ABSTRACT
For improving the performance of multitemporal Sentinel-1 (S1) SAR and Sentinel-2 (S2) optical imagery for land cover classification, a framework based on Rotating Kernel Transformation (RKT) denoising algorithm and the stratified sampling method based on the Crop Data Layer (CDL) is proposed. Random Forest classifications based on different denoising algorithms and sampling methods are carried out to compare their accuracy and applicability for land cover classification. The results show that the RKT algorithm and the stratified sampling method can significantly improve the classification accuracy. The classification accuracy by S1 data alone without denoising (overall accuracy: 0.873, Kappa: 0.796) is significantly lower than that of S2 (overall accuracy: 0.979, Kappa: 0.970) resulting from effects of serious salt-and-pepper noise. After RKT filtering, the speckle noise of the S1 classification result is significantly reduced and the accuracy is significantly improved (overall accuracy: 0.944, Kappa: 0.912). RKT filter outperforms the Lee and Median filters in improving the classification accuracy of SAR imagery. Feature-level fusion of S1 and S2 achieves the highest classification accuracy (overall accuracy: 0.983, Kappa: 0.972) which is significantly higher than that of S1 and slightly higher than that of S2 data alone. It proves that the fusion of the optical and SAR data can weaken the speckle noises on classification maps and improve the classification accuracy. The stratified sampling method applied in this study significantly improves the classification accuracy of each experimental group, with the overall accuracy increasing by about 10% and the Kappa coefficient increasing by more than 15% on average.
- I. Abou EL-Magd and T. Tanton, Improvements in land use mapping for irrigated agriculture from satellite sensor data using a multi-stage maximum likelihood classification, International Journal of Remote Sensing, vol. 24, pp. 4197-4206, June 2003. https://doi.org/10.1080/0143116031000139791.Google ScholarCross Ref
- J. You, Z. Pei, F. Wang, Q. Wu, and L. Guo, Area extraction of winter wheat at county scale based on modified multivariate texture and GF1 satellite images, Transactions of the Chinese Society of Agricultural Engineering, vol. 32, pp. 131-139, July 2016. https://doi.org/10.11975/j.issn.1002-6819.2016.13.019Google Scholar
- L. Yan and D. Roy, Improved time series land cover classification by missing-observation-adaptive nonlinear dimensionality reduction, Remote Sensing of Environment, vol. 158, pp. 478-491, March 2015. https://doi.org/10.1016/j.rse.2014.11.024.Google ScholarCross Ref
- J. Yan, L. Wang, W. Song, Y. Chen, X. Chen, and Z. Deng, A time-series classification approach based on change detection for rapid land cover mapping, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 158, pp. 249-262, December 2019. https://doi.org/10.1016/j.isprsjprs.2019.10.003.Google ScholarCross Ref
- G Jin, Q Xu, H Zhang, Synthetic Aperture Radar Interferometry, Beijing: National Defense Industry Press, 2014.Google Scholar
- G Jin, H Zhang, Q Xu, Radargrammetry, Beijing:Surveying and Mapping Press, 2015.Google Scholar
- N. F. Nafari, S. Homayouni, A. Safari, and V. Akbari, Assessment of full and compact polarimetric SAR observations for land-cover and crop classification, in Living Planet Symposium, pp. 85, 2016./Google Scholar
- Q Zhao, K Xie, G Wang and Y Li, Land cover classification of polarimetric SAR with fully convolution network and conditional Random Forest, Acta Geodaetica et Cartographica Sinica, vol. 49, pp. 69-82, 2020. https://doi.org/CNKI:SUN:CHXB.0.2020-01-007.Google Scholar
- X. Blaes, L. Vanhalle, and P. Defourny, Efficiency of crop identification based on optical and SAR image time series, Remote sensing of environment, vol. 96, pp. 352-365, June 2005. https://doi.org/10.1016/j.rse.2005.03.010.Google ScholarCross Ref
- S. Banerjee, S. Sinha Chaudhuri, R. Mehra, and A. Misra, A survey on Lee filter and its improved variants, in Advances in Smart Communication Technology and Information Processing: OPTRONIX 2020, pp. 371-383, February 2021.Google ScholarCross Ref
- L. Jiao, X. Zhang, B. Hou, S. Wang, and F. Liu, Intelligent SAR image processing and interpretation, Science Press, January 2008.Google Scholar
- G. Cai, X. Luo, and J. Yang, Characteristic analysis of SAR noise based on wavelet transform, in 2012 2nd International Conference on Remote Sensing, Environment and Transportation Engineering, pp. 1-7, June 2012.Google ScholarCross Ref
- Y.-K. Lee and W. T. Rhodes, Rotating-kernel min-max algorithms for straight-line feature enhancement, Applied Optics, vol. 34, pp. 290, January 1995. https://doi.org/10.1364/AO.34.000290.Google ScholarCross Ref
- Q. Guo, F. Dong, S. Sun, X. Ren, S. Feng, and B. Z. Gao, Improved rotating kernel transformation based contourlet domain image denoising framework, in Pacific-Rim Conference on Multimedia, pp. 146-157, December 2013. https://doi.org/10.1007/978-3-319-03731-8_14.Google ScholarDigital Library
- W Huang, J Wu, H Ren, Rotating kernel transformation denoising algorithm based on wavelet transform in photo thermal optical coherence tomography, Laser and Optoelectronics Progress, vol. 57(22), pp. 1-11, January 2020. https://doi.org/10.3788/LOP57.221005.Google Scholar
- C Wang, Research on imbalanced data classification based on the distribution of near neighbors, Xidian University, 2020. https://doi.org/10.27389/d.cnki.gxadu.2019.002749.Google Scholar
- J. Chen, J. Chen, A. Liao, X. Cao, L. Chen, X. Chen, , Global land cover mapping at 30 m resolution: A POK-based operational approach, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 103, pp. 7-27, May 2015. https://doi.org/10.1016/j.isprsjprs.2014.09.002.Google ScholarCross Ref
- Peng Gong, Han Liu, Meinan Zhang, Congcong Li, Jie Wang, Huabing Huang, Nicholas Clinton, , Stable classification with limited sample: Transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017, Sci. Bull, vol. 64, pp. 370-373, February 2019. https://doi.org/10.1016/j.scib.2019.03.002.Google ScholarCross Ref
- C. Boryan, Z. Yang, R. Mueller, and M. Craig, Monitoring US agriculture: the US department of agriculture, national agricultural statistics service, cropland data layer program, Geocarto International, vol. 26, pp. 341-358, April 2011. https://doi.org/10.1080/10106049.2011.562309.Google ScholarCross Ref
Index Terms
- Improvement in Land Cover Classification Using Multitemporal Sentinel-1 and Sentinel-2 Satellite Imagery
Recommendations
Seasonal multitemporal land-cover classification and change detection analysis of Bochum, Germany, using multitemporal Landsat TM data
3D remote sensing and urban remote sensingThe 40-year Landsat time series makes it possible to continuously map and examine land-cover changes. By using images from two dates in each classification year, we can improve the classification accuracy of monotemporal approaches for each year and ...
Improving land cover classification through contextual-based optimum-path forest
A new contextual classifier based on optimum-path forest has been presented (OPF-MRF).A meta-heuristic-based framework has been proposed to estimate the contextual-dependent parameter for OPF-MRF.The proposed approach has been validated in the context ...
Fully automatic multi-temporal land cover classification using Sentinel-2 image data
AbstractThe analysis of remote sensing images represents a highly important issue to be performed in many relevant fields such as climate change studies or land cover mapping. Traditional proposals usually identify the land cover classes from general ...
Comments