Multi-scale RoIs selection for classifying multi-spectral images
- 15 Downloads
The applications of object-based image analysis (OBIA) in remote sensing studies have received a considerable amount of attention over the recent decade due to dramatically increasing of the spatial resolution of satellite imaging sensors for earth observation. In this study, an unsupervised methodology based on OBIA paradigm for the estimation of multi-scale training sets for land cover classification is proposed. The proposed method consists of selection of valid region of interests in an unsupervised way and its characterization using some attributes in order to form meaningful and reliable training sets for supervised classification of different land covers of a satellite image. Multi-scale image segmentation is a prerequisite step for estimation of multi-scale training sets. However, scale selection remains a challenge in multi-scale segmentation. In this work, we propose a method to determine the appropriate segmentation scale for each land cover with the help of prior knowledge in the form of in-situ data. The proposed method is further discussed and validated through multi-scale segmentation using quick shift and random forest algorithms on two multi-spectral images captured using Worldview-2 sensor. Experimental results indicate that the proposed method qualitatively and quantitatively outperforms three state-of-the-art methods.
KeywordsObject based image analysis Multi-scale RoIs Quick shift Random forest
A. Seal is thankful to MeiTY, Govt. of India for proving him Young Faculty Research Fellowship under Visvesvaraya PhD Scheme for Electronics and IT. This work has been partially funded by the Water Research Center For Agriculture and Mining, CRHIAM (CONICYT-FONDAP-1513001).
- Aplin, P., & Smith, G. M. (2008). Advances in object-based image classification. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 37, 725–728.Google Scholar
- Baatz, M., & Shape, A. (2000). Multiresolution segmentation-an optimization approach for high quality multi-scale image segmentation. http://www.agit.at/papers/2000/baatz_FP_12.pdf
- Bhattarai, N., Quackenbush, L. J., Calandra, L., Im, J., & Teale, S. (2011). Spectral analysis of scotch pine infested by SirexNoctilio. In ASPRS annual conference, Milwaukee, Wisconsin.Google Scholar
- Blaschke, T., & Lang, S. (2006). Object based image analysis for automated information extraction—A synthesis. In Measuring the Earth II ASPRS fall conference, San Antonio, Texas (pp. 6–10).Google Scholar
- Blaschke, T., & Strobl, J. (2001). What’s wrong with pixels? Some recent developments interfacing remote sensing and GIS. GeoBIT/GIS, 6, 12–17.Google Scholar
- Breiman, L. (2000). Some infinity theory for predictor ensembles. In Technical Report 579. Statistics Department, UCB.Google Scholar
- Breiman, L. (2004). Consistency for a simple model of random forests. Technical Report 670. https://www.stat.berkeley.edu/~breiman/RandomForests/consistencyRFA.pdf. Accessed 6 Oct 2019.
- Castilla, G., & Hay, G. J. (2008). Image objects and geographic objects. In T. Blaschke, S. Lang, & G. J. Hay (Eds.), Object-based image analysis (pp. 91–110). Berlin: Springer.Google Scholar
- Dey, V., Zhang, Y., & Zhong, M. (2010). A review on image segmentation techniques with remote sensing perspective. In ISPRS TC VII symposium (Vol. 38, pp. 31–42).Google Scholar
- Digital Globe. (2011). http://worldview2.digitalglobe.com/docs/WorldView-2_8-Band_Applications_Whitepaper.pdf.
- Gao, Y., & Mas, J. F. (2008). A comparison of the performance of pixel-based and object-based classifications over images with various spatial resolutions. Online Journal of Earth Sciences, 2(1), 27–35.Google Scholar
- Gholoobi, M., Tayyebi, A., Taleyi, M., & Tayyebi, A. H. (2010). Comparing pixel based and object based approaches in land use classification in mountainous areas. In International archives of the photogrammetry, remote sensing and spatial information science, Kyoto, Japan (Vol. 38).Google Scholar
- Gonzalo-Martín, C., Lillo-Saavedra, M., Gómez-Carpintero, J., García-Pedrero, Á. M., & Menasalvas, E. (2013). Unsupervised multi-scale ROIs determination for supervised thematic classification. Towards Horizon, 2020, 783–790.Google Scholar
- Hay, G. J., & Marceau, D. J. (2004). Multiscale object-specific analysis (MOSA): An integrative approach for multiscale landscape analysis. In S. M. De Jong & F. D. Van der Meer (Eds.), Remote sensing image analysis: Including the spatial domain (pp. 71–92). Dordrecht: Springer.CrossRefGoogle Scholar
- Kim M., Madden M., & Warner T. (2008) Estimation of optimal image object size for the segmentation of forest stands with multispectral IKONOS imagery. In T. Blaschke, S. Lang, & G. J. Hay (Eds.), Object-based image analysis. Lecture notes in geoinformation and cartography. Berlin, Heidelberg: Springer.Google Scholar
- Meinel, G., & Neubert, M. (2004). A comparison of segmentation programs for high resolution remote sensing data. International Archives of Photogrammetry and Remote Sensing, 35, 1097–1105.Google Scholar
- Mohan, B. K., & Ladha, S. N. (2009). Comparison of object based and pixel based classification of high resolution satellite images using artificial neural networks. In National symposium on security and soft computing. Mumbai: IIT Bombay.Google Scholar
- Sheikh, Y. A., Khan, E. A., & Kanade, T. (2007) . Mode-seeking by medoidshifts. In 2007 IEEE 11th international conference on computer vision (pp. 1–8).Google Scholar
- Tan, P. N. (2018). Introduction to data mining. Noida: Pearson Education.Google Scholar
- UcaAvci, Z. D., Karaman, M., Ozelkan, E., & Papila, I. (2011). A comparison of pixel-based and object-based classification methods, a case study: Istanbul, Turkey. In 34th International symposium on remote sensing of environment, Sydney.Google Scholar
- Vedaldi, A., & Soatto, S. (2008). Quick shift and kernel methods for mode seeking. ECCV, Part IV. In European conference on computer vision, Springer, Berlin, Heidelberg (pp. 705–718).Google Scholar
- Whiteside, T., & Ahmad, W. (2005) . A comparison of object-oriented and pixel-based classification methods for mapping land cover in Northern Australia. In Proceedings of SSC2005 spatial intelligence, innovation and praxis: The National Biennial Conference of the Spatial Sciences Institute.Google Scholar