Advertisement

Adaptive scale selection in multiscale segmentation based on the segmented object complexity of GF-2 satellite image

  • Fang Wang
  • Wunian YangEmail author
  • Jintong Ren
GMGDA 2019
  • 18 Downloads
Part of the following topical collections:
  1. Geological Modeling and Geospatial Data Analysis

Abstract

Image segmentation is the premise and key step of object-oriented classification, but scale selection remains a challenge in image segmentation. Over the years, scale selection methods of image segmentation have been extensively explored and developed. When the scale is chosen, all the features are generally extracted from images in these methods. In addition, in these methods, an optimal scale is generally selected based on the pre-estimation of the statistical variance of remote sensing images or determined by the post-segmentation evaluation results, rather than during the segmentation. In this study, with the central and eastern parts of Longchang City in Mid-Sichuan Hilly Region as the study area, based on the Gaofen-2 (GF-2) image, an adaptive scale selection method was proposed to determine the optimal scale of each segmentation object during the segmentation. First, the single-scale optimal image segmentation is determined by an unsupervised evaluation method which uses weighted variance and Moran’s I to measure global intra-segment homogeneity and inter-segment heterogeneity, respectively. Then, spectral, texture, and shape features of each segmented object were extracted to construct the complexity index function, and the optimal scale of the segmentation objects was determined through the iterative calculation according to the threshold value. The proposed method was applied to process GF-2 image to obtain the segmentation results and classification map, compared with the methods of determining the optimal scale through estimation local statistic variances of image and post-evaluation of segmentation results. The experimental results showed that the proposed method is of practical helpfulness and effectiveness for generating the optimal scale matching the actual ground objects.

Keywords

Object features complexity Multiscale segmentation Scale selection Object-based classification 

Notes

Acknowledgments

We appreciate CRESDA for providing the GF-2 image data and acknowledge the careful guidance of Professor Wunian Yang and helpful suggestions of the members of the research group.

Funding information

This study received financial support from the National Natural Science Foundation Project of China (Granted Nos. 41671432 and 41372340) and Department of Land and Resources Project of Sichuan Province of China (KJ-2016-12).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. Blaschke T (2010) Object based image analysis for remote sensing. Isprs J Photogramm 65(1):2–16CrossRefGoogle Scholar
  2. Blaschke T, Hay GJ, Kelly M et al (2014) Geographic object-based image analysis – towards a new paradigm. Isprs J Photogramm 87(100):180CrossRefGoogle Scholar
  3. Chen J, Li J, Pan D et al (2012) Edge-guided multiscale segmentation of satellite multispectral imagery. Ieee T Geosci Remote 50(11):4513–4520CrossRefGoogle Scholar
  4. Chen Y, Fan R, Yang X, et al (2018) Extraction of urban water bodies from high-resolution remote-sensing imagery using deep learningGoogle Scholar
  5. China Centre for Resources Satellite Data and Application (2015) GF-2 Satellites. http://www.cresda.com/EN/satellite/7157.shtml
  6. Chu S, Hong L, Liu C, et al (2014) A new regional shape index for classification of high resolution remote sensing images. Paper presented at: International Workshop on Earth Observation and Remote Sensing ApplicationsGoogle Scholar
  7. Clinton N, Holt A, Scarborough J et al (2010) Accuracy assessment measures for object-based image segmentation goodness. Photogramm Eng Rem S 76(3):289–299CrossRefGoogle Scholar
  8. Dey V, Zhang Y, Zhong M (2010) A review on image segmentation techniques with remote sensing perspective. Pattern Recogn 38(9):1277–1294Google Scholar
  9. Drăguţ L, Csillik O, Eisank C, Tiede D (2014) Automated parameterisation for multi-scale image segmentation on multiple layers. ISPRS J Photogramm Remote Sens 88(100):119–127CrossRefGoogle Scholar
  10. Drǎguţ L, Tiede D, Levick SR (2010) ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data. Int J Geogr Inf Sci 24(6):859–871CrossRefGoogle Scholar
  11. Dronova I, Gong P, Clinton NE et al (2012) Landscape analysis of wetland plant functional types: the effects of image segmentation scale, vegetation classes and classification methods. Remote Sens Environ 127(140):357–369CrossRefGoogle Scholar
  12. Duro DC, Franklin SE, Dubé MG (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 Sens Environ 118(6):259–272CrossRefGoogle Scholar
  13. Espindola GM, Camara G, Reis IA et al (2006) Parameter selection for region-growing image segmentation algorithms using spatial autocorrelation. Int J Remote Sens 27(14):3035–3040CrossRefGoogle Scholar
  14. Fotheringham AS, Brunsdon CF, Charlton ME (2000) Quantitative geography: perspectives on modern spatial analysisGoogle Scholar
  15. Gao Y, Mas JF, Kerle N et al (2011) Optimal region growing segmentation and its effect on classification accuracy. Int J Remote Sens 32(13):3747–3763CrossRefGoogle Scholar
  16. Gotlieb CC, Kreyszig HE (1990) Texture descriptors based on co-occurrence matrices. Comput Vis Graph Image Process 51(1):70–86CrossRefGoogle Scholar
  17. Haralick RM, Shapiro LG (1985) Survey: image segmentation techniques. Comput Vis Graph Image Process 29(1):100–132CrossRefGoogle Scholar
  18. Huang X, Zhang L (2008) An adaptive mean-shift analysis approach for object extraction and classification from urban hyperspectral imagery. Ieee T Geosci Remote 46(12):4173–4185CrossRefGoogle Scholar
  19. Johnson B, Xie Z (2011) Unsupervised image segmentation evaluation and refinement using a multi-scale approach. Isprs J Photogramm 66(4):473–483CrossRefGoogle Scholar
  20. Kim M, Madden M, Warner T (2008) Estimation of optimal image object size for the segmentation of forest stands with multispectral IKONOS imagery: Springer Berlin HeidelbergGoogle Scholar
  21. Kurtz C, Passat N, Gançarski P, Puissant A (2012) Extraction of complex patterns from multiresolution remote sensing images: a hierarchical top-down methodology. Pattern Recogn 45(2):685–706CrossRefGoogle Scholar
  22. Li X, Shao G (2014) Object-based land-cover mapping with high resolution aerial photography at a county scale in midwestern USA. Remote Sens-Basel 6(11):11372–11390CrossRefGoogle Scholar
  23. Liu D, Huang L, Li B (2013) An assessment method for optimal segmentation scale of remote sensing image based on similarity between objects. Journal of Geodesy and Geodynamics 33(6):137–140Google Scholar
  24. Liu Y, Bian L, Meng Y et al (2012) Discrepancy measures for selecting optimal combination of parameter values in object-based image analysis. Isprs J Photogramm 68(1):144–156CrossRefGoogle Scholar
  25. Lu H, Fu X, Li L et al (2016) Soil and water resources information classification in high resolution images with optimal segmentation scale. Transactions of the Chinese Society of Agricultural Machinery 47(9):327–333Google Scholar
  26. Ma Y, Ming D, Yang H (2017) Scale estimation of object-oriented image analysis based on spectral-spatial statistics. J Remote Sens 21(4):566–578Google Scholar
  27. Marpu PR, Neubert M, Herold H et al (2010) Enhanced evaluation of image segmentation results. Surveyor 55(1):55–68Google Scholar
  28. Ming D, Li J, Wang J et al (2015) Scale parameter selection by spatial statistics for GeOBIA: using mean-shift based multi-scale segmentation as an example. Isprs J Photogramm 106:28–41CrossRefGoogle Scholar
  29. Molenaar M (2005) Quality assessment for geo-spatial objects derived from remotely sensed data. Int J Remote Sens 26(14):2953–2974CrossRefGoogle Scholar
  30. Myint SW, Gober P, Brazel A et al (2011) Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery. Remote Sens Environ 115(5):1145–1161CrossRefGoogle Scholar
  31. Padraig C, Adam W, Peter M (2010) Segmentation performance evaluation for object-based remotely sensed image analysis. Int J Remote Sens 31(3):617–645CrossRefGoogle Scholar
  32. Persello C, Bruzzone L (2010) A novel protocol for accuracy assessment in classification of very high resolution images. Ieee T Geosci Remote 48(3):1232–1244CrossRefGoogle Scholar
  33. Räsänen A, Rusanen A, Kuitunen M et al (2013) What makes segmentation good? A case study in boreal forest habitat mapping. Int J Remote Sens 34(23):8603–8627CrossRefGoogle Scholar
  34. Vieira MA, Formaggio AR, Rennó CD et al (2012) Object based image analysis and data mining applied to a remotely sensed Landsat time-series to map sugarcane over large areas. Remote Sens Environ 123(8):553–562CrossRefGoogle Scholar
  35. Wang Z, Lu C, Yang X (2018) Exponentially sampling scale parameters for the efficient segmentation of remote-sensing images. Int J Remote Sens 39(6):1628–1654CrossRefGoogle Scholar
  36. Witharana C, Civco DL, Meyer TH (2014) Evaluation of data fusion and image segmentation in earth observation based rapid mapping workflows. Isprs J Photogramm 87(2014):1–18CrossRefGoogle Scholar
  37. Woodcock CE, Strahler AH (1987) The factor of scale in remote sensing. Remote Sens Environ 21(3):311–332CrossRefGoogle Scholar
  38. Wu B, Lin S, Zhou G (2013) Quantitatively evaluating indexes for object-based segmentation of high spatial resolution image. Journal of Geo-Information Science 4(15):567–573CrossRefGoogle Scholar
  39. Xiao P, Feng X (2012) Segmentation and information extraction of high resolution remote sensing image. Science Press, BeijingGoogle Scholar
  40. Yang J, He Y, Caspersen J et al (2015) A discrepancy measure for segmentation evaluation from the perspective of object recognition. Isprs J Photogramm 101:186–192CrossRefGoogle Scholar
  41. Yang J, Li P, He Y (2014) A multi-band approach to unsupervised scale parameter selection for multi-scale image segmentation. Isprs J Photogramm 94(8):13–24CrossRefGoogle Scholar
  42. Yin R, Shi R, Gao W (2013b) Automatic selection of optimal segmentation scales for high-resolution remote sensing images. Paper presented at: Remote Sensing and Modeling of Ecosystems for Sustainability XGoogle Scholar
  43. Yin R, Shi R, Li J (2013a) Automatic selection of optimal segmentation scale of high-resolution remote sensing images. Journal of Geo-information Science 15(3):902–910CrossRefGoogle Scholar
  44. Zhang D, Ni Q, Fang D, et al (2017) Application of multispectral remote sensing technology in surface water body extraction. Paper presented at: International Conference on Audio, Language and Image ProcessingGoogle Scholar
  45. Zhang H, Fritts JE, Goldman SA (2008) Image segmentation evaluation: a survey of unsupervised methods. Comput Vis Image Und 110(2):260–280CrossRefGoogle Scholar
  46. Zhang T, Yang X, Tong L et al (2016) Selection of best - fitting scale parameters in image segmentation based on multiscale seg-mentation image database. Remote Sensing for Land and Resources 28(4):59–63CrossRefGoogle Scholar
  47. Zhang X, Xiao P, Feng X (2012) An unsupervised evaluation method for remotely sensed imagery segmentation. Ieee Geosci Remote S 9(2):156–160CrossRefGoogle Scholar
  48. Zhang X, Xiao P, Feng X et al (2015) Toward evaluating multiscale segmentations of high spatial resolution remote sensing images. Ieee T Geosci Remote 53(7):3694–3706CrossRefGoogle Scholar
  49. Zhou Y, Feng L, Chen Y, et al (2017b) Object-based land cover mapping using adaptive scale segmentation from ZY-3 satellite images. Paper presented at: IGARSS 2017 - 2017 IEEE International Geoscience and Remote Sensing SymposiumGoogle Scholar
  50. Zhou Y, Li J, Feng L et al (2017a) Adaptive scale selection for multiscale segmentation of satellite images. Ieee J-Stars 10(8):3641–3651Google Scholar
  51. Zhou YN, Luo J, Shen Z et al (2014) Multiscale water body extraction in urban environments from satellite images. IEEE Ieee J-Stars 7(10):4301–4312Google Scholar
  52. Zhu C, Yang S, Cui S et al (2015) Accurary evaluation method for object-based segmentation of high resolution remote sesing image. High Power Laser and Particle Beams 27(6):43–49Google Scholar
  53. Zhuang Y, Zhao S, Chen C et al (2016) Supervised evaluation of optimal segmentation scale with object–oriented method in remote sensing image. Remote Sensing for Land and Resources 28(4):49–58Google Scholar

Copyright information

© Saudi Society for Geosciences 2019

Authors and Affiliations

  1. 1.Key Laboratory of Geoscience Spatial Information Technology of Ministry of Land and ResourcesChengdu University of TechnologyChengduChina
  2. 2.College of Geography and Resources ScienceNeijiang Normal UniversityNeijiangChina

Personalised recommendations