Abstract
The preparation of accurate LULC is of great importance as it is used in various studies ranging from change detection to geospatial modelling. Literature offers studies comparing different classification algorithms/approaches to prepare LULC maps. However, still there is a lack of studies that can provide a comprehensive analysis on widely used classification algorithms. Hence, in the present study, nine different pixel- and object-based classification algorithms have been used to compare their relative effectiveness in generating remotely sensed LULC maps. The algorithms include maximum likelihood, neural network, support vector machine (linear, polynomial, RBF (radial basis function), sigmoid kernels), random forest (RF) and Naive Bayes for pixel-based classification and maximum likelihood algorithm for object-based classification (OBC) approach. Additionally, the study has analysed the impact of different types of satellite datasets (i.e., high resolution image and resolution merged images of same resolution) on relative effectiveness of the algorithms in classifying the satellite imageries accurately. High resolution (5 m) satellite image LISS 4 MX70, resolution merged satellite images (5 m) LISS 3 merged with LISS 4 mono and LISS 3 merged with IRS-1D are employed for classification. 27 LULC maps (9 classification algorithms * 3 images) are evaluated for comparing classification algorithms. The accuracy assessment of the images is carried out using confusion matrix and Mc Nemar’s test. It has been observed that (1) the performance of all classification algorithms differs from each other and (2) resolution merged data impacts classification accuracy differently when compared to other satellite image of same spatial resolution. RF and OBC are identified as potential classifiers with majority of datasets. The results suggest that due to heterogeneity in urban land-use, it is difficult to achieve higher overall accuracy in classifying a large urban area using 5 m resolution satellite dataset. Moreover, visual examination of LULC should be considered for choosing better classification approach as pixel-based approach produces salt-pepper effect in LULC, whereas OBC produces visually smoothened LULC and identifies even smaller objects in urban landscape. The comparative evaluation of different image types reveal that RF performs better with all images, however, the performance of OBC was found to be improved with original high-resolution data.
Similar content being viewed by others
Availability of data and material
There are no linked research data sets for this submission. The data that has been used is confidential.
Code availability
ERDAS® IMAGINE 2016, ArcGIS 10.5 and R version 3.3.2 softwares are used in this manuscript.
References
Agrafiotis P, Georgopoulos A (2015) Comparative assessment of very high resolution satellite and aerial orthoimagery. Int Arch Photogram Remote Sens Spatial Inf Sci 40(3):1
Agresti A (2002) Categorical data analysis. Wiley, New York
Anderson JR, Hardy EE, Roach JT, Witmer RE (1976) A land use and land cover classification system for use with remote sensor data. U.S. Geological Survey Professional Paper 964:28.
Baatz M, Benz U, Dehghani S, Heynen M, Höltje A, Hofmann P, Lingenfelder I, Mimler M, Sohlbach M, Weber M, Willhauck G (2004) eCognition Professional 4.0 User Guide. Definiens Imaging GmbH. Definiens, Munich
Benz UC, Hofmann P, Willhauck G, Lingenfelder I, Heynen M (2004) Multiresolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS J Photogram Remote Sens 58(3–4):239–258
Chen Z, Zhao Z, Gong P, Zeng B (2006) A new process for the segmentation of high resolution remote sensing imagery. Int J Remote Sens 27:4991–5001
Chi M, Feng R, Bruzzone L (2008) Classification of hyperspectral remote-sensing data with primal SVM for small-sized training dataset problem. Adv Space Res 41(11):1793–1799
Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Meas 20(1):37–46
Cleve C, Kelly M, Kearns FR, Moritz M (2008) Classification of the wildland–urban interface: a comparison of pixel-and object-based classifications using high-resolution aerial photography. Comput Environ Urb Syst 32(4):317–326
Dahiya S, Garg PK, Jat MK (2013) A comparative study of various pixel-based image fusion techniques as applied to an urban environment. Int J Image Data Fusion 4(3):197–213
De Leeuw J, Jia H, Yang L, Liu X, Schmidt K, Skidmore AK (2006) Comparing accuracy assessments to infer superiority of image classification methods. Int J Remote Sens 27:223–232
Dietterich TG (1998) Approximate statistical tests for comparing supervised classification learning algorithms. Neural Comput 10:1895–1923
Dingle Robertson L, King DJ (2011) Comparison of pixel- and object-based classification in land cover change mapping. Int J Remote Sens 32(6):1505–1529
Domingos P, Pazzani M (1997) On the optimality of the simple Bayesian classifier under zero-one loss. Mac Learn 29:103–130
Durieux L, Lagabrielle E, Nelson A (2008) A method for monitoring building construction in urban sprawl areas using object-based analysis of Spot 5 images and existing GIS data. ISPRS J Photogram Remote Sens 63(4):399–408
Duro DC, Franklin SE, Dubé MG (2012) A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery. Remote Sens Environ 118:259–272
ESRI AD (2016) Release 10.5. Environmental Systems Research Institute, Inc., Redlands, CA
Foody GM (2004) Thematic map comparison: evaluating the statistical significance of differences in classification accuracy. Photogram Eng Remote Sens 70:627–634
Foody GM, Mathur A (2004) Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification. Remote Sens Environ 93(1):107–117
Gao Y, Kerle N, Mas JF (2009) Object-based image analysis for coal fire-related land cover mapping in coal mining areas. Geocarto Int 24(1):25–36
Gao Y, Marpu P, Niemeyer I, Runfola DM, Giner NM, Hamill T, Pontius RG Jr (2011) Object-based classification with features extracted by a semi-automatic feature extraction algorithm–SEaTH. Geocarto Int 26(3):211–226
Ghosh A, Joshi PK (2013) Assessment of pan-sharpened very high-resolution WorldView-2 images. Int J Remote Sens 34(23):8336–8359
Gudiyangada Nachappa T, Kienberger S, Meena SR, Hölbling D, Blaschke T (2020) Comparison and validation of per-pixel and object-based approaches for landslide susceptibility mapping. Geomat Nat Hazard Risk 11(1):572–600
Hay GJ, Marceau DJ, Dube P, Bouchard A (2001) A multiscale framework for landscape analysis: object-specific analysis and upscaling. Lands Ecol 16(6):471–490
Hayes MM, Miller SN, Murphy MA (2014) High-resolution landcover classification using Random Forest. Remote Sens Lett 5(2):112–121
Herold M, Liu X, Clarke KC (2003) Spatial metrics and image texture for mapping urban land use. Photogramm Eng Remote Sensing 69(9):991–1001
Hexagon Geospatial (2016) ERDAS IMAGINE 2016. Intergraph Geospatial, Huntsville
Hu X, Weng Q (2011) Impervious surface area extraction from IKONOS imagery using an object-based fuzzy method. Geocarto Int 26(1):3–20
Jadhav SD, Channe HP (2016) Comparative study of K-NN, naive bayes and decision tree classification techniques. Int J Sci Res 5(1):1842–1845
Jozdani SE, Johnson BA, Chen D (2019) Comparing deep neural networks, ensemble classifiers, and support vector machine algorithms for object-based urban land use/land cover classification. Remote Sens 11(14):1713
Karatzoglou A, Smola A, Hornik K, Zeileis A (2004) kernlab-an S4 package for kernel methods in R. J Stat Softw 11(9):1–20
Kavzoglu T (2017) Object-oriented random forest for high resolution land cover mapping using Quickbird-2 imagery. In: Handbook of neural computation, Academic Press, pp 607-619
Kelly M, Shaari D, Guo Q, Liu D (2004) A comparison of standard and hybrid classifier methods for mapping hardwood mortality in areas affected by sudden oak death. Photogram Eng Remote Sens 70(11):1229–1239
Kotsiantis SB, Zaharakis I, Pintelas P (2007) Supervised machine learning: A review of classification techniques. Emerg Artif Intell Appl Comput Eng 160(1):3–24
Liaw A, Wiener M (2002) Classification and regression by randomForest. R News 2(3):18–22
Long JA, Lawrence RL, Greenwood MC, Marshall L, Miller PR (2013) Object oriented crop classification using multitemporal ETM+ SLC-off imagery and random forest. Gisci Remote Sens 50(4):418–436
Majka M (2018) naivebayes: High Performance Implementation of the Naive Bayes Algorithm. R package version 0.9.2. https://CRAN.R-project.org/package=naivebayes. Accessed April 2018
Manandhar R, Odeh IO, Ancev T (2009) Improving the accuracy of land use and land cover classification of Landsat data using post-classification enhancement. Remote Sens 1(3):330–344
Mountrakis G, Im J, Ogole C (2011) Support vector machines in remote sensing: A review. ISPRS J Photogram Remote Sens 66(3):247–259
Myint SW, Gober P, Brazel A, Grossman-Clarke S, Weng Q (2011) Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery. Remote Sens Environ 115(5):1145–1161.
Myint SW, Mesev V, Lam NSN (2006) Texture analysis and classification through a modified lacunarity analysis based on differential box counting method. Geograph Anal 38:371–390
Nemmour H, Chibani Y (2006) Multiple support vector machines for land cover change detection: an application for mapping urban extensions. ISPRS J Photogram Remote Sens 61(2):125–133
Otukei JR, Blaschke T (2010) Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms. Int J Appl Earth Observ Geoinform 12:S27–S31
Ouyang ZT, Zhang MQ, Xie X, Shen Q, Guo HQ, Zhao B (2011) A comparison of pixel-based and object-oriented approaches to VHR imagery for mapping saltmarsh plants. Ecol Inform 6(2):136–146
Padwick C, Deskevich M, Pacifici F, Smallwood S (2010) WorldView-2 pan-sharpening. In: Proceedings of the ASPRS 2010 annual conference, San Diego, CA, USA, vol 2630
Petropoulos GP, Kalaitzidis C, Vadrevu KP (2012) Support vector machines and object-based classification for obtaining land-use/cover cartography from hyperion hyperspectral imagery. Comp Geosci 41:99–107
Puissant A, Rougier S, Stumpf A (2014) Object-oriented mapping of urban trees using Random Forest classifiers. Int J Appl Earth Obser Geoinform 26:235–245
Qu LA, Chen Z, Li M, Zhi J, Wang H (2021) Accuracy improvements to pixel-based and object-based LULC classification with auxiliary datasets from Google Earth engine. Remote Sens 13(3):453
R Development Core Team (2016) R: a language and environment for statistical computing, Vienna, Austria. http://www.R-project.org/. Accessed September 2017
Ren J (2012) ANN vs. SVM: Which one performs better in classification of MCCs in mammogram imaging. Knowledge-Based Syst 26:144–153
Robles Granda PD (2011) A new image classification algorithm based on additive groves. Unpublished MSc Thesis. Carbondale (IL): Southern Illinois University at Carbondale.
Rodriguez-Galiano VF, Ghimire B, Rogan J, Chica-Olmo M, Rigol-Sanchez JP (2012) An assessment of the effectiveness of a random forest classifier for landcover classification. ISPRS J Photogram Remote Sens 67:93–104
Rozenstein O, Karnieli A (2011) Comparison of methods for land-use classification incorporating remote sensing and GIS inputs. Appl Geograp 31(2):533–544
Shao Y, Lunetta RS (2012) Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points. ISPRS J Photogram Remote Sens 70:78–87
Srivastava PK, Han D, Rico-Ramirez MA, Bray M, Islam T (2012) Selection of classification techniques for land use/land cover change investigation. Adv Space Res 50(9):1250–1265
Su Y, Huang PS, Lin CF, Tu TM (2004) Target-cluster fusion approach for classifying high resolution IKONOS imagery. IEEE Proc Vis Image Sig Process 151:241–249
Tassi A, Gigante D, Modica G, Di Martino L, Vizzari M (2021) Pixel-vs object-based Landsat 8 data classification in google earth engine using random forest: the case study of Maiella National Park. Remote Sens 13(12):2299.
Tehrany MS, Pradhan B, Jebuv MN (2014) A comparative assessment between object and pixel-based classification approaches for land use/land cover mapping using SPOT 5 imagery. Geocarto Int 29(4):351–369
Tien Bui D, Pradhan B, Lofman O, Revhaug I (2012) Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and Naïve Bayes models. Math Probl Eng 2012:26. https://doi.org/10.1155/2012/974638
Tu JV (1996) Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidem 49(11):1225–1231
Venables WN, Ripley BD (2002) Modern applied statistics with S, 4th edn. Springer, New York. ISBN 0-387-95457-0
Walter V (2004) Object-based classification of remote sensing data for change detection. ISPRS J Photogram Remote Sens 58:225–238
Wang Z, Ziou D, Armenakis C, Li D, Li Q (2005) A comparative analysis of image fusion methods. IEEE Trans Geosci Remote Sens 43(6):1391–1402
Whiteside TG, Boggs GS, Maier SW (2011) Comparing object-based and pixel based classifications for mapping savannas. Int J Appl Earth Observ Geoinform 13(6):884–893
Wiesmann D, Quinn D (2011) Rasclass: supervised raster image classification. R package version 0.2.1. http://cran.r-project.org/web/packages/rasclass/index.html. Accessed January 2018
Yan G, Mas JF, Maathuis BHP, Xiangmin Z, Van Dijk PM (2006) Comparison of pixel-based and object-oriented image classification approaches—a case study in a coal fire area, Wuda, Inner Mongolia, China. Int J Remote Sens 27(18):4039–4055
Zar JH (2009) Biostatistical analysis, 5th edn. Prentice Hall, Upper Saddle River
Zhang A (2014) Collaboration in the Australian and Chinese mobile telecommunication markets. Springer, New York
Acknowledgements
The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work under grant number (RGP2/194/42). The authors are thankful to National Aeronautics and Space Administration (NASA) and U.S. Geological Survey (USGS) for providing freely available Landsat data, used in this manuscript. The authors are thankful to Geoinformatics laboratory, TERI School of Advanced Studies for providing access to software.
Funding
This research received partial grant from United Nations University-Institute for the Advanced Study of Sustainability. The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work.
Author information
Authors and Affiliations
Contributions
The author AB and CKS prepared the concept of manuscript. Analysis was conducted by AB, JM and supervised by CKS. Draft writing was done by AB, SP, JM and edited by SP, SG, and CKS.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there are no conflict of interest associated with this manuscript.
Ethical statement
All ethical practices have been followed in relation to the development, writing, and publication of the article.
Additional information
Communicated by H. Babaie.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Balha, A., Mallick, J., Pandey, S. et al. A comparative analysis of different pixel and object-based classification algorithms using multi-source high spatial resolution satellite data for LULC mapping. Earth Sci Inform 14, 2231–2247 (2021). https://doi.org/10.1007/s12145-021-00685-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-021-00685-4