Précédent|Prochain

Scale estimation of object-oriented image analysis based on spectral-spatial statistics

  • role： First author第一作者
  • Affiliation：

    School of Information Engineering, China University of Geosciences, Beijing 100083, China

  • Email：mayanni@cugb.edu.cn
  • Introduction：马燕妮(1992—　)，女，硕士研究生，研究方向为高空间分辨率遥感影像信息提取。E-mail：mayanni@cugb.edu.cn
MA Yanni1,  
  • role： Corresponding author通信作者
  • Affiliation：

    School of Information Engineering, China University of Geosciences, Beijing 100083, China

  • Email：mingdp@cugb.edu.cn
  • Introduction：明冬萍(1976—　)，女，副教授，研究方向为遥感信息提取及地学尺度。E-mail：mingdp@cugb.edu.cn
MING Dongping1*,  
  • Affiliation：

    School of Computer Science, Zhejiang University of Technology, Hangzhou 310014, China

YANG Haiping2

résumé

Multi-scale segmentation is the key step of analysis in remotely-sensed imagery. Scale parameter selection in the segmentation process is directly related to the quality and accuracy of object-oriented analysis. Only on the basis of experience for segmentation parameter choice that has less quantitative analysis ways, currently. These methods lack quantitative estimation before segmentation, with considerable workloads and low efficiency. From the perspective of scientific research, the scientificity and universality of these methods are poor. The objective of this paper is to use the quantitative method to determine the scale parameterin order to realize the automatic extracting target on the object-oriented analysis. This paper summarizes the concept of scale parameter in the object-oriented analysis. The commonly used segmentation scale parameters into spatial and attribute bandwidths were also analyzed. This paper used a spatial and spectral statistics-based scale parameter selection method for object-based information extraction from high spatial resolution remote sensing images. The relationship between Fractal Net Evolution Approach (FNEA) in multi-scale segmentation and spatial statistical characteristics was analyzed. Scale estimation based on spatial and spectral statistical characteristics was applied to FNEA in multi-scale segmentation. Meanwhile, the scale estimation approach proposed in this paper was verified by high spatial resolution image, namely IKONOS and SPOT 5 data. Construction and farmland areas were selected for spatial and spectral statistical characteristics, respectively, to further estimate the optimal scale parameters in segmentation. A series of supervised classification was performed to verify the reasonability of the predicted optimal scale parameter. The classification and accuracy assessment results show that the estimated scale by spatial statistical characteristics is basically close to the optimal one in the FNEA-based multi-scale segmentation. The proposed scale estimation approach can ensure the accuracy of the following object-oriented image classification. The method can be used to estimate the appropriate scale parameters before segmentation. In addition, it is an essentially data-driven method that requires nearly no prior knowledge; thus, it can enhance the efficiency and automatic degree of object-based image analysis.

mots-clés

object oriented image analysis;image segmentation;scale estimation;scale selection;spatial statistics;fractal net evolution approach

References

  1. 1.
    Atkinson P M and Aplin P. 2004. Spatial variation in land cover and choice of spatial resolution for remote sensing. International Journal of Remote Sensing, 25(18): 3687–3702
  2. 2.
    Baatz M and Schäpe A. 2000.Multiresolution segmentation: an optimization approach for high quality multi-scale image segmentation//AngewandteGeographischeInformationsverarbeitung XII: Beiträgezum AGIT-Symposium. Salzburg: Herbert Wichmann Verlag.
  3. 3.
    Benz U C, Hofmann P, Willhauck G, Lingenfelder I and Heynen M. 2004. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS Journal of Photogrammetry and Remote Sensing, 58(3/4): 239–258
  4. 4.
    Blaschke T and Hay G J. 2001. Object-oriented image analysis and scale-space: theory and methods for modeling and evaluating multi-scale landscape structure. International Archives of Photogrammetry and Remote Sensing, 34: 22–29
  5. 5.
    Blaschke T, Hay G J, Kelly M, Lang S, Hofmann P, Addink E, Feitosa R Q, van der Meer F, van der Werff H, van Coillie F and Tiede D. 2014. Geographic object-based image analysis-towards a new paradigm. ISPRS Journal of Photogrammetry and Remote Sensing, 87: 180–191
  6. 6.
    Chen J, Deng M, Xiao P F, Yang M H, Mei X M and Liu H M. 2011. Optimal spatial scale choosing for high resolution imagery based on texture frequency analysis. Journal of Remote Sensing, 15(3): 492–511
  7. 7.
    Comaniciu D. 2003. An algorithm for data-driven bandwidth selection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(2): 281–288
  8. 8.
    Definiens AG.2007. Definiens Developer 7 User Guide, version 7.0.2.936, 23.
  9. 9.
    Drăgut L, Tiede D and Levick S R. 2010. ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data. International Journal of Geographical Information Science, 24(6): 859–871 ])
  10. 10.
    Dronova I, Gong P, Clinton N E, Wang L, Fu W, Qi S H and Liu Y. 2012. Landscape analysis of wetland plantfunctional types: the effects of image segmentation scale, vegetation classes and classification methods. Remote Sensing of Environment, 127: 357–369
  11. 11.
    Feng X, Qin K, Cui W H, Chen Y X and Li X H. 2014. Multiscale description and recognition of target shape in high-resolution remote sensing images. Journal of Remote Sensing, 18(1): 90–104
  12. 12.
    Hay G J, Castilla G, Wulder M A and Ruiz J R. 2005. An automated object-based approach for the multiscale image segmentation of forest scenes. International Journal of Applied Earth Observation and Geoinformation, 7(4): 339–359 ])
  13. 13.
    Johnson B and Xie Z X. 2011 2011. Unsupervised image segmentation evaluation and refinement using a multi-scaleapproach. ISPRS Journal of Photogrammetry and Remote Sensing, 66(4): 473–483
  14. 14.
    Jung C R. 2007. Combining wavelets and watersheds for robust multiscale image segmentation. Image and Vision Computing, 25(1): 24–33
  15. 15.
    Kim M, Madden M and Warner T.2008. Estimation of optimal image object size for the segmentation of foreststands with multispectral IKONOS imagery//Blaschke T, Lang S and Hay G J, eds. Object-based Image Analysis: Spatial Concepts for Knowledge-Driven Remote Sensing Applications. Berlin: Springer: 291–307[DOI: 10.1007/978-3-540-77058-9_16]
  16. 16.
    Ming D P, Ci T Y, Cai H Y, Li L X, Qiao C and Du J Y. 2012. Semivariogram-based spatial bandwidth selection for remote sensing image segmentation with mean-shift algorithm. IEEE Geoscience and Remote Sensing Letters, 9(5): 813–817
  17. 17.
    Ming D P, Li J, Wang J Y and Zhang M. 2015. Scale parameter selection by spatial statistics for GeOBIA: using mean-shift based multi-scale segmentation as an example. ISPRS Journal of Photogrammetry and Remote Sensing, 106: 28–41
  18. 18.
    Ming D P, Wang Q and Yang J Y. 2008. Spatial scale of remote sensing image and selection of optimal spatial resolution. Journal of Remote Sensing, 12(4): 529–537
  19. 19.
    Ming D P, Zhou W and Wang M. 2016. Scale parameter estimation based on the spatial and spectral statistics in high spatial resolution image segmentation. Journal of Geo-Information Science, 18(5): 622–631
  20. 20.
    Myint S W, Gober P, Brazel A, Grossman-Clarke S and Weng Q H. 2011. Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery. Remote Sensing of Environment, 115(5): 1145–1161 ])
  21. 21.
    Nogueira K, Penatti O A B and dos Santos J A. 2017. Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification. Pattern Recognition, 61: 539–556
  22. 22.
    Pinheiro P O, Collobert R and Dollar P. 2015. Learning to segment object candidates//Proceedings of the Advances in Neural Information Processing Systems 28. Montreal, Canada: Neural Information Processing Systems
  23. 23.
    Ševo I and Avramović A. 2016. Convolutional neural network based automatic object detection on aerial images. IEEE Geoscience and Remote Sensing Letters, 13(5): 740–744
  24. 24.
    Walter V. 2000. Automatic change detection of GIS databases based on classification of multispectral data. International Archives of Photogrammetry and Remote Sensing, 33: 1138–1145
  25. 25.
    Walter V. 2004. Object-based classification of remote sensing data for change detection. ISPRS Journal of Photogrammetry andRemote Sensing, 58(3/4): 225–238
  26. 26.
    Woodcock C E and Strahler A H. 1987. The factor of scale in remote sensing. Remote Sensing of Environment, 21(3): 311–332
  27. 27.
    Woodcock C E, Strahler A H and Jupp D L B. 1988. The use of variograms in remote sensing: I. Scene models and simulated images. Remote Sensing of Environment, 25(3): 323–348
  28. 28.
    Yang J, Li P J and He Y H. 2014. A multi-band approach to unsupervised scale parameter selection for multi-scale image segmentation. ISPRS Journal of Photogrammetry and Remote Sensing, 94: 13–24
  29. 29.
    Yang J, He Y H, Caspersun J and Jones T. 2015. A discrepancy measure for segmentation evaluation from the perspective of object recognition. ISPRS Journal of Photogrammetry and Remote Sensing, 101: 186–192
  30. 30.
    Zhang X L, Xiao P F, Feng X Z, Feng L and Ye N. 2015. Toward evaluating multiscale segmentations of highspatialresolution remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 53(7): 3694–3706
  31. 31.
    Zhang Y J. 1997. Evaluation and comparison of different segmentation algorithms. Pattern Recognition Letters, 18(10): 963–974
  32. 32.
    Zhao W Z and Du S H. 2016a. Learning multiscale and deep representations for classifying remotely sensed imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 113: 155–165
  33. 33.
    Zhao W Z and Du S H. 2016b. Spectral-spatial feature extraction for hyperspectral image classification: adimension reduction and deep learning approach. IEEE Transactions on Geoscience and Remote Sensing, 54(8): 4544–4554

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