Experimental Investigations of Object based Urban Land Classification of Multispectral IRS R2 Image using Supervised ML Algorithms

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2022 by IJETT Journal
Volume-70 Issue-4
Year of Publication : 2022
Authors : Alpesh M. Patel, Anil Suthar
  10.14445/22315381/IJETT-V70I4P211

MLA 

MLA Style: Alpesh M. Patel, and Anil Suthar "Experimental Investigations of Object based Urban Land Classification of Multispectral IRS R2 Image using Supervised ML Algorithms." International Journal of Engineering Trends and Technology, vol. 70, no. 4, Apr. 2022, pp. 135-145. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I4P211

APA Style: Alpesh M. Patel, & Anil Suthar. (2022). Experimental Investigations of Object based Urban Land Classification of Multispectral IRS R2 Image using Supervised ML Algorithms. International Journal of Engineering Trends and Technology, 70(4), 135-145. https://doi.org/10.14445/22315381/IJETT-V70I4P211

Abstract
The migration of people towards city and town areas is the dominant factor for urban development and financial policymakers of developing countries like India. In the last decades, numerous availability of satellite data and the increasing computational capability of machines have inspired for effective utilization of remote sensing technology for urban planning. There are various machine learning methods that can be employed for urban land area classification with different performance capabilities. This paper compares six object-based supervised machine learning classifier algorithms with regard to classification accuracy and execution time and investigates the sensitivity of these classifiers for numerous training samples sizes for the classification of the urban area of Surat city. Linear imaging self-scanner (LISS-IV) sensor data of Indian Remote Sensing Resources at-2 (IRS-R2) was utilized for this urban object-based classification (OBC) investigation. The effect of the number of training samples used for training the supervised machine learning classifier has been explored with reference to the kappa coefficient (KC) and overall accuracy (OA) with the Shepherd algorithm used as the segmentation step. The ensemble-based bagging and random forest (RF) algorithms have illustrated superior performance compared to the support vector machine (SVM) classifier for object-oriented classification of urban land. The k neighbors classifier (KNC) has shown the least performance accuracy with an OA of 85.37%. The object-based RF classifier has displayed the highest precision with OA of 93.45% and KC of 0.9 in order to classify an urban area.

Keywords
Segmentation, Object-Based Classification (OBC), Machine Learning (ML), Very High Resolution (VHR), Random forest.

Reference
[1] T. Blaschke, Object-based image analysis for remote sensing, ISPRS J. Photogramm. Remote Sens. vol. 65(1) (2010) 2–16.
[2] R. C. Estoque, Y. Murayama, and C. M. Akiyama, Pixel-based and object-based classifications using high- and medium-spatialresolution imageries in the urban and suburban landscapes, Geocarto Int. 30(10) (2015) 1113–1129.
[3] N. Zhang, Y. Wu, and Q. Zhang, Detection of sea ice in sediment-laden water using MODIS in the Bohai Sea: a CART decision tree method, Int. J. Remote Sens. 36(6) (2015) 1661–1674.
[4] E. Raczko and B. Zagajewski, Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images, Eur. J. Remote Sens. 50(1) (2017) 144–154.
[5] P. Thanh Noi and M. Kappas, Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery, Sensors (Basel). 18(1) (2017)
[6] L. Ballantine, L. Blasius, E. Hines, and B. Kruse, Tree species classification using hyperspectral imagery: A comparison of two classifiers, Remote Sens. 8(6) (2016) 1–18.
[7] S. Amini, S. Homayouni, A. Safari, and A. A. Darvishsefat, Object-based classification of hyperspectral data using Random Forest algorithm, Geo-Spatial Inf. Sci. 21(2) (2018) 127–138.
[8] Y. Cai, H. Lin, and M. Zhang, Mapping paddy rice by the object-based random forest method using time series Sentinel-1/Sentinel-2 data, Adv. Sp. Res. 64(11) (2019) 2233–2244.
[9] Z. Shirvani, A holistic analysis for landslide susceptibility mapping applying geographic object-based random forest: A comparison between protected and non-protected forests, Remote Sens. 12(3) (2020) 1–22.
[10] Harmony, V. P. Siregar, S. Wouthuyzen, and S. B. Agus, Object-based classification of benthic habitat using Sentinel 2 imagery by applying with support vector machine and random forest algorithms in shallow waters of Kepulauan Seribu, Indonesia, Biodiversitas. 23(1) (2022) 514–520.
[11] D. C. Duro, S. E. Franklin, and M. G. Dubé, 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(2012) 259–272.
[12] R. N. Keyport, T. Oommen, T. R. Martha, K. S. Sajinkumar, and J. S. Gierke, A comparative analysis of pixel- and object-based detection of landslides from very high-resolution images, Int. J. Appl. Earth Obs. Geoinf. 64 (2018) 1–11.
[13] C. Cleve, M. Kelly, F. R. Kearns, and M. Moritz, Classification of the wildland-urban interface: A comparison of pixel- and object-based classifications using high-resolution aerial photography, Comput. Environ. Urban Syst. 32(4) (2008) 317–326.
[14] I. L. Castillejo-González et al., Object- and pixel-based analysis for mapping crops and their agro-environmental associated measures using QuickBird imagery, Comput. Electron. Agric. 68(2) (2009) 207–215.
[15] B. Fu et al., Comparison of object-based and pixel-based Random Forest algorithm for wetland vegetation mapping using high spatial resolution GF-1 and SAR data, Ecol. Indic. 73 (2017) 105–117.
[16] E. M. O. Silveira et al., Object-based random forest modelling of aboveground forest biomass outperforms a pixel-based approach in a heterogeneous and mountain tropical environment, Int. J. Appl. Earth Obs. Geoinf. 78 (2019) 175–188.
[17] A. Tassi, D. Gigante, G. Modica, L. Di Martino, and M. Vizzari, Pixel-vs. Object-based Landsat 8 data classification in google earth engine using random forest: The case study of Majella national park, Remote Sens. 13(12) (2021) 2299.
[18] Z. Zhou, L. Ma, T. Fu, G. Zhang, M. Yao, and M. Li, Change detection in coral reef environment using high-resolution images: Comparison of object-based and pixel-based paradigms, ISPRS Int. J. Geo-Information. 7(11) (2018) 441.
[19] T. G. Whiteside, G. S. Boggs, and S. W. Maier Comparing object-based and pixel-based classifications for mapping savannas, Int. J. Appl. Earth Obs. Geoinf. 13(6) (2011) 884–893.
[20] M. Hussain, D. Chen, A. Cheng, H. Wei, and D. Stanley, ISPRS Journal of Photogrammetry and Remote Sensing Change detection from remotely sensed images : From pixel-based to object-based approaches, ISPRS J. Photogramm. Remote Sens. 80 (2013) 91–106.
[21] Q. Wu, R. Zhong, W. Zhao, H. Fu, and K. Song, A comparison of pixel-based decision tree an object-based support vector machine methods for land-cover classification based on aerial images and airborne lidar data, Int. J. Remote Sens. 38(23) (2017) 7170–7195.
[22] T. Novack, T. Esch, H. Kux, and U. Stilla, Machine learning comparison between WorldView-2 and QuickBird-2-simulated imagery regarding object-based urban land cover classification, Remote Sens. 3(10) (2011) 2263–2282.
[23] D. C. Duro, S. E. Franklin, and M. G. Dubé, Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests, Int. J. Remote Sens., 33(14) (2012) 4502–4526.
[24] L. Xun and L. Wang, An object-based SVM method is incorporating optimal segmentation scale estimation using Bhattacharyya Distance for mapping salt cedar (Tamarisk spp.) with QuickBird imagery, GIScience Remote Sens. 52(3) (2015) 257–273.
[25] Y. Qian, W. Zhou, J. Yan, W. Li, and L. Han, Comparing machine learning classifiers for object-based land cover classification using very high-resolution imagery, Remote Sens. 7(1) (2015) 153–168.
[26] D. Li, Y. Ke, H. Gong, and X. Li, Object-based urban tree species classification using bi-temporal worldview-2 and worldview-3 images, Remote Sens. 7(12) (2015) 16917–16937.
[27] M. Li, L. Ma, T. Blaschke, L. Cheng, and D. Tiede, A systematic comparison of different object-based classification techniques using high spatial resolution imagery in agricultural environments, Int. J. Appl. Earth Obs. Geoinf. 49 (2016) 87–98.
[28] B. Melville, A. Lucieer, and J. Aryal, Object-based random forest classification of Landsat ETM+ and WorldView-2 satellite imagery for mapping lowland native grassland communities in Tasmania, Australia, Int. J. Appl. Earth Obs. Geoinf. 66 (2018) 46–55.
[29] J. Cao, W. Leng, K. Liu, L. Liu, Z. He, and Y. Zhu, Object-Based mangrove species classification using unmanned aerial vehicle hyperspectral images and digital surface models, Remote Sens. 10(1) (2018) 89.
[30] G. Modica, G. De Luca, G. Messina, and S. Praticò, Comparison and assessment of different object-based classifications using machine learning algorithms and UAVs multispectral imagery: a case study in a citrus orchard and an onion crop, Eur. J. Remote Sens. 54(1) (2021) 431–460.
[31] Pedregosa et al., Scikit-learn: Machine Learning in Python, Journal of Machine Learning Research. 12 (2011) 2825-2830.
[32] T. Blaschke et al., Geographic object-based image analysis towards a new paradigm, ISPRS J. Photogrammetry Remote Sens. 87 (2014) 180–191.
[33] D. Liu and F. Xia, Assessing object-based classification: Advantages and limitations, Remote Sens. Lett. 1(4) (2010) 187–194.
[34] D. Clewley et al., A python-based open-source system for Geographic Object-Based Image Analysis (GEOBIA) utilizing raster attribute tables, Remote Sens. 6(7) (2014) 6111–6135. [35] J. D. Shepherd and P. Bunting, Operational Large-Scale Segmentation of Imagery Based on Iterative Elimination, Remote Sens. 11(6) (2019) 658.
[36] Career, A.P.; Debeir, O.; Wolff, E., Assessment of Very High Spatial Resolution Satellite Image Segmentations, Photogramm. Eng. Remote Sens. 71(11) (2005) 1285-1294.
[37] R. Mathieu and J. Aryal, Object-based classification of Ikonos imagery for mapping large-scale vegetation communities in urban areas, Sensors, 7(11) (2007) 2860–2880.
[38] M. A. Aguilar, M. M. Saldana, and F. J. Aguilar, GeoEye-1 and WorldView-2 pan-sharpened imagery for object-based classification in urban environments, Int. J. Remote Sens. 34(7) (2013) 2583–2606.
[39] QGIS Development Team, QGIS (Version 2.18). Open Source Geospatial Foundation Project. (2019) https://qgis.org/en/site/.
[40] P. Du, A. Samat, B. Waske, S. Liu, and Z. Li, Random Forest and Rotation Forest for fully polarized SAR image classification using polarimetric and spatial features, ISPRS J. Photogramm. Remote Sens. 105 (2015) 38–53.
[41] Duda, Richard O. and Peter E. Hart. Pattern classification and scene analysis. A Wiley-Interscience Publication. 3 (1973) 731-739.
[42] Akbulut, Yaman, Abdulkadir Sengur, Yanhui Guo, and Florentin Smarandache. NS-k-NN: Neutrosophic set-based k-nearest neighbors classifier, Symmetry 9(9) (2017) 179.
[43] Wei, Chuanwen, et al. Estimation and mapping of winter oilseed rape LAI from high spatial resolution satellite data based on a hybrid method, Remote Sensing. 9(5) (2017) 488.
[44] Mountrakis, G.; Im, J.; Ogle, C. Support vector machines in remote sensing: A review, ISPRS J. Photogramm. Remote Sens. 66(3) (2011) 247–259.
[45] Mantero, Paolo, Gabriele Moser, and Sebastiano B. Serpico. Partially supervised classification of remote sensing images through SVMbased probability density estimation, IEEE Transactions on Geoscience and Remote Sensing 43(3) (2005) 559-570.
[46] K. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, Machine Learning in Agriculture: A Review, Sensors. 18(8) (2018) 2674.
[47] S. Singh and P. Gupta, Comparative Study Id3, Cart and C4.5 Decision Tree Algorithm: a Survey, Int. J. Adv. Inf. Sci. Technol. 27(27) (2014) 97–102.
[48] L. Sun and K. Schulz, The Improvement of Land Cover Classification by Thermal Remote Sensing, Remote Sensing, 7(7) (2015) 8368– 8390.
[49] L. Breiman, Random forests, Machine learning 45(1) (2001) 5-32.
[50] Rodriguez-Galiano, Victor Francisco, et al., An assessment of the effectiveness of a random forest classifier for land-cover classification, ISPRS journal of photogrammetry and remote sensing. 67 (2012) 93-104.
[51] The story, Michael, and Russell G. Congalton, Accuracy assessment: a user’s perspective, Photogrammetric Engineering and remote sensing. 52(3) (1986) 397-399.
[52] Cohen, Jacob, A coefficient of agreement for nominal scales, Educational and psychological measurement. 20(1) (1960) 37-46.
[53] Gómez, Daniel, and Javier Montero Determining the accuracy in image supervised classification problems, (2011) 342-349.