Crop classification from multi-temporal PolSAR data with regularized greedy forest
Main Article Content
Abstract
Polarimetric Synthetic Aperture Radar (PolSAR) images are considered as an important data source for the crop mapping and monitoring especially for the time-critical agricultural applications. The objective of this paper is to evaluate the potential of a novel ensemble learning algorithm, Regularized Greedy Forest (RGF), for crop classification from multi-temporal quad-pol PolSAR data. For the classification of crops (maize, potato, wheat, sunflower, and alfalfa) in the study site, the polarimetric features of Cloude–Pottier decomposition (a.k.a H/A/α decomposition) were used as the input data. The performance of RGF was compared to Random Forests (RF) and Support Vector Machines (SVM) in terms of overall accuracy and Kappa values. Our experimental results demonstrated that RGF can yield higher accuracy (with an overall accuracy of 0.78) than RF and SVM for crop classification using PolSAR images. Moreover, it can be concluded that polarimetric features of Cloude–Pottier decomposition are of efficient for the discrimination of crops using multi-temporal PolSAR data.
Article Details
References
McNairn, H., & Brisco, B. (2004). The application of C-band polarimetric SAR for agriculture: A review. Canadian Journal of Remote Sensing, 30(3), 525-542.
Soria-Ruiz, J., Fernandez-Ordonez, Y., McNairm, H., & Bugden-Storie, J. (2007, July). Corn monitoring and crop yield using optical and RADARSAT-2 images. In 2007 IEEE International Geoscience and Remote Sensing Symposium (pp. 3655-3658). IEEE.
Jiao, X., Kovacs, J. M., Shang, J., McNairn, H., Walters, D., Ma, B., & Geng, X. (2014). Object-oriented crop mapping and monitoring using multi-temporal polarimetric RADARSAT-2 data. ISPRS Journal of Photogrammetry and Remote Sensing, 96, 38-46.
Tamiminia, H., Homayouni, S., McNairn, H., & Safari, A. (2017). A particle swarm optimized kernel-based clustering method for crop mapping from multi-temporal polarimetric L-band SAR observations. International Journal of Applied Earth Observation and Geoinformation, 58, 201-212.
Cloude, S. R., & Pottier, E. (1997). An entropy based classification scheme for land applications of polarimetric SAR. IEEE transactions on geoscience and remote sensing, 35(1), 68-78.
Chen, S. W., Li, Y. Z., Wang, X. S., Xiao, S. P., & Sato, M. (2014). Modeling and interpretation of scattering mechanisms in polarimetric synthetic aperture radar: Advances and perspectives. IEEE Signal Processing Magazine, 31(4), 79-89.
Steele-Dunne, S. C., McNairn, H., Monsivais-Huertero, A., Judge, J., Liu, P. W., & Papathanassiou, K. (2017). Radar remote sensing of agricultural canopies: A review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(5), 2249-2273.
Pal, M. (2005). Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1), 217-222.
Barrett, B., Nitze, I., Green, S., & Cawkwell, F. (2014). Assessment of multi-temporal, multi-sensor radar and ancillary spatial data for grasslands monitoring in Ireland using machine learning approaches. Remote Sensing of Environment, 152, 109-124.
Samat, A., Persello, C., Liu, S., Li, E., Miao, Z., & Abuduwaili, J. (2018). Classification of VHR multispectral images using extratrees and maximally stable extremal region-guided morphological profile. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(9), 3179-3195.
Colkesen, I., & Kavzoglu, T. (2017). Ensemble-based canonical correlation forest (CCF) for land use and land cover classification using sentinel-2 and Landsat OLI imagery. Remote Sensing Letters, 8(11), 1082-1091.
Xia, J., Yokoya, N., & Iwasaki, A. (2016). Hyperspectral image classification with canonical correlation forests. IEEE Transactions on Geoscience and Remote Sensing, 55(1), 421-431.
Georganos, S., Grippa, T., Vanhuysse, S., Lennert, M., Shimoni, M., & Wolff, E. (2018). Very high resolution object-based land use–land cover urban classification using extreme gradient boosting. IEEE geoscience and remote sensing letters, 15(4), 607-611.
Ustuner, M., & Balik Sanli, F. (2019). Polarimetric Target Decompositions and Light Gradient Boosting Machine for Crop Classification: A Comparative Evaluation. ISPRS International Journal of Geo-Information, 8(2), 97. MDPI AG.
Yang, F., Xu, Q., Li, B., & Ji, Y. (2018). Ship detection from thermal remote sensing imagery through region-based deep forest. IEEE Geoscience and Remote Sensing Letters, 15(3), 449-453.
Cloude, S. R., & Pottier, E. (1996). A review of target decomposition theorems in radar polarimetry. IEEE Transactions on Geoscience and Remote Sensing, 34(2), 498-518.
Johnson, R., & Zhang, T. (2013). Learning nonlinear functions using regularized greedy forest. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(5), 942-954.
RGF Team, "Regularized Greedy Forest (RGF) library" [Online] (2018). Available: https://github.com/RGF-team/rgf, 2018. (Accessed on: December. 30, 2019)
Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. (2006). Random forests for land cover classification. Pattern Recognition Letters, 27(4), 294-300.
Melgani, F., & Bruzzone, L. (2004). Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(8), 1778-1790.
Zeybek, M. (2021). Inlier point preservation in outlier points removed from the ALS point cloud. Journal of the Indian Society of Remote Sensing, 49(10), 2347-2363.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Vanderplas, J. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12(Oct), 2825-2830.