A particle swarm optimized kernel-based clustering method for crop mapping from multi-temporal polarimetric L-band SAR observations
Citation
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, [online] 58 201-212. http://dx.doi.org/10.1016/j.jag.2017.02.010
Plain language summary
Synthetic Aperture Radar (SAR) satellites offer many advantages in observing the Earth including their ability to map the Earth through cloud cover. An advanced type of SAR, Polarimetric SAR or PolSAR, offers a very rich set of radar parameters that can be helpful in land cover mapping. In this paper, an optimized kernel-based C-means clustering algorithm is developed and tested with PolSAR data for crop identification. Several radar features were extracted including linear polarization intensities, and radar decomposition data layers from Cloude-Pottier, Freeman-Durden and Yamaguchi techniques. These radar data layers were used in a kernelized version of hard and fuzzy C-means clustering algorithms. The kernel function simplifies the non-spherical and non-linearly patterns of data structure, improving the ability of the algorithm to cluster the data. In addition the Particle Swarm Optimization (PSO) algorithm was used to tune the kernel parameters, cluster centers and to optimize features selection. This classification method was evaluated using a time series of airborne L-band images acquired over an agricultural area in Manitoba (Canada) during June and July of 2012. This method resulted in an increase in crop classification accuracy of 12%, when compared to other classification methods. When the optimization technique is used classification accuracy is improved a further 5%. This research advances new methods for crop classification using SAR imagery, improving accuracies. SAR imagery can be an important source of data for national crop mapping, and the methods tested in this study will help inform further improvements to these operational services.
Abstract
Polarimetric Synthetic Aperture Radar (PolSAR) data, thanks to their specific characteristics such as high resolution, weather and daylight independence, have become a valuable source of information for environment monitoring and management. The discrimination capability of observations acquired by these sensors can be used for land cover classification and mapping. The aim of this paper is to propose an optimized kernel-based C-means clustering algorithm for agriculture crop mapping from multi-temporal PolSAR data. Firstly, several polarimetric features are extracted from preprocessed data. These features are linear polarization intensities, and several statistical and physical based decompositions such as Cloude-Pottier, Freeman-Durden and Yamaguchi techniques. Then, the kernelized version of hard and fuzzy C-means clustering algorithms are applied to these polarimetric features in order to identify crop types. The kernel function, unlike the conventional partitioning clustering algorithms, simplifies the non-spherical and non-linearly patterns of data structure, to be clustered easily. In addition, in order to enhance the results, Particle Swarm Optimization (PSO) algorithm is used to tune the kernel parameters, cluster centers and to optimize features selection. The efficiency of this method was evaluated by using multi-temporal UAVSAR L-band images acquired over an agricultural area near Winnipeg, Manitoba, Canada, during June and July in 2012. The results demonstrate more accurate crop maps using the proposed method when compared to the classical approaches, (e.g. 12% improvement in general). In addition, when the optimization technique is used, greater improvement is observed in crop classification, e.g. 5% in overall. Furthermore, a strong relationship between Freeman-Durden volume scattering component, which is related to canopy structure, and phenological growth stages is observed.