Applied Geomatics

, Volume 4, Issue 4, pp 245–255 | Cite as

Analysis of parcel-based image classification methods for monitoring the activities of the Land Bank of Galicia (Spain)

  • T. Hermosilla
  • J. M. Díaz-Manso
  • L. A. Ruiz
  • J. A. Recio
  • A. Fernández-Sarría
  • P. Ferradáns-Nogueira
Original Paper


The abandonment of agricultural plots entails a low economic productivity of the land and a higher vulnerability to wildfires and degradation of affected areas. In this sense, the local government of Galicia is promoting new methodologies based on high-resolution images in order to classify the territory in basic and generic land uses. This procedure will be used to control the sustainable management of plots belonging to the Land Bank. This paper presents an application study for maintaining and updating land use/land cover geospatial databases using parcel-oriented classification. The test is performed over two geographic areas of Galicia, in the northwest of Spain. In this region, forest and shrublands in mountain environments are very heterogeneous with many private unproductive plots, some of which are in a high state of abandonment. The dataset is made of high spatial resolution multispectral imagery, cadastral cartography employed to define the image objects (plots), and field samples used to define evaluation and training samples. A set of descriptive features is computed quantifying different properties of the objects, i.e. spectral, texture, structural, and geometrical. Additionally, the effect on the classification and updating processes of the historical land use as a descriptive feature is tested. Three different classification methodologies are analyzed: linear discriminant analysis, decision trees, and support vector machine. The overall accuracies of the classifications obtained are always above 90 % and support vector machine method is proved to provide the best performance. Forest and shrublands areas are especially undefined, so the discrimination between these two classes is low. The results enable to conclude that the use of automatic parcel-oriented classification techniques for updating tasks of land use/land cover geospatial databases, is effective in the areas tested, particularly when broad and well defined classes are required.


Object-based classification Change detection High-resolution imagery Mapping Agriculture 


  1. Arikan M (2004) Parcel-based crop mapping through multi-temporal masking classification of landsat 7 images in Karacabey, Turkey. Int Arch Photogramm Remote Sens Spat Inf Sci 35:1085–1090Google Scholar
  2. Balaguer A, Ruiz LA, Hermosilla T, Recio JA (2010) Definition of a comprehensive set of texture semivariogram features and their evaluation for object-oriented image classification. Comput Geosci 36(2):231–240CrossRefGoogle Scholar
  3. Balaguer-Besser A, Hermosilla T, Recio JA, Ruiz LA (2011) Semivariogram calculation optimization for object-oriented image classification. Model Sci Educ Learn 4(7):91–104Google Scholar
  4. Blaschke T (2010) Object based image analysis for remote sensing. ISPRS J Photogramm 65(1):2–16CrossRefGoogle Scholar
  5. Cohen Y, Shoshany M (2000) Integration of remote sensing, GIS and expert knowledge in national knowledge-based crop recognition in Mediterranean environment. Int Arch Photogramm Remote Sens 33(Part B7):280–286Google Scholar
  6. Congalton R (1991) A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens Environ 37(1):35–46CrossRefGoogle Scholar
  7. Dadhwal VK, Singh RP, Dutta S, Parihar JS (2002) Remote sensing based crop inventory: a review of Indian experience. Trop Ecol 43(1):107–122Google Scholar
  8. De Wit AJW, Clevers JGPW (2004) Efficiency and accuracy of per-field classification for operational crop mapping. Int J Remote Sens 25:4091–4112CrossRefGoogle Scholar
  9. Del Frate F, Pacifici F, Solimini D (2008) Monitoring urban land cover in Rome, Italy, and its changes by single-polarization multitemporal SAR images. IEEE J Sel Top Appl Earth Obs Remote Sens 1:87–97CrossRefGoogle Scholar
  10. Díaz-Manso JM, Ferradáns-Nogueira P (2011) Modelo de uso actual da terra. In: Cobelle-Rico EJ, Diaz-Manso JM, Crecente-Maseda R, Martínez-Rivas EM (eds) Mercado e Mobilidade de Terras en Galícia, 1st edn. Servizo de Publicacións e Intercambio Científico, Santiago de Compostela, Spain, pp 31–44Google Scholar
  11. Dupas CA (2000) SAR and LANDSAT TM image fusion for land cover classification in the Brazilian Atlantic Forest Domain. Int Arch Photogramm Remote Sens XXXIII(Part B1):96–103Google Scholar
  12. El Kady M, Mack CB (1992) Remote sensing for crop inventory of Egypt’s old agricultural lands. Int Arch Photogramm Remote Sens 29:176–185Google Scholar
  13. Everitt BS, Dunn G (2001) Applied multivariate data analysis, 2nd edn. Edward Arnold, LondonGoogle Scholar
  14. Haralick RM, Shanmugam K, Dinstein I (1973) Texture features for image classification. IEEE Transact Syst Man Cybern 3(6):610–622CrossRefGoogle Scholar
  15. Hermosilla T, Almonacid J, Fernández-Sarría A, Ruiz LA, Recio JA (2010) Combining features extracted from imagery and lidar data for object-oriented classification of forest areas. Int Arch Photogramm Remote Sens Spat Inf Sci 38(4/C7)Google Scholar
  16. Hernández Orallo J, Ramírez Quintana MJ, Ferri Ramírez C (2004) Introducción a la minería de datos. Pearson Educación S.A, MadridGoogle Scholar
  17. Homer C, Huang C, Yang L, Wylie B, Coan M (2004) Development of a 2001 National Land-Cover Database for the United States. Photogramm Eng Remote Sens 70:829–840Google Scholar
  18. Huberty CJ (1994) Applied discriminant analysis. Wiley, New YorkGoogle Scholar
  19. Laws KI (1985) Goal-directed texture image segmentation. Appl Artif Intel II, SPIE 548:19–26Google Scholar
  20. Ormeci C, Alganci U, Sertel E (2010) Identification of crop areas using SPOT-5 data, FIG Congress 2010 Facing the Challenges—building the capacity. Sydney, Australia, pp 11–16Google Scholar
  21. Peled A, Gilichinsky M (2004) GIS-driven analyses of remotely sensed data for quality assessment of existing land cover classification. Int Arch Photogramm Remote Sens Spat Inf Sci 35Google Scholar
  22. Peled A, Gilichinsky M (2010) Knowledge-based classification of land cover for the quality assessment of GIS database. Int Arch Photogramm Remote Sens Spat Inf Sci 38:217–222Google Scholar
  23. Perveen F, Nagasawa R, Ali S, Husnain (2008) Evaluation of ASTER spectral bands for agricultural land cover mapping using pixel-based and object-based classification approaches. Int Arch Photogramm Remote Sens Spat Inf Sci 37(4-C1)Google Scholar
  24. Petit CC, Lambin EF (2002) Impact of data integration technique on historical land-use/land-cover change: comparing historical maps with remote sensing data in the Belgian Ardennes. Landsc Ecol 17:117–132CrossRefGoogle Scholar
  25. Quinlan JR (1993) C4.5: Programs for machine learning. Kaufmann, San FranciscoGoogle Scholar
  26. Rabe A, van der Linden S, Hostert P (2010) imageSVM, Version 2.1.
  27. Recio JA, Hermosilla T, Ruiz LA, Fernández-Sarría A (2011) Historical land use as a feature for image classification. Photogramm Eng Remote Sens 77(4):377–387Google Scholar
  28. Ruiz LA, Fernández-Sarría A, Recio JA (2004) Texture feature extraction for classification of remote sensing data using wavelet decomposition: a comparative study. Int Arch Photogramm Remote Sens Spat Inf Sci 35(B4):1109–1115Google Scholar
  29. Ruiz LA, Recio JA, Hermosilla T, Fdez. Sarriá A (2009) Identification of agricultural and land cover database changes using object-oriented classification techniques. 33rd International Symposium on Remote Sensing of Environment, May 4–8, Stresa (Italy)Google Scholar
  30. Ruiz LA, Recio JA, Fernández-Sarría A, Hermosilla T (2011) A feature extraction software tool for agricultural object-based image analysis. Comput Electron Agric 76(4):284–296CrossRefGoogle Scholar
  31. Tansey K, Chambers I, Anstee A, Denniss A, Lamb A (2009) Object-oriented classification of very high resolution airborne imagery for the extraction of hedgerows and field margin cover in agricultural areas. Appl Geogr 29(2):145–157CrossRefGoogle Scholar
  32. van der Linden S, Rabe A, Wirth F, Suess S, Okujeni A, Hostert P (2010) imageSVM regression, application manual: imageSVM version 2.1. Humboldt-Universität zu Berlin, GermanyGoogle Scholar
  33. Vapnik VN (1998) Statistical learning theory. Wiley, New YorkGoogle Scholar
  34. Walsh SJ, McCleary AL, Mena CF, Shao Y, Tuttle JP, Gonzalez A, Atkinson R (2008) QuickBird and Hyperion data analysis of an invasive plant species in the Galapagos Islands of Ecuador: implications for control and land use management. Remote Sens Environ 112(5):1927–1941CrossRefGoogle Scholar
  35. Walter V (2004) Object-based classification of remote sensing data for change detection. ISPRS J Photogramm Remote Sens 58:225–238CrossRefGoogle Scholar
  36. Walter V (2005) Object-based evaluation of lidar and multiespectral data for automatic change detection in GIS databases. Geo-Inf Syst 18:10–15Google Scholar
  37. Zaragozí, B, Rabasa, A, Rodríguez-Sala, JJ, Navarro, JT, Belda, A, Ramón, A (2012) Modelling farmland abandonment: A study combining GIS and data mining techniques. Agric Ecosys Environ 155:124–132Google Scholar
  38. Zhang S, Liu X (2005) Realization of data mining model for expert classification using multi-scale spatial data. Int Arch Photogramm Remote Sens Spat Inf Sci 26(4/W6):107–111Google Scholar

Copyright information

© Società Italiana di Fotogrammetria e Topografia (SIFET) 2012

Authors and Affiliations

  • T. Hermosilla
    • 1
  • J. M. Díaz-Manso
    • 2
  • L. A. Ruiz
    • 1
  • J. A. Recio
    • 1
  • A. Fernández-Sarría
    • 1
  • P. Ferradáns-Nogueira
    • 2
  1. 1.GeoEnvironmental Cartography and Remote Sensing Research GroupUniversitat Politècnica de ValènciaValenciaSpain
  2. 2.Sociedade para o Desenvolvemento Comarcal de GaliciaSantiago de CompostelaSpain

Personalised recommendations