Skills and Expertise
Research Items (3)
In this study, we propose a multi-temporal and multi-polarization approach to discriminate different crop types in the Marchefel region, Austria. The sensitivity of X-band COSMO-SkyMed ® (CSK ®) data with respect to five crop classes, namely carrot, corn, potato, soybean and sugarbeet is investigated. In particular, the capabilities of dual-polarization (StripMap PingPong) HH/HV, and single-polarization (StripMap Himage), HH and VH, in distinguishing among the five crop types are evaluated. A total of twenty-one Himage and ten PingPong images were acquired in a seven-months period, from April to October 2014. Therefore, the backscattering coefficient was extracted for each dataset and the classification was performed using a pixel-based support vector machine (SVM) approach. The accuracy of the obtained crop classifications was assessed by comparing them with ground truth. The dual-polarization results are contrasted between the HH and HV polarization, and with single-polarization ones (HH and VH polarizations). The best accuracy is obtained by using time-series of StripMap Himage data, at VH polarization, covering the whole season period.
This study presents a preliminary assessment of the potentialities of the COSMO-SkyMed® (CSK®) satellite constellation to accurately classify different crops. The experiment is focused on the main crops grown in the agricultural region of Marchfeld (Austria) namely carrot, corn, potato, soybean and sugar beet. A Support Vector Machine (SVM) classifier was fed with temporally dense series of backscattering coefficients extracted from a stack of CSK® GTC products. In particular, twenty one CSK® dual polarization (11 HH, 10 VH) images were acquired over the site for the growing season (early April – mid October) in Stripmap Himage mode, with a nominal incidence angle at scene center of 40°. A comparison of the classifications obtained at the two different polarizations are reported and the result are analyzed in terms of the achieved accuracies. The SVM method was able to classify all five crop types with an overall accuracy of 81.6% (Kappa 0.77) at VH polarization and of 84.5% (Kappa 0.80) at HH polarization. Sugar beet, potato and carrot were accurately identified with OA never less than 83% at both polarizations, whereas corn and soybean showed remarkably differences in terms of producer’s and user’s accuracies, probably due to particular agricultural practices adopted for these two crop species. These first results show that the CSK® capability of acquiring temporally dense data sets can accurately identify several crop types.