Abstract
Land use and land cover (LULC) mapping is one of the widely adopted applications of satellite data. With the advent of new technologies and sensor improvements, many classification algorithms are being developed. However, there are rarely studies on comparison of these classifiers using identical classification scheme and training data over different sensors and their products. In this article, we tested the effect of improved spectral and spatial resolution on classification performance of ASTER data (15 m), Hyperion data (30 m) and their fused product (15 m). For this purpose, we have used five supervised classification algorithms -three spatial classifiers, namely, Maximum Likelihood (MLC), Support Vector Machines (SVM), Artificial Neural Network (ANN) and two spectral classifiers, namely, Spectral Angle Mapper (SAM) and Spectral Information Divergence (SID). The performance of image classification algorithms was assessed using overall accuracy (OA) and kappa coefficient. MLC and SVM performed the best on all the three datasets. OA and kappa values for almost all the classifiers were comparable for higher spatial resolution ASTER and fused product and were higher by nearly 10% than that for higher spectral resolution Hyperion data.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Foody GM (2002) Status of land cover classification accuracy assessment. Remote Sens Environ 80:185–201
Munechika CK, Warnick JS, Salvaggio C, Schott JR (1993) Resolution enhancement of multi-spectral image data to improve classification accuracy. Photogramm Eng Remote Sensing 59(1):67–72
Pohl C, Van Genderen JL (1998) Multisensor image fusion in remote sensing: concepts, methods and applications. Int J Remote Sens 19(5):823–854
Nejad AM, Ghassemian H, Mirzapour F (2015) GLCM texture features efficiency assessment of Pan-sharpened hyperspectral image classification for residential and industrial regions in Southern Tehran. J Geomat Sci Technol 5(1):55–64
Licciardi GA, Villa A, Khan MM, Chanussot J (2012) Image fusion and spectral unmixing of hyperspectral images for spatial improvement of classification maps. In: Geoscience and remote sensing symposium (IGARSS), 2012 IEEE International (pp 7290–7293)
Gong P, Howarth PJ (1992) Land-use classification of SPOT HRV data using a cover-frequency method. Int J Remote Sens 13:1459–1471
Shackelford AK, Davis CH (2003) A hierarchical fuzzy classification approach for high resolution multispectral data over urban areas. IEEE Trans Geosci Remote Sens 41:1920–1932
Pu RL, Landry S, Yu Q (2011) Object-based detailed land-cover classification with high spatial resolution IKONOS imagery. Int J Remote Sens 32:3285–3308
Tzeng YC, Fan KT, Chen KS (2009) An adaptive thresholding multiple classifiers system for remote sensing image classification. Photogramm Eng Remote Sens 75:679–687
Amarsaikhan D, Douglas T (2004) Data fusion and multisource image classification. Int J Remote Sens 25(17):3529–3539
Colditz RR, Wehrmann T, Bachmann M, Steinnocher K, Schmidt M, Strunz G, Dech S (2006) Influence of image fusion approaches on classification accuracy: a case study. Int J Remote Sens 27(15):3311–3335
Nikolakopoulos KG (2008) Comparison of nine fusion techniques for very high resolution data. Photogramm Eng Remote Sens 74(5):647–659
Taylor S, Kumar L, Reid N (2010) Mapping Lantana camara: accuracy comparison of various fusion techniques. Photogramm Eng Remote Sens 76(6):691–700
Mann D, Kushwaha A, Joshi PK (2017) Fusion of EO-1 Hyperion and Terra ASTER using Gram Schmidt image sharpening algorithm. Geocarto International (communicated)
Kumar L, Sinha P, Taylor S (2014) Improving image classification in a complex wetland ecosystem through image fusion techniques. J Appl Remote Sens 8(1):083616
Erdas Inc. (1999) Erdas field guide. Erdas Inc., Atlanta, p 344
Vapnik VN (1995) The nature of statistical learning theory. Springer, New York, p 17
Szuster BW, Chen Q, Borger M (2011) A comparison of classification techniques to support land cover and land use analysis in tropical coastal zones. Appl Geogr 31(2):525–532
Pal M, Mather PM (2005) Support vector machines for classification in remote sensing. Int J Remote Sens 26(5):1007–1011
Zhu G, Blumberg DG (2002) Classification using ASTER data and SVM algorithms: the case study of Beer Sheva, Israel. Remote Sens Environ 80(2):233–240
Richards JA (1999) Remote sensing digital image analysis. Springer, Berlin, p 240
Shafri HZM, Suhaili A, Manso S (2007) The performance of maximum likelihood, spectral angle mapper, neural network and decision tree classifiers in hyperspectral image analysis. J Comput Sci 3(6):419–423
Zhou HC, Peng Y, Liang GH (2008) The research of monthly discharge predictor corrector model based on wavelet decomposition. Water Resour Manag 22:217–227
Congalton RG, Oderwald RG, Mead RA (1983) Assessing Landsat classification accuracy using discrete multivariate analysis statistical techniques. Photogramm Eng Remote Sens 49(12):1671–1678
CongaltonRG Green K (2008) Assessing the accuracy of remotely sensed data: principles and practices. CRC Press, Boca Raton
Joshi PK, Gupta B, Roy PS (2008) Spectral evaluation of vegetation features using multi-satellite sensor system (Terra Aster, Landsat ETM + and IRS 1D LISS III) in man-made and natural landscape. Sens Rev 28(1):52–61
Leckie DG, Teillet PM, Ostaff DP, Fedosejevs G (1988) Sensor band selection for detecting current defoliation caused by the spruce budworm. Remote Sens Environ 26(1):31–36
Ma Z, Olson C (1989) A measurement of spectral overlapping among cover types. Photogramm Eng Remote Sens 55(10):1441–1444
Decker AG, Malthus TJ, Wijnen MM, Seyhan E (1992) The effect of spectral bandwidth and positioning on the spectral signature analysis of inland waters. Remote Sens Environ 41(2/3):211–225
Oza MP, Sharma SA (1990) A comparative study of supervised classifiers on a subscene in Junagadh district of Gujarat. J Indian Soc Remote Sens 18:18–24
Roy PS, Ranganath BK, Vohra TPS, Diwakar PG (1988) Analysis of IRS-1A LISS II multispectral digital data for forest type discrimination and its comparison with Landsat-TM and SPOT-1. In: Proceedings of national seminaron Indian remote sensing satellite-1A (IRS-1A) mission and its application potential, Hyderabad
Ghamisi P, Plaza J, Chen Y, Li J, Plaza AJ (2017) Advanced spectral classifiers for hyperspectral images: a review. IEEE Geosci Remote Sens Mag 5(1):8–32
Acknowledgement
Authors are thankful to the guest editors, anonymous reviewers and the editorial board of the journal for providing constructive comments and recommendations on earlier version of the manuscript. Authors acknowledge the support of the Ministry of Science & Technology, Department of Space & Technology, Big Data Initiatives Division (No. BDID/01/23/2014-HSRS) and JNU UPOE-II (ID: 300). DM is thankful to Shiv Nadar University for the technical infrastructure and PhD fellowship for research support. PKJ is thankful to DST-PURSE of Jawaharlal Nehru University for research support.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mann, D., Joshi, P.K. Evaluation of Image Classification Algorithms on Hyperion and ASTER Data for Land Cover Classification. Proc. Natl. Acad. Sci., India, Sect. A Phys. Sci. 87, 855–865 (2017). https://doi.org/10.1007/s40010-017-0454-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40010-017-0454-6