Evaluation of Pixel and Object-Oriented Classification Techniques for Detection and Zoning of Erosion Lands Using Sentinel-2 Remote Sensing Data (Case Study: Lighvan Watershed)

Document Type : Original Article

Authors

1 University of Tabriz - Faculty of Agriculture - Department of Physics and Soil Conservation

2 عضو هیئت علمی دانشگاه تبریز

3 عضو هیئت علمی گروه سنجش از دور و سیستم اطلاعات جغرافیایی دانشگاه تبریز

4 Soil Science Department, Tabriz university, Tabriz, Iran

5 عضو هیات علمی

Abstract

Water erosion is one of the most important causes of soil destruction, and it is considered a serious environmental hazard all over the world. Recently, remote sensing is customarily used in conservation and erosion projects that most of them use air photography which, despite the many benefits, bot have limitations. The present study was aimed to detect and zoning soil erosion levels using high resolution of Sentinel-2 satellite image, its integration with aerial photographs, base maps, and implementation of various classification methods, including pixel-based and object-oriented techniques. After the staff operations, atmospheric and geometric corrections, pre-processing, and processing done on images of Sentinel-2 for detecting the area of erosion in the Lighvan watershed. In order to evaluate the correctness and accuracy of each method in this study, the criterions of user and producer accuracy, accuracy and kappa coefficient were compared. Based on the results, the supervised tuning method with user accuracy equal 77.78 and 33.33, has the highest and lowest accuracy for classification using spectral angle map algorithm and Mahalanubis distance, respectively. The maximum of overall accuracy and kappa coefficients, 72 and 62 percent, respectively, indicate the medium accuracy of the produced maps with pixel based algorithms. The results of object-oriented processing show that based on user and producer accuracy, object-oriented methods have increased accuracy (12­%) compared to pixel-based methods. Classification results with object-oriented algorithms and based on overall accuracy, 88 and 84 percent, respectively, for the brightness and the combination of brightness and slope, and the kappa coefficient for these two algorithms was 0.86 and 0.79, respectively. This result represents an acceptable increase in classification accuracy in the use of object-oriented algorithms compared to pixel base algorithms.

Keywords

References

Alimohamadi A., Metkan A.A., Ziyaiian P., and Tabatabayi H. 2009. comparison of pixel basic, object base and decision tree classification methods in forest types mapping using remote sensing data (case study: Astara forest). Journal of Applied Researches in Geographical Sciences, 10(13): 7-26.
Brockhaus J.A., Khorram S., Bruck R.I., and Campbell M. V. 1992. a comparsion of landsat TM and spot HRV data for use in the development of forest defoliation models. International journal of remote sensing, 13: 3235- 3240.
Chen G., Hay G.J., Carvalho L.M., and Wulder M.A. 2012. Object-based change detection. International Journal of Remote Sensing, 33(14): 4434-4457.
Fazizadeh B., and Helali H. 2010. Comparison of pixel-based and object-oriented and parameters affecting the on land use/cover West Azerbaijan province. Geography Studies, 71:73-84. (In Persian)
Feizizadeh B., and Blaschke T. 2013. Land suitability analysis for Tabriz County, Iran: a multi-criteria evaluation approach using GIS. J. Environ. Plan. Manag, 56: 1–23.
Hussaina M., Chen D., Cheng A., Wei H., and Stenle D. 2013. Change detection from remotely sensed images: From pixel-based to object based approaches. ISPRS Journal of Photogrammetry and Remote Sensing, International Conference on Object based Image Analysis (OBIA 2006), university of Salzburg, pp. 91–106.
Karami A., Khorani A. A., Falahshamsi S. R., Mosavi V., and Khosravi GH. 2012. Object-oriented application of remote sensing to map gully erosion. 20th Conference of Geomatics of Iran, 8p. (In Persian)
Khosraviaqdam K., Momtaz H.R, and Asadzadeh A. 2019. Estimation of soil erodibility factor of USLE model and its relation to landscape features in some parts of Nazlou-chai basin, Iran.Applied Soil Research, 7(1): 31 -43.
Martha T.R., Kerle N., Jetten J., van Westen C.J., and Vinod K.K. 2010. Characterising spectral, spatial and morphometric properties of landslides for semi automatic detection using object oriented methods. Geomorphology, 116: 24–36.
Matinfar H.R., Sarmadian F., Alavi panah S.K., Rechard Heck. 2007. Characterizing land use/land cover types by Landsat7 data based upon object oriented approach in Kashan region. Iranian Journal of Range and Desert Research, 12(4): 589-602.
Oruc M., Marangoz A.M., and Buyuksalih G. 2004. Comparison of pixel-based and object oriented classifiation approaches using Landsat-7 ETM spectral bands. ZKU, Engineering Faculty, 67100 Zonguldak, Turkey.
Paola J., and Showengerdt R. 1995. A detailed comparison of back-propagation neural network and maximum likelihood classifiers for urban land use classification. IEEE Transactions on Geoscience and Remote Sensing, 33: 981-996.
Petropoulos G. P., Kalaitzidis C., and Vadrevu K. P. 2012. Support vector machines and object-based classification for obtaining land use/cover cartography from Hyperion hyperspectral imagery. Computers and Geosciences, 41: 99–107.
Puissant A., Rougier S., and Stumpf A. 2014. Object-oriented mapping of urban trees using Random Forest classifiers. International Journal of Applied Earth Observation and Geoinformation, 26: 235–245.
Rafieyan O., Darvishsefat A. A., Babaii S., and Mataji A. 2011. Evaluation of pixel-based and object-based classification methods for tree identification using aerial images (Case study: a forestation in Chamestan-Nur). Iranian Journal of Forest, 3 (1): 35-47. (In Persian)
Singh P., Gupta A., and Singh M. 2014. Hydrological inferences from watershed analysis for water resource management using remote sensing and GIS techniques. The Egyptian Journal of Remote Sensing and Space Science, 17(2): 111-121.
Tso B., and Mather P.M. 2001. Classification methods for remotely sensed data. Taylor and Francis Inc. ISBN: 0-415-25909-6.
Applied Soil Research
Volume 9, Issue 1
June 2021
Pages 28-40

Files

History

  • Receive Date: 22 January 2019
  • Revise Date: 15 March 2020
  • Accept Date: 15 June 2021

Share

How to cite

Statistics