal of Photogrammetry and Remote Sensing, 90: 36-48
  13. 13.
    Khatami R, Mountrakis G and Stehman S V. 2016. A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: general guidelines for practitioners and future research. Remote Sensing of Environment, 177: 89-100
  14. 14.
    Lan Z Y and Liu Y. 2018. Study on multi-scale window determination for GLCM texture description in high-resolution remote sensing image geo-analysis supported by GIS and domain knowledge. ISPRS International Journal of Geo-Information, 7(5): 175
  15. 15.
    Li L, She M Y and Luo H. 2014. Comparison on fusion algorithms of ZY-3 panchromatic and multi-spectral images. Transactions of the Chinese Society of Agricultural Engineering, 30(16): 157-165
  16. 16.
    Li X J, Chen W T, Cheng X W and Wang L Z. 2016. A comparison of machine learning algorithms for mapping of complex surface mined and agricultural landscapes using ZiYuan-3 stereo satellite imagery. Remote Sensing, 8(6): 514
  17. 17.
    Liu H F, Yang Y B, Yu S, Kong L T and Zhang Y. 2014. Adaptability evaluation of different fusion methods on ZY-3 and Landsat8 images. Remote Sensing For Land and Resources, 26(4): 63-70
  18. 18.
    Liu X S. 2015. Study on soil bidirectional reflectance characteristics and application of soil standard spectral library. Wuhan: Huazhong Agricultural University
  19. 19.
    Matasci G, Longbotham N, Pacifici F, Kanevski M and Tuia D. 2015. Understanding angular effects in VHR imagery and their significance for urban land-cover model portability: a study of two multi-angle in-track image sequences. ISPRS Journal of Photogrammetry and Remote Sensing, 107: 99-111
  20. 20.
    Roujean J L, Leroy M and Deschamps P Y. 1992. A bidirectional reflectance model of the Earth's surface for the correction of remote sensing data. Journal of Geophysical Research: Atmospheres, 97(D18): 20455-20468
  21. 21.
    Schaepman-Strub G, Schaepman M E, Painter T H, Dangel S and Martonchik J V. 2006. Reflectance quantities in optical remote sensing—definitions and case studies. Remote Sensing of Environment, 103(1): 27-42
  22. 22.
    Song D J, Zhang C M, Yang X X, Li F, Han Y J, Gao S and Dong H Y. 2020. Extracting winter wheat spatial distribution information from GF-2 image. Journal of Remote Sensing (Chinese), 24(5): 596-608
  23. 23.
    Su L H, Chopping M J, Rango A, Martonchik J V and Peters D P C. 2007. Support vector machines for recognition of semi-arid vegetation types using MISR multi-angle imagery. Remote Sensing of Environment, 107(1/2): 299-311
  24. 24.
    Tian J, Reinartz P, d’Angelo P and Ehlers M. 2013. Region-based automatic building and forest change detection on Cartosat-1 stereo imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 79: 226-239
  25. 25.
    Waldner F, Canto G S and Defourny P. 2015. Automated annual cropland mapping using knowledge-based temporal features. ISPRS Journal of Photogrammetry and Remote Sensing, 110: 1-13
  26. 26.
    Wu J Y, Liu X L, Bo Y X, Shi Z T and Fu Z. 2019. Plastic greenhouse recognition based on GF-2 data and multi-texture features. Transactions of the Chinese Society of Agricultural Engineering, 35(4): 106-113
  27. 27.
    Yang Y J, Tian Q J, Zhan Y L, Tao B and Xu K J. 2018. Effects of spatial resolution and texture features on multi-spectral remote sensing classification. Journal of Geo-Information Science, 20(1): 99-107
  28. 28.
    Yu W W, Xu K J, Zhao P, Shen P J and Zhao Y J. 2021. Influence of red-edge spectrum of sentinel-2 image on identification of dominant tree species in different growing periods. Geography and Geo-Information Science, 37(3): 42-49
  29. 29.
    Zhang D J, Pan Y Z, Zhang J S, Hu T G, Zhao J H, Li N and Chen Q. 2020. A generalized approach based on convolutional neural networks for large area cropland mapping at very high resolution. Remote Sensing of Environment, 247: 111912
  30. 30.
    Zhang J S, Pan Y Z, Han L J, Su W and He Y C. 2007. Land Use/cover Change Detection with Multi-source Data, (04):500-510
  31. 31.
    Zhu S, Zhang J S, Shuai G Y and Yu Q Y. 2014. Winter wheat mapping by soft and hard land use / cover change detection, 18(02):476-496
  32. 32.
    Zhu X F, Li S B and Xiao G F. 2019. Method on extraction of area and distribution of plastic-mulched farmland based on UAV images. Transactions of the Chinese Society of Agricultural Engineering, 35(4): 106-113

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website