Performance comparisons of particle swarm optimization, echo state neural network and genetic algorithm for vegetation segmentation

  • Authors

    • Rincy Merlin Mathew
    • S. Purushothaman
    • P. Rajeswari
    2017-12-21
    https://doi.org/10.14419/ijet.v7i1.1.9286
  • Particle Swarm Optimization, Echostate Neural Network, Genetic Algorithm, Vegetation Segmentation.
  • This article presents the implementation of vegetation segmentation by using soft computing methods: particle swarm optimization (PSO), echostate neural network(ESNN) and genetic algorithm (GA). Multispectral image with the required band from Landsat 8 (5, 4, 3) and Landsat 7 (4, 3, 2) are used. In this paper, images from ERDAS format acquired by Landsat 7 ‘Paris.lan’ (band 4, band 3, Band 2) and image acquired from Landsat 8 (band5, band 4, band 3) are used. The soft computing algorithms are used to segment the plane-1(Near infra-red spectra) and plane 2(RED spectra). The monochrome of the two segmented images is compared to present performance comparisons of the implemented algorithms.

  • References

    1. [1] Hussain M, Chen D, Cheng A, Wei H & Stanley D, “Change detection from remotely sensed images: From pixel-based to object-based approachesâ€, ISPRS Journal of Photogrammetry and Remote Sensing, Vol.80, (2013), pp.91–106.

      [2] Müller H, Griffiths P & Hostert P, “Long-term deforestation dynamics in the Brazilian Amazon-Uncovering historic frontier development along the Cuiabá–Santarém highwayâ€, International Journal of Applied Earth Observation and Geoinformation, Vol.44, (2016), pp.61–69.

      [3] Pasher J, McGovern M & Putinski V, “Measuring and monitoring linear woody features in agricultural landscapes through earth observation data as an indicator of habitat availabilityâ€, International Journal of Applied Earth Observation and Geoinformation, Vol.44, (2016), pp.113–123.

      [4] Chance CM, Hermosilla T, Coops NC, Wulder MA & White JC, “Effect of topographic correction on forest change detection using spectral trend analysis of Landsat pixel-based compositesâ€, International Journal of Applied Earth Observation and Geoinformation, Vol.44, (2016), pp.186–194.

      [5] Li ZL, Tang BH, Wu H, Ren H, Yan G, Wan Z, Trigo IF & Sobrino JA, “Satellite-derived land surface temperature: Current status and perspectivesâ€, Remote Sensing of Environment, Vol.131, (2013), pp.14–37.

      [6] O'Loughlin FE, Paiva RCD, Durand M, Alsdorf DE & Bates PD, “A multi-sensor approach towards a global vegetation corrected SRTM DEM productâ€, Remote Sensing of Environment, Vol.182, (2016), pp.49–59.

      [7] Cunliffe AM, Brazier RE & Anderson K, “Ultra-fine grain landscape-scale quantification of dryland vegetation structure with drone-acquired structure-from-motion photogrammetryâ€, Remote Sensing of Environment, Vol.183, (2016), pp.129–143.

      [8] Feng M, Sexton JO, Huang C, Anand A, Channan S, Song XP, Song DX, Kim DH, Noojipady P & Townshend JR, “Earth science data records of global forest cover and change: Assessment of accuracy in 1990, 2000, and 2005 epochsâ€, Remote Sensing of Environment, Vol.184, (2016), pp.73-85.

      [9] Ghebrezgabher MG, Yang T, Yang X, Wang X & Khan M, “Extracting and analyzing forest and woodland cover change in Eritrea based on landsat data using supervised classificationâ€, The Egyptian Journal of Remote Sensing and Space Sciences, Vol.19, (2016), pp. 37–47.

      [10] AbdelRahman MAE, Natarajan A & Hegde R, “Assessment of land suitability and capability by integrating remote sensing and GIS for agriculture in Chamarajanagar district, Karnataka, Indiaâ€, The Egyptian Journal of Remote Sensing and Space Sciences, Vol.19, (2016), pp.125–141.

      [11] Zhang Y, Wang T, Cai C, Li C, Liu Y, Bao Y & Guan W,†Landscape pattern and transition under natural and anthropogenic disturbance in an arid region of north western Chinaâ€, International Journal of Applied Earth Observation and Geoinformation, Vol.44, (2016), pp.1–10.

      [12] Michez A, Piégay H, Jonathan L, Claessens H & Lejeune P, “Mapping of riparian invasive species with supervised classification of Unmanned Aerial System (UAS) imageryâ€, International Journal of Applied Earth Observation and Geoinformation, Vol.44, (2016), pp.88–94.

      [13] Kodikara GR, Chauhan P & Chatterjee RS, “Spectral mapping of morphological features on the moon with MGM and SAMâ€, International Journal of Applied Earth Observation and Geoinformation, Vol.44, (2016), pp.31-41.

      [14] Pippuri I, Suvanto A, Maltamo M, Korhonen KT, Pitkänen J & Packalen P, “Classification of forest land attributes using multi-source remotely sensed dataâ€, International Journal of Applied Earth Observation and Geoinformation, Vol.44, (2016), pp.11–22.

      [15] Tran TV, de Beurs KM & Julian JP, “Monitoring forest disturbances in southeast oklahoma using landsat and MODIS imagesâ€, International Journal of Applied Earth Observation and Geoinformation,Vol.44, (2016), pp.42–52.

      [16] Robinson TP, Wardell-Johnson GW, Pracilio G, Brown C, Corner R & van Klinken RD, “Testing the discrimination and detection limits of World View-imagery on a challenging invasive plant targetâ€, International Journal of Applied Earth Observation and Geoinformation, Vol.44, (2016), pp.23–30.

  • Downloads

  • How to Cite

    Merlin Mathew, R., Purushothaman, S., & Rajeswari, P. (2017). Performance comparisons of particle swarm optimization, echo state neural network and genetic algorithm for vegetation segmentation. International Journal of Engineering & Technology, 7(1.1), 184-188. https://doi.org/10.14419/ijet.v7i1.1.9286