Incorporation of textural information with SAR and optical imagery for improved land cover mapping
- 17 Downloads
This study focuses on evaluating the capability and contribution of using backscatter intensity image and textural bands from Sentinel-1A synthetic aperture radar (SAR) data for reducing the limitation of optical image classification and improving the classification accuracy. The study was carried out at Theni district of Tamil Nadu, India, which is characterized by very heterogeneous features. The optical multispectral images such as Linear imaging self scanning sensor-IV (LISS-IV), Sentinel-2A and Landsat8 were used. Support vector machine classifier performed on the different combination of SAR, optical image and texture features. Results showed that the optimal window size was 11 × 11, and mean and variance are optimal textural bands of gray-level co-occurrence matrix techniques. The best classification result was achieved with the combination of LISS-IV and Sentinel-1A-derived features (backscatter intensity and texture features) with an overall accuracy up to 78.49% and a kappa coefficient of up to 0.68, respectively. The combination of optical image and Sentinel-1A data decreased the spectral confusions between the classes, provided better classification results, and reasonably improved the accuracy.
KeywordsSAR GLCM SVM Sentinel-1A LISS-IV Sentinel-2A and Landsat8 OLI
We are grateful to NRSC-ISRO, NASA and ESA for providing optical and SAR data sets for this study. I sincerely thank Dr. Kari Ramu and Dr. Mehmuna Bagum, Scientist, National Centre for Coastal Research (NCCR), Ministry of Earth Sciences, Government of India for their valuable suggestions.
- Brisco B, Brown RJ (1995) Multidate SAR/TM synergism for crop classification in Western Canada. Photogramm Eng Remote Sens 61(8):1009–1014Google Scholar
- Cetin M (2015) Using GIS analysis to assess urban green space in terms of accessibility: case study in Kutahya. Int J Sustain Dev World Ecol 22(5):420–424Google Scholar
- Iyyappan M, Ramakrishnan SS, Srinivasa Raju K (2014) Study of discrimination between plantation and dense scrub based on backscattering behavior of C band SAR data. Int Arch Photogramm Remote Sens Spat Inf Sci (ISPRS Arch XL) 8:755–760. https://doi.org/10.5194/isprsarchives-xl-8-755-2014 CrossRefGoogle Scholar
- Lillesand TM, Kiefer RW, Chipman JW (2004) Remote sensing and image interpretation, 5th edn. Wiley, New YorkGoogle Scholar
- Mishra VN, Kumar P, Gupta DK, Prasad R (2014) Classification of various land features using Risat-1 dual polarimetric data. Int Arch Photogramm Remote Sens Spat Inf Sci (ISPRS Arch XL) 8:833–837. https://doi.org/10.5194/isprsarchives-xl-8-833-2014 CrossRefGoogle Scholar
- NRSC (2011) RESOURCESAT-2 Manual. http://www.euromap.de/download/R2_data_user_handbook.pdf
- de Oliveira Silveira EM, de Menezes MD, Acerbi Júnior FW, Santos Terra MCN, de Mello JM (2017) Assessment of geostatistical features for object-based image classification of contrasted landscape vegetation cover. J Appl Remote Sens 11(3):036004. https://doi.org/10.1117/1.JRS.11.036004 CrossRefGoogle Scholar
- Wei L, Hu Z, Gu M et al. (2012) Texture feature analysis in oil spill monitoring by SAR image. In: IEEE - 2012 20th international conference on geoinformatics, pp 1–6. https://doi.org/10.1109/Geoinformatics.2012.6270284