Novel Hsv Colour Space based Threshold Method for Vegetation Extraction and its Performance on Landsat TM Images

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    This paper deals with a novel proposed vegetation extraction method applied in multi spectral satellite images (Landsat TM). This proposed method essentially consists of three steps: image enhancement using histogram equalisation, image transformation to new colour model called HSV (Hue, Saturation, and Value) and thresholding application on Hue and Saturation components.  For post-processing a hybrid filter median has been used to improve the results and remove isolated pixels. The proposed method is applied to three different scenes of Beni Mellal region in Morocco. The obtained results are compared with two other thresholding methods. Pixels identified as vegetation have an average sensitivity value of 95.88% and an accuracy value of 93.02%.

     

     


  • Keywords


    Vegetation extraction, HSV colour space, Thresholding, Hybrid filter, Satellite image.

  • References


      [1] M. W. A. Halmy and P. E. Gessler, The application of ensemble techniques for land-cover classification in arid lands, Int. J. Remote Sens., vol. 36, no. 22, (2015),pp. 5613–5636.

      [2] O. S. Ahmed et al., ‘Hierarchical land cover and vegetation classification using multispectral data acquired from an unmanned aerial vehicle’, Int. J. Remote Sens., vol. 38, no. 8–10, (2017), pp. 2037–2052.

      [3] M.-C. Girard and C.-M. Girard, Traitement des données de télédétection - 2ème édition - Environnement et ressources naturelles, Dunod, 2010.

      [4] M. Izadi and P. Saeedi, Automatic Building Detection in Aerial Images Using a Hierarchical Feature Based Image Segmentation, 20th International Conference on Pattern Recognition, (2010), pp. 472–475.

      [5] A. Maarir, B. Bouikhalene, and Y. Chajri, Building Detection from Satellite Images based on Curvature Scale Space Method, Walailak J. Sci. Technol. WJST, vol. 14, no. 6, (2016), pp. 517–525.

      [6] A. Maarir and B. Bouikhalene, Roads Detection from Satellite Images Based on Active Contour Model and Distance Transform, 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV), (2016), pp. 94–98.

      [7] A. Bannari, D. Morin, F. Bonn, and A. R. Huete, A review of vegetation indices, Remote Sens. Rev., vol. 13, no. 1–2, ( 1995), pp. 95–120.

      [8] C. Bacour, F.-M. Bréon, and F. Maignan, Normalization of the directional effects in NOAA–AVHRR reflectance measurements for an improved monitoring of vegetation cycles, Remote Sens. Environ., vol. 102, no. 3, (2006), pp. 402–413.

      [9] C. J. Tucker, Red and photographic infrared linear combinations for monitoring vegetation, Remote Sens. Environ., vol. 8, no. 2, (1979), pp. 127–150.

      [10] J. Verbesselt, A. Zeileis, and M. Herold, Near real-time disturbance detection using satellite image time series, Remote Sens. Environ., vol. 123, (2012), pp. 98–108.

      [11] B. DeVries, J. Verbesselt, L. Kooistra, and M. Herold, Robust monitoring of small-scale forest disturbances in a tropical montane forest using Landsat time series, Remote Sens. Environ., vol. 161, (2015), pp. 107–121.

      [12] Y. Yang, J. Zhu, C. Zhao, S. Liu, and X. Tong, The spatial continuity study of NDVI based on Kriging and BPNN algorithm, Math. Comput. Model., vol. 54, no. 3, (2011), pp. 1138–1144.

      [13] D. M. El-Shikha, P. Waller, D. Hunsaker, T. Clarke, and E. Barnes, Ground-based remote sensing for assessing water and nitrogen status of broccoli, Agric. Water Manag., vol. 92, no. 3, (2007), pp. 183–193.

      [14] G. M. Gandhi, S. Parthiban, N. Thummalu, and A. Christy, Ndvi: Vegetation Change Detection Using Remote Sensing and Gis – A Case Study of Vellore District, Procedia Comput. Sci., vol. 57, (2015), pp. 1199–1210.

      [15] W. Li, J. Du, and B. Yi, Study on classification for vegetation spectral feature extraction method based on decision tree algorithm, International Conference on Image Analysis and Signal Processing, (2011), pp. 665–669.

      [16] H. Demirel and G. Anbarjafari, Discrete Wavelet Transform-Based Satellite Image Resolution Enhancement, IEEE Trans. Geosci. Remote Sens., vol. 49, no. 6, (2011), pp. 1997–2004.

      [17] A. K. Bhandari, A. Kumar, and G. K. Singh, Feature Extraction using Normalized Difference Vegetation Index (NDVI): A Case Study of Jabalpur City, Procedia Technol., vol. 6, (2012), pp. 612–621.

      [18] A. K. Bhandari, A. Kumar, and G. K. Singh, Improved feature extraction scheme for satellite images using NDVI and NDWI technique based on DWT and SVD, Arab. J. Geosci., vol. 8, no. 9, (2015), pp. 6949–6966.

      [19] A. R. Smith, Color Gamut Transform Pairs, in Proceedings of the 5th Annual Conference on Computer Graphics and Interactive Techniques, New York, NY, USA, (1978), pp. 12–19.

      [20] T. N. Mundhenk, HSV color space, Encyclopedia of Microfluidics and Nanofluidics. Springer US, Boston, MA, (2007), pp. 793–793.

      [21] J. S. Lim, Two-dimensional signal and image processing. 1990, http://adsabs.harvard.edu/abs/1990ph...book.....l.

      [22] N. Otsu, A Threshold Selection Method from Gray-Level Histograms, IEEE Trans. Syst. Man Cybern., vol. 9, no. 1, (1979), pp. 62–66.

      [23] D. M. Powers, Evaluation: from Precision, Recall and F-measure to ROC, Informedness, Markedness and Correlation, J. Mach. Learn. Technol., vol. 2, no. 1, (2011) , pp. 37–63.


 

View

Download

Article ID: 23239
 
DOI: 10.14419/ijet.v7i4.32.23239




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.