Under the influence of the physicochemical characteristics of the crops and the space-time environmental factors, even the same crop will show some oscillation in the spectrum. Previous studies mostly used arithmetic mean value to reduce the uncertainty caused by spectral oscillation, but the characterization ability of mean value is susceptible to the degree of numerical difference. To solve these problems and to explore the relationship between the accuracy of typical crop identification and the growth period and spectral characteristics, we proposed a spectral construction algorithm based on Spectral Domain Interpolation (SDI). Using SDI and traditional Arithmetic Mean (AM) method, the characteristic spectra of typical crops (winter wheat, oilseed grape) and the main background vegetation (trees, grasses, rice stubble) were constructed at different growth stages (March, April and May). Then, feature parameters were extracted based on the constructed characteristic spectrum. The importance evaluation and linear discriminant analysis of the extracted feature parameters were carried out at last. The optimal identifying growth period and identifying feature parameters of typical crops were obtained through comparative analysis, at the same time, the availability and superiority of SDI were verified. The following conclusions were drawn: (1) SDI has a good resistance to extremes, and can retain the spectral characteristics of crops well, and construct a more characterizing characteristic spectrum. (2) The best identifying growth periods of oilseed grape and winter wheat are early flowering period in March and heading period in April, respectively. The best identifying characteristics of winter wheat and oilseed grape are yellow edge position and red edge amplitude, respectively. (3) Winter wheat and oilseed grape can be well identified by using the position of the yellow edge in March and the blue edge area and the red edge amplitude in April.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.